forked from Archives/langchain
Compare commits
22 Commits
tool-patch
...
main
Author | SHA1 | Date | |
---|---|---|---|
|
84d7ad397d | ||
|
de551d62a8 | ||
|
d8fd0e790c | ||
|
97c2b31cc5 | ||
|
f1dc03d0cc | ||
|
f76e9eaab1 | ||
|
db2e9c2b0d | ||
|
d22651d82a | ||
|
c46478d70e | ||
|
e3fcc72879 | ||
|
2fdb1d842b | ||
|
c30ef7dbc4 | ||
|
8a7871ece3 | ||
|
201ecdc9ee | ||
|
149fe0055e | ||
|
096b82f2a1 | ||
|
87b5a84cfb | ||
|
ed97aa65af | ||
|
c9e6baf60d | ||
|
7cde1cbfc3 | ||
|
17213209e0 | ||
|
895f862662 |
144
.dockerignore
Normal file
144
.dockerignore
Normal file
@ -0,0 +1,144 @@
|
||||
.vscode/
|
||||
.idea/
|
||||
# Byte-compiled / optimized / DLL files
|
||||
__pycache__/
|
||||
*.py[cod]
|
||||
*$py.class
|
||||
|
||||
# C extensions
|
||||
*.so
|
||||
|
||||
# Distribution / packaging
|
||||
.Python
|
||||
build/
|
||||
develop-eggs/
|
||||
dist/
|
||||
downloads/
|
||||
eggs/
|
||||
.eggs/
|
||||
lib/
|
||||
lib64/
|
||||
parts/
|
||||
sdist/
|
||||
var/
|
||||
wheels/
|
||||
pip-wheel-metadata/
|
||||
share/python-wheels/
|
||||
*.egg-info/
|
||||
.installed.cfg
|
||||
*.egg
|
||||
MANIFEST
|
||||
|
||||
# PyInstaller
|
||||
# Usually these files are written by a python script from a template
|
||||
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
||||
*.manifest
|
||||
*.spec
|
||||
|
||||
# Installer logs
|
||||
pip-log.txt
|
||||
pip-delete-this-directory.txt
|
||||
|
||||
# Unit test / coverage reports
|
||||
htmlcov/
|
||||
.tox/
|
||||
.nox/
|
||||
.coverage
|
||||
.coverage.*
|
||||
.cache
|
||||
nosetests.xml
|
||||
coverage.xml
|
||||
*.cover
|
||||
*.py,cover
|
||||
.hypothesis/
|
||||
.pytest_cache/
|
||||
|
||||
# Translations
|
||||
*.mo
|
||||
*.pot
|
||||
|
||||
# Django stuff:
|
||||
*.log
|
||||
local_settings.py
|
||||
db.sqlite3
|
||||
db.sqlite3-journal
|
||||
|
||||
# Flask stuff:
|
||||
instance/
|
||||
.webassets-cache
|
||||
|
||||
# Scrapy stuff:
|
||||
.scrapy
|
||||
|
||||
# Sphinx documentation
|
||||
docs/_build/
|
||||
|
||||
# PyBuilder
|
||||
target/
|
||||
|
||||
# Jupyter Notebook
|
||||
.ipynb_checkpoints
|
||||
notebooks/
|
||||
|
||||
# IPython
|
||||
profile_default/
|
||||
ipython_config.py
|
||||
|
||||
# pyenv
|
||||
.python-version
|
||||
|
||||
# pipenv
|
||||
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
|
||||
# However, in case of collaboration, if having platform-specific dependencies or dependencies
|
||||
# having no cross-platform support, pipenv may install dependencies that don't work, or not
|
||||
# install all needed dependencies.
|
||||
#Pipfile.lock
|
||||
|
||||
# PEP 582; used by e.g. github.com/David-OConnor/pyflow
|
||||
__pypackages__/
|
||||
|
||||
# Celery stuff
|
||||
celerybeat-schedule
|
||||
celerybeat.pid
|
||||
|
||||
# SageMath parsed files
|
||||
*.sage.py
|
||||
|
||||
# Environments
|
||||
.env
|
||||
.venv
|
||||
.venvs
|
||||
env/
|
||||
venv/
|
||||
ENV/
|
||||
env.bak/
|
||||
venv.bak/
|
||||
|
||||
# Spyder project settings
|
||||
.spyderproject
|
||||
.spyproject
|
||||
|
||||
# Rope project settings
|
||||
.ropeproject
|
||||
|
||||
# mkdocs documentation
|
||||
/site
|
||||
|
||||
# mypy
|
||||
.mypy_cache/
|
||||
.dmypy.json
|
||||
dmypy.json
|
||||
|
||||
# Pyre type checker
|
||||
.pyre/
|
||||
|
||||
# macOS display setting files
|
||||
.DS_Store
|
||||
|
||||
|
||||
|
||||
# docker
|
||||
docker/
|
||||
!docker/assets/
|
||||
.dockerignore
|
||||
docker.build
|
9
.gitignore
vendored
9
.gitignore
vendored
@ -106,7 +106,7 @@ celerybeat.pid
|
||||
|
||||
# Environments
|
||||
.env
|
||||
.envrc
|
||||
!docker/.env
|
||||
.venv
|
||||
.venvs
|
||||
env/
|
||||
@ -135,9 +135,4 @@ dmypy.json
|
||||
|
||||
# macOS display setting files
|
||||
.DS_Store
|
||||
|
||||
# Wandb directory
|
||||
wandb/
|
||||
|
||||
# asdf tool versions
|
||||
.tool-versions
|
||||
docker.build
|
||||
|
@ -73,8 +73,6 @@ poetry install -E all
|
||||
|
||||
This will install all requirements for running the package, examples, linting, formatting, tests, and coverage. Note the `-E all` flag will install all optional dependencies necessary for integration testing.
|
||||
|
||||
❗Note: If you're running Poetry 1.4.1 and receive a `WheelFileValidationError` for `debugpy` during installation, you can try either downgrading to Poetry 1.4.0 or disabling "modern installation" (`poetry config installer.modern-installation false`) and re-install requirements. See [this `debugpy` issue](https://github.com/microsoft/debugpy/issues/1246) for more details.
|
||||
|
||||
Now, you should be able to run the common tasks in the following section.
|
||||
|
||||
## ✅Common Tasks
|
||||
@ -153,6 +151,10 @@ poetry run jupyter notebook
|
||||
|
||||
When you run `poetry install`, the `langchain` package is installed as editable in the virtualenv, so your new logic can be imported into the notebook.
|
||||
|
||||
## Using Docker
|
||||
|
||||
Refer to [DOCKER.md](docker/DOCKER.md) for more information.
|
||||
|
||||
## Documentation
|
||||
|
||||
### Contribute Documentation
|
24
Makefile
24
Makefile
@ -1,5 +1,8 @@
|
||||
.PHONY: all clean format lint test tests test_watch integration_tests help
|
||||
|
||||
GIT_HASH ?= $(shell git rev-parse --short HEAD)
|
||||
LANGCHAIN_VERSION := $(shell grep '^version' pyproject.toml | cut -d '=' -f2 | tr -d '"')
|
||||
|
||||
all: help
|
||||
|
||||
coverage:
|
||||
@ -31,8 +34,7 @@ lint:
|
||||
test:
|
||||
poetry run pytest tests/unit_tests
|
||||
|
||||
tests:
|
||||
poetry run pytest tests/unit_tests
|
||||
tests: test
|
||||
|
||||
test_watch:
|
||||
poetry run ptw --now . -- tests/unit_tests
|
||||
@ -46,8 +48,26 @@ help:
|
||||
@echo 'docs_build - build the documentation'
|
||||
@echo 'docs_clean - clean the documentation build artifacts'
|
||||
@echo 'docs_linkcheck - run linkchecker on the documentation'
|
||||
ifneq ($(shell command -v docker 2> /dev/null),)
|
||||
@echo 'docker - build and run the docker dev image'
|
||||
@echo 'docker.run - run the docker dev image'
|
||||
@echo 'docker.jupyter - start a jupyter notebook inside container'
|
||||
@echo 'docker.build - build the docker dev image'
|
||||
@echo 'docker.force_build - force a rebuild'
|
||||
@echo 'docker.test - run the unit tests in docker'
|
||||
@echo 'docker.lint - run the linters in docker'
|
||||
@echo 'docker.clean - remove the docker dev image'
|
||||
endif
|
||||
@echo 'format - run code formatters'
|
||||
@echo 'lint - run linters'
|
||||
@echo 'test - run unit tests'
|
||||
@echo 'test_watch - run unit tests in watch mode'
|
||||
@echo 'integration_tests - run integration tests'
|
||||
|
||||
# include the following makefile if the docker executable is available
|
||||
ifeq ($(shell command -v docker 2> /dev/null),)
|
||||
$(info Docker not found, skipping docker-related targets)
|
||||
else
|
||||
include docker/Makefile
|
||||
endif
|
||||
|
||||
|
18
README.md
18
README.md
@ -1,11 +1,15 @@
|
||||
# 🦜️🔗 LangChain
|
||||
# 🦜️🔗 LangChain - Docker
|
||||
|
||||
⚡ Building applications with LLMs through composability ⚡
|
||||
WIP: This is a fork of langchain focused on implementing a docker warpper and
|
||||
toolchain. The goal is to make it easy to use LLM chains running inside a
|
||||
container, build custom docker based tools and let agents run arbitrary
|
||||
untrusted code inside.
|
||||
|
||||
[![lint](https://github.com/hwchase17/langchain/actions/workflows/lint.yml/badge.svg)](https://github.com/hwchase17/langchain/actions/workflows/lint.yml) [![test](https://github.com/hwchase17/langchain/actions/workflows/test.yml/badge.svg)](https://github.com/hwchase17/langchain/actions/workflows/test.yml) [![linkcheck](https://github.com/hwchase17/langchain/actions/workflows/linkcheck.yml/badge.svg)](https://github.com/hwchase17/langchain/actions/workflows/linkcheck.yml) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai) [![](https://dcbadge.vercel.app/api/server/6adMQxSpJS?compact=true&style=flat)](https://discord.gg/6adMQxSpJS)
|
||||
Currently exploring the following:
|
||||
|
||||
**Production Support:** As you move your LangChains into production, we'd love to offer more comprehensive support.
|
||||
Please fill out [this form](https://forms.gle/57d8AmXBYp8PP8tZA) and we'll set up a dedicated support Slack channel.
|
||||
- Docker wrapper for LLMs and chains
|
||||
- Creating a toolchain for building docker based LLM tools.
|
||||
- Building agents that can run arbitrary untrusted code inside a container.
|
||||
|
||||
## Quick Install
|
||||
|
||||
@ -42,7 +46,7 @@ Please see [here](https://langchain.readthedocs.io/en/latest/?) for full documen
|
||||
- Getting started (installation, setting up the environment, simple examples)
|
||||
- How-To examples (demos, integrations, helper functions)
|
||||
- Reference (full API docs)
|
||||
- Resources (high-level explanation of core concepts)
|
||||
Resources (high-level explanation of core concepts)
|
||||
|
||||
## 🚀 What can this help with?
|
||||
|
||||
@ -79,4 +83,4 @@ For more information on these concepts, please see our [full documentation](http
|
||||
|
||||
As an open source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infra, or better documentation.
|
||||
|
||||
For detailed information on how to contribute, see [here](.github/CONTRIBUTING.md).
|
||||
For detailed information on how to contribute, see [here](CONTRIBUTING.md).
|
||||
|
13
docker/.env
Normal file
13
docker/.env
Normal file
@ -0,0 +1,13 @@
|
||||
# python env
|
||||
PYTHON_VERSION=3.10
|
||||
|
||||
# -E flag is required
|
||||
# comment the following line to only install dev dependencies
|
||||
POETRY_EXTRA_PACKAGES="-E all"
|
||||
|
||||
# at least one group needed
|
||||
POETRY_DEPENDENCIES="dev,test,lint,typing"
|
||||
|
||||
# langchain env. warning: these variables will be baked into the docker image !
|
||||
OPENAI_API_KEY=${OPENAI_API_KEY:-}
|
||||
SERPAPI_API_KEY=${SERPAPI_API_KEY:-}
|
53
docker/DOCKER.md
Normal file
53
docker/DOCKER.md
Normal file
@ -0,0 +1,53 @@
|
||||
# Using Docker
|
||||
|
||||
To quickly get started, run the command `make docker`.
|
||||
|
||||
If docker is installed the Makefile will export extra targets in the fomrat `docker.*` to build and run the docker image. Type `make` for a list of available tasks.
|
||||
|
||||
There is a basic `docker-compose.yml` in the docker directory.
|
||||
|
||||
## Building the development image
|
||||
|
||||
Using `make docker` will build the dev image if it does not exist, then drops
|
||||
you inside the container with the langchain environment available in the shell.
|
||||
|
||||
### Customizing the image and installed dependencies
|
||||
|
||||
The image is built with a default python version and all extras and dev
|
||||
dependencies. It can be customized by changing the variables in the [.env](/docker/.env)
|
||||
file.
|
||||
|
||||
If you don't need all the `extra` dependencies a slimmer image can be obtained by
|
||||
commenting out `POETRY_EXTRA_PACKAGES` in the [.env](docker/.env) file.
|
||||
|
||||
### Image caching
|
||||
|
||||
The Dockerfile is optimized to cache the poetry install step. A rebuild is triggered when there a change to the source code.
|
||||
|
||||
## Example Usage
|
||||
|
||||
All commands from langchain's python environment are available by default in the container.
|
||||
|
||||
A few examples:
|
||||
```bash
|
||||
# run jupyter notebook
|
||||
docker run --rm -it IMG jupyter notebook
|
||||
|
||||
# run ipython
|
||||
docker run --rm -it IMG ipython
|
||||
|
||||
# start web server
|
||||
docker run --rm -p 8888:8888 IMG python -m http.server 8888
|
||||
```
|
||||
|
||||
## Testing / Linting
|
||||
|
||||
Tests and lints are run using your local source directory that is mounted on the volume /src.
|
||||
|
||||
Run unit tests in the container with `make docker.test`.
|
||||
|
||||
Run the linting and formatting checks with `make docker.lint`.
|
||||
|
||||
Note: this task can run in parallel using `make -j4 docker.lint`.
|
||||
|
||||
|
104
docker/Dockerfile
Normal file
104
docker/Dockerfile
Normal file
@ -0,0 +1,104 @@
|
||||
# vim: ft=dockerfile
|
||||
#
|
||||
# see also: https://github.com/python-poetry/poetry/discussions/1879
|
||||
# - with https://github.com/bneijt/poetry-lock-docker
|
||||
# see https://github.com/thehale/docker-python-poetry
|
||||
# see https://github.com/max-pfeiffer/uvicorn-poetry
|
||||
|
||||
# use by default the slim version of python
|
||||
ARG PYTHON_IMAGE_TAG=slim
|
||||
ARG PYTHON_VERSION=${PYTHON_VERSION:-3.11.2}
|
||||
|
||||
####################
|
||||
# Base Environment
|
||||
####################
|
||||
FROM python:$PYTHON_VERSION-$PYTHON_IMAGE_TAG AS lchain-base
|
||||
|
||||
ARG UID=1000
|
||||
ARG USERNAME=lchain
|
||||
|
||||
ENV USERNAME=$USERNAME
|
||||
|
||||
RUN groupadd -g ${UID} $USERNAME
|
||||
RUN useradd -l -m -u ${UID} -g ${UID} $USERNAME
|
||||
|
||||
# used for mounting source code
|
||||
RUN mkdir /src
|
||||
VOLUME /src
|
||||
|
||||
|
||||
#######################
|
||||
## Poetry Builder Image
|
||||
#######################
|
||||
FROM lchain-base AS lchain-base-builder
|
||||
|
||||
ARG POETRY_EXTRA_PACKAGES=$POETRY_EXTRA_PACKAGES
|
||||
ARG POETRY_DEPENDENCIES=$POETRY_DEPENDENCIES
|
||||
|
||||
ENV HOME=/root
|
||||
ENV POETRY_HOME=/root/.poetry
|
||||
ENV POETRY_VIRTUALENVS_IN_PROJECT=false
|
||||
ENV POETRY_NO_INTERACTION=1
|
||||
ENV CACHE_DIR=$HOME/.cache
|
||||
ENV POETRY_CACHE_DIR=$CACHE_DIR/pypoetry
|
||||
ENV PATH="$POETRY_HOME/bin:$PATH"
|
||||
|
||||
WORKDIR /root
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y \
|
||||
build-essential \
|
||||
git \
|
||||
curl
|
||||
|
||||
SHELL ["/bin/bash", "-o", "pipefail", "-c"]
|
||||
|
||||
RUN mkdir -p $CACHE_DIR
|
||||
|
||||
## setup poetry
|
||||
RUN curl -sSL -o $CACHE_DIR/pypoetry-installer.py https://install.python-poetry.org/
|
||||
RUN python3 $CACHE_DIR/pypoetry-installer.py
|
||||
|
||||
|
||||
# # Copy poetry files
|
||||
COPY poetry.* pyproject.toml ./
|
||||
|
||||
RUN mkdir /pip-prefix
|
||||
|
||||
RUN poetry export $POETRY_EXTRA_PACKAGES --with $POETRY_DEPENDENCIES -f requirements.txt --output requirements.txt --without-hashes && \
|
||||
pip install --no-cache-dir --disable-pip-version-check --prefix /pip-prefix -r requirements.txt
|
||||
|
||||
|
||||
# add custom motd message
|
||||
COPY docker/assets/etc/motd /tmp/motd
|
||||
RUN cat /tmp/motd > /etc/motd
|
||||
|
||||
RUN printf "\n%s\n%s\n" "$(poetry version)" "$(python --version)" >> /etc/motd
|
||||
|
||||
###################
|
||||
## Runtime Image
|
||||
###################
|
||||
FROM lchain-base AS lchain
|
||||
|
||||
#jupyter port
|
||||
EXPOSE 8888
|
||||
|
||||
COPY docker/assets/entry.sh /entry
|
||||
RUN chmod +x /entry
|
||||
|
||||
COPY --from=lchain-base-builder /etc/motd /etc/motd
|
||||
COPY --from=lchain-base-builder /usr/bin/git /usr/bin/git
|
||||
|
||||
USER ${USERNAME:-lchain}
|
||||
ENV HOME /home/$USERNAME
|
||||
WORKDIR /home/$USERNAME
|
||||
|
||||
COPY --chown=lchain:lchain --from=lchain-base-builder /pip-prefix $HOME/.local/
|
||||
|
||||
COPY . .
|
||||
|
||||
SHELL ["/bin/bash", "-o", "pipefail", "-c"]
|
||||
RUN pip install --no-deps --disable-pip-version-check --no-cache-dir -e .
|
||||
|
||||
|
||||
entrypoint ["/entry"]
|
84
docker/Makefile
Normal file
84
docker/Makefile
Normal file
@ -0,0 +1,84 @@
|
||||
#do not call this makefile it is included in the main Makefile
|
||||
.PHONY: docker docker.jupyter docker.run docker.force_build docker.clean \
|
||||
docker.test docker.lint docker.lint.mypy docker.lint.black \
|
||||
docker.lint.isort docker.lint.flake
|
||||
|
||||
# read python version from .env file ignoring comments
|
||||
PYTHON_VERSION := $(shell grep PYTHON_VERSION docker/.env | cut -d '=' -f2)
|
||||
POETRY_EXTRA_PACKAGES := $(shell grep '^[^#]*POETRY_EXTRA_PACKAGES' docker/.env | cut -d '=' -f2)
|
||||
POETRY_DEPENDENCIES := $(shell grep 'POETRY_DEPENDENCIES' docker/.env | cut -d '=' -f2)
|
||||
|
||||
|
||||
DOCKER_SRC := $(shell find docker -type f)
|
||||
DOCKER_IMAGE_NAME = langchain/dev
|
||||
|
||||
# SRC is all files matched by the git ls-files command
|
||||
SRC := $(shell git ls-files -- '*' ':!:docker/*')
|
||||
|
||||
# set DOCKER_BUILD_PROGRESS=plain to see detailed build progress
|
||||
DOCKER_BUILD_PROGRESS ?= auto
|
||||
|
||||
# extra message to show when entering the docker container
|
||||
DOCKER_MOTD := docker/assets/etc/motd
|
||||
|
||||
ROOTDIR := $(shell git rev-parse --show-toplevel)
|
||||
|
||||
DOCKER_LINT_CMD = docker run --rm -i -u lchain -v $(ROOTDIR):/src $(DOCKER_IMAGE_NAME):$(GIT_HASH)
|
||||
|
||||
docker: docker.run
|
||||
|
||||
docker.run: docker.build
|
||||
@echo "Docker image: $(DOCKER_IMAGE_NAME):$(GIT_HASH)"
|
||||
docker run --rm -it -u lchain -v $(ROOTDIR):/src $(DOCKER_IMAGE_NAME):$(GIT_HASH)
|
||||
|
||||
docker.jupyter: docker.build
|
||||
docker run --rm -it -v $(ROOTDIR):/src $(DOCKER_IMAGE_NAME):$(GIT_HASH) jupyter notebook
|
||||
|
||||
docker.build: $(SRC) $(DOCKER_SRC) $(DOCKER_MOTD)
|
||||
ifdef $(DOCKER_BUILDKIT)
|
||||
docker buildx build --build-arg PYTHON_VERSION=$(PYTHON_VERSION) \
|
||||
--build-arg POETRY_EXTRA_PACKAGES=$(POETRY_EXTRA_PACKAGES) \
|
||||
--build-arg POETRY_DEPENDENCIES=$(POETRY_DEPENDENCIES) \
|
||||
--progress=$(DOCKER_BUILD_PROGRESS) \
|
||||
$(BUILD_FLAGS) -f docker/Dockerfile -t $(DOCKER_IMAGE_NAME):$(GIT_HASH) .
|
||||
else
|
||||
docker build --build-arg PYTHON_VERSION=$(PYTHON_VERSION) \
|
||||
--build-arg POETRY_EXTRA_PACKAGES=$(POETRY_EXTRA_PACKAGES) \
|
||||
--build-arg POETRY_DEPENDENCIES=$(POETRY_DEPENDENCIES) \
|
||||
$(BUILD_FLAGS) -f docker/Dockerfile -t $(DOCKER_IMAGE_NAME):$(GIT_HASH) .
|
||||
endif
|
||||
docker tag $(DOCKER_IMAGE_NAME):$(GIT_HASH) $(DOCKER_IMAGE_NAME):latest
|
||||
@touch $@ # this prevents docker from rebuilding dependencies that have not
|
||||
@ # changed. Remove the file `docker/docker.build` to force a rebuild.
|
||||
|
||||
docker.force_build: $(DOCKER_SRC)
|
||||
@rm -f docker.build
|
||||
@$(MAKE) docker.build BUILD_FLAGS=--no-cache
|
||||
|
||||
docker.clean:
|
||||
docker rmi $(DOCKER_IMAGE_NAME):$(GIT_HASH) $(DOCKER_IMAGE_NAME):latest
|
||||
|
||||
docker.test: docker.build
|
||||
docker run --rm -it -u lchain -v $(ROOTDIR):/src $(DOCKER_IMAGE_NAME):$(GIT_HASH) \
|
||||
pytest /src/tests/unit_tests
|
||||
|
||||
# this assumes that the docker image has been built
|
||||
docker.lint: docker.lint.mypy docker.lint.black docker.lint.isort \
|
||||
docker.lint.flake
|
||||
|
||||
# these can run in parallel with -j[njobs]
|
||||
docker.lint.mypy:
|
||||
@$(DOCKER_LINT_CMD) mypy /src
|
||||
@printf "\t%s\n" "mypy ... "
|
||||
|
||||
docker.lint.black:
|
||||
@$(DOCKER_LINT_CMD) black /src --check
|
||||
@printf "\t%s\n" "black ... "
|
||||
|
||||
docker.lint.isort:
|
||||
@$(DOCKER_LINT_CMD) isort /src --check
|
||||
@printf "\t%s\n" "isort ... "
|
||||
|
||||
docker.lint.flake:
|
||||
@$(DOCKER_LINT_CMD) flake8 /src
|
||||
@printf "\t%s\n" "flake8 ... "
|
10
docker/assets/entry.sh
Normal file
10
docker/assets/entry.sh
Normal file
@ -0,0 +1,10 @@
|
||||
#!/usr/bin/env bash
|
||||
|
||||
export PATH=$HOME/.local/bin:$PATH
|
||||
|
||||
if [ -z "$1" ]; then
|
||||
cat /etc/motd
|
||||
exec /bin/bash
|
||||
fi
|
||||
|
||||
exec "$@"
|
8
docker/assets/etc/motd
Normal file
8
docker/assets/etc/motd
Normal file
@ -0,0 +1,8 @@
|
||||
All dependencies have been installed in the current shell. There is no
|
||||
virtualenv or a need for `poetry` inside the container.
|
||||
|
||||
Running the command `make docker.run` at the root directory of the project will
|
||||
build the container the first time. On the next runs it will use the cached
|
||||
image. A rebuild will happen when changes are made to the source code.
|
||||
|
||||
You local source directory has been mounted to the /src directory.
|
17
docker/docker-compose.yml
Normal file
17
docker/docker-compose.yml
Normal file
@ -0,0 +1,17 @@
|
||||
version: "3.7"
|
||||
|
||||
services:
|
||||
langchain:
|
||||
hostname: langchain
|
||||
image: langchain/dev:latest
|
||||
build:
|
||||
context: ../
|
||||
dockerfile: docker/Dockerfile
|
||||
args:
|
||||
PYTHON_VERSION: ${PYTHON_VERSION}
|
||||
POETRY_EXTRA_PACKAGES: ${POETRY_EXTRA_PACKAGES}
|
||||
POETRY_DEPENDENCIES: ${POETRY_DEPENDENCIES}
|
||||
|
||||
restart: unless-stopped
|
||||
ports:
|
||||
- 127.0.0.1:8888:8888
|
@ -23,14 +23,13 @@ with open("../pyproject.toml") as f:
|
||||
# -- Project information -----------------------------------------------------
|
||||
|
||||
project = "🦜🔗 LangChain"
|
||||
copyright = "2023, Harrison Chase"
|
||||
copyright = "2022, Harrison Chase"
|
||||
author = "Harrison Chase"
|
||||
|
||||
version = data["tool"]["poetry"]["version"]
|
||||
release = version
|
||||
|
||||
html_title = project + " " + version
|
||||
html_last_updated_fmt = "%b %d, %Y"
|
||||
|
||||
|
||||
# -- General configuration ---------------------------------------------------
|
||||
@ -46,7 +45,6 @@ extensions = [
|
||||
"sphinx.ext.viewcode",
|
||||
"sphinxcontrib.autodoc_pydantic",
|
||||
"myst_nb",
|
||||
"sphinx_copybutton",
|
||||
"sphinx_panels",
|
||||
"IPython.sphinxext.ipython_console_highlighting",
|
||||
]
|
||||
|
@ -1,21 +1,19 @@
|
||||
# AtlasDB
|
||||
|
||||
This page covers how to use Nomic's Atlas ecosystem within LangChain.
|
||||
This page covers how to Nomic's Atlas ecosystem within LangChain.
|
||||
It is broken into two parts: installation and setup, and then references to specific Atlas wrappers.
|
||||
|
||||
## Installation and Setup
|
||||
- Install the Python package with `pip install nomic`
|
||||
- Nomic is also included in langchains poetry extras `poetry install -E all`
|
||||
|
||||
-
|
||||
## Wrappers
|
||||
|
||||
### VectorStore
|
||||
|
||||
There exists a wrapper around the Atlas neural database, allowing you to use it as a vectorstore.
|
||||
This vectorstore also gives you full access to the underlying AtlasProject object, which will allow you to use the full range of Atlas map interactions, such as bulk tagging and automatic topic modeling.
|
||||
Please see [the Atlas docs](https://docs.nomic.ai/atlas_api.html) for more detailed information.
|
||||
|
||||
|
||||
Please see [the Nomic docs](https://docs.nomic.ai/atlas_api.html) for more detailed information.
|
||||
|
||||
|
||||
|
||||
@ -24,4 +22,4 @@ To import this vectorstore:
|
||||
from langchain.vectorstores import AtlasDB
|
||||
```
|
||||
|
||||
For a more detailed walkthrough of the AtlasDB wrapper, see [this notebook](../modules/indexes/vectorstore_examples/atlas.ipynb)
|
||||
For a more detailed walkthrough of the Chroma wrapper, see [this notebook](../modules/indexes/examples/vectorstores.ipynb)
|
||||
|
@ -5,7 +5,7 @@ It is broken into two parts: installation and setup, and then references to spec
|
||||
|
||||
## Installation and Setup
|
||||
|
||||
- Install with `pip install banana-dev`
|
||||
- Install with `pip3 install banana-dev`
|
||||
- Get an Banana api key and set it as an environment variable (`BANANA_API_KEY`)
|
||||
|
||||
## Define your Banana Template
|
||||
|
@ -34,8 +34,7 @@ search = GoogleSerperAPIWrapper()
|
||||
tools = [
|
||||
Tool(
|
||||
name="Intermediate Answer",
|
||||
func=search.run,
|
||||
description="useful for when you need to ask with search"
|
||||
func=search.run
|
||||
)
|
||||
]
|
||||
|
||||
|
@ -1,6 +1,6 @@
|
||||
# Graphsignal
|
||||
|
||||
This page covers how to use the Graphsignal ecosystem to trace and monitor LangChain.
|
||||
This page covers how to use the Graphsignal to trace and monitor LangChain.
|
||||
|
||||
## Installation and Setup
|
||||
|
||||
|
@ -1,6 +1,6 @@
|
||||
# Helicone
|
||||
|
||||
This page covers how to use the [Helicone](https://helicone.ai) ecosystem within LangChain.
|
||||
This page covers how to use the [Helicone](https://helicone.ai) within LangChain.
|
||||
|
||||
## What is Helicone?
|
||||
|
||||
|
@ -1,20 +0,0 @@
|
||||
# Milvus
|
||||
|
||||
This page covers how to use the Milvus ecosystem within LangChain.
|
||||
It is broken into two parts: installation and setup, and then references to specific Milvus wrappers.
|
||||
|
||||
## Installation and Setup
|
||||
- Install the Python SDK with `pip install pymilvus`
|
||||
## Wrappers
|
||||
|
||||
### VectorStore
|
||||
|
||||
There exists a wrapper around Milvus indexes, allowing you to use it as a vectorstore,
|
||||
whether for semantic search or example selection.
|
||||
|
||||
To import this vectorstore:
|
||||
```python
|
||||
from langchain.vectorstores import Milvus
|
||||
```
|
||||
|
||||
For a more detailed walkthrough of the Miluvs wrapper, see [this notebook](../modules/indexes/vectorstore_examples/milvus.ipynb)
|
@ -1,29 +0,0 @@
|
||||
# PGVector
|
||||
|
||||
This page covers how to use the Postgres [PGVector](https://github.com/pgvector/pgvector) ecosystem within LangChain
|
||||
It is broken into two parts: installation and setup, and then references to specific PGVector wrappers.
|
||||
|
||||
## Installation
|
||||
- Install the Python package with `pip install pgvector`
|
||||
|
||||
|
||||
## Setup
|
||||
1. The first step is to create a database with the `pgvector` extension installed.
|
||||
|
||||
Follow the steps at [PGVector Installation Steps](https://github.com/pgvector/pgvector#installation) to install the database and the extension. The docker image is the easiest way to get started.
|
||||
|
||||
## Wrappers
|
||||
|
||||
### VectorStore
|
||||
|
||||
There exists a wrapper around Postgres vector databases, allowing you to use it as a vectorstore,
|
||||
whether for semantic search or example selection.
|
||||
|
||||
To import this vectorstore:
|
||||
```python
|
||||
from langchain.vectorstores.pgvector import PGVector
|
||||
```
|
||||
|
||||
### Usage
|
||||
|
||||
For a more detailed walkthrough of the PGVector Wrapper, see [this notebook](../modules/indexes/vectorstore_examples/pgvector.ipynb)
|
@ -17,4 +17,4 @@ To import this vectorstore:
|
||||
from langchain.vectorstores import Pinecone
|
||||
```
|
||||
|
||||
For a more detailed walkthrough of the Pinecone wrapper, see [this notebook](../modules/indexes/vectorstore_examples/pinecone.ipynb)
|
||||
For a more detailed walkthrough of the Pinecone wrapper, see [this notebook](../modules/indexes/examples/vectorstores.ipynb)
|
||||
|
@ -25,25 +25,7 @@ from langchain.llms import PromptLayerOpenAI
|
||||
llm = PromptLayerOpenAI(pl_tags=["langchain-requests", "chatbot"])
|
||||
```
|
||||
|
||||
To get the PromptLayer request id, use the argument `return_pl_id` when instanializing the LLM
|
||||
```python
|
||||
from langchain.llms import PromptLayerOpenAI
|
||||
llm = PromptLayerOpenAI(return_pl_id=True)
|
||||
```
|
||||
This will add the PromptLayer request ID in the `generation_info` field of the `Generation` returned when using `.generate` or `.agenerate`
|
||||
|
||||
For example:
|
||||
```python
|
||||
llm_results = llm.generate(["hello world"])
|
||||
for res in llm_results.generations:
|
||||
print("pl request id: ", res[0].generation_info["pl_request_id"])
|
||||
```
|
||||
You can use the PromptLayer request ID to add a prompt, score, or other metadata to your request. [Read more about it here](https://magniv.notion.site/Track-4deee1b1f7a34c1680d085f82567dab9).
|
||||
|
||||
This LLM is identical to the [OpenAI LLM](./openai), except that
|
||||
- all your requests will be logged to your PromptLayer account
|
||||
- you can add `pl_tags` when instantializing to tag your requests on PromptLayer
|
||||
- you can add `return_pl_id` when instantializing to return a PromptLayer request id to use [while tracking requests](https://magniv.notion.site/Track-4deee1b1f7a34c1680d085f82567dab9).
|
||||
|
||||
|
||||
PromptLayer also provides native wrappers for [`PromptLayerChatOpenAI`](../modules/chat/examples/promptlayer_chat_openai.ipynb) and `PromptLayerOpenAIChat`
|
||||
|
@ -1,20 +0,0 @@
|
||||
# Qdrant
|
||||
|
||||
This page covers how to use the Qdrant ecosystem within LangChain.
|
||||
It is broken into two parts: installation and setup, and then references to specific Qdrant wrappers.
|
||||
|
||||
## Installation and Setup
|
||||
- Install the Python SDK with `pip install qdrant-client`
|
||||
## Wrappers
|
||||
|
||||
### VectorStore
|
||||
|
||||
There exists a wrapper around Qdrant indexes, allowing you to use it as a vectorstore,
|
||||
whether for semantic search or example selection.
|
||||
|
||||
To import this vectorstore:
|
||||
```python
|
||||
from langchain.vectorstores import Qdrant
|
||||
```
|
||||
|
||||
For a more detailed walkthrough of the Qdrant wrapper, see [this notebook](../modules/indexes/vectorstore_examples/qdrant.ipynb)
|
@ -5,44 +5,21 @@ It is broken into two parts: installation and setup, and then references to the
|
||||
|
||||
## Installation and Setup
|
||||
|
||||
While it is possible to utilize the wrapper in conjunction with [public searx
|
||||
instances](https://searx.space/) these instances frequently do not permit API
|
||||
access (see note on output format below) and have limitations on the frequency
|
||||
of requests. It is recommended to opt for a self-hosted instance instead.
|
||||
|
||||
### Self Hosted Instance:
|
||||
|
||||
See [this page](https://searxng.github.io/searxng/admin/installation.html) for installation instructions.
|
||||
|
||||
When you install SearxNG, the only active output format by default is the HTML format.
|
||||
You need to activate the `json` format to use the API. This can be done by adding the following line to the `settings.yml` file:
|
||||
```yaml
|
||||
search:
|
||||
formats:
|
||||
- html
|
||||
- json
|
||||
```
|
||||
You can make sure that the API is working by issuing a curl request to the API endpoint:
|
||||
|
||||
`curl -kLX GET --data-urlencode q='langchain' -d format=json http://localhost:8888`
|
||||
|
||||
This should return a JSON object with the results.
|
||||
|
||||
- You can find a list of public SearxNG instances [here](https://searx.space/).
|
||||
- It recommended to use a self-hosted instance to avoid abuse on the public instances. Also note that public instances often have a limit on the number of requests.
|
||||
- To run a self-hosted instance see [this page](https://searxng.github.io/searxng/admin/installation.html) for more information.
|
||||
- To use the tool you need to provide the searx host url by:
|
||||
1. passing the named parameter `searx_host` when creating the instance.
|
||||
2. exporting the environment variable `SEARXNG_HOST`.
|
||||
|
||||
## Wrappers
|
||||
|
||||
### Utility
|
||||
|
||||
To use the wrapper we need to pass the host of the SearxNG instance to the wrapper with:
|
||||
1. the named parameter `searx_host` when creating the instance.
|
||||
2. exporting the environment variable `SEARXNG_HOST`.
|
||||
|
||||
You can use the wrapper to get results from a SearxNG instance.
|
||||
|
||||
```python
|
||||
from langchain.utilities import SearxSearchWrapper
|
||||
s = SearxSearchWrapper(searx_host="http://localhost:8888")
|
||||
s.run("what is a large language model?")
|
||||
```
|
||||
|
||||
### Tool
|
||||
@ -52,7 +29,7 @@ You can do this with:
|
||||
|
||||
```python
|
||||
from langchain.agents import load_tools
|
||||
tools = load_tools(["searx-search"], searx_host="http://localhost:8888")
|
||||
tools = load_tools(["searx-search"], searx_host="https://searx.example.com")
|
||||
```
|
||||
|
||||
For more information on tools, see [this page](../modules/agents/tools.md)
|
||||
For more information on this, see [this page](../modules/agents/tools.md)
|
||||
|
@ -17,12 +17,9 @@ This page is broken into two parts: installation and setup, and then references
|
||||
- `poppler-utils`
|
||||
- `tesseract-ocr`
|
||||
- `libreoffice`
|
||||
- If you are parsing PDFs using the `"hi_res"` strategy, run the following to install the `detectron2` model, which
|
||||
- If you are parsing PDFs, run the following to install the `detectron2` model, which
|
||||
`unstructured` uses for layout detection:
|
||||
- `pip install "detectron2@git+https://github.com/facebookresearch/detectron2.git@v0.6#egg=detectron2"`
|
||||
- If `detectron2` is not installed, `unstructured` will fallback to processing PDFs
|
||||
using the `"fast"` strategy, which uses `pdfminer` directly and doesn't require
|
||||
`detectron2`.
|
||||
|
||||
## Wrappers
|
||||
|
||||
|
@ -1,625 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Weights & Biases\n",
|
||||
"\n",
|
||||
"This notebook goes over how to track your LangChain experiments into one centralized Weights and Biases dashboard. To learn more about prompt engineering and the callback please refer to this Report which explains both alongside the resultant dashboards you can expect to see.\n",
|
||||
"\n",
|
||||
"Run in Colab: https://colab.research.google.com/drive/1DXH4beT4HFaRKy_Vm4PoxhXVDRf7Ym8L?usp=sharing\n",
|
||||
"\n",
|
||||
"View Report: https://wandb.ai/a-sh0ts/langchain_callback_demo/reports/Prompt-Engineering-LLMs-with-LangChain-and-W-B--VmlldzozNjk1NTUw#👋-how-to-build-a-callback-in-langchain-for-better-prompt-engineering"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip install wandb\n",
|
||||
"!pip install pandas\n",
|
||||
"!pip install textstat\n",
|
||||
"!pip install spacy\n",
|
||||
"!python -m spacy download en_core_web_sm"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {
|
||||
"id": "T1bSmKd6V2If"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"os.environ[\"WANDB_API_KEY\"] = \"\"\n",
|
||||
"# os.environ[\"OPENAI_API_KEY\"] = \"\"\n",
|
||||
"# os.environ[\"SERPAPI_API_KEY\"] = \"\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {
|
||||
"id": "8WAGnTWpUUnD"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from datetime import datetime\n",
|
||||
"from langchain.callbacks import WandbCallbackHandler, StdOutCallbackHandler\n",
|
||||
"from langchain.callbacks.base import CallbackManager\n",
|
||||
"from langchain.llms import OpenAI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"```\n",
|
||||
"Callback Handler that logs to Weights and Biases.\n",
|
||||
"\n",
|
||||
"Parameters:\n",
|
||||
" job_type (str): The type of job.\n",
|
||||
" project (str): The project to log to.\n",
|
||||
" entity (str): The entity to log to.\n",
|
||||
" tags (list): The tags to log.\n",
|
||||
" group (str): The group to log to.\n",
|
||||
" name (str): The name of the run.\n",
|
||||
" notes (str): The notes to log.\n",
|
||||
" visualize (bool): Whether to visualize the run.\n",
|
||||
" complexity_metrics (bool): Whether to log complexity metrics.\n",
|
||||
" stream_logs (bool): Whether to stream callback actions to W&B\n",
|
||||
"```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "cxBFfZR8d9FC"
|
||||
},
|
||||
"source": [
|
||||
"```\n",
|
||||
"Default values for WandbCallbackHandler(...)\n",
|
||||
"\n",
|
||||
"visualize: bool = False,\n",
|
||||
"complexity_metrics: bool = False,\n",
|
||||
"stream_logs: bool = False,\n",
|
||||
"```\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"NOTE: For beta workflows we have made the default analysis based on textstat and the visualizations based on spacy"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {
|
||||
"id": "KAz8weWuUeXF"
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: Currently logged in as: \u001b[33mharrison-chase\u001b[0m. Use \u001b[1m`wandb login --relogin`\u001b[0m to force relogin\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"Tracking run with wandb version 0.14.0"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"Run data is saved locally in <code>/Users/harrisonchase/workplace/langchain/docs/ecosystem/wandb/run-20230318_150408-e47j1914</code>"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"Syncing run <strong><a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/e47j1914' target=\"_blank\">llm</a></strong> to <a href='https://wandb.ai/harrison-chase/langchain_callback_demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/run' target=\"_blank\">docs</a>)<br/>"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
" View project at <a href='https://wandb.ai/harrison-chase/langchain_callback_demo' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo</a>"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
" View run at <a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/e47j1914' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo/runs/e47j1914</a>"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m The wandb callback is currently in beta and is subject to change based on updates to `langchain`. Please report any issues to https://github.com/wandb/wandb/issues with the tag `langchain`.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"\"\"\"Main function.\n",
|
||||
"\n",
|
||||
"This function is used to try the callback handler.\n",
|
||||
"Scenarios:\n",
|
||||
"1. OpenAI LLM\n",
|
||||
"2. Chain with multiple SubChains on multiple generations\n",
|
||||
"3. Agent with Tools\n",
|
||||
"\"\"\"\n",
|
||||
"session_group = datetime.now().strftime(\"%m.%d.%Y_%H.%M.%S\")\n",
|
||||
"wandb_callback = WandbCallbackHandler(\n",
|
||||
" job_type=\"inference\",\n",
|
||||
" project=\"langchain_callback_demo\",\n",
|
||||
" group=f\"minimal_{session_group}\",\n",
|
||||
" name=\"llm\",\n",
|
||||
" tags=[\"test\"],\n",
|
||||
")\n",
|
||||
"manager = CallbackManager([StdOutCallbackHandler(), wandb_callback])\n",
|
||||
"llm = OpenAI(temperature=0, callback_manager=manager, verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "Q-65jwrDeK6w"
|
||||
},
|
||||
"source": [
|
||||
"\n",
|
||||
"\n",
|
||||
"```\n",
|
||||
"# Defaults for WandbCallbackHandler.flush_tracker(...)\n",
|
||||
"\n",
|
||||
"reset: bool = True,\n",
|
||||
"finish: bool = False,\n",
|
||||
"```\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The `flush_tracker` function is used to log LangChain sessions to Weights & Biases. It takes in the LangChain module or agent, and logs at minimum the prompts and generations alongside the serialized form of the LangChain module to the specified Weights & Biases project. By default we reset the session as opposed to concluding the session outright."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {
|
||||
"id": "o_VmneyIUyx8"
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"Waiting for W&B process to finish... <strong style=\"color:green\">(success).</strong>"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
" View run <strong style=\"color:#cdcd00\">llm</strong> at: <a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/e47j1914' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo/runs/e47j1914</a><br/>Synced 5 W&B file(s), 2 media file(s), 5 artifact file(s) and 0 other file(s)"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"Find logs at: <code>./wandb/run-20230318_150408-e47j1914/logs</code>"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"application/vnd.jupyter.widget-view+json": {
|
||||
"model_id": "0d7b4307ccdb450ea631497174fca2d1",
|
||||
"version_major": 2,
|
||||
"version_minor": 0
|
||||
},
|
||||
"text/plain": [
|
||||
"VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.016745895149999985, max=1.0…"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"Tracking run with wandb version 0.14.0"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"Run data is saved locally in <code>/Users/harrisonchase/workplace/langchain/docs/ecosystem/wandb/run-20230318_150534-jyxma7hu</code>"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"Syncing run <strong><a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/jyxma7hu' target=\"_blank\">simple_sequential</a></strong> to <a href='https://wandb.ai/harrison-chase/langchain_callback_demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/run' target=\"_blank\">docs</a>)<br/>"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
" View project at <a href='https://wandb.ai/harrison-chase/langchain_callback_demo' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo</a>"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
" View run at <a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/jyxma7hu' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo/runs/jyxma7hu</a>"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# SCENARIO 1 - LLM\n",
|
||||
"llm_result = llm.generate([\"Tell me a joke\", \"Tell me a poem\"] * 3)\n",
|
||||
"wandb_callback.flush_tracker(llm, name=\"simple_sequential\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {
|
||||
"id": "trxslyb1U28Y"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.prompts import PromptTemplate\n",
|
||||
"from langchain.chains import LLMChain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {
|
||||
"id": "uauQk10SUzF6"
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"Waiting for W&B process to finish... <strong style=\"color:green\">(success).</strong>"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
" View run <strong style=\"color:#cdcd00\">simple_sequential</strong> at: <a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/jyxma7hu' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo/runs/jyxma7hu</a><br/>Synced 4 W&B file(s), 2 media file(s), 6 artifact file(s) and 0 other file(s)"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"Find logs at: <code>./wandb/run-20230318_150534-jyxma7hu/logs</code>"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"application/vnd.jupyter.widget-view+json": {
|
||||
"model_id": "dbdbf28fb8ed40a3a60218d2e6d1a987",
|
||||
"version_major": 2,
|
||||
"version_minor": 0
|
||||
},
|
||||
"text/plain": [
|
||||
"VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.016736786816666675, max=1.0…"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"Tracking run with wandb version 0.14.0"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"Run data is saved locally in <code>/Users/harrisonchase/workplace/langchain/docs/ecosystem/wandb/run-20230318_150550-wzy59zjq</code>"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"Syncing run <strong><a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/wzy59zjq' target=\"_blank\">agent</a></strong> to <a href='https://wandb.ai/harrison-chase/langchain_callback_demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/run' target=\"_blank\">docs</a>)<br/>"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
" View project at <a href='https://wandb.ai/harrison-chase/langchain_callback_demo' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo</a>"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
" View run at <a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/wzy59zjq' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo/runs/wzy59zjq</a>"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# SCENARIO 2 - Chain\n",
|
||||
"template = \"\"\"You are a playwright. Given the title of play, it is your job to write a synopsis for that title.\n",
|
||||
"Title: {title}\n",
|
||||
"Playwright: This is a synopsis for the above play:\"\"\"\n",
|
||||
"prompt_template = PromptTemplate(input_variables=[\"title\"], template=template)\n",
|
||||
"synopsis_chain = LLMChain(llm=llm, prompt=prompt_template, callback_manager=manager)\n",
|
||||
"\n",
|
||||
"test_prompts = [\n",
|
||||
" {\n",
|
||||
" \"title\": \"documentary about good video games that push the boundary of game design\"\n",
|
||||
" },\n",
|
||||
" {\"title\": \"cocaine bear vs heroin wolf\"},\n",
|
||||
" {\"title\": \"the best in class mlops tooling\"},\n",
|
||||
"]\n",
|
||||
"synopsis_chain.apply(test_prompts)\n",
|
||||
"wandb_callback.flush_tracker(synopsis_chain, name=\"agent\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {
|
||||
"id": "_jN73xcPVEpI"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import initialize_agent, load_tools"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"metadata": {
|
||||
"id": "Gpq4rk6VT9cu"
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I need to find out who Leo DiCaprio's girlfriend is and then calculate her age raised to the 0.43 power.\n",
|
||||
"Action: Search\n",
|
||||
"Action Input: \"Leo DiCaprio girlfriend\"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mDiCaprio had a steady girlfriend in Camila Morrone. He had been with the model turned actress for nearly five years, as they were first said to be dating at the end of 2017. And the now 26-year-old Morrone is no stranger to Hollywood.\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate her age raised to the 0.43 power.\n",
|
||||
"Action: Calculator\n",
|
||||
"Action Input: 26^0.43\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3mAnswer: 4.059182145592686\n",
|
||||
"\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
|
||||
"Final Answer: Leo DiCaprio's girlfriend is Camila Morrone and her current age raised to the 0.43 power is 4.059182145592686.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"Waiting for W&B process to finish... <strong style=\"color:green\">(success).</strong>"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
" View run <strong style=\"color:#cdcd00\">agent</strong> at: <a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/wzy59zjq' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo/runs/wzy59zjq</a><br/>Synced 5 W&B file(s), 2 media file(s), 7 artifact file(s) and 0 other file(s)"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"Find logs at: <code>./wandb/run-20230318_150550-wzy59zjq/logs</code>"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# SCENARIO 3 - Agent with Tools\n",
|
||||
"tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm, callback_manager=manager)\n",
|
||||
"agent = initialize_agent(\n",
|
||||
" tools,\n",
|
||||
" llm,\n",
|
||||
" agent=\"zero-shot-react-description\",\n",
|
||||
" callback_manager=manager,\n",
|
||||
" verbose=True,\n",
|
||||
")\n",
|
||||
"agent.run(\n",
|
||||
" \"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\"\n",
|
||||
")\n",
|
||||
"wandb_callback.flush_tracker(agent, reset=False, finish=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"provenance": []
|
||||
},
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 1
|
||||
}
|
@ -158,14 +158,14 @@ Open Source
|
||||
|
||||
---
|
||||
|
||||
.. link-button:: https://github.com/jerryjliu/llama_index
|
||||
.. link-button:: https://github.com/jerryjliu/gpt_index
|
||||
:type: url
|
||||
:text: LlamaIndex
|
||||
:text: GPT Index
|
||||
:classes: stretched-link btn-lg
|
||||
|
||||
+++
|
||||
|
||||
LlamaIndex (formerly GPT Index) is a project consisting of a set of data structures that are created using GPT-3 and can be traversed using GPT-3 in order to answer queries.
|
||||
GPT Index is a project consisting of a set of data structures that are created using GPT-3 and can be traversed using GPT-3 in order to answer queries.
|
||||
|
||||
---
|
||||
|
||||
@ -322,14 +322,5 @@ Proprietary
|
||||
|
||||
By Zahid Khawaja, this demo utilizes question answering to answer questions about a given website. A followup added this for `YouTube videos <https://twitter.com/chillzaza_/status/1593739682013220865?s=20&t=EhU8jl0KyCPJ7vE9Rnz-cQ>`_, and then another followup added it for `Wikipedia <https://twitter.com/chillzaza_/status/1594847151238037505?s=20&t=EhU8jl0KyCPJ7vE9Rnz-cQ>`_.
|
||||
|
||||
---
|
||||
|
||||
.. link-button:: https://mynd.so
|
||||
:type: url
|
||||
:text: Mynd
|
||||
:classes: stretched-link btn-lg
|
||||
|
||||
+++
|
||||
|
||||
A journaling app for self-care that uses AI to uncover insights and patterns over time.
|
||||
|
||||
|
@ -66,7 +66,7 @@ llm = OpenAI(temperature=0.9)
|
||||
We can now call it on some input!
|
||||
|
||||
```python
|
||||
text = "What would be a good company name for a company that makes colorful socks?"
|
||||
text = "What would be a good company name a company that makes colorful socks?"
|
||||
print(llm(text))
|
||||
```
|
||||
|
||||
|
@ -63,8 +63,6 @@ These modules are, in increasing order of complexity:
|
||||
|
||||
- `Memory <./modules/memory.html>`_: Memory is the concept of persisting state between calls of a chain/agent. LangChain provides a standard interface for memory, a collection of memory implementations, and examples of chains/agents that use memory.
|
||||
|
||||
- `Chat <./modules/chat.html>`_: Chat models are a variation on Language Models that expose a different API - rather than working with raw text, they work with messages. LangChain provides a standard interface for working with them and doing all the same things as above.
|
||||
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
@ -80,7 +78,6 @@ These modules are, in increasing order of complexity:
|
||||
./modules/chains.md
|
||||
./modules/agents.md
|
||||
./modules/memory.md
|
||||
./modules/chat.md
|
||||
|
||||
Use Cases
|
||||
----------
|
||||
@ -97,8 +94,6 @@ The above modules can be used in a variety of ways. LangChain also provides guid
|
||||
|
||||
- `Summarization <./use_cases/summarization.html>`_: Summarizing longer documents into shorter, more condensed chunks of information. A type of Data Augmented Generation.
|
||||
|
||||
- `Querying Tabular Data <./use_cases/tabular.html>`_: If you want to understand how to use LLMs to query data that is stored in a tabular format (csvs, SQL, dataframes, etc) you should read this page.
|
||||
|
||||
- `Evaluation <./use_cases/evaluation.html>`_: Generative models are notoriously hard to evaluate with traditional metrics. One new way of evaluating them is using language models themselves to do the evaluation. LangChain provides some prompts/chains for assisting in this.
|
||||
|
||||
- `Generate similar examples <./use_cases/generate_examples.html>`_: Generating similar examples to a given input. This is a common use case for many applications, and LangChain provides some prompts/chains for assisting in this.
|
||||
@ -119,8 +114,6 @@ The above modules can be used in a variety of ways. LangChain also provides guid
|
||||
./use_cases/combine_docs.md
|
||||
./use_cases/question_answering.md
|
||||
./use_cases/summarization.md
|
||||
./use_cases/tabular.rst
|
||||
./use_cases/extraction.md
|
||||
./use_cases/evaluation.rst
|
||||
./use_cases/model_laboratory.ipynb
|
||||
|
||||
|
@ -1,202 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "7094e328",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# CSV Agent\n",
|
||||
"\n",
|
||||
"This notebook shows how to use agents to interact with a csv. It is mostly optimized for question answering.\n",
|
||||
"\n",
|
||||
"**NOTE: this agent calls the Pandas DataFrame agent under the hood, which in turn calls the Python agent, which executes LLM generated Python code - this can be bad if the LLM generated Python code is harmful. Use cautiously.**\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "827982c7",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import create_csv_agent"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "caae0bec",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.llms import OpenAI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "16c4dc59",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent = create_csv_agent(OpenAI(temperature=0), 'titanic.csv', verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"id": "46b9489d",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mThought: I need to count the number of rows\n",
|
||||
"Action: python_repl_ast\n",
|
||||
"Action Input: len(df)\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m891\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: There are 891 rows in the dataframe.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'There are 891 rows in the dataframe.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 12,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent.run(\"how many rows are there?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "a96309be",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mThought: I need to count the number of people with more than 3 siblings\n",
|
||||
"Action: python_repl_ast\n",
|
||||
"Action Input: df[df['SibSp'] > 3].shape[0]\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m30\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: 30 people have more than 3 siblings.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'30 people have more than 3 siblings.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent.run(\"how many people have more than 3 sibligngs\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "964a09f7",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mThought: I need to calculate the average age first\n",
|
||||
"Action: python_repl_ast\n",
|
||||
"Action Input: df['Age'].mean()\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m29.69911764705882\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I can now calculate the square root\n",
|
||||
"Action: python_repl_ast\n",
|
||||
"Action Input: math.sqrt(df['Age'].mean())\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mname 'math' is not defined\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I need to import the math library\n",
|
||||
"Action: python_repl_ast\n",
|
||||
"Action Input: import math\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mNone\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I can now calculate the square root\n",
|
||||
"Action: python_repl_ast\n",
|
||||
"Action Input: math.sqrt(df['Age'].mean())\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m5.449689683556195\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: 5.449689683556195\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'5.449689683556195'"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent.run(\"whats the square root of the average age?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "551de2be",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
@ -1,190 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "85fb2c03-ab88-4c8c-97e3-a7f2954555ab",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# JSON Agent\n",
|
||||
"\n",
|
||||
"This notebook showcases an agent designed to interact with large JSON/dict objects. This is useful when you want to answer questions about a JSON blob that's too large to fit in the context window of an LLM. The agent is able to iteratively explore the blob to find what it needs to answer the user's question.\n",
|
||||
"\n",
|
||||
"In the below example, we are using the OpenAPI spec for the OpenAI API, which you can find [here](https://github.com/openai/openai-openapi/blob/master/openapi.yaml).\n",
|
||||
"\n",
|
||||
"We will use the JSON agent to answer some questions about the API spec."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "893f90fd-f8f6-470a-a76d-1f200ba02e2f",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Initialization"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "ff988466-c389-4ec6-b6ac-14364a537fd5",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"import yaml\n",
|
||||
"\n",
|
||||
"from langchain.agents import (\n",
|
||||
" create_json_agent,\n",
|
||||
" AgentExecutor\n",
|
||||
")\n",
|
||||
"from langchain.agents.agent_toolkits import JsonToolkit\n",
|
||||
"from langchain.chains import LLMChain\n",
|
||||
"from langchain.llms.openai import OpenAI\n",
|
||||
"from langchain.requests import RequestsWrapper\n",
|
||||
"from langchain.tools.json.tool import JsonSpec"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "9ecd1ba0-3937-4359-a41e-68605f0596a1",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with open(\"openai_openapi.yml\") as f:\n",
|
||||
" data = yaml.load(f, Loader=yaml.FullLoader)\n",
|
||||
"json_spec = JsonSpec(dict_=data, max_value_length=4000)\n",
|
||||
"json_toolkit = JsonToolkit(spec=json_spec)\n",
|
||||
"\n",
|
||||
"json_agent_executor = create_json_agent(\n",
|
||||
" llm=OpenAI(temperature=0),\n",
|
||||
" toolkit=json_toolkit,\n",
|
||||
" verbose=True\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "05cfcb24-4389-4b8f-ad9e-466e3fca8db0",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Example: getting the required POST parameters for a request"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "faf13702-50f0-4d1b-b91f-48c750ccfd98",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mAction: json_spec_list_keys\n",
|
||||
"Action Input: data\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta']\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the paths key to see what endpoints exist\n",
|
||||
"Action: json_spec_list_keys\n",
|
||||
"Action Input: data[\"paths\"]\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m['/engines', '/engines/{engine_id}', '/completions', '/edits', '/images/generations', '/images/edits', '/images/variations', '/embeddings', '/engines/{engine_id}/search', '/files', '/files/{file_id}', '/files/{file_id}/content', '/answers', '/classifications', '/fine-tunes', '/fine-tunes/{fine_tune_id}', '/fine-tunes/{fine_tune_id}/cancel', '/fine-tunes/{fine_tune_id}/events', '/models', '/models/{model}', '/moderations']\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the /completions endpoint to see what parameters are required\n",
|
||||
"Action: json_spec_list_keys\n",
|
||||
"Action Input: data[\"paths\"][\"/completions\"]\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m['post']\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the post key to see what parameters are required\n",
|
||||
"Action: json_spec_list_keys\n",
|
||||
"Action Input: data[\"paths\"][\"/completions\"][\"post\"]\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m['operationId', 'tags', 'summary', 'requestBody', 'responses', 'x-oaiMeta']\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the requestBody key to see what parameters are required\n",
|
||||
"Action: json_spec_list_keys\n",
|
||||
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"]\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m['required', 'content']\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the required key to see what parameters are required\n",
|
||||
"Action: json_spec_get_value\n",
|
||||
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"required\"]\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3mTrue\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the content key to see what parameters are required\n",
|
||||
"Action: json_spec_list_keys\n",
|
||||
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"]\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m['application/json']\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the application/json key to see what parameters are required\n",
|
||||
"Action: json_spec_list_keys\n",
|
||||
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"]\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m['schema']\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the schema key to see what parameters are required\n",
|
||||
"Action: json_spec_list_keys\n",
|
||||
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"]\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m['$ref']\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the $ref key to see what parameters are required\n",
|
||||
"Action: json_spec_get_value\n",
|
||||
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"][\"$ref\"]\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3m#/components/schemas/CreateCompletionRequest\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the CreateCompletionRequest schema to see what parameters are required\n",
|
||||
"Action: json_spec_list_keys\n",
|
||||
"Action Input: data[\"components\"][\"schemas\"][\"CreateCompletionRequest\"]\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m['type', 'properties', 'required']\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the required key to see what parameters are required\n",
|
||||
"Action: json_spec_get_value\n",
|
||||
"Action Input: data[\"components\"][\"schemas\"][\"CreateCompletionRequest\"][\"required\"]\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3m['model']\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: The required parameters in the request body to the /completions endpoint are 'model'.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"The required parameters in the request body to the /completions endpoint are 'model'.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"json_agent_executor.run(\"What are the required parameters in the request body to the /completions endpoint?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "ba9c9d30",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.9"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
File diff suppressed because it is too large
Load Diff
@ -1,242 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "85fb2c03-ab88-4c8c-97e3-a7f2954555ab",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# OpenAPI Agent\n",
|
||||
"\n",
|
||||
"This notebook showcases an agent designed to interact with an OpenAPI spec and make a correct API request based on the information it has gathered from the spec.\n",
|
||||
"\n",
|
||||
"In the below example, we are using the OpenAPI spec for the OpenAI API, which you can find [here](https://github.com/openai/openai-openapi/blob/master/openapi.yaml)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "893f90fd-f8f6-470a-a76d-1f200ba02e2f",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Initialization"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "ff988466-c389-4ec6-b6ac-14364a537fd5",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"import yaml\n",
|
||||
"\n",
|
||||
"from langchain.agents import create_openapi_agent\n",
|
||||
"from langchain.agents.agent_toolkits import OpenAPIToolkit\n",
|
||||
"from langchain.llms.openai import OpenAI\n",
|
||||
"from langchain.requests import RequestsWrapper\n",
|
||||
"from langchain.tools.json.tool import JsonSpec"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "9ecd1ba0-3937-4359-a41e-68605f0596a1",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with open(\"openai_openapi.yml\") as f:\n",
|
||||
" data = yaml.load(f, Loader=yaml.FullLoader)\n",
|
||||
"json_spec=JsonSpec(dict_=data, max_value_length=4000)\n",
|
||||
"headers = {\n",
|
||||
" \"Authorization\": f\"Bearer {os.getenv('OPENAI_API_KEY')}\"\n",
|
||||
"}\n",
|
||||
"requests_wrapper=RequestsWrapper(headers=headers)\n",
|
||||
"openapi_toolkit = OpenAPIToolkit.from_llm(OpenAI(temperature=0), json_spec, requests_wrapper, verbose=True)\n",
|
||||
"openapi_agent_executor = create_openapi_agent(\n",
|
||||
" llm=OpenAI(temperature=0),\n",
|
||||
" toolkit=openapi_toolkit,\n",
|
||||
" verbose=True\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f111879d-ae84-41f9-ad82-d3e6b72c41ba",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Example: agent capable of analyzing OpenAPI spec and making requests"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "548db7f7-337b-4ba8-905c-e7fd58c01799",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mAction: json_explorer\n",
|
||||
"Action Input: What is the base url for the API?\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mAction: json_spec_list_keys\n",
|
||||
"Action Input: data\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta']\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the servers key to see what the base url is\n",
|
||||
"Action: json_spec_list_keys\n",
|
||||
"Action Input: data[\"servers\"][0]\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mValueError('Value at path `data[\"servers\"][0]` is not a dict, get the value directly.')\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should get the value of the servers key\n",
|
||||
"Action: json_spec_get_value\n",
|
||||
"Action Input: data[\"servers\"][0]\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3m{'url': 'https://api.openai.com/v1'}\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the base url for the API\n",
|
||||
"Final Answer: The base url for the API is https://api.openai.com/v1\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||
"\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3mThe base url for the API is https://api.openai.com/v1\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should find the path for the /completions endpoint.\n",
|
||||
"Action: json_explorer\n",
|
||||
"Action Input: What is the path for the /completions endpoint?\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mAction: json_spec_list_keys\n",
|
||||
"Action Input: data\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta']\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the paths key to see what endpoints exist\n",
|
||||
"Action: json_spec_list_keys\n",
|
||||
"Action Input: data[\"paths\"]\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m['/engines', '/engines/{engine_id}', '/completions', '/edits', '/images/generations', '/images/edits', '/images/variations', '/embeddings', '/engines/{engine_id}/search', '/files', '/files/{file_id}', '/files/{file_id}/content', '/answers', '/classifications', '/fine-tunes', '/fine-tunes/{fine_tune_id}', '/fine-tunes/{fine_tune_id}/cancel', '/fine-tunes/{fine_tune_id}/events', '/models', '/models/{model}', '/moderations']\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the path for the /completions endpoint\n",
|
||||
"Final Answer: data[\"paths\"][2]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||
"\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3mdata[\"paths\"][2]\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should find the required parameters for the POST request.\n",
|
||||
"Action: json_explorer\n",
|
||||
"Action Input: What are the required parameters for a POST request to the /completions endpoint?\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mAction: json_spec_list_keys\n",
|
||||
"Action Input: data\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta']\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the paths key to see what endpoints exist\n",
|
||||
"Action: json_spec_list_keys\n",
|
||||
"Action Input: data[\"paths\"]\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m['/engines', '/engines/{engine_id}', '/completions', '/edits', '/images/generations', '/images/edits', '/images/variations', '/embeddings', '/engines/{engine_id}/search', '/files', '/files/{file_id}', '/files/{file_id}/content', '/answers', '/classifications', '/fine-tunes', '/fine-tunes/{fine_tune_id}', '/fine-tunes/{fine_tune_id}/cancel', '/fine-tunes/{fine_tune_id}/events', '/models', '/models/{model}', '/moderations']\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the /completions endpoint to see what parameters are required\n",
|
||||
"Action: json_spec_list_keys\n",
|
||||
"Action Input: data[\"paths\"][\"/completions\"]\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m['post']\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the post key to see what parameters are required\n",
|
||||
"Action: json_spec_list_keys\n",
|
||||
"Action Input: data[\"paths\"][\"/completions\"][\"post\"]\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m['operationId', 'tags', 'summary', 'requestBody', 'responses', 'x-oaiMeta']\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the requestBody key to see what parameters are required\n",
|
||||
"Action: json_spec_list_keys\n",
|
||||
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"]\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m['required', 'content']\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the content key to see what parameters are required\n",
|
||||
"Action: json_spec_list_keys\n",
|
||||
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"]\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m['application/json']\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the application/json key to see what parameters are required\n",
|
||||
"Action: json_spec_list_keys\n",
|
||||
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"]\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m['schema']\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the schema key to see what parameters are required\n",
|
||||
"Action: json_spec_list_keys\n",
|
||||
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"]\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m['$ref']\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the $ref key to see what parameters are required\n",
|
||||
"Action: json_spec_list_keys\n",
|
||||
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"][\"$ref\"]\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mValueError('Value at path `data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"][\"$ref\"]` is not a dict, get the value directly.')\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the $ref key to get the value directly\n",
|
||||
"Action: json_spec_get_value\n",
|
||||
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"][\"$ref\"]\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3m#/components/schemas/CreateCompletionRequest\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the CreateCompletionRequest schema to see what parameters are required\n",
|
||||
"Action: json_spec_list_keys\n",
|
||||
"Action Input: data[\"components\"][\"schemas\"][\"CreateCompletionRequest\"]\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m['type', 'properties', 'required']\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the required key to see what parameters are required\n",
|
||||
"Action: json_spec_get_value\n",
|
||||
"Action Input: data[\"components\"][\"schemas\"][\"CreateCompletionRequest\"][\"required\"]\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3m['model']\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: The required parameters for a POST request to the /completions endpoint are 'model'.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||
"\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3mThe required parameters for a POST request to the /completions endpoint are 'model'.\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the parameters needed to make the request.\n",
|
||||
"Action: requests_post\n",
|
||||
"Action Input: { \"url\": \"https://api.openai.com/v1/completions\", \"data\": { \"model\": \"davinci\", \"prompt\": \"tell me a joke\" } }\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3m{\"id\":\"cmpl-6oeEcNETfq8TOuIUQvAct6NrBXihs\",\"object\":\"text_completion\",\"created\":1677529082,\"model\":\"davinci\",\"choices\":[{\"text\":\"\\n\\n\\n\\nLove is a battlefield\\n\\n\\n\\nIt's me...And some\",\"index\":0,\"logprobs\":null,\"finish_reason\":\"length\"}],\"usage\":{\"prompt_tokens\":4,\"completion_tokens\":16,\"total_tokens\":20}}\n",
|
||||
"\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
|
||||
"Final Answer: Love is a battlefield. It's me...And some.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"Love is a battlefield. It's me...And some.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"openapi_agent_executor.run(\"Make a post request to openai /completions. The prompt should be 'tell me a joke.'\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "6ec9582b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.9"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
@ -1,204 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "c81da886",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Pandas Dataframe Agent\n",
|
||||
"\n",
|
||||
"This notebook shows how to use agents to interact with a pandas dataframe. It is mostly optimized for question answering.\n",
|
||||
"\n",
|
||||
"**NOTE: this agent calls the Python agent under the hood, which executes LLM generated Python code - this can be bad if the LLM generated Python code is harmful. Use cautiously.**"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "0cdd9bf5",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import create_pandas_dataframe_agent"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "051ebe84",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.llms import OpenAI\n",
|
||||
"import pandas as pd\n",
|
||||
"\n",
|
||||
"df = pd.read_csv('titanic.csv')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "4185ff46",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent = create_pandas_dataframe_agent(OpenAI(temperature=0), df, verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "a9207a2e",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mThought: I need to count the number of rows\n",
|
||||
"Action: python_repl_ast\n",
|
||||
"Action Input: len(df)\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m891\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: There are 891 rows in the dataframe.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'There are 891 rows in the dataframe.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent.run(\"how many rows are there?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "bd43617c",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mThought: I need to count the number of people with more than 3 siblings\n",
|
||||
"Action: python_repl_ast\n",
|
||||
"Action Input: df[df['SibSp'] > 3].shape[0]\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m30\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: 30 people have more than 3 siblings.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'30 people have more than 3 siblings.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent.run(\"how many people have more than 3 sibligngs\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "94e64b58",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mThought: I need to calculate the average age first\n",
|
||||
"Action: python_repl_ast\n",
|
||||
"Action Input: df['Age'].mean()\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m29.69911764705882\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I can now calculate the square root\n",
|
||||
"Action: python_repl_ast\n",
|
||||
"Action Input: math.sqrt(df['Age'].mean())\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mname 'math' is not defined\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I need to import the math library\n",
|
||||
"Action: python_repl_ast\n",
|
||||
"Action Input: import math\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mNone\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I can now calculate the square root\n",
|
||||
"Action: python_repl_ast\n",
|
||||
"Action Input: math.sqrt(df['Age'].mean())\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m5.449689683556195\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: 5.449689683556195\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'5.449689683556195'"
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent.run(\"whats the square root of the average age?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "eba13b4d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
@ -1,228 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "82a4c2cc-20ea-4b20-a565-63e905dee8ff",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Python Agent\n",
|
||||
"\n",
|
||||
"This notebook showcases an agent designed to write and execute python code to answer a question."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "f98e9c90-5c37-4fb9-af3e-d09693af8543",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents.agent_toolkits import create_python_agent\n",
|
||||
"from langchain.tools.python.tool import PythonREPLTool\n",
|
||||
"from langchain.python import PythonREPL\n",
|
||||
"from langchain.llms.openai import OpenAI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "cc422f53-c51c-4694-a834-72ecd1e68363",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent_executor = create_python_agent(\n",
|
||||
" llm=OpenAI(temperature=0, max_tokens=1000),\n",
|
||||
" tool=PythonREPLTool(),\n",
|
||||
" verbose=True\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "c16161de",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Fibonacci Example\n",
|
||||
"This example was created by [John Wiseman](https://twitter.com/lemonodor/status/1628270074074398720?s=20)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "25cd4f92-ea9b-4fe6-9838-a4f85f81eebe",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I need to calculate the 10th fibonacci number\n",
|
||||
"Action: Python REPL\n",
|
||||
"Action Input: def fibonacci(n):\n",
|
||||
" if n == 0:\n",
|
||||
" return 0\n",
|
||||
" elif n == 1:\n",
|
||||
" return 1\n",
|
||||
" else:\n",
|
||||
" return fibonacci(n-1) + fibonacci(n-2)\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I need to call the function with 10 as the argument\n",
|
||||
"Action: Python REPL\n",
|
||||
"Action Input: fibonacci(10)\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: 55\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'55'"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_executor.run(\"What is the 10th fibonacci number?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "7caa30de",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Training neural net\n",
|
||||
"This example was created by [Samee Ur Rehman](https://twitter.com/sameeurehman/status/1630130518133207046?s=20)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "4b9f60e7-eb6a-4f14-8604-498d863d4482",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I need to write a neural network in PyTorch and train it on the given data.\n",
|
||||
"Action: Python REPL\n",
|
||||
"Action Input: \n",
|
||||
"import torch\n",
|
||||
"\n",
|
||||
"# Define the model\n",
|
||||
"model = torch.nn.Sequential(\n",
|
||||
" torch.nn.Linear(1, 1)\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# Define the loss\n",
|
||||
"loss_fn = torch.nn.MSELoss()\n",
|
||||
"\n",
|
||||
"# Define the optimizer\n",
|
||||
"optimizer = torch.optim.SGD(model.parameters(), lr=0.01)\n",
|
||||
"\n",
|
||||
"# Define the data\n",
|
||||
"x_data = torch.tensor([[1.0], [2.0], [3.0], [4.0]])\n",
|
||||
"y_data = torch.tensor([[2.0], [4.0], [6.0], [8.0]])\n",
|
||||
"\n",
|
||||
"# Train the model\n",
|
||||
"for epoch in range(1000):\n",
|
||||
" # Forward pass\n",
|
||||
" y_pred = model(x_data)\n",
|
||||
"\n",
|
||||
" # Compute and print loss\n",
|
||||
" loss = loss_fn(y_pred, y_data)\n",
|
||||
" if (epoch+1) % 100 == 0:\n",
|
||||
" print(f'Epoch {epoch+1}: loss = {loss.item():.4f}')\n",
|
||||
"\n",
|
||||
" # Zero the gradients\n",
|
||||
" optimizer.zero_grad()\n",
|
||||
"\n",
|
||||
" # Backward pass\n",
|
||||
" loss.backward()\n",
|
||||
"\n",
|
||||
" # Update the weights\n",
|
||||
" optimizer.step()\n",
|
||||
"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mEpoch 100: loss = 0.0013\n",
|
||||
"Epoch 200: loss = 0.0007\n",
|
||||
"Epoch 300: loss = 0.0004\n",
|
||||
"Epoch 400: loss = 0.0002\n",
|
||||
"Epoch 500: loss = 0.0001\n",
|
||||
"Epoch 600: loss = 0.0001\n",
|
||||
"Epoch 700: loss = 0.0000\n",
|
||||
"Epoch 800: loss = 0.0000\n",
|
||||
"Epoch 900: loss = 0.0000\n",
|
||||
"Epoch 1000: loss = 0.0000\n",
|
||||
"\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: The prediction for x = 5 is 10.0.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'The prediction for x = 5 is 10.0.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_executor.run(\"\"\"Understand, write a single neuron neural network in PyTorch.\n",
|
||||
"Take synthetic data for y=2x. Train for 1000 epochs and print every 100 epochs.\n",
|
||||
"Return prediction for x = 5\"\"\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "eb654671",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
@ -1,527 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "0e499e90-7a6d-4fab-8aab-31a4df417601",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# SQL Database Agent\n",
|
||||
"\n",
|
||||
"This notebook showcases an agent designed to interact with a sql databases. The agent builds off of [SQLDatabaseChain](https://langchain.readthedocs.io/en/latest/modules/chains/examples/sqlite.html) and is designed to answer more general questions about a database, as well as recover from errors.\n",
|
||||
"\n",
|
||||
"Note that, as this agent is in active development, all answers might not be correct. Additionally, it is not guaranteed that the agent won't perform DML statements on your database given certain questions. Be careful running it on sensitive data!\n",
|
||||
"\n",
|
||||
"This uses the example Chinook database. To set it up follow the instructions on https://database.guide/2-sample-databases-sqlite/, placing the .db file in a notebooks folder at the root of this repository."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "ec927ac6-9b2a-4e8a-9a6e-3e429191875c",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"source": [
|
||||
"## Initialization"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "53422913-967b-4f2a-8022-00269c1be1b1",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import create_sql_agent\n",
|
||||
"from langchain.agents.agent_toolkits import SQLDatabaseToolkit\n",
|
||||
"from langchain.sql_database import SQLDatabase\n",
|
||||
"from langchain.llms.openai import OpenAI\n",
|
||||
"from langchain.agents import AgentExecutor"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "090f3699-79c6-4ce1-ab96-a94f0121fd64",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"db = SQLDatabase.from_uri(\"sqlite:///../../../../notebooks/Chinook.db\")\n",
|
||||
"toolkit = SQLDatabaseToolkit(db=db)\n",
|
||||
"\n",
|
||||
"agent_executor = create_sql_agent(\n",
|
||||
" llm=OpenAI(temperature=0),\n",
|
||||
" toolkit=toolkit,\n",
|
||||
" verbose=True\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "36ae48c7-cb08-4fef-977e-c7d4b96a464b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Example: describing a table"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "ff70e83d-5ad0-4fc7-bb96-27d82ac166d7",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mAction: list_tables_sql_db\n",
|
||||
"Action Input: \"\"\u001b[0m\n",
|
||||
"Observation: \u001b[38;5;200m\u001b[1;3mArtist, Invoice, Playlist, Genre, Album, PlaylistTrack, Track, InvoiceLine, MediaType, Employee, Customer\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the schema of the playlisttrack table\n",
|
||||
"Action: schema_sql_db\n",
|
||||
"Action Input: \"PlaylistTrack\"\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3m\n",
|
||||
"CREATE TABLE \"PlaylistTrack\" (\n",
|
||||
"\t\"PlaylistId\" INTEGER NOT NULL, \n",
|
||||
"\t\"TrackId\" INTEGER NOT NULL, \n",
|
||||
"\tPRIMARY KEY (\"PlaylistId\", \"TrackId\"), \n",
|
||||
"\tFOREIGN KEY(\"TrackId\") REFERENCES \"Track\" (\"TrackId\"), \n",
|
||||
"\tFOREIGN KEY(\"PlaylistId\") REFERENCES \"Playlist\" (\"PlaylistId\")\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"SELECT * FROM 'PlaylistTrack' LIMIT 3;\n",
|
||||
"PlaylistId TrackId\n",
|
||||
"1 3402\n",
|
||||
"1 3389\n",
|
||||
"1 3390\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: The PlaylistTrack table has two columns, PlaylistId and TrackId, and is linked to the Playlist and Track tables.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'The PlaylistTrack table has two columns, PlaylistId and TrackId, and is linked to the Playlist and Track tables.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_executor.run(\"Describe the playlisttrack table\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "9abcfe8e-1868-42a4-8345-ad2d9b44c681",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Example: describing a table, recovering from an error\n",
|
||||
"\n",
|
||||
"In this example, the agent tries to search for a table that doesn't exist, but finds the next best result"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"id": "bea76658-a65b-47e2-b294-6d52c5556246",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mAction: list_tables_sql_db\n",
|
||||
"Action Input: \"\"\u001b[0m\n",
|
||||
"Observation: \u001b[38;5;200m\u001b[1;3mGenre, PlaylistTrack, MediaType, Invoice, InvoiceLine, Track, Playlist, Customer, Album, Employee, Artist\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the schema of the PlaylistSong table\n",
|
||||
"Action: schema_sql_db\n",
|
||||
"Action Input: \"PlaylistSong\"\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3mError: table_names {'PlaylistSong'} not found in database\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should check the spelling of the table\n",
|
||||
"Action: list_tables_sql_db\n",
|
||||
"Action Input: \"\"\u001b[0m\n",
|
||||
"Observation: \u001b[38;5;200m\u001b[1;3mGenre, PlaylistTrack, MediaType, Invoice, InvoiceLine, Track, Playlist, Customer, Album, Employee, Artist\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m The table is called PlaylistTrack\n",
|
||||
"Action: schema_sql_db\n",
|
||||
"Action Input: \"PlaylistTrack\"\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3m\n",
|
||||
"CREATE TABLE \"PlaylistTrack\" (\n",
|
||||
"\t\"PlaylistId\" INTEGER NOT NULL, \n",
|
||||
"\t\"TrackId\" INTEGER NOT NULL, \n",
|
||||
"\tPRIMARY KEY (\"PlaylistId\", \"TrackId\"), \n",
|
||||
"\tFOREIGN KEY(\"TrackId\") REFERENCES \"Track\" (\"TrackId\"), \n",
|
||||
"\tFOREIGN KEY(\"PlaylistId\") REFERENCES \"Playlist\" (\"PlaylistId\")\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"SELECT * FROM 'PlaylistTrack' LIMIT 3;\n",
|
||||
"PlaylistId TrackId\n",
|
||||
"1 3402\n",
|
||||
"1 3389\n",
|
||||
"1 3390\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: The PlaylistTrack table contains two columns, PlaylistId and TrackId, which are both integers and are used to link Playlist and Track tables.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'The PlaylistTrack table contains two columns, PlaylistId and TrackId, which are both integers and are used to link Playlist and Track tables.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 15,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_executor.run(\"Describe the playlistsong table\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "6fbc26af-97e4-4a21-82aa-48bdc992da26",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Example: running queries"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "17bea710-4a23-4de0-b48e-21d57be48293",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mAction: list_tables_sql_db\n",
|
||||
"Action Input: \"\"\u001b[0m\n",
|
||||
"Observation: \u001b[38;5;200m\u001b[1;3mInvoice, MediaType, Artist, InvoiceLine, Genre, Playlist, Employee, Album, PlaylistTrack, Track, Customer\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the schema of the relevant tables to see what columns I can use.\n",
|
||||
"Action: schema_sql_db\n",
|
||||
"Action Input: \"Invoice, Customer\"\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3m\n",
|
||||
"CREATE TABLE \"Customer\" (\n",
|
||||
"\t\"CustomerId\" INTEGER NOT NULL, \n",
|
||||
"\t\"FirstName\" NVARCHAR(40) NOT NULL, \n",
|
||||
"\t\"LastName\" NVARCHAR(20) NOT NULL, \n",
|
||||
"\t\"Company\" NVARCHAR(80), \n",
|
||||
"\t\"Address\" NVARCHAR(70), \n",
|
||||
"\t\"City\" NVARCHAR(40), \n",
|
||||
"\t\"State\" NVARCHAR(40), \n",
|
||||
"\t\"Country\" NVARCHAR(40), \n",
|
||||
"\t\"PostalCode\" NVARCHAR(10), \n",
|
||||
"\t\"Phone\" NVARCHAR(24), \n",
|
||||
"\t\"Fax\" NVARCHAR(24), \n",
|
||||
"\t\"Email\" NVARCHAR(60) NOT NULL, \n",
|
||||
"\t\"SupportRepId\" INTEGER, \n",
|
||||
"\tPRIMARY KEY (\"CustomerId\"), \n",
|
||||
"\tFOREIGN KEY(\"SupportRepId\") REFERENCES \"Employee\" (\"EmployeeId\")\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"SELECT * FROM 'Customer' LIMIT 3;\n",
|
||||
"CustomerId FirstName LastName Company Address City State Country PostalCode Phone Fax Email SupportRepId\n",
|
||||
"1 Luís Gonçalves Embraer - Empresa Brasileira de Aeronáutica S.A. Av. Brigadeiro Faria Lima, 2170 São José dos Campos SP Brazil 12227-000 +55 (12) 3923-5555 +55 (12) 3923-5566 luisg@embraer.com.br 3\n",
|
||||
"2 Leonie Köhler None Theodor-Heuss-Straße 34 Stuttgart None Germany 70174 +49 0711 2842222 None leonekohler@surfeu.de 5\n",
|
||||
"3 François Tremblay None 1498 rue Bélanger Montréal QC Canada H2G 1A7 +1 (514) 721-4711 None ftremblay@gmail.com 3\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"CREATE TABLE \"Invoice\" (\n",
|
||||
"\t\"InvoiceId\" INTEGER NOT NULL, \n",
|
||||
"\t\"CustomerId\" INTEGER NOT NULL, \n",
|
||||
"\t\"InvoiceDate\" DATETIME NOT NULL, \n",
|
||||
"\t\"BillingAddress\" NVARCHAR(70), \n",
|
||||
"\t\"BillingCity\" NVARCHAR(40), \n",
|
||||
"\t\"BillingState\" NVARCHAR(40), \n",
|
||||
"\t\"BillingCountry\" NVARCHAR(40), \n",
|
||||
"\t\"BillingPostalCode\" NVARCHAR(10), \n",
|
||||
"\t\"Total\" NUMERIC(10, 2) NOT NULL, \n",
|
||||
"\tPRIMARY KEY (\"InvoiceId\"), \n",
|
||||
"\tFOREIGN KEY(\"CustomerId\") REFERENCES \"Customer\" (\"CustomerId\")\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"SELECT * FROM 'Invoice' LIMIT 3;\n",
|
||||
"InvoiceId CustomerId InvoiceDate BillingAddress BillingCity BillingState BillingCountry BillingPostalCode Total\n",
|
||||
"1 2 2009-01-01 00:00:00 Theodor-Heuss-Straße 34 Stuttgart None Germany 70174 1.98\n",
|
||||
"2 4 2009-01-02 00:00:00 Ullevålsveien 14 Oslo None Norway 0171 3.96\n",
|
||||
"3 8 2009-01-03 00:00:00 Grétrystraat 63 Brussels None Belgium 1000 5.94\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should query the Invoice and Customer tables to get the total sales per country.\n",
|
||||
"Action: query_sql_db\n",
|
||||
"Action Input: SELECT c.Country, SUM(i.Total) AS TotalSales FROM Invoice i INNER JOIN Customer c ON i.CustomerId = c.CustomerId GROUP BY c.Country ORDER BY TotalSales DESC LIMIT 10\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m[('USA', 523.0600000000003), ('Canada', 303.9599999999999), ('France', 195.09999999999994), ('Brazil', 190.09999999999997), ('Germany', 156.48), ('United Kingdom', 112.85999999999999), ('Czech Republic', 90.24000000000001), ('Portugal', 77.23999999999998), ('India', 75.25999999999999), ('Chile', 46.62)]\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: The customers from the USA spent the most, with a total of $523.06.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'The customers from the USA spent the most, with a total of $523.06.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_executor.run(\"List the total sales per country. Which country's customers spent the most?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "474dddda-c067-4eeb-98b1-e763ee78b18c",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mAction: list_tables_sql_db\n",
|
||||
"Action Input: \"\"\u001b[0m\n",
|
||||
"Observation: \u001b[38;5;200m\u001b[1;3mInvoice, MediaType, Artist, InvoiceLine, Genre, Playlist, Employee, Album, PlaylistTrack, Track, Customer\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the schema of the Playlist and PlaylistTrack tables to see what columns I can use.\n",
|
||||
"Action: schema_sql_db\n",
|
||||
"Action Input: \"Playlist, PlaylistTrack\"\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3m\n",
|
||||
"CREATE TABLE \"Playlist\" (\n",
|
||||
"\t\"PlaylistId\" INTEGER NOT NULL, \n",
|
||||
"\t\"Name\" NVARCHAR(120), \n",
|
||||
"\tPRIMARY KEY (\"PlaylistId\")\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"SELECT * FROM 'Playlist' LIMIT 3;\n",
|
||||
"PlaylistId Name\n",
|
||||
"1 Music\n",
|
||||
"2 Movies\n",
|
||||
"3 TV Shows\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"CREATE TABLE \"PlaylistTrack\" (\n",
|
||||
"\t\"PlaylistId\" INTEGER NOT NULL, \n",
|
||||
"\t\"TrackId\" INTEGER NOT NULL, \n",
|
||||
"\tPRIMARY KEY (\"PlaylistId\", \"TrackId\"), \n",
|
||||
"\tFOREIGN KEY(\"TrackId\") REFERENCES \"Track\" (\"TrackId\"), \n",
|
||||
"\tFOREIGN KEY(\"PlaylistId\") REFERENCES \"Playlist\" (\"PlaylistId\")\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"SELECT * FROM 'PlaylistTrack' LIMIT 3;\n",
|
||||
"PlaylistId TrackId\n",
|
||||
"1 3402\n",
|
||||
"1 3389\n",
|
||||
"1 3390\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I can use a SELECT statement to get the total number of tracks in each playlist.\n",
|
||||
"Action: query_checker_sql_db\n",
|
||||
"Action Input: SELECT Playlist.Name, COUNT(PlaylistTrack.TrackId) AS TotalTracks FROM Playlist INNER JOIN PlaylistTrack ON Playlist.PlaylistId = PlaylistTrack.PlaylistId GROUP BY Playlist.Name\u001b[0m\n",
|
||||
"Observation: \u001b[31;1m\u001b[1;3m\n",
|
||||
"\n",
|
||||
"SELECT Playlist.Name, COUNT(PlaylistTrack.TrackId) AS TotalTracks FROM Playlist INNER JOIN PlaylistTrack ON Playlist.PlaylistId = PlaylistTrack.PlaylistId GROUP BY Playlist.Name\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m The query looks correct, I can now execute it.\n",
|
||||
"Action: query_sql_db\n",
|
||||
"Action Input: SELECT Playlist.Name, COUNT(PlaylistTrack.TrackId) AS TotalTracks FROM Playlist INNER JOIN PlaylistTrack ON Playlist.PlaylistId = PlaylistTrack.PlaylistId GROUP BY Playlist.Name LIMIT 10\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m[('90’s Music', 1477), ('Brazilian Music', 39), ('Classical', 75), ('Classical 101 - Deep Cuts', 25), ('Classical 101 - Next Steps', 25), ('Classical 101 - The Basics', 25), ('Grunge', 15), ('Heavy Metal Classic', 26), ('Music', 6580), ('Music Videos', 1)]\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
|
||||
"Final Answer: The total number of tracks in each playlist are: '90’s Music' (1477), 'Brazilian Music' (39), 'Classical' (75), 'Classical 101 - Deep Cuts' (25), 'Classical 101 - Next Steps' (25), 'Classical 101 - The Basics' (25), 'Grunge' (15), 'Heavy Metal Classic' (26), 'Music' (6580), 'Music Videos' (1).\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"The total number of tracks in each playlist are: '90’s Music' (1477), 'Brazilian Music' (39), 'Classical' (75), 'Classical 101 - Deep Cuts' (25), 'Classical 101 - Next Steps' (25), 'Classical 101 - The Basics' (25), 'Grunge' (15), 'Heavy Metal Classic' (26), 'Music' (6580), 'Music Videos' (1).\""
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_executor.run(\"Show the total number of tracks in each playlist. The Playlist name should be included in the result.\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "7c7503b5-d9d9-4faa-b064-29fcdb5ff213",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Recovering from an error\n",
|
||||
"\n",
|
||||
"In this example, the agent is able to recover from an error after initially trying to access an attribute (`Track.ArtistId`) which doesn't exist."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 16,
|
||||
"id": "9fe4901e-f9e1-4022-b6bc-80e2b2d6a3a4",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mAction: list_tables_sql_db\n",
|
||||
"Action Input: \"\"\u001b[0m\n",
|
||||
"Observation: \u001b[38;5;200m\u001b[1;3mMediaType, Track, Invoice, Album, Playlist, Customer, Employee, InvoiceLine, PlaylistTrack, Genre, Artist\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the schema of the Artist, InvoiceLine, and Track tables to see what columns I can use.\n",
|
||||
"Action: schema_sql_db\n",
|
||||
"Action Input: \"Artist, InvoiceLine, Track\"\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3m\n",
|
||||
"CREATE TABLE \"Artist\" (\n",
|
||||
"\t\"ArtistId\" INTEGER NOT NULL, \n",
|
||||
"\t\"Name\" NVARCHAR(120), \n",
|
||||
"\tPRIMARY KEY (\"ArtistId\")\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"SELECT * FROM 'Artist' LIMIT 3;\n",
|
||||
"ArtistId Name\n",
|
||||
"1 AC/DC\n",
|
||||
"2 Accept\n",
|
||||
"3 Aerosmith\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"CREATE TABLE \"Track\" (\n",
|
||||
"\t\"TrackId\" INTEGER NOT NULL, \n",
|
||||
"\t\"Name\" NVARCHAR(200) NOT NULL, \n",
|
||||
"\t\"AlbumId\" INTEGER, \n",
|
||||
"\t\"MediaTypeId\" INTEGER NOT NULL, \n",
|
||||
"\t\"GenreId\" INTEGER, \n",
|
||||
"\t\"Composer\" NVARCHAR(220), \n",
|
||||
"\t\"Milliseconds\" INTEGER NOT NULL, \n",
|
||||
"\t\"Bytes\" INTEGER, \n",
|
||||
"\t\"UnitPrice\" NUMERIC(10, 2) NOT NULL, \n",
|
||||
"\tPRIMARY KEY (\"TrackId\"), \n",
|
||||
"\tFOREIGN KEY(\"MediaTypeId\") REFERENCES \"MediaType\" (\"MediaTypeId\"), \n",
|
||||
"\tFOREIGN KEY(\"GenreId\") REFERENCES \"Genre\" (\"GenreId\"), \n",
|
||||
"\tFOREIGN KEY(\"AlbumId\") REFERENCES \"Album\" (\"AlbumId\")\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"SELECT * FROM 'Track' LIMIT 3;\n",
|
||||
"TrackId Name AlbumId MediaTypeId GenreId Composer Milliseconds Bytes UnitPrice\n",
|
||||
"1 For Those About To Rock (We Salute You) 1 1 1 Angus Young, Malcolm Young, Brian Johnson 343719 11170334 0.99\n",
|
||||
"2 Balls to the Wall 2 2 1 None 342562 5510424 0.99\n",
|
||||
"3 Fast As a Shark 3 2 1 F. Baltes, S. Kaufman, U. Dirkscneider & W. Hoffman 230619 3990994 0.99\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"CREATE TABLE \"InvoiceLine\" (\n",
|
||||
"\t\"InvoiceLineId\" INTEGER NOT NULL, \n",
|
||||
"\t\"InvoiceId\" INTEGER NOT NULL, \n",
|
||||
"\t\"TrackId\" INTEGER NOT NULL, \n",
|
||||
"\t\"UnitPrice\" NUMERIC(10, 2) NOT NULL, \n",
|
||||
"\t\"Quantity\" INTEGER NOT NULL, \n",
|
||||
"\tPRIMARY KEY (\"InvoiceLineId\"), \n",
|
||||
"\tFOREIGN KEY(\"TrackId\") REFERENCES \"Track\" (\"TrackId\"), \n",
|
||||
"\tFOREIGN KEY(\"InvoiceId\") REFERENCES \"Invoice\" (\"InvoiceId\")\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"SELECT * FROM 'InvoiceLine' LIMIT 3;\n",
|
||||
"InvoiceLineId InvoiceId TrackId UnitPrice Quantity\n",
|
||||
"1 1 2 0.99 1\n",
|
||||
"2 1 4 0.99 1\n",
|
||||
"3 2 6 0.99 1\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should query the database to get the top 3 best selling artists.\n",
|
||||
"Action: query_sql_db\n",
|
||||
"Action Input: SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity FROM Artist INNER JOIN Track ON Artist.ArtistId = Track.ArtistId INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId GROUP BY Artist.Name ORDER BY TotalQuantity DESC LIMIT 3\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mError: (sqlite3.OperationalError) no such column: Track.ArtistId\n",
|
||||
"[SQL: SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity FROM Artist INNER JOIN Track ON Artist.ArtistId = Track.ArtistId INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId GROUP BY Artist.Name ORDER BY TotalQuantity DESC LIMIT 3]\n",
|
||||
"(Background on this error at: https://sqlalche.me/e/14/e3q8)\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should double check my query before executing it.\n",
|
||||
"Action: query_checker_sql_db\n",
|
||||
"Action Input: SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity FROM Artist INNER JOIN Track ON Artist.ArtistId = Track.ArtistId INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId GROUP BY Artist.Name ORDER BY TotalQuantity DESC LIMIT 3\u001b[0m\n",
|
||||
"Observation: \u001b[31;1m\u001b[1;3m\n",
|
||||
"\n",
|
||||
"SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity \n",
|
||||
"FROM Artist \n",
|
||||
"INNER JOIN Track ON Artist.ArtistId = Track.ArtistId \n",
|
||||
"INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId \n",
|
||||
"GROUP BY Artist.Name \n",
|
||||
"ORDER BY TotalQuantity DESC \n",
|
||||
"LIMIT 3;\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
|
||||
"Action: query_sql_db\n",
|
||||
"Action Input: SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity FROM Artist INNER JOIN Album ON Artist.ArtistId = Album.ArtistId INNER JOIN Track ON Album.AlbumId = Track.AlbumId INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId GROUP BY Artist.Name ORDER BY TotalQuantity DESC LIMIT 3\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m[('Iron Maiden', 140), ('U2', 107), ('Metallica', 91)]\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
|
||||
"Final Answer: The top 3 best selling artists are Iron Maiden, U2, and Metallica.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'The top 3 best selling artists are Iron Maiden, U2, and Metallica.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 16,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_executor.run(\"Who are the top 3 best selling artists?\")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.9"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
@ -1,892 +0,0 @@
|
||||
PassengerId,Survived,Pclass,Name,Sex,Age,SibSp,Parch,Ticket,Fare,Cabin,Embarked
|
||||
1,0,3,"Braund, Mr. Owen Harris",male,22,1,0,A/5 21171,7.25,,S
|
||||
2,1,1,"Cumings, Mrs. John Bradley (Florence Briggs Thayer)",female,38,1,0,PC 17599,71.2833,C85,C
|
||||
3,1,3,"Heikkinen, Miss. Laina",female,26,0,0,STON/O2. 3101282,7.925,,S
|
||||
4,1,1,"Futrelle, Mrs. Jacques Heath (Lily May Peel)",female,35,1,0,113803,53.1,C123,S
|
||||
5,0,3,"Allen, Mr. William Henry",male,35,0,0,373450,8.05,,S
|
||||
6,0,3,"Moran, Mr. James",male,,0,0,330877,8.4583,,Q
|
||||
7,0,1,"McCarthy, Mr. Timothy J",male,54,0,0,17463,51.8625,E46,S
|
||||
8,0,3,"Palsson, Master. Gosta Leonard",male,2,3,1,349909,21.075,,S
|
||||
9,1,3,"Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)",female,27,0,2,347742,11.1333,,S
|
||||
10,1,2,"Nasser, Mrs. Nicholas (Adele Achem)",female,14,1,0,237736,30.0708,,C
|
||||
11,1,3,"Sandstrom, Miss. Marguerite Rut",female,4,1,1,PP 9549,16.7,G6,S
|
||||
12,1,1,"Bonnell, Miss. Elizabeth",female,58,0,0,113783,26.55,C103,S
|
||||
13,0,3,"Saundercock, Mr. William Henry",male,20,0,0,A/5. 2151,8.05,,S
|
||||
14,0,3,"Andersson, Mr. Anders Johan",male,39,1,5,347082,31.275,,S
|
||||
15,0,3,"Vestrom, Miss. Hulda Amanda Adolfina",female,14,0,0,350406,7.8542,,S
|
||||
16,1,2,"Hewlett, Mrs. (Mary D Kingcome) ",female,55,0,0,248706,16,,S
|
||||
17,0,3,"Rice, Master. Eugene",male,2,4,1,382652,29.125,,Q
|
||||
18,1,2,"Williams, Mr. Charles Eugene",male,,0,0,244373,13,,S
|
||||
19,0,3,"Vander Planke, Mrs. Julius (Emelia Maria Vandemoortele)",female,31,1,0,345763,18,,S
|
||||
20,1,3,"Masselmani, Mrs. Fatima",female,,0,0,2649,7.225,,C
|
||||
21,0,2,"Fynney, Mr. Joseph J",male,35,0,0,239865,26,,S
|
||||
22,1,2,"Beesley, Mr. Lawrence",male,34,0,0,248698,13,D56,S
|
||||
23,1,3,"McGowan, Miss. Anna ""Annie""",female,15,0,0,330923,8.0292,,Q
|
||||
24,1,1,"Sloper, Mr. William Thompson",male,28,0,0,113788,35.5,A6,S
|
||||
25,0,3,"Palsson, Miss. Torborg Danira",female,8,3,1,349909,21.075,,S
|
||||
26,1,3,"Asplund, Mrs. Carl Oscar (Selma Augusta Emilia Johansson)",female,38,1,5,347077,31.3875,,S
|
||||
27,0,3,"Emir, Mr. Farred Chehab",male,,0,0,2631,7.225,,C
|
||||
28,0,1,"Fortune, Mr. Charles Alexander",male,19,3,2,19950,263,C23 C25 C27,S
|
||||
29,1,3,"O'Dwyer, Miss. Ellen ""Nellie""",female,,0,0,330959,7.8792,,Q
|
||||
30,0,3,"Todoroff, Mr. Lalio",male,,0,0,349216,7.8958,,S
|
||||
31,0,1,"Uruchurtu, Don. Manuel E",male,40,0,0,PC 17601,27.7208,,C
|
||||
32,1,1,"Spencer, Mrs. William Augustus (Marie Eugenie)",female,,1,0,PC 17569,146.5208,B78,C
|
||||
33,1,3,"Glynn, Miss. Mary Agatha",female,,0,0,335677,7.75,,Q
|
||||
34,0,2,"Wheadon, Mr. Edward H",male,66,0,0,C.A. 24579,10.5,,S
|
||||
35,0,1,"Meyer, Mr. Edgar Joseph",male,28,1,0,PC 17604,82.1708,,C
|
||||
36,0,1,"Holverson, Mr. Alexander Oskar",male,42,1,0,113789,52,,S
|
||||
37,1,3,"Mamee, Mr. Hanna",male,,0,0,2677,7.2292,,C
|
||||
38,0,3,"Cann, Mr. Ernest Charles",male,21,0,0,A./5. 2152,8.05,,S
|
||||
39,0,3,"Vander Planke, Miss. Augusta Maria",female,18,2,0,345764,18,,S
|
||||
40,1,3,"Nicola-Yarred, Miss. Jamila",female,14,1,0,2651,11.2417,,C
|
||||
41,0,3,"Ahlin, Mrs. Johan (Johanna Persdotter Larsson)",female,40,1,0,7546,9.475,,S
|
||||
42,0,2,"Turpin, Mrs. William John Robert (Dorothy Ann Wonnacott)",female,27,1,0,11668,21,,S
|
||||
43,0,3,"Kraeff, Mr. Theodor",male,,0,0,349253,7.8958,,C
|
||||
44,1,2,"Laroche, Miss. Simonne Marie Anne Andree",female,3,1,2,SC/Paris 2123,41.5792,,C
|
||||
45,1,3,"Devaney, Miss. Margaret Delia",female,19,0,0,330958,7.8792,,Q
|
||||
46,0,3,"Rogers, Mr. William John",male,,0,0,S.C./A.4. 23567,8.05,,S
|
||||
47,0,3,"Lennon, Mr. Denis",male,,1,0,370371,15.5,,Q
|
||||
48,1,3,"O'Driscoll, Miss. Bridget",female,,0,0,14311,7.75,,Q
|
||||
49,0,3,"Samaan, Mr. Youssef",male,,2,0,2662,21.6792,,C
|
||||
50,0,3,"Arnold-Franchi, Mrs. Josef (Josefine Franchi)",female,18,1,0,349237,17.8,,S
|
||||
51,0,3,"Panula, Master. Juha Niilo",male,7,4,1,3101295,39.6875,,S
|
||||
52,0,3,"Nosworthy, Mr. Richard Cater",male,21,0,0,A/4. 39886,7.8,,S
|
||||
53,1,1,"Harper, Mrs. Henry Sleeper (Myna Haxtun)",female,49,1,0,PC 17572,76.7292,D33,C
|
||||
54,1,2,"Faunthorpe, Mrs. Lizzie (Elizabeth Anne Wilkinson)",female,29,1,0,2926,26,,S
|
||||
55,0,1,"Ostby, Mr. Engelhart Cornelius",male,65,0,1,113509,61.9792,B30,C
|
||||
56,1,1,"Woolner, Mr. Hugh",male,,0,0,19947,35.5,C52,S
|
||||
57,1,2,"Rugg, Miss. Emily",female,21,0,0,C.A. 31026,10.5,,S
|
||||
58,0,3,"Novel, Mr. Mansouer",male,28.5,0,0,2697,7.2292,,C
|
||||
59,1,2,"West, Miss. Constance Mirium",female,5,1,2,C.A. 34651,27.75,,S
|
||||
60,0,3,"Goodwin, Master. William Frederick",male,11,5,2,CA 2144,46.9,,S
|
||||
61,0,3,"Sirayanian, Mr. Orsen",male,22,0,0,2669,7.2292,,C
|
||||
62,1,1,"Icard, Miss. Amelie",female,38,0,0,113572,80,B28,
|
||||
63,0,1,"Harris, Mr. Henry Birkhardt",male,45,1,0,36973,83.475,C83,S
|
||||
64,0,3,"Skoog, Master. Harald",male,4,3,2,347088,27.9,,S
|
||||
65,0,1,"Stewart, Mr. Albert A",male,,0,0,PC 17605,27.7208,,C
|
||||
66,1,3,"Moubarek, Master. Gerios",male,,1,1,2661,15.2458,,C
|
||||
67,1,2,"Nye, Mrs. (Elizabeth Ramell)",female,29,0,0,C.A. 29395,10.5,F33,S
|
||||
68,0,3,"Crease, Mr. Ernest James",male,19,0,0,S.P. 3464,8.1583,,S
|
||||
69,1,3,"Andersson, Miss. Erna Alexandra",female,17,4,2,3101281,7.925,,S
|
||||
70,0,3,"Kink, Mr. Vincenz",male,26,2,0,315151,8.6625,,S
|
||||
71,0,2,"Jenkin, Mr. Stephen Curnow",male,32,0,0,C.A. 33111,10.5,,S
|
||||
72,0,3,"Goodwin, Miss. Lillian Amy",female,16,5,2,CA 2144,46.9,,S
|
||||
73,0,2,"Hood, Mr. Ambrose Jr",male,21,0,0,S.O.C. 14879,73.5,,S
|
||||
74,0,3,"Chronopoulos, Mr. Apostolos",male,26,1,0,2680,14.4542,,C
|
||||
75,1,3,"Bing, Mr. Lee",male,32,0,0,1601,56.4958,,S
|
||||
76,0,3,"Moen, Mr. Sigurd Hansen",male,25,0,0,348123,7.65,F G73,S
|
||||
77,0,3,"Staneff, Mr. Ivan",male,,0,0,349208,7.8958,,S
|
||||
78,0,3,"Moutal, Mr. Rahamin Haim",male,,0,0,374746,8.05,,S
|
||||
79,1,2,"Caldwell, Master. Alden Gates",male,0.83,0,2,248738,29,,S
|
||||
80,1,3,"Dowdell, Miss. Elizabeth",female,30,0,0,364516,12.475,,S
|
||||
81,0,3,"Waelens, Mr. Achille",male,22,0,0,345767,9,,S
|
||||
82,1,3,"Sheerlinck, Mr. Jan Baptist",male,29,0,0,345779,9.5,,S
|
||||
83,1,3,"McDermott, Miss. Brigdet Delia",female,,0,0,330932,7.7875,,Q
|
||||
84,0,1,"Carrau, Mr. Francisco M",male,28,0,0,113059,47.1,,S
|
||||
85,1,2,"Ilett, Miss. Bertha",female,17,0,0,SO/C 14885,10.5,,S
|
||||
86,1,3,"Backstrom, Mrs. Karl Alfred (Maria Mathilda Gustafsson)",female,33,3,0,3101278,15.85,,S
|
||||
87,0,3,"Ford, Mr. William Neal",male,16,1,3,W./C. 6608,34.375,,S
|
||||
88,0,3,"Slocovski, Mr. Selman Francis",male,,0,0,SOTON/OQ 392086,8.05,,S
|
||||
89,1,1,"Fortune, Miss. Mabel Helen",female,23,3,2,19950,263,C23 C25 C27,S
|
||||
90,0,3,"Celotti, Mr. Francesco",male,24,0,0,343275,8.05,,S
|
||||
91,0,3,"Christmann, Mr. Emil",male,29,0,0,343276,8.05,,S
|
||||
92,0,3,"Andreasson, Mr. Paul Edvin",male,20,0,0,347466,7.8542,,S
|
||||
93,0,1,"Chaffee, Mr. Herbert Fuller",male,46,1,0,W.E.P. 5734,61.175,E31,S
|
||||
94,0,3,"Dean, Mr. Bertram Frank",male,26,1,2,C.A. 2315,20.575,,S
|
||||
95,0,3,"Coxon, Mr. Daniel",male,59,0,0,364500,7.25,,S
|
||||
96,0,3,"Shorney, Mr. Charles Joseph",male,,0,0,374910,8.05,,S
|
||||
97,0,1,"Goldschmidt, Mr. George B",male,71,0,0,PC 17754,34.6542,A5,C
|
||||
98,1,1,"Greenfield, Mr. William Bertram",male,23,0,1,PC 17759,63.3583,D10 D12,C
|
||||
99,1,2,"Doling, Mrs. John T (Ada Julia Bone)",female,34,0,1,231919,23,,S
|
||||
100,0,2,"Kantor, Mr. Sinai",male,34,1,0,244367,26,,S
|
||||
101,0,3,"Petranec, Miss. Matilda",female,28,0,0,349245,7.8958,,S
|
||||
102,0,3,"Petroff, Mr. Pastcho (""Pentcho"")",male,,0,0,349215,7.8958,,S
|
||||
103,0,1,"White, Mr. Richard Frasar",male,21,0,1,35281,77.2875,D26,S
|
||||
104,0,3,"Johansson, Mr. Gustaf Joel",male,33,0,0,7540,8.6542,,S
|
||||
105,0,3,"Gustafsson, Mr. Anders Vilhelm",male,37,2,0,3101276,7.925,,S
|
||||
106,0,3,"Mionoff, Mr. Stoytcho",male,28,0,0,349207,7.8958,,S
|
||||
107,1,3,"Salkjelsvik, Miss. Anna Kristine",female,21,0,0,343120,7.65,,S
|
||||
108,1,3,"Moss, Mr. Albert Johan",male,,0,0,312991,7.775,,S
|
||||
109,0,3,"Rekic, Mr. Tido",male,38,0,0,349249,7.8958,,S
|
||||
110,1,3,"Moran, Miss. Bertha",female,,1,0,371110,24.15,,Q
|
||||
111,0,1,"Porter, Mr. Walter Chamberlain",male,47,0,0,110465,52,C110,S
|
||||
112,0,3,"Zabour, Miss. Hileni",female,14.5,1,0,2665,14.4542,,C
|
||||
113,0,3,"Barton, Mr. David John",male,22,0,0,324669,8.05,,S
|
||||
114,0,3,"Jussila, Miss. Katriina",female,20,1,0,4136,9.825,,S
|
||||
115,0,3,"Attalah, Miss. Malake",female,17,0,0,2627,14.4583,,C
|
||||
116,0,3,"Pekoniemi, Mr. Edvard",male,21,0,0,STON/O 2. 3101294,7.925,,S
|
||||
117,0,3,"Connors, Mr. Patrick",male,70.5,0,0,370369,7.75,,Q
|
||||
118,0,2,"Turpin, Mr. William John Robert",male,29,1,0,11668,21,,S
|
||||
119,0,1,"Baxter, Mr. Quigg Edmond",male,24,0,1,PC 17558,247.5208,B58 B60,C
|
||||
120,0,3,"Andersson, Miss. Ellis Anna Maria",female,2,4,2,347082,31.275,,S
|
||||
121,0,2,"Hickman, Mr. Stanley George",male,21,2,0,S.O.C. 14879,73.5,,S
|
||||
122,0,3,"Moore, Mr. Leonard Charles",male,,0,0,A4. 54510,8.05,,S
|
||||
123,0,2,"Nasser, Mr. Nicholas",male,32.5,1,0,237736,30.0708,,C
|
||||
124,1,2,"Webber, Miss. Susan",female,32.5,0,0,27267,13,E101,S
|
||||
125,0,1,"White, Mr. Percival Wayland",male,54,0,1,35281,77.2875,D26,S
|
||||
126,1,3,"Nicola-Yarred, Master. Elias",male,12,1,0,2651,11.2417,,C
|
||||
127,0,3,"McMahon, Mr. Martin",male,,0,0,370372,7.75,,Q
|
||||
128,1,3,"Madsen, Mr. Fridtjof Arne",male,24,0,0,C 17369,7.1417,,S
|
||||
129,1,3,"Peter, Miss. Anna",female,,1,1,2668,22.3583,F E69,C
|
||||
130,0,3,"Ekstrom, Mr. Johan",male,45,0,0,347061,6.975,,S
|
||||
131,0,3,"Drazenoic, Mr. Jozef",male,33,0,0,349241,7.8958,,C
|
||||
132,0,3,"Coelho, Mr. Domingos Fernandeo",male,20,0,0,SOTON/O.Q. 3101307,7.05,,S
|
||||
133,0,3,"Robins, Mrs. Alexander A (Grace Charity Laury)",female,47,1,0,A/5. 3337,14.5,,S
|
||||
134,1,2,"Weisz, Mrs. Leopold (Mathilde Francoise Pede)",female,29,1,0,228414,26,,S
|
||||
135,0,2,"Sobey, Mr. Samuel James Hayden",male,25,0,0,C.A. 29178,13,,S
|
||||
136,0,2,"Richard, Mr. Emile",male,23,0,0,SC/PARIS 2133,15.0458,,C
|
||||
137,1,1,"Newsom, Miss. Helen Monypeny",female,19,0,2,11752,26.2833,D47,S
|
||||
138,0,1,"Futrelle, Mr. Jacques Heath",male,37,1,0,113803,53.1,C123,S
|
||||
139,0,3,"Osen, Mr. Olaf Elon",male,16,0,0,7534,9.2167,,S
|
||||
140,0,1,"Giglio, Mr. Victor",male,24,0,0,PC 17593,79.2,B86,C
|
||||
141,0,3,"Boulos, Mrs. Joseph (Sultana)",female,,0,2,2678,15.2458,,C
|
||||
142,1,3,"Nysten, Miss. Anna Sofia",female,22,0,0,347081,7.75,,S
|
||||
143,1,3,"Hakkarainen, Mrs. Pekka Pietari (Elin Matilda Dolck)",female,24,1,0,STON/O2. 3101279,15.85,,S
|
||||
144,0,3,"Burke, Mr. Jeremiah",male,19,0,0,365222,6.75,,Q
|
||||
145,0,2,"Andrew, Mr. Edgardo Samuel",male,18,0,0,231945,11.5,,S
|
||||
146,0,2,"Nicholls, Mr. Joseph Charles",male,19,1,1,C.A. 33112,36.75,,S
|
||||
147,1,3,"Andersson, Mr. August Edvard (""Wennerstrom"")",male,27,0,0,350043,7.7958,,S
|
||||
148,0,3,"Ford, Miss. Robina Maggie ""Ruby""",female,9,2,2,W./C. 6608,34.375,,S
|
||||
149,0,2,"Navratil, Mr. Michel (""Louis M Hoffman"")",male,36.5,0,2,230080,26,F2,S
|
||||
150,0,2,"Byles, Rev. Thomas Roussel Davids",male,42,0,0,244310,13,,S
|
||||
151,0,2,"Bateman, Rev. Robert James",male,51,0,0,S.O.P. 1166,12.525,,S
|
||||
152,1,1,"Pears, Mrs. Thomas (Edith Wearne)",female,22,1,0,113776,66.6,C2,S
|
||||
153,0,3,"Meo, Mr. Alfonzo",male,55.5,0,0,A.5. 11206,8.05,,S
|
||||
154,0,3,"van Billiard, Mr. Austin Blyler",male,40.5,0,2,A/5. 851,14.5,,S
|
||||
155,0,3,"Olsen, Mr. Ole Martin",male,,0,0,Fa 265302,7.3125,,S
|
||||
156,0,1,"Williams, Mr. Charles Duane",male,51,0,1,PC 17597,61.3792,,C
|
||||
157,1,3,"Gilnagh, Miss. Katherine ""Katie""",female,16,0,0,35851,7.7333,,Q
|
||||
158,0,3,"Corn, Mr. Harry",male,30,0,0,SOTON/OQ 392090,8.05,,S
|
||||
159,0,3,"Smiljanic, Mr. Mile",male,,0,0,315037,8.6625,,S
|
||||
160,0,3,"Sage, Master. Thomas Henry",male,,8,2,CA. 2343,69.55,,S
|
||||
161,0,3,"Cribb, Mr. John Hatfield",male,44,0,1,371362,16.1,,S
|
||||
162,1,2,"Watt, Mrs. James (Elizabeth ""Bessie"" Inglis Milne)",female,40,0,0,C.A. 33595,15.75,,S
|
||||
163,0,3,"Bengtsson, Mr. John Viktor",male,26,0,0,347068,7.775,,S
|
||||
164,0,3,"Calic, Mr. Jovo",male,17,0,0,315093,8.6625,,S
|
||||
165,0,3,"Panula, Master. Eino Viljami",male,1,4,1,3101295,39.6875,,S
|
||||
166,1,3,"Goldsmith, Master. Frank John William ""Frankie""",male,9,0,2,363291,20.525,,S
|
||||
167,1,1,"Chibnall, Mrs. (Edith Martha Bowerman)",female,,0,1,113505,55,E33,S
|
||||
168,0,3,"Skoog, Mrs. William (Anna Bernhardina Karlsson)",female,45,1,4,347088,27.9,,S
|
||||
169,0,1,"Baumann, Mr. John D",male,,0,0,PC 17318,25.925,,S
|
||||
170,0,3,"Ling, Mr. Lee",male,28,0,0,1601,56.4958,,S
|
||||
171,0,1,"Van der hoef, Mr. Wyckoff",male,61,0,0,111240,33.5,B19,S
|
||||
172,0,3,"Rice, Master. Arthur",male,4,4,1,382652,29.125,,Q
|
||||
173,1,3,"Johnson, Miss. Eleanor Ileen",female,1,1,1,347742,11.1333,,S
|
||||
174,0,3,"Sivola, Mr. Antti Wilhelm",male,21,0,0,STON/O 2. 3101280,7.925,,S
|
||||
175,0,1,"Smith, Mr. James Clinch",male,56,0,0,17764,30.6958,A7,C
|
||||
176,0,3,"Klasen, Mr. Klas Albin",male,18,1,1,350404,7.8542,,S
|
||||
177,0,3,"Lefebre, Master. Henry Forbes",male,,3,1,4133,25.4667,,S
|
||||
178,0,1,"Isham, Miss. Ann Elizabeth",female,50,0,0,PC 17595,28.7125,C49,C
|
||||
179,0,2,"Hale, Mr. Reginald",male,30,0,0,250653,13,,S
|
||||
180,0,3,"Leonard, Mr. Lionel",male,36,0,0,LINE,0,,S
|
||||
181,0,3,"Sage, Miss. Constance Gladys",female,,8,2,CA. 2343,69.55,,S
|
||||
182,0,2,"Pernot, Mr. Rene",male,,0,0,SC/PARIS 2131,15.05,,C
|
||||
183,0,3,"Asplund, Master. Clarence Gustaf Hugo",male,9,4,2,347077,31.3875,,S
|
||||
184,1,2,"Becker, Master. Richard F",male,1,2,1,230136,39,F4,S
|
||||
185,1,3,"Kink-Heilmann, Miss. Luise Gretchen",female,4,0,2,315153,22.025,,S
|
||||
186,0,1,"Rood, Mr. Hugh Roscoe",male,,0,0,113767,50,A32,S
|
||||
187,1,3,"O'Brien, Mrs. Thomas (Johanna ""Hannah"" Godfrey)",female,,1,0,370365,15.5,,Q
|
||||
188,1,1,"Romaine, Mr. Charles Hallace (""Mr C Rolmane"")",male,45,0,0,111428,26.55,,S
|
||||
189,0,3,"Bourke, Mr. John",male,40,1,1,364849,15.5,,Q
|
||||
190,0,3,"Turcin, Mr. Stjepan",male,36,0,0,349247,7.8958,,S
|
||||
191,1,2,"Pinsky, Mrs. (Rosa)",female,32,0,0,234604,13,,S
|
||||
192,0,2,"Carbines, Mr. William",male,19,0,0,28424,13,,S
|
||||
193,1,3,"Andersen-Jensen, Miss. Carla Christine Nielsine",female,19,1,0,350046,7.8542,,S
|
||||
194,1,2,"Navratil, Master. Michel M",male,3,1,1,230080,26,F2,S
|
||||
195,1,1,"Brown, Mrs. James Joseph (Margaret Tobin)",female,44,0,0,PC 17610,27.7208,B4,C
|
||||
196,1,1,"Lurette, Miss. Elise",female,58,0,0,PC 17569,146.5208,B80,C
|
||||
197,0,3,"Mernagh, Mr. Robert",male,,0,0,368703,7.75,,Q
|
||||
198,0,3,"Olsen, Mr. Karl Siegwart Andreas",male,42,0,1,4579,8.4042,,S
|
||||
199,1,3,"Madigan, Miss. Margaret ""Maggie""",female,,0,0,370370,7.75,,Q
|
||||
200,0,2,"Yrois, Miss. Henriette (""Mrs Harbeck"")",female,24,0,0,248747,13,,S
|
||||
201,0,3,"Vande Walle, Mr. Nestor Cyriel",male,28,0,0,345770,9.5,,S
|
||||
202,0,3,"Sage, Mr. Frederick",male,,8,2,CA. 2343,69.55,,S
|
||||
203,0,3,"Johanson, Mr. Jakob Alfred",male,34,0,0,3101264,6.4958,,S
|
||||
204,0,3,"Youseff, Mr. Gerious",male,45.5,0,0,2628,7.225,,C
|
||||
205,1,3,"Cohen, Mr. Gurshon ""Gus""",male,18,0,0,A/5 3540,8.05,,S
|
||||
206,0,3,"Strom, Miss. Telma Matilda",female,2,0,1,347054,10.4625,G6,S
|
||||
207,0,3,"Backstrom, Mr. Karl Alfred",male,32,1,0,3101278,15.85,,S
|
||||
208,1,3,"Albimona, Mr. Nassef Cassem",male,26,0,0,2699,18.7875,,C
|
||||
209,1,3,"Carr, Miss. Helen ""Ellen""",female,16,0,0,367231,7.75,,Q
|
||||
210,1,1,"Blank, Mr. Henry",male,40,0,0,112277,31,A31,C
|
||||
211,0,3,"Ali, Mr. Ahmed",male,24,0,0,SOTON/O.Q. 3101311,7.05,,S
|
||||
212,1,2,"Cameron, Miss. Clear Annie",female,35,0,0,F.C.C. 13528,21,,S
|
||||
213,0,3,"Perkin, Mr. John Henry",male,22,0,0,A/5 21174,7.25,,S
|
||||
214,0,2,"Givard, Mr. Hans Kristensen",male,30,0,0,250646,13,,S
|
||||
215,0,3,"Kiernan, Mr. Philip",male,,1,0,367229,7.75,,Q
|
||||
216,1,1,"Newell, Miss. Madeleine",female,31,1,0,35273,113.275,D36,C
|
||||
217,1,3,"Honkanen, Miss. Eliina",female,27,0,0,STON/O2. 3101283,7.925,,S
|
||||
218,0,2,"Jacobsohn, Mr. Sidney Samuel",male,42,1,0,243847,27,,S
|
||||
219,1,1,"Bazzani, Miss. Albina",female,32,0,0,11813,76.2917,D15,C
|
||||
220,0,2,"Harris, Mr. Walter",male,30,0,0,W/C 14208,10.5,,S
|
||||
221,1,3,"Sunderland, Mr. Victor Francis",male,16,0,0,SOTON/OQ 392089,8.05,,S
|
||||
222,0,2,"Bracken, Mr. James H",male,27,0,0,220367,13,,S
|
||||
223,0,3,"Green, Mr. George Henry",male,51,0,0,21440,8.05,,S
|
||||
224,0,3,"Nenkoff, Mr. Christo",male,,0,0,349234,7.8958,,S
|
||||
225,1,1,"Hoyt, Mr. Frederick Maxfield",male,38,1,0,19943,90,C93,S
|
||||
226,0,3,"Berglund, Mr. Karl Ivar Sven",male,22,0,0,PP 4348,9.35,,S
|
||||
227,1,2,"Mellors, Mr. William John",male,19,0,0,SW/PP 751,10.5,,S
|
||||
228,0,3,"Lovell, Mr. John Hall (""Henry"")",male,20.5,0,0,A/5 21173,7.25,,S
|
||||
229,0,2,"Fahlstrom, Mr. Arne Jonas",male,18,0,0,236171,13,,S
|
||||
230,0,3,"Lefebre, Miss. Mathilde",female,,3,1,4133,25.4667,,S
|
||||
231,1,1,"Harris, Mrs. Henry Birkhardt (Irene Wallach)",female,35,1,0,36973,83.475,C83,S
|
||||
232,0,3,"Larsson, Mr. Bengt Edvin",male,29,0,0,347067,7.775,,S
|
||||
233,0,2,"Sjostedt, Mr. Ernst Adolf",male,59,0,0,237442,13.5,,S
|
||||
234,1,3,"Asplund, Miss. Lillian Gertrud",female,5,4,2,347077,31.3875,,S
|
||||
235,0,2,"Leyson, Mr. Robert William Norman",male,24,0,0,C.A. 29566,10.5,,S
|
||||
236,0,3,"Harknett, Miss. Alice Phoebe",female,,0,0,W./C. 6609,7.55,,S
|
||||
237,0,2,"Hold, Mr. Stephen",male,44,1,0,26707,26,,S
|
||||
238,1,2,"Collyer, Miss. Marjorie ""Lottie""",female,8,0,2,C.A. 31921,26.25,,S
|
||||
239,0,2,"Pengelly, Mr. Frederick William",male,19,0,0,28665,10.5,,S
|
||||
240,0,2,"Hunt, Mr. George Henry",male,33,0,0,SCO/W 1585,12.275,,S
|
||||
241,0,3,"Zabour, Miss. Thamine",female,,1,0,2665,14.4542,,C
|
||||
242,1,3,"Murphy, Miss. Katherine ""Kate""",female,,1,0,367230,15.5,,Q
|
||||
243,0,2,"Coleridge, Mr. Reginald Charles",male,29,0,0,W./C. 14263,10.5,,S
|
||||
244,0,3,"Maenpaa, Mr. Matti Alexanteri",male,22,0,0,STON/O 2. 3101275,7.125,,S
|
||||
245,0,3,"Attalah, Mr. Sleiman",male,30,0,0,2694,7.225,,C
|
||||
246,0,1,"Minahan, Dr. William Edward",male,44,2,0,19928,90,C78,Q
|
||||
247,0,3,"Lindahl, Miss. Agda Thorilda Viktoria",female,25,0,0,347071,7.775,,S
|
||||
248,1,2,"Hamalainen, Mrs. William (Anna)",female,24,0,2,250649,14.5,,S
|
||||
249,1,1,"Beckwith, Mr. Richard Leonard",male,37,1,1,11751,52.5542,D35,S
|
||||
250,0,2,"Carter, Rev. Ernest Courtenay",male,54,1,0,244252,26,,S
|
||||
251,0,3,"Reed, Mr. James George",male,,0,0,362316,7.25,,S
|
||||
252,0,3,"Strom, Mrs. Wilhelm (Elna Matilda Persson)",female,29,1,1,347054,10.4625,G6,S
|
||||
253,0,1,"Stead, Mr. William Thomas",male,62,0,0,113514,26.55,C87,S
|
||||
254,0,3,"Lobb, Mr. William Arthur",male,30,1,0,A/5. 3336,16.1,,S
|
||||
255,0,3,"Rosblom, Mrs. Viktor (Helena Wilhelmina)",female,41,0,2,370129,20.2125,,S
|
||||
256,1,3,"Touma, Mrs. Darwis (Hanne Youssef Razi)",female,29,0,2,2650,15.2458,,C
|
||||
257,1,1,"Thorne, Mrs. Gertrude Maybelle",female,,0,0,PC 17585,79.2,,C
|
||||
258,1,1,"Cherry, Miss. Gladys",female,30,0,0,110152,86.5,B77,S
|
||||
259,1,1,"Ward, Miss. Anna",female,35,0,0,PC 17755,512.3292,,C
|
||||
260,1,2,"Parrish, Mrs. (Lutie Davis)",female,50,0,1,230433,26,,S
|
||||
261,0,3,"Smith, Mr. Thomas",male,,0,0,384461,7.75,,Q
|
||||
262,1,3,"Asplund, Master. Edvin Rojj Felix",male,3,4,2,347077,31.3875,,S
|
||||
263,0,1,"Taussig, Mr. Emil",male,52,1,1,110413,79.65,E67,S
|
||||
264,0,1,"Harrison, Mr. William",male,40,0,0,112059,0,B94,S
|
||||
265,0,3,"Henry, Miss. Delia",female,,0,0,382649,7.75,,Q
|
||||
266,0,2,"Reeves, Mr. David",male,36,0,0,C.A. 17248,10.5,,S
|
||||
267,0,3,"Panula, Mr. Ernesti Arvid",male,16,4,1,3101295,39.6875,,S
|
||||
268,1,3,"Persson, Mr. Ernst Ulrik",male,25,1,0,347083,7.775,,S
|
||||
269,1,1,"Graham, Mrs. William Thompson (Edith Junkins)",female,58,0,1,PC 17582,153.4625,C125,S
|
||||
270,1,1,"Bissette, Miss. Amelia",female,35,0,0,PC 17760,135.6333,C99,S
|
||||
271,0,1,"Cairns, Mr. Alexander",male,,0,0,113798,31,,S
|
||||
272,1,3,"Tornquist, Mr. William Henry",male,25,0,0,LINE,0,,S
|
||||
273,1,2,"Mellinger, Mrs. (Elizabeth Anne Maidment)",female,41,0,1,250644,19.5,,S
|
||||
274,0,1,"Natsch, Mr. Charles H",male,37,0,1,PC 17596,29.7,C118,C
|
||||
275,1,3,"Healy, Miss. Hanora ""Nora""",female,,0,0,370375,7.75,,Q
|
||||
276,1,1,"Andrews, Miss. Kornelia Theodosia",female,63,1,0,13502,77.9583,D7,S
|
||||
277,0,3,"Lindblom, Miss. Augusta Charlotta",female,45,0,0,347073,7.75,,S
|
||||
278,0,2,"Parkes, Mr. Francis ""Frank""",male,,0,0,239853,0,,S
|
||||
279,0,3,"Rice, Master. Eric",male,7,4,1,382652,29.125,,Q
|
||||
280,1,3,"Abbott, Mrs. Stanton (Rosa Hunt)",female,35,1,1,C.A. 2673,20.25,,S
|
||||
281,0,3,"Duane, Mr. Frank",male,65,0,0,336439,7.75,,Q
|
||||
282,0,3,"Olsson, Mr. Nils Johan Goransson",male,28,0,0,347464,7.8542,,S
|
||||
283,0,3,"de Pelsmaeker, Mr. Alfons",male,16,0,0,345778,9.5,,S
|
||||
284,1,3,"Dorking, Mr. Edward Arthur",male,19,0,0,A/5. 10482,8.05,,S
|
||||
285,0,1,"Smith, Mr. Richard William",male,,0,0,113056,26,A19,S
|
||||
286,0,3,"Stankovic, Mr. Ivan",male,33,0,0,349239,8.6625,,C
|
||||
287,1,3,"de Mulder, Mr. Theodore",male,30,0,0,345774,9.5,,S
|
||||
288,0,3,"Naidenoff, Mr. Penko",male,22,0,0,349206,7.8958,,S
|
||||
289,1,2,"Hosono, Mr. Masabumi",male,42,0,0,237798,13,,S
|
||||
290,1,3,"Connolly, Miss. Kate",female,22,0,0,370373,7.75,,Q
|
||||
291,1,1,"Barber, Miss. Ellen ""Nellie""",female,26,0,0,19877,78.85,,S
|
||||
292,1,1,"Bishop, Mrs. Dickinson H (Helen Walton)",female,19,1,0,11967,91.0792,B49,C
|
||||
293,0,2,"Levy, Mr. Rene Jacques",male,36,0,0,SC/Paris 2163,12.875,D,C
|
||||
294,0,3,"Haas, Miss. Aloisia",female,24,0,0,349236,8.85,,S
|
||||
295,0,3,"Mineff, Mr. Ivan",male,24,0,0,349233,7.8958,,S
|
||||
296,0,1,"Lewy, Mr. Ervin G",male,,0,0,PC 17612,27.7208,,C
|
||||
297,0,3,"Hanna, Mr. Mansour",male,23.5,0,0,2693,7.2292,,C
|
||||
298,0,1,"Allison, Miss. Helen Loraine",female,2,1,2,113781,151.55,C22 C26,S
|
||||
299,1,1,"Saalfeld, Mr. Adolphe",male,,0,0,19988,30.5,C106,S
|
||||
300,1,1,"Baxter, Mrs. James (Helene DeLaudeniere Chaput)",female,50,0,1,PC 17558,247.5208,B58 B60,C
|
||||
301,1,3,"Kelly, Miss. Anna Katherine ""Annie Kate""",female,,0,0,9234,7.75,,Q
|
||||
302,1,3,"McCoy, Mr. Bernard",male,,2,0,367226,23.25,,Q
|
||||
303,0,3,"Johnson, Mr. William Cahoone Jr",male,19,0,0,LINE,0,,S
|
||||
304,1,2,"Keane, Miss. Nora A",female,,0,0,226593,12.35,E101,Q
|
||||
305,0,3,"Williams, Mr. Howard Hugh ""Harry""",male,,0,0,A/5 2466,8.05,,S
|
||||
306,1,1,"Allison, Master. Hudson Trevor",male,0.92,1,2,113781,151.55,C22 C26,S
|
||||
307,1,1,"Fleming, Miss. Margaret",female,,0,0,17421,110.8833,,C
|
||||
308,1,1,"Penasco y Castellana, Mrs. Victor de Satode (Maria Josefa Perez de Soto y Vallejo)",female,17,1,0,PC 17758,108.9,C65,C
|
||||
309,0,2,"Abelson, Mr. Samuel",male,30,1,0,P/PP 3381,24,,C
|
||||
310,1,1,"Francatelli, Miss. Laura Mabel",female,30,0,0,PC 17485,56.9292,E36,C
|
||||
311,1,1,"Hays, Miss. Margaret Bechstein",female,24,0,0,11767,83.1583,C54,C
|
||||
312,1,1,"Ryerson, Miss. Emily Borie",female,18,2,2,PC 17608,262.375,B57 B59 B63 B66,C
|
||||
313,0,2,"Lahtinen, Mrs. William (Anna Sylfven)",female,26,1,1,250651,26,,S
|
||||
314,0,3,"Hendekovic, Mr. Ignjac",male,28,0,0,349243,7.8958,,S
|
||||
315,0,2,"Hart, Mr. Benjamin",male,43,1,1,F.C.C. 13529,26.25,,S
|
||||
316,1,3,"Nilsson, Miss. Helmina Josefina",female,26,0,0,347470,7.8542,,S
|
||||
317,1,2,"Kantor, Mrs. Sinai (Miriam Sternin)",female,24,1,0,244367,26,,S
|
||||
318,0,2,"Moraweck, Dr. Ernest",male,54,0,0,29011,14,,S
|
||||
319,1,1,"Wick, Miss. Mary Natalie",female,31,0,2,36928,164.8667,C7,S
|
||||
320,1,1,"Spedden, Mrs. Frederic Oakley (Margaretta Corning Stone)",female,40,1,1,16966,134.5,E34,C
|
||||
321,0,3,"Dennis, Mr. Samuel",male,22,0,0,A/5 21172,7.25,,S
|
||||
322,0,3,"Danoff, Mr. Yoto",male,27,0,0,349219,7.8958,,S
|
||||
323,1,2,"Slayter, Miss. Hilda Mary",female,30,0,0,234818,12.35,,Q
|
||||
324,1,2,"Caldwell, Mrs. Albert Francis (Sylvia Mae Harbaugh)",female,22,1,1,248738,29,,S
|
||||
325,0,3,"Sage, Mr. George John Jr",male,,8,2,CA. 2343,69.55,,S
|
||||
326,1,1,"Young, Miss. Marie Grice",female,36,0,0,PC 17760,135.6333,C32,C
|
||||
327,0,3,"Nysveen, Mr. Johan Hansen",male,61,0,0,345364,6.2375,,S
|
||||
328,1,2,"Ball, Mrs. (Ada E Hall)",female,36,0,0,28551,13,D,S
|
||||
329,1,3,"Goldsmith, Mrs. Frank John (Emily Alice Brown)",female,31,1,1,363291,20.525,,S
|
||||
330,1,1,"Hippach, Miss. Jean Gertrude",female,16,0,1,111361,57.9792,B18,C
|
||||
331,1,3,"McCoy, Miss. Agnes",female,,2,0,367226,23.25,,Q
|
||||
332,0,1,"Partner, Mr. Austen",male,45.5,0,0,113043,28.5,C124,S
|
||||
333,0,1,"Graham, Mr. George Edward",male,38,0,1,PC 17582,153.4625,C91,S
|
||||
334,0,3,"Vander Planke, Mr. Leo Edmondus",male,16,2,0,345764,18,,S
|
||||
335,1,1,"Frauenthal, Mrs. Henry William (Clara Heinsheimer)",female,,1,0,PC 17611,133.65,,S
|
||||
336,0,3,"Denkoff, Mr. Mitto",male,,0,0,349225,7.8958,,S
|
||||
337,0,1,"Pears, Mr. Thomas Clinton",male,29,1,0,113776,66.6,C2,S
|
||||
338,1,1,"Burns, Miss. Elizabeth Margaret",female,41,0,0,16966,134.5,E40,C
|
||||
339,1,3,"Dahl, Mr. Karl Edwart",male,45,0,0,7598,8.05,,S
|
||||
340,0,1,"Blackwell, Mr. Stephen Weart",male,45,0,0,113784,35.5,T,S
|
||||
341,1,2,"Navratil, Master. Edmond Roger",male,2,1,1,230080,26,F2,S
|
||||
342,1,1,"Fortune, Miss. Alice Elizabeth",female,24,3,2,19950,263,C23 C25 C27,S
|
||||
343,0,2,"Collander, Mr. Erik Gustaf",male,28,0,0,248740,13,,S
|
||||
344,0,2,"Sedgwick, Mr. Charles Frederick Waddington",male,25,0,0,244361,13,,S
|
||||
345,0,2,"Fox, Mr. Stanley Hubert",male,36,0,0,229236,13,,S
|
||||
346,1,2,"Brown, Miss. Amelia ""Mildred""",female,24,0,0,248733,13,F33,S
|
||||
347,1,2,"Smith, Miss. Marion Elsie",female,40,0,0,31418,13,,S
|
||||
348,1,3,"Davison, Mrs. Thomas Henry (Mary E Finck)",female,,1,0,386525,16.1,,S
|
||||
349,1,3,"Coutts, Master. William Loch ""William""",male,3,1,1,C.A. 37671,15.9,,S
|
||||
350,0,3,"Dimic, Mr. Jovan",male,42,0,0,315088,8.6625,,S
|
||||
351,0,3,"Odahl, Mr. Nils Martin",male,23,0,0,7267,9.225,,S
|
||||
352,0,1,"Williams-Lambert, Mr. Fletcher Fellows",male,,0,0,113510,35,C128,S
|
||||
353,0,3,"Elias, Mr. Tannous",male,15,1,1,2695,7.2292,,C
|
||||
354,0,3,"Arnold-Franchi, Mr. Josef",male,25,1,0,349237,17.8,,S
|
||||
355,0,3,"Yousif, Mr. Wazli",male,,0,0,2647,7.225,,C
|
||||
356,0,3,"Vanden Steen, Mr. Leo Peter",male,28,0,0,345783,9.5,,S
|
||||
357,1,1,"Bowerman, Miss. Elsie Edith",female,22,0,1,113505,55,E33,S
|
||||
358,0,2,"Funk, Miss. Annie Clemmer",female,38,0,0,237671,13,,S
|
||||
359,1,3,"McGovern, Miss. Mary",female,,0,0,330931,7.8792,,Q
|
||||
360,1,3,"Mockler, Miss. Helen Mary ""Ellie""",female,,0,0,330980,7.8792,,Q
|
||||
361,0,3,"Skoog, Mr. Wilhelm",male,40,1,4,347088,27.9,,S
|
||||
362,0,2,"del Carlo, Mr. Sebastiano",male,29,1,0,SC/PARIS 2167,27.7208,,C
|
||||
363,0,3,"Barbara, Mrs. (Catherine David)",female,45,0,1,2691,14.4542,,C
|
||||
364,0,3,"Asim, Mr. Adola",male,35,0,0,SOTON/O.Q. 3101310,7.05,,S
|
||||
365,0,3,"O'Brien, Mr. Thomas",male,,1,0,370365,15.5,,Q
|
||||
366,0,3,"Adahl, Mr. Mauritz Nils Martin",male,30,0,0,C 7076,7.25,,S
|
||||
367,1,1,"Warren, Mrs. Frank Manley (Anna Sophia Atkinson)",female,60,1,0,110813,75.25,D37,C
|
||||
368,1,3,"Moussa, Mrs. (Mantoura Boulos)",female,,0,0,2626,7.2292,,C
|
||||
369,1,3,"Jermyn, Miss. Annie",female,,0,0,14313,7.75,,Q
|
||||
370,1,1,"Aubart, Mme. Leontine Pauline",female,24,0,0,PC 17477,69.3,B35,C
|
||||
371,1,1,"Harder, Mr. George Achilles",male,25,1,0,11765,55.4417,E50,C
|
||||
372,0,3,"Wiklund, Mr. Jakob Alfred",male,18,1,0,3101267,6.4958,,S
|
||||
373,0,3,"Beavan, Mr. William Thomas",male,19,0,0,323951,8.05,,S
|
||||
374,0,1,"Ringhini, Mr. Sante",male,22,0,0,PC 17760,135.6333,,C
|
||||
375,0,3,"Palsson, Miss. Stina Viola",female,3,3,1,349909,21.075,,S
|
||||
376,1,1,"Meyer, Mrs. Edgar Joseph (Leila Saks)",female,,1,0,PC 17604,82.1708,,C
|
||||
377,1,3,"Landergren, Miss. Aurora Adelia",female,22,0,0,C 7077,7.25,,S
|
||||
378,0,1,"Widener, Mr. Harry Elkins",male,27,0,2,113503,211.5,C82,C
|
||||
379,0,3,"Betros, Mr. Tannous",male,20,0,0,2648,4.0125,,C
|
||||
380,0,3,"Gustafsson, Mr. Karl Gideon",male,19,0,0,347069,7.775,,S
|
||||
381,1,1,"Bidois, Miss. Rosalie",female,42,0,0,PC 17757,227.525,,C
|
||||
382,1,3,"Nakid, Miss. Maria (""Mary"")",female,1,0,2,2653,15.7417,,C
|
||||
383,0,3,"Tikkanen, Mr. Juho",male,32,0,0,STON/O 2. 3101293,7.925,,S
|
||||
384,1,1,"Holverson, Mrs. Alexander Oskar (Mary Aline Towner)",female,35,1,0,113789,52,,S
|
||||
385,0,3,"Plotcharsky, Mr. Vasil",male,,0,0,349227,7.8958,,S
|
||||
386,0,2,"Davies, Mr. Charles Henry",male,18,0,0,S.O.C. 14879,73.5,,S
|
||||
387,0,3,"Goodwin, Master. Sidney Leonard",male,1,5,2,CA 2144,46.9,,S
|
||||
388,1,2,"Buss, Miss. Kate",female,36,0,0,27849,13,,S
|
||||
389,0,3,"Sadlier, Mr. Matthew",male,,0,0,367655,7.7292,,Q
|
||||
390,1,2,"Lehmann, Miss. Bertha",female,17,0,0,SC 1748,12,,C
|
||||
391,1,1,"Carter, Mr. William Ernest",male,36,1,2,113760,120,B96 B98,S
|
||||
392,1,3,"Jansson, Mr. Carl Olof",male,21,0,0,350034,7.7958,,S
|
||||
393,0,3,"Gustafsson, Mr. Johan Birger",male,28,2,0,3101277,7.925,,S
|
||||
394,1,1,"Newell, Miss. Marjorie",female,23,1,0,35273,113.275,D36,C
|
||||
395,1,3,"Sandstrom, Mrs. Hjalmar (Agnes Charlotta Bengtsson)",female,24,0,2,PP 9549,16.7,G6,S
|
||||
396,0,3,"Johansson, Mr. Erik",male,22,0,0,350052,7.7958,,S
|
||||
397,0,3,"Olsson, Miss. Elina",female,31,0,0,350407,7.8542,,S
|
||||
398,0,2,"McKane, Mr. Peter David",male,46,0,0,28403,26,,S
|
||||
399,0,2,"Pain, Dr. Alfred",male,23,0,0,244278,10.5,,S
|
||||
400,1,2,"Trout, Mrs. William H (Jessie L)",female,28,0,0,240929,12.65,,S
|
||||
401,1,3,"Niskanen, Mr. Juha",male,39,0,0,STON/O 2. 3101289,7.925,,S
|
||||
402,0,3,"Adams, Mr. John",male,26,0,0,341826,8.05,,S
|
||||
403,0,3,"Jussila, Miss. Mari Aina",female,21,1,0,4137,9.825,,S
|
||||
404,0,3,"Hakkarainen, Mr. Pekka Pietari",male,28,1,0,STON/O2. 3101279,15.85,,S
|
||||
405,0,3,"Oreskovic, Miss. Marija",female,20,0,0,315096,8.6625,,S
|
||||
406,0,2,"Gale, Mr. Shadrach",male,34,1,0,28664,21,,S
|
||||
407,0,3,"Widegren, Mr. Carl/Charles Peter",male,51,0,0,347064,7.75,,S
|
||||
408,1,2,"Richards, Master. William Rowe",male,3,1,1,29106,18.75,,S
|
||||
409,0,3,"Birkeland, Mr. Hans Martin Monsen",male,21,0,0,312992,7.775,,S
|
||||
410,0,3,"Lefebre, Miss. Ida",female,,3,1,4133,25.4667,,S
|
||||
411,0,3,"Sdycoff, Mr. Todor",male,,0,0,349222,7.8958,,S
|
||||
412,0,3,"Hart, Mr. Henry",male,,0,0,394140,6.8583,,Q
|
||||
413,1,1,"Minahan, Miss. Daisy E",female,33,1,0,19928,90,C78,Q
|
||||
414,0,2,"Cunningham, Mr. Alfred Fleming",male,,0,0,239853,0,,S
|
||||
415,1,3,"Sundman, Mr. Johan Julian",male,44,0,0,STON/O 2. 3101269,7.925,,S
|
||||
416,0,3,"Meek, Mrs. Thomas (Annie Louise Rowley)",female,,0,0,343095,8.05,,S
|
||||
417,1,2,"Drew, Mrs. James Vivian (Lulu Thorne Christian)",female,34,1,1,28220,32.5,,S
|
||||
418,1,2,"Silven, Miss. Lyyli Karoliina",female,18,0,2,250652,13,,S
|
||||
419,0,2,"Matthews, Mr. William John",male,30,0,0,28228,13,,S
|
||||
420,0,3,"Van Impe, Miss. Catharina",female,10,0,2,345773,24.15,,S
|
||||
421,0,3,"Gheorgheff, Mr. Stanio",male,,0,0,349254,7.8958,,C
|
||||
422,0,3,"Charters, Mr. David",male,21,0,0,A/5. 13032,7.7333,,Q
|
||||
423,0,3,"Zimmerman, Mr. Leo",male,29,0,0,315082,7.875,,S
|
||||
424,0,3,"Danbom, Mrs. Ernst Gilbert (Anna Sigrid Maria Brogren)",female,28,1,1,347080,14.4,,S
|
||||
425,0,3,"Rosblom, Mr. Viktor Richard",male,18,1,1,370129,20.2125,,S
|
||||
426,0,3,"Wiseman, Mr. Phillippe",male,,0,0,A/4. 34244,7.25,,S
|
||||
427,1,2,"Clarke, Mrs. Charles V (Ada Maria Winfield)",female,28,1,0,2003,26,,S
|
||||
428,1,2,"Phillips, Miss. Kate Florence (""Mrs Kate Louise Phillips Marshall"")",female,19,0,0,250655,26,,S
|
||||
429,0,3,"Flynn, Mr. James",male,,0,0,364851,7.75,,Q
|
||||
430,1,3,"Pickard, Mr. Berk (Berk Trembisky)",male,32,0,0,SOTON/O.Q. 392078,8.05,E10,S
|
||||
431,1,1,"Bjornstrom-Steffansson, Mr. Mauritz Hakan",male,28,0,0,110564,26.55,C52,S
|
||||
432,1,3,"Thorneycroft, Mrs. Percival (Florence Kate White)",female,,1,0,376564,16.1,,S
|
||||
433,1,2,"Louch, Mrs. Charles Alexander (Alice Adelaide Slow)",female,42,1,0,SC/AH 3085,26,,S
|
||||
434,0,3,"Kallio, Mr. Nikolai Erland",male,17,0,0,STON/O 2. 3101274,7.125,,S
|
||||
435,0,1,"Silvey, Mr. William Baird",male,50,1,0,13507,55.9,E44,S
|
||||
436,1,1,"Carter, Miss. Lucile Polk",female,14,1,2,113760,120,B96 B98,S
|
||||
437,0,3,"Ford, Miss. Doolina Margaret ""Daisy""",female,21,2,2,W./C. 6608,34.375,,S
|
||||
438,1,2,"Richards, Mrs. Sidney (Emily Hocking)",female,24,2,3,29106,18.75,,S
|
||||
439,0,1,"Fortune, Mr. Mark",male,64,1,4,19950,263,C23 C25 C27,S
|
||||
440,0,2,"Kvillner, Mr. Johan Henrik Johannesson",male,31,0,0,C.A. 18723,10.5,,S
|
||||
441,1,2,"Hart, Mrs. Benjamin (Esther Ada Bloomfield)",female,45,1,1,F.C.C. 13529,26.25,,S
|
||||
442,0,3,"Hampe, Mr. Leon",male,20,0,0,345769,9.5,,S
|
||||
443,0,3,"Petterson, Mr. Johan Emil",male,25,1,0,347076,7.775,,S
|
||||
444,1,2,"Reynaldo, Ms. Encarnacion",female,28,0,0,230434,13,,S
|
||||
445,1,3,"Johannesen-Bratthammer, Mr. Bernt",male,,0,0,65306,8.1125,,S
|
||||
446,1,1,"Dodge, Master. Washington",male,4,0,2,33638,81.8583,A34,S
|
||||
447,1,2,"Mellinger, Miss. Madeleine Violet",female,13,0,1,250644,19.5,,S
|
||||
448,1,1,"Seward, Mr. Frederic Kimber",male,34,0,0,113794,26.55,,S
|
||||
449,1,3,"Baclini, Miss. Marie Catherine",female,5,2,1,2666,19.2583,,C
|
||||
450,1,1,"Peuchen, Major. Arthur Godfrey",male,52,0,0,113786,30.5,C104,S
|
||||
451,0,2,"West, Mr. Edwy Arthur",male,36,1,2,C.A. 34651,27.75,,S
|
||||
452,0,3,"Hagland, Mr. Ingvald Olai Olsen",male,,1,0,65303,19.9667,,S
|
||||
453,0,1,"Foreman, Mr. Benjamin Laventall",male,30,0,0,113051,27.75,C111,C
|
||||
454,1,1,"Goldenberg, Mr. Samuel L",male,49,1,0,17453,89.1042,C92,C
|
||||
455,0,3,"Peduzzi, Mr. Joseph",male,,0,0,A/5 2817,8.05,,S
|
||||
456,1,3,"Jalsevac, Mr. Ivan",male,29,0,0,349240,7.8958,,C
|
||||
457,0,1,"Millet, Mr. Francis Davis",male,65,0,0,13509,26.55,E38,S
|
||||
458,1,1,"Kenyon, Mrs. Frederick R (Marion)",female,,1,0,17464,51.8625,D21,S
|
||||
459,1,2,"Toomey, Miss. Ellen",female,50,0,0,F.C.C. 13531,10.5,,S
|
||||
460,0,3,"O'Connor, Mr. Maurice",male,,0,0,371060,7.75,,Q
|
||||
461,1,1,"Anderson, Mr. Harry",male,48,0,0,19952,26.55,E12,S
|
||||
462,0,3,"Morley, Mr. William",male,34,0,0,364506,8.05,,S
|
||||
463,0,1,"Gee, Mr. Arthur H",male,47,0,0,111320,38.5,E63,S
|
||||
464,0,2,"Milling, Mr. Jacob Christian",male,48,0,0,234360,13,,S
|
||||
465,0,3,"Maisner, Mr. Simon",male,,0,0,A/S 2816,8.05,,S
|
||||
466,0,3,"Goncalves, Mr. Manuel Estanslas",male,38,0,0,SOTON/O.Q. 3101306,7.05,,S
|
||||
467,0,2,"Campbell, Mr. William",male,,0,0,239853,0,,S
|
||||
468,0,1,"Smart, Mr. John Montgomery",male,56,0,0,113792,26.55,,S
|
||||
469,0,3,"Scanlan, Mr. James",male,,0,0,36209,7.725,,Q
|
||||
470,1,3,"Baclini, Miss. Helene Barbara",female,0.75,2,1,2666,19.2583,,C
|
||||
471,0,3,"Keefe, Mr. Arthur",male,,0,0,323592,7.25,,S
|
||||
472,0,3,"Cacic, Mr. Luka",male,38,0,0,315089,8.6625,,S
|
||||
473,1,2,"West, Mrs. Edwy Arthur (Ada Mary Worth)",female,33,1,2,C.A. 34651,27.75,,S
|
||||
474,1,2,"Jerwan, Mrs. Amin S (Marie Marthe Thuillard)",female,23,0,0,SC/AH Basle 541,13.7917,D,C
|
||||
475,0,3,"Strandberg, Miss. Ida Sofia",female,22,0,0,7553,9.8375,,S
|
||||
476,0,1,"Clifford, Mr. George Quincy",male,,0,0,110465,52,A14,S
|
||||
477,0,2,"Renouf, Mr. Peter Henry",male,34,1,0,31027,21,,S
|
||||
478,0,3,"Braund, Mr. Lewis Richard",male,29,1,0,3460,7.0458,,S
|
||||
479,0,3,"Karlsson, Mr. Nils August",male,22,0,0,350060,7.5208,,S
|
||||
480,1,3,"Hirvonen, Miss. Hildur E",female,2,0,1,3101298,12.2875,,S
|
||||
481,0,3,"Goodwin, Master. Harold Victor",male,9,5,2,CA 2144,46.9,,S
|
||||
482,0,2,"Frost, Mr. Anthony Wood ""Archie""",male,,0,0,239854,0,,S
|
||||
483,0,3,"Rouse, Mr. Richard Henry",male,50,0,0,A/5 3594,8.05,,S
|
||||
484,1,3,"Turkula, Mrs. (Hedwig)",female,63,0,0,4134,9.5875,,S
|
||||
485,1,1,"Bishop, Mr. Dickinson H",male,25,1,0,11967,91.0792,B49,C
|
||||
486,0,3,"Lefebre, Miss. Jeannie",female,,3,1,4133,25.4667,,S
|
||||
487,1,1,"Hoyt, Mrs. Frederick Maxfield (Jane Anne Forby)",female,35,1,0,19943,90,C93,S
|
||||
488,0,1,"Kent, Mr. Edward Austin",male,58,0,0,11771,29.7,B37,C
|
||||
489,0,3,"Somerton, Mr. Francis William",male,30,0,0,A.5. 18509,8.05,,S
|
||||
490,1,3,"Coutts, Master. Eden Leslie ""Neville""",male,9,1,1,C.A. 37671,15.9,,S
|
||||
491,0,3,"Hagland, Mr. Konrad Mathias Reiersen",male,,1,0,65304,19.9667,,S
|
||||
492,0,3,"Windelov, Mr. Einar",male,21,0,0,SOTON/OQ 3101317,7.25,,S
|
||||
493,0,1,"Molson, Mr. Harry Markland",male,55,0,0,113787,30.5,C30,S
|
||||
494,0,1,"Artagaveytia, Mr. Ramon",male,71,0,0,PC 17609,49.5042,,C
|
||||
495,0,3,"Stanley, Mr. Edward Roland",male,21,0,0,A/4 45380,8.05,,S
|
||||
496,0,3,"Yousseff, Mr. Gerious",male,,0,0,2627,14.4583,,C
|
||||
497,1,1,"Eustis, Miss. Elizabeth Mussey",female,54,1,0,36947,78.2667,D20,C
|
||||
498,0,3,"Shellard, Mr. Frederick William",male,,0,0,C.A. 6212,15.1,,S
|
||||
499,0,1,"Allison, Mrs. Hudson J C (Bessie Waldo Daniels)",female,25,1,2,113781,151.55,C22 C26,S
|
||||
500,0,3,"Svensson, Mr. Olof",male,24,0,0,350035,7.7958,,S
|
||||
501,0,3,"Calic, Mr. Petar",male,17,0,0,315086,8.6625,,S
|
||||
502,0,3,"Canavan, Miss. Mary",female,21,0,0,364846,7.75,,Q
|
||||
503,0,3,"O'Sullivan, Miss. Bridget Mary",female,,0,0,330909,7.6292,,Q
|
||||
504,0,3,"Laitinen, Miss. Kristina Sofia",female,37,0,0,4135,9.5875,,S
|
||||
505,1,1,"Maioni, Miss. Roberta",female,16,0,0,110152,86.5,B79,S
|
||||
506,0,1,"Penasco y Castellana, Mr. Victor de Satode",male,18,1,0,PC 17758,108.9,C65,C
|
||||
507,1,2,"Quick, Mrs. Frederick Charles (Jane Richards)",female,33,0,2,26360,26,,S
|
||||
508,1,1,"Bradley, Mr. George (""George Arthur Brayton"")",male,,0,0,111427,26.55,,S
|
||||
509,0,3,"Olsen, Mr. Henry Margido",male,28,0,0,C 4001,22.525,,S
|
||||
510,1,3,"Lang, Mr. Fang",male,26,0,0,1601,56.4958,,S
|
||||
511,1,3,"Daly, Mr. Eugene Patrick",male,29,0,0,382651,7.75,,Q
|
||||
512,0,3,"Webber, Mr. James",male,,0,0,SOTON/OQ 3101316,8.05,,S
|
||||
513,1,1,"McGough, Mr. James Robert",male,36,0,0,PC 17473,26.2875,E25,S
|
||||
514,1,1,"Rothschild, Mrs. Martin (Elizabeth L. Barrett)",female,54,1,0,PC 17603,59.4,,C
|
||||
515,0,3,"Coleff, Mr. Satio",male,24,0,0,349209,7.4958,,S
|
||||
516,0,1,"Walker, Mr. William Anderson",male,47,0,0,36967,34.0208,D46,S
|
||||
517,1,2,"Lemore, Mrs. (Amelia Milley)",female,34,0,0,C.A. 34260,10.5,F33,S
|
||||
518,0,3,"Ryan, Mr. Patrick",male,,0,0,371110,24.15,,Q
|
||||
519,1,2,"Angle, Mrs. William A (Florence ""Mary"" Agnes Hughes)",female,36,1,0,226875,26,,S
|
||||
520,0,3,"Pavlovic, Mr. Stefo",male,32,0,0,349242,7.8958,,S
|
||||
521,1,1,"Perreault, Miss. Anne",female,30,0,0,12749,93.5,B73,S
|
||||
522,0,3,"Vovk, Mr. Janko",male,22,0,0,349252,7.8958,,S
|
||||
523,0,3,"Lahoud, Mr. Sarkis",male,,0,0,2624,7.225,,C
|
||||
524,1,1,"Hippach, Mrs. Louis Albert (Ida Sophia Fischer)",female,44,0,1,111361,57.9792,B18,C
|
||||
525,0,3,"Kassem, Mr. Fared",male,,0,0,2700,7.2292,,C
|
||||
526,0,3,"Farrell, Mr. James",male,40.5,0,0,367232,7.75,,Q
|
||||
527,1,2,"Ridsdale, Miss. Lucy",female,50,0,0,W./C. 14258,10.5,,S
|
||||
528,0,1,"Farthing, Mr. John",male,,0,0,PC 17483,221.7792,C95,S
|
||||
529,0,3,"Salonen, Mr. Johan Werner",male,39,0,0,3101296,7.925,,S
|
||||
530,0,2,"Hocking, Mr. Richard George",male,23,2,1,29104,11.5,,S
|
||||
531,1,2,"Quick, Miss. Phyllis May",female,2,1,1,26360,26,,S
|
||||
532,0,3,"Toufik, Mr. Nakli",male,,0,0,2641,7.2292,,C
|
||||
533,0,3,"Elias, Mr. Joseph Jr",male,17,1,1,2690,7.2292,,C
|
||||
534,1,3,"Peter, Mrs. Catherine (Catherine Rizk)",female,,0,2,2668,22.3583,,C
|
||||
535,0,3,"Cacic, Miss. Marija",female,30,0,0,315084,8.6625,,S
|
||||
536,1,2,"Hart, Miss. Eva Miriam",female,7,0,2,F.C.C. 13529,26.25,,S
|
||||
537,0,1,"Butt, Major. Archibald Willingham",male,45,0,0,113050,26.55,B38,S
|
||||
538,1,1,"LeRoy, Miss. Bertha",female,30,0,0,PC 17761,106.425,,C
|
||||
539,0,3,"Risien, Mr. Samuel Beard",male,,0,0,364498,14.5,,S
|
||||
540,1,1,"Frolicher, Miss. Hedwig Margaritha",female,22,0,2,13568,49.5,B39,C
|
||||
541,1,1,"Crosby, Miss. Harriet R",female,36,0,2,WE/P 5735,71,B22,S
|
||||
542,0,3,"Andersson, Miss. Ingeborg Constanzia",female,9,4,2,347082,31.275,,S
|
||||
543,0,3,"Andersson, Miss. Sigrid Elisabeth",female,11,4,2,347082,31.275,,S
|
||||
544,1,2,"Beane, Mr. Edward",male,32,1,0,2908,26,,S
|
||||
545,0,1,"Douglas, Mr. Walter Donald",male,50,1,0,PC 17761,106.425,C86,C
|
||||
546,0,1,"Nicholson, Mr. Arthur Ernest",male,64,0,0,693,26,,S
|
||||
547,1,2,"Beane, Mrs. Edward (Ethel Clarke)",female,19,1,0,2908,26,,S
|
||||
548,1,2,"Padro y Manent, Mr. Julian",male,,0,0,SC/PARIS 2146,13.8625,,C
|
||||
549,0,3,"Goldsmith, Mr. Frank John",male,33,1,1,363291,20.525,,S
|
||||
550,1,2,"Davies, Master. John Morgan Jr",male,8,1,1,C.A. 33112,36.75,,S
|
||||
551,1,1,"Thayer, Mr. John Borland Jr",male,17,0,2,17421,110.8833,C70,C
|
||||
552,0,2,"Sharp, Mr. Percival James R",male,27,0,0,244358,26,,S
|
||||
553,0,3,"O'Brien, Mr. Timothy",male,,0,0,330979,7.8292,,Q
|
||||
554,1,3,"Leeni, Mr. Fahim (""Philip Zenni"")",male,22,0,0,2620,7.225,,C
|
||||
555,1,3,"Ohman, Miss. Velin",female,22,0,0,347085,7.775,,S
|
||||
556,0,1,"Wright, Mr. George",male,62,0,0,113807,26.55,,S
|
||||
557,1,1,"Duff Gordon, Lady. (Lucille Christiana Sutherland) (""Mrs Morgan"")",female,48,1,0,11755,39.6,A16,C
|
||||
558,0,1,"Robbins, Mr. Victor",male,,0,0,PC 17757,227.525,,C
|
||||
559,1,1,"Taussig, Mrs. Emil (Tillie Mandelbaum)",female,39,1,1,110413,79.65,E67,S
|
||||
560,1,3,"de Messemaeker, Mrs. Guillaume Joseph (Emma)",female,36,1,0,345572,17.4,,S
|
||||
561,0,3,"Morrow, Mr. Thomas Rowan",male,,0,0,372622,7.75,,Q
|
||||
562,0,3,"Sivic, Mr. Husein",male,40,0,0,349251,7.8958,,S
|
||||
563,0,2,"Norman, Mr. Robert Douglas",male,28,0,0,218629,13.5,,S
|
||||
564,0,3,"Simmons, Mr. John",male,,0,0,SOTON/OQ 392082,8.05,,S
|
||||
565,0,3,"Meanwell, Miss. (Marion Ogden)",female,,0,0,SOTON/O.Q. 392087,8.05,,S
|
||||
566,0,3,"Davies, Mr. Alfred J",male,24,2,0,A/4 48871,24.15,,S
|
||||
567,0,3,"Stoytcheff, Mr. Ilia",male,19,0,0,349205,7.8958,,S
|
||||
568,0,3,"Palsson, Mrs. Nils (Alma Cornelia Berglund)",female,29,0,4,349909,21.075,,S
|
||||
569,0,3,"Doharr, Mr. Tannous",male,,0,0,2686,7.2292,,C
|
||||
570,1,3,"Jonsson, Mr. Carl",male,32,0,0,350417,7.8542,,S
|
||||
571,1,2,"Harris, Mr. George",male,62,0,0,S.W./PP 752,10.5,,S
|
||||
572,1,1,"Appleton, Mrs. Edward Dale (Charlotte Lamson)",female,53,2,0,11769,51.4792,C101,S
|
||||
573,1,1,"Flynn, Mr. John Irwin (""Irving"")",male,36,0,0,PC 17474,26.3875,E25,S
|
||||
574,1,3,"Kelly, Miss. Mary",female,,0,0,14312,7.75,,Q
|
||||
575,0,3,"Rush, Mr. Alfred George John",male,16,0,0,A/4. 20589,8.05,,S
|
||||
576,0,3,"Patchett, Mr. George",male,19,0,0,358585,14.5,,S
|
||||
577,1,2,"Garside, Miss. Ethel",female,34,0,0,243880,13,,S
|
||||
578,1,1,"Silvey, Mrs. William Baird (Alice Munger)",female,39,1,0,13507,55.9,E44,S
|
||||
579,0,3,"Caram, Mrs. Joseph (Maria Elias)",female,,1,0,2689,14.4583,,C
|
||||
580,1,3,"Jussila, Mr. Eiriik",male,32,0,0,STON/O 2. 3101286,7.925,,S
|
||||
581,1,2,"Christy, Miss. Julie Rachel",female,25,1,1,237789,30,,S
|
||||
582,1,1,"Thayer, Mrs. John Borland (Marian Longstreth Morris)",female,39,1,1,17421,110.8833,C68,C
|
||||
583,0,2,"Downton, Mr. William James",male,54,0,0,28403,26,,S
|
||||
584,0,1,"Ross, Mr. John Hugo",male,36,0,0,13049,40.125,A10,C
|
||||
585,0,3,"Paulner, Mr. Uscher",male,,0,0,3411,8.7125,,C
|
||||
586,1,1,"Taussig, Miss. Ruth",female,18,0,2,110413,79.65,E68,S
|
||||
587,0,2,"Jarvis, Mr. John Denzil",male,47,0,0,237565,15,,S
|
||||
588,1,1,"Frolicher-Stehli, Mr. Maxmillian",male,60,1,1,13567,79.2,B41,C
|
||||
589,0,3,"Gilinski, Mr. Eliezer",male,22,0,0,14973,8.05,,S
|
||||
590,0,3,"Murdlin, Mr. Joseph",male,,0,0,A./5. 3235,8.05,,S
|
||||
591,0,3,"Rintamaki, Mr. Matti",male,35,0,0,STON/O 2. 3101273,7.125,,S
|
||||
592,1,1,"Stephenson, Mrs. Walter Bertram (Martha Eustis)",female,52,1,0,36947,78.2667,D20,C
|
||||
593,0,3,"Elsbury, Mr. William James",male,47,0,0,A/5 3902,7.25,,S
|
||||
594,0,3,"Bourke, Miss. Mary",female,,0,2,364848,7.75,,Q
|
||||
595,0,2,"Chapman, Mr. John Henry",male,37,1,0,SC/AH 29037,26,,S
|
||||
596,0,3,"Van Impe, Mr. Jean Baptiste",male,36,1,1,345773,24.15,,S
|
||||
597,1,2,"Leitch, Miss. Jessie Wills",female,,0,0,248727,33,,S
|
||||
598,0,3,"Johnson, Mr. Alfred",male,49,0,0,LINE,0,,S
|
||||
599,0,3,"Boulos, Mr. Hanna",male,,0,0,2664,7.225,,C
|
||||
600,1,1,"Duff Gordon, Sir. Cosmo Edmund (""Mr Morgan"")",male,49,1,0,PC 17485,56.9292,A20,C
|
||||
601,1,2,"Jacobsohn, Mrs. Sidney Samuel (Amy Frances Christy)",female,24,2,1,243847,27,,S
|
||||
602,0,3,"Slabenoff, Mr. Petco",male,,0,0,349214,7.8958,,S
|
||||
603,0,1,"Harrington, Mr. Charles H",male,,0,0,113796,42.4,,S
|
||||
604,0,3,"Torber, Mr. Ernst William",male,44,0,0,364511,8.05,,S
|
||||
605,1,1,"Homer, Mr. Harry (""Mr E Haven"")",male,35,0,0,111426,26.55,,C
|
||||
606,0,3,"Lindell, Mr. Edvard Bengtsson",male,36,1,0,349910,15.55,,S
|
||||
607,0,3,"Karaic, Mr. Milan",male,30,0,0,349246,7.8958,,S
|
||||
608,1,1,"Daniel, Mr. Robert Williams",male,27,0,0,113804,30.5,,S
|
||||
609,1,2,"Laroche, Mrs. Joseph (Juliette Marie Louise Lafargue)",female,22,1,2,SC/Paris 2123,41.5792,,C
|
||||
610,1,1,"Shutes, Miss. Elizabeth W",female,40,0,0,PC 17582,153.4625,C125,S
|
||||
611,0,3,"Andersson, Mrs. Anders Johan (Alfrida Konstantia Brogren)",female,39,1,5,347082,31.275,,S
|
||||
612,0,3,"Jardin, Mr. Jose Neto",male,,0,0,SOTON/O.Q. 3101305,7.05,,S
|
||||
613,1,3,"Murphy, Miss. Margaret Jane",female,,1,0,367230,15.5,,Q
|
||||
614,0,3,"Horgan, Mr. John",male,,0,0,370377,7.75,,Q
|
||||
615,0,3,"Brocklebank, Mr. William Alfred",male,35,0,0,364512,8.05,,S
|
||||
616,1,2,"Herman, Miss. Alice",female,24,1,2,220845,65,,S
|
||||
617,0,3,"Danbom, Mr. Ernst Gilbert",male,34,1,1,347080,14.4,,S
|
||||
618,0,3,"Lobb, Mrs. William Arthur (Cordelia K Stanlick)",female,26,1,0,A/5. 3336,16.1,,S
|
||||
619,1,2,"Becker, Miss. Marion Louise",female,4,2,1,230136,39,F4,S
|
||||
620,0,2,"Gavey, Mr. Lawrence",male,26,0,0,31028,10.5,,S
|
||||
621,0,3,"Yasbeck, Mr. Antoni",male,27,1,0,2659,14.4542,,C
|
||||
622,1,1,"Kimball, Mr. Edwin Nelson Jr",male,42,1,0,11753,52.5542,D19,S
|
||||
623,1,3,"Nakid, Mr. Sahid",male,20,1,1,2653,15.7417,,C
|
||||
624,0,3,"Hansen, Mr. Henry Damsgaard",male,21,0,0,350029,7.8542,,S
|
||||
625,0,3,"Bowen, Mr. David John ""Dai""",male,21,0,0,54636,16.1,,S
|
||||
626,0,1,"Sutton, Mr. Frederick",male,61,0,0,36963,32.3208,D50,S
|
||||
627,0,2,"Kirkland, Rev. Charles Leonard",male,57,0,0,219533,12.35,,Q
|
||||
628,1,1,"Longley, Miss. Gretchen Fiske",female,21,0,0,13502,77.9583,D9,S
|
||||
629,0,3,"Bostandyeff, Mr. Guentcho",male,26,0,0,349224,7.8958,,S
|
||||
630,0,3,"O'Connell, Mr. Patrick D",male,,0,0,334912,7.7333,,Q
|
||||
631,1,1,"Barkworth, Mr. Algernon Henry Wilson",male,80,0,0,27042,30,A23,S
|
||||
632,0,3,"Lundahl, Mr. Johan Svensson",male,51,0,0,347743,7.0542,,S
|
||||
633,1,1,"Stahelin-Maeglin, Dr. Max",male,32,0,0,13214,30.5,B50,C
|
||||
634,0,1,"Parr, Mr. William Henry Marsh",male,,0,0,112052,0,,S
|
||||
635,0,3,"Skoog, Miss. Mabel",female,9,3,2,347088,27.9,,S
|
||||
636,1,2,"Davis, Miss. Mary",female,28,0,0,237668,13,,S
|
||||
637,0,3,"Leinonen, Mr. Antti Gustaf",male,32,0,0,STON/O 2. 3101292,7.925,,S
|
||||
638,0,2,"Collyer, Mr. Harvey",male,31,1,1,C.A. 31921,26.25,,S
|
||||
639,0,3,"Panula, Mrs. Juha (Maria Emilia Ojala)",female,41,0,5,3101295,39.6875,,S
|
||||
640,0,3,"Thorneycroft, Mr. Percival",male,,1,0,376564,16.1,,S
|
||||
641,0,3,"Jensen, Mr. Hans Peder",male,20,0,0,350050,7.8542,,S
|
||||
642,1,1,"Sagesser, Mlle. Emma",female,24,0,0,PC 17477,69.3,B35,C
|
||||
643,0,3,"Skoog, Miss. Margit Elizabeth",female,2,3,2,347088,27.9,,S
|
||||
644,1,3,"Foo, Mr. Choong",male,,0,0,1601,56.4958,,S
|
||||
645,1,3,"Baclini, Miss. Eugenie",female,0.75,2,1,2666,19.2583,,C
|
||||
646,1,1,"Harper, Mr. Henry Sleeper",male,48,1,0,PC 17572,76.7292,D33,C
|
||||
647,0,3,"Cor, Mr. Liudevit",male,19,0,0,349231,7.8958,,S
|
||||
648,1,1,"Simonius-Blumer, Col. Oberst Alfons",male,56,0,0,13213,35.5,A26,C
|
||||
649,0,3,"Willey, Mr. Edward",male,,0,0,S.O./P.P. 751,7.55,,S
|
||||
650,1,3,"Stanley, Miss. Amy Zillah Elsie",female,23,0,0,CA. 2314,7.55,,S
|
||||
651,0,3,"Mitkoff, Mr. Mito",male,,0,0,349221,7.8958,,S
|
||||
652,1,2,"Doling, Miss. Elsie",female,18,0,1,231919,23,,S
|
||||
653,0,3,"Kalvik, Mr. Johannes Halvorsen",male,21,0,0,8475,8.4333,,S
|
||||
654,1,3,"O'Leary, Miss. Hanora ""Norah""",female,,0,0,330919,7.8292,,Q
|
||||
655,0,3,"Hegarty, Miss. Hanora ""Nora""",female,18,0,0,365226,6.75,,Q
|
||||
656,0,2,"Hickman, Mr. Leonard Mark",male,24,2,0,S.O.C. 14879,73.5,,S
|
||||
657,0,3,"Radeff, Mr. Alexander",male,,0,0,349223,7.8958,,S
|
||||
658,0,3,"Bourke, Mrs. John (Catherine)",female,32,1,1,364849,15.5,,Q
|
||||
659,0,2,"Eitemiller, Mr. George Floyd",male,23,0,0,29751,13,,S
|
||||
660,0,1,"Newell, Mr. Arthur Webster",male,58,0,2,35273,113.275,D48,C
|
||||
661,1,1,"Frauenthal, Dr. Henry William",male,50,2,0,PC 17611,133.65,,S
|
||||
662,0,3,"Badt, Mr. Mohamed",male,40,0,0,2623,7.225,,C
|
||||
663,0,1,"Colley, Mr. Edward Pomeroy",male,47,0,0,5727,25.5875,E58,S
|
||||
664,0,3,"Coleff, Mr. Peju",male,36,0,0,349210,7.4958,,S
|
||||
665,1,3,"Lindqvist, Mr. Eino William",male,20,1,0,STON/O 2. 3101285,7.925,,S
|
||||
666,0,2,"Hickman, Mr. Lewis",male,32,2,0,S.O.C. 14879,73.5,,S
|
||||
667,0,2,"Butler, Mr. Reginald Fenton",male,25,0,0,234686,13,,S
|
||||
668,0,3,"Rommetvedt, Mr. Knud Paust",male,,0,0,312993,7.775,,S
|
||||
669,0,3,"Cook, Mr. Jacob",male,43,0,0,A/5 3536,8.05,,S
|
||||
670,1,1,"Taylor, Mrs. Elmer Zebley (Juliet Cummins Wright)",female,,1,0,19996,52,C126,S
|
||||
671,1,2,"Brown, Mrs. Thomas William Solomon (Elizabeth Catherine Ford)",female,40,1,1,29750,39,,S
|
||||
672,0,1,"Davidson, Mr. Thornton",male,31,1,0,F.C. 12750,52,B71,S
|
||||
673,0,2,"Mitchell, Mr. Henry Michael",male,70,0,0,C.A. 24580,10.5,,S
|
||||
674,1,2,"Wilhelms, Mr. Charles",male,31,0,0,244270,13,,S
|
||||
675,0,2,"Watson, Mr. Ennis Hastings",male,,0,0,239856,0,,S
|
||||
676,0,3,"Edvardsson, Mr. Gustaf Hjalmar",male,18,0,0,349912,7.775,,S
|
||||
677,0,3,"Sawyer, Mr. Frederick Charles",male,24.5,0,0,342826,8.05,,S
|
||||
678,1,3,"Turja, Miss. Anna Sofia",female,18,0,0,4138,9.8417,,S
|
||||
679,0,3,"Goodwin, Mrs. Frederick (Augusta Tyler)",female,43,1,6,CA 2144,46.9,,S
|
||||
680,1,1,"Cardeza, Mr. Thomas Drake Martinez",male,36,0,1,PC 17755,512.3292,B51 B53 B55,C
|
||||
681,0,3,"Peters, Miss. Katie",female,,0,0,330935,8.1375,,Q
|
||||
682,1,1,"Hassab, Mr. Hammad",male,27,0,0,PC 17572,76.7292,D49,C
|
||||
683,0,3,"Olsvigen, Mr. Thor Anderson",male,20,0,0,6563,9.225,,S
|
||||
684,0,3,"Goodwin, Mr. Charles Edward",male,14,5,2,CA 2144,46.9,,S
|
||||
685,0,2,"Brown, Mr. Thomas William Solomon",male,60,1,1,29750,39,,S
|
||||
686,0,2,"Laroche, Mr. Joseph Philippe Lemercier",male,25,1,2,SC/Paris 2123,41.5792,,C
|
||||
687,0,3,"Panula, Mr. Jaako Arnold",male,14,4,1,3101295,39.6875,,S
|
||||
688,0,3,"Dakic, Mr. Branko",male,19,0,0,349228,10.1708,,S
|
||||
689,0,3,"Fischer, Mr. Eberhard Thelander",male,18,0,0,350036,7.7958,,S
|
||||
690,1,1,"Madill, Miss. Georgette Alexandra",female,15,0,1,24160,211.3375,B5,S
|
||||
691,1,1,"Dick, Mr. Albert Adrian",male,31,1,0,17474,57,B20,S
|
||||
692,1,3,"Karun, Miss. Manca",female,4,0,1,349256,13.4167,,C
|
||||
693,1,3,"Lam, Mr. Ali",male,,0,0,1601,56.4958,,S
|
||||
694,0,3,"Saad, Mr. Khalil",male,25,0,0,2672,7.225,,C
|
||||
695,0,1,"Weir, Col. John",male,60,0,0,113800,26.55,,S
|
||||
696,0,2,"Chapman, Mr. Charles Henry",male,52,0,0,248731,13.5,,S
|
||||
697,0,3,"Kelly, Mr. James",male,44,0,0,363592,8.05,,S
|
||||
698,1,3,"Mullens, Miss. Katherine ""Katie""",female,,0,0,35852,7.7333,,Q
|
||||
699,0,1,"Thayer, Mr. John Borland",male,49,1,1,17421,110.8833,C68,C
|
||||
700,0,3,"Humblen, Mr. Adolf Mathias Nicolai Olsen",male,42,0,0,348121,7.65,F G63,S
|
||||
701,1,1,"Astor, Mrs. John Jacob (Madeleine Talmadge Force)",female,18,1,0,PC 17757,227.525,C62 C64,C
|
||||
702,1,1,"Silverthorne, Mr. Spencer Victor",male,35,0,0,PC 17475,26.2875,E24,S
|
||||
703,0,3,"Barbara, Miss. Saiide",female,18,0,1,2691,14.4542,,C
|
||||
704,0,3,"Gallagher, Mr. Martin",male,25,0,0,36864,7.7417,,Q
|
||||
705,0,3,"Hansen, Mr. Henrik Juul",male,26,1,0,350025,7.8542,,S
|
||||
706,0,2,"Morley, Mr. Henry Samuel (""Mr Henry Marshall"")",male,39,0,0,250655,26,,S
|
||||
707,1,2,"Kelly, Mrs. Florence ""Fannie""",female,45,0,0,223596,13.5,,S
|
||||
708,1,1,"Calderhead, Mr. Edward Pennington",male,42,0,0,PC 17476,26.2875,E24,S
|
||||
709,1,1,"Cleaver, Miss. Alice",female,22,0,0,113781,151.55,,S
|
||||
710,1,3,"Moubarek, Master. Halim Gonios (""William George"")",male,,1,1,2661,15.2458,,C
|
||||
711,1,1,"Mayne, Mlle. Berthe Antonine (""Mrs de Villiers"")",female,24,0,0,PC 17482,49.5042,C90,C
|
||||
712,0,1,"Klaber, Mr. Herman",male,,0,0,113028,26.55,C124,S
|
||||
713,1,1,"Taylor, Mr. Elmer Zebley",male,48,1,0,19996,52,C126,S
|
||||
714,0,3,"Larsson, Mr. August Viktor",male,29,0,0,7545,9.4833,,S
|
||||
715,0,2,"Greenberg, Mr. Samuel",male,52,0,0,250647,13,,S
|
||||
716,0,3,"Soholt, Mr. Peter Andreas Lauritz Andersen",male,19,0,0,348124,7.65,F G73,S
|
||||
717,1,1,"Endres, Miss. Caroline Louise",female,38,0,0,PC 17757,227.525,C45,C
|
||||
718,1,2,"Troutt, Miss. Edwina Celia ""Winnie""",female,27,0,0,34218,10.5,E101,S
|
||||
719,0,3,"McEvoy, Mr. Michael",male,,0,0,36568,15.5,,Q
|
||||
720,0,3,"Johnson, Mr. Malkolm Joackim",male,33,0,0,347062,7.775,,S
|
||||
721,1,2,"Harper, Miss. Annie Jessie ""Nina""",female,6,0,1,248727,33,,S
|
||||
722,0,3,"Jensen, Mr. Svend Lauritz",male,17,1,0,350048,7.0542,,S
|
||||
723,0,2,"Gillespie, Mr. William Henry",male,34,0,0,12233,13,,S
|
||||
724,0,2,"Hodges, Mr. Henry Price",male,50,0,0,250643,13,,S
|
||||
725,1,1,"Chambers, Mr. Norman Campbell",male,27,1,0,113806,53.1,E8,S
|
||||
726,0,3,"Oreskovic, Mr. Luka",male,20,0,0,315094,8.6625,,S
|
||||
727,1,2,"Renouf, Mrs. Peter Henry (Lillian Jefferys)",female,30,3,0,31027,21,,S
|
||||
728,1,3,"Mannion, Miss. Margareth",female,,0,0,36866,7.7375,,Q
|
||||
729,0,2,"Bryhl, Mr. Kurt Arnold Gottfrid",male,25,1,0,236853,26,,S
|
||||
730,0,3,"Ilmakangas, Miss. Pieta Sofia",female,25,1,0,STON/O2. 3101271,7.925,,S
|
||||
731,1,1,"Allen, Miss. Elisabeth Walton",female,29,0,0,24160,211.3375,B5,S
|
||||
732,0,3,"Hassan, Mr. Houssein G N",male,11,0,0,2699,18.7875,,C
|
||||
733,0,2,"Knight, Mr. Robert J",male,,0,0,239855,0,,S
|
||||
734,0,2,"Berriman, Mr. William John",male,23,0,0,28425,13,,S
|
||||
735,0,2,"Troupiansky, Mr. Moses Aaron",male,23,0,0,233639,13,,S
|
||||
736,0,3,"Williams, Mr. Leslie",male,28.5,0,0,54636,16.1,,S
|
||||
737,0,3,"Ford, Mrs. Edward (Margaret Ann Watson)",female,48,1,3,W./C. 6608,34.375,,S
|
||||
738,1,1,"Lesurer, Mr. Gustave J",male,35,0,0,PC 17755,512.3292,B101,C
|
||||
739,0,3,"Ivanoff, Mr. Kanio",male,,0,0,349201,7.8958,,S
|
||||
740,0,3,"Nankoff, Mr. Minko",male,,0,0,349218,7.8958,,S
|
||||
741,1,1,"Hawksford, Mr. Walter James",male,,0,0,16988,30,D45,S
|
||||
742,0,1,"Cavendish, Mr. Tyrell William",male,36,1,0,19877,78.85,C46,S
|
||||
743,1,1,"Ryerson, Miss. Susan Parker ""Suzette""",female,21,2,2,PC 17608,262.375,B57 B59 B63 B66,C
|
||||
744,0,3,"McNamee, Mr. Neal",male,24,1,0,376566,16.1,,S
|
||||
745,1,3,"Stranden, Mr. Juho",male,31,0,0,STON/O 2. 3101288,7.925,,S
|
||||
746,0,1,"Crosby, Capt. Edward Gifford",male,70,1,1,WE/P 5735,71,B22,S
|
||||
747,0,3,"Abbott, Mr. Rossmore Edward",male,16,1,1,C.A. 2673,20.25,,S
|
||||
748,1,2,"Sinkkonen, Miss. Anna",female,30,0,0,250648,13,,S
|
||||
749,0,1,"Marvin, Mr. Daniel Warner",male,19,1,0,113773,53.1,D30,S
|
||||
750,0,3,"Connaghton, Mr. Michael",male,31,0,0,335097,7.75,,Q
|
||||
751,1,2,"Wells, Miss. Joan",female,4,1,1,29103,23,,S
|
||||
752,1,3,"Moor, Master. Meier",male,6,0,1,392096,12.475,E121,S
|
||||
753,0,3,"Vande Velde, Mr. Johannes Joseph",male,33,0,0,345780,9.5,,S
|
||||
754,0,3,"Jonkoff, Mr. Lalio",male,23,0,0,349204,7.8958,,S
|
||||
755,1,2,"Herman, Mrs. Samuel (Jane Laver)",female,48,1,2,220845,65,,S
|
||||
756,1,2,"Hamalainen, Master. Viljo",male,0.67,1,1,250649,14.5,,S
|
||||
757,0,3,"Carlsson, Mr. August Sigfrid",male,28,0,0,350042,7.7958,,S
|
||||
758,0,2,"Bailey, Mr. Percy Andrew",male,18,0,0,29108,11.5,,S
|
||||
759,0,3,"Theobald, Mr. Thomas Leonard",male,34,0,0,363294,8.05,,S
|
||||
760,1,1,"Rothes, the Countess. of (Lucy Noel Martha Dyer-Edwards)",female,33,0,0,110152,86.5,B77,S
|
||||
761,0,3,"Garfirth, Mr. John",male,,0,0,358585,14.5,,S
|
||||
762,0,3,"Nirva, Mr. Iisakki Antino Aijo",male,41,0,0,SOTON/O2 3101272,7.125,,S
|
||||
763,1,3,"Barah, Mr. Hanna Assi",male,20,0,0,2663,7.2292,,C
|
||||
764,1,1,"Carter, Mrs. William Ernest (Lucile Polk)",female,36,1,2,113760,120,B96 B98,S
|
||||
765,0,3,"Eklund, Mr. Hans Linus",male,16,0,0,347074,7.775,,S
|
||||
766,1,1,"Hogeboom, Mrs. John C (Anna Andrews)",female,51,1,0,13502,77.9583,D11,S
|
||||
767,0,1,"Brewe, Dr. Arthur Jackson",male,,0,0,112379,39.6,,C
|
||||
768,0,3,"Mangan, Miss. Mary",female,30.5,0,0,364850,7.75,,Q
|
||||
769,0,3,"Moran, Mr. Daniel J",male,,1,0,371110,24.15,,Q
|
||||
770,0,3,"Gronnestad, Mr. Daniel Danielsen",male,32,0,0,8471,8.3625,,S
|
||||
771,0,3,"Lievens, Mr. Rene Aime",male,24,0,0,345781,9.5,,S
|
||||
772,0,3,"Jensen, Mr. Niels Peder",male,48,0,0,350047,7.8542,,S
|
||||
773,0,2,"Mack, Mrs. (Mary)",female,57,0,0,S.O./P.P. 3,10.5,E77,S
|
||||
774,0,3,"Elias, Mr. Dibo",male,,0,0,2674,7.225,,C
|
||||
775,1,2,"Hocking, Mrs. Elizabeth (Eliza Needs)",female,54,1,3,29105,23,,S
|
||||
776,0,3,"Myhrman, Mr. Pehr Fabian Oliver Malkolm",male,18,0,0,347078,7.75,,S
|
||||
777,0,3,"Tobin, Mr. Roger",male,,0,0,383121,7.75,F38,Q
|
||||
778,1,3,"Emanuel, Miss. Virginia Ethel",female,5,0,0,364516,12.475,,S
|
||||
779,0,3,"Kilgannon, Mr. Thomas J",male,,0,0,36865,7.7375,,Q
|
||||
780,1,1,"Robert, Mrs. Edward Scott (Elisabeth Walton McMillan)",female,43,0,1,24160,211.3375,B3,S
|
||||
781,1,3,"Ayoub, Miss. Banoura",female,13,0,0,2687,7.2292,,C
|
||||
782,1,1,"Dick, Mrs. Albert Adrian (Vera Gillespie)",female,17,1,0,17474,57,B20,S
|
||||
783,0,1,"Long, Mr. Milton Clyde",male,29,0,0,113501,30,D6,S
|
||||
784,0,3,"Johnston, Mr. Andrew G",male,,1,2,W./C. 6607,23.45,,S
|
||||
785,0,3,"Ali, Mr. William",male,25,0,0,SOTON/O.Q. 3101312,7.05,,S
|
||||
786,0,3,"Harmer, Mr. Abraham (David Lishin)",male,25,0,0,374887,7.25,,S
|
||||
787,1,3,"Sjoblom, Miss. Anna Sofia",female,18,0,0,3101265,7.4958,,S
|
||||
788,0,3,"Rice, Master. George Hugh",male,8,4,1,382652,29.125,,Q
|
||||
789,1,3,"Dean, Master. Bertram Vere",male,1,1,2,C.A. 2315,20.575,,S
|
||||
790,0,1,"Guggenheim, Mr. Benjamin",male,46,0,0,PC 17593,79.2,B82 B84,C
|
||||
791,0,3,"Keane, Mr. Andrew ""Andy""",male,,0,0,12460,7.75,,Q
|
||||
792,0,2,"Gaskell, Mr. Alfred",male,16,0,0,239865,26,,S
|
||||
793,0,3,"Sage, Miss. Stella Anna",female,,8,2,CA. 2343,69.55,,S
|
||||
794,0,1,"Hoyt, Mr. William Fisher",male,,0,0,PC 17600,30.6958,,C
|
||||
795,0,3,"Dantcheff, Mr. Ristiu",male,25,0,0,349203,7.8958,,S
|
||||
796,0,2,"Otter, Mr. Richard",male,39,0,0,28213,13,,S
|
||||
797,1,1,"Leader, Dr. Alice (Farnham)",female,49,0,0,17465,25.9292,D17,S
|
||||
798,1,3,"Osman, Mrs. Mara",female,31,0,0,349244,8.6833,,S
|
||||
799,0,3,"Ibrahim Shawah, Mr. Yousseff",male,30,0,0,2685,7.2292,,C
|
||||
800,0,3,"Van Impe, Mrs. Jean Baptiste (Rosalie Paula Govaert)",female,30,1,1,345773,24.15,,S
|
||||
801,0,2,"Ponesell, Mr. Martin",male,34,0,0,250647,13,,S
|
||||
802,1,2,"Collyer, Mrs. Harvey (Charlotte Annie Tate)",female,31,1,1,C.A. 31921,26.25,,S
|
||||
803,1,1,"Carter, Master. William Thornton II",male,11,1,2,113760,120,B96 B98,S
|
||||
804,1,3,"Thomas, Master. Assad Alexander",male,0.42,0,1,2625,8.5167,,C
|
||||
805,1,3,"Hedman, Mr. Oskar Arvid",male,27,0,0,347089,6.975,,S
|
||||
806,0,3,"Johansson, Mr. Karl Johan",male,31,0,0,347063,7.775,,S
|
||||
807,0,1,"Andrews, Mr. Thomas Jr",male,39,0,0,112050,0,A36,S
|
||||
808,0,3,"Pettersson, Miss. Ellen Natalia",female,18,0,0,347087,7.775,,S
|
||||
809,0,2,"Meyer, Mr. August",male,39,0,0,248723,13,,S
|
||||
810,1,1,"Chambers, Mrs. Norman Campbell (Bertha Griggs)",female,33,1,0,113806,53.1,E8,S
|
||||
811,0,3,"Alexander, Mr. William",male,26,0,0,3474,7.8875,,S
|
||||
812,0,3,"Lester, Mr. James",male,39,0,0,A/4 48871,24.15,,S
|
||||
813,0,2,"Slemen, Mr. Richard James",male,35,0,0,28206,10.5,,S
|
||||
814,0,3,"Andersson, Miss. Ebba Iris Alfrida",female,6,4,2,347082,31.275,,S
|
||||
815,0,3,"Tomlin, Mr. Ernest Portage",male,30.5,0,0,364499,8.05,,S
|
||||
816,0,1,"Fry, Mr. Richard",male,,0,0,112058,0,B102,S
|
||||
817,0,3,"Heininen, Miss. Wendla Maria",female,23,0,0,STON/O2. 3101290,7.925,,S
|
||||
818,0,2,"Mallet, Mr. Albert",male,31,1,1,S.C./PARIS 2079,37.0042,,C
|
||||
819,0,3,"Holm, Mr. John Fredrik Alexander",male,43,0,0,C 7075,6.45,,S
|
||||
820,0,3,"Skoog, Master. Karl Thorsten",male,10,3,2,347088,27.9,,S
|
||||
821,1,1,"Hays, Mrs. Charles Melville (Clara Jennings Gregg)",female,52,1,1,12749,93.5,B69,S
|
||||
822,1,3,"Lulic, Mr. Nikola",male,27,0,0,315098,8.6625,,S
|
||||
823,0,1,"Reuchlin, Jonkheer. John George",male,38,0,0,19972,0,,S
|
||||
824,1,3,"Moor, Mrs. (Beila)",female,27,0,1,392096,12.475,E121,S
|
||||
825,0,3,"Panula, Master. Urho Abraham",male,2,4,1,3101295,39.6875,,S
|
||||
826,0,3,"Flynn, Mr. John",male,,0,0,368323,6.95,,Q
|
||||
827,0,3,"Lam, Mr. Len",male,,0,0,1601,56.4958,,S
|
||||
828,1,2,"Mallet, Master. Andre",male,1,0,2,S.C./PARIS 2079,37.0042,,C
|
||||
829,1,3,"McCormack, Mr. Thomas Joseph",male,,0,0,367228,7.75,,Q
|
||||
830,1,1,"Stone, Mrs. George Nelson (Martha Evelyn)",female,62,0,0,113572,80,B28,
|
||||
831,1,3,"Yasbeck, Mrs. Antoni (Selini Alexander)",female,15,1,0,2659,14.4542,,C
|
||||
832,1,2,"Richards, Master. George Sibley",male,0.83,1,1,29106,18.75,,S
|
||||
833,0,3,"Saad, Mr. Amin",male,,0,0,2671,7.2292,,C
|
||||
834,0,3,"Augustsson, Mr. Albert",male,23,0,0,347468,7.8542,,S
|
||||
835,0,3,"Allum, Mr. Owen George",male,18,0,0,2223,8.3,,S
|
||||
836,1,1,"Compton, Miss. Sara Rebecca",female,39,1,1,PC 17756,83.1583,E49,C
|
||||
837,0,3,"Pasic, Mr. Jakob",male,21,0,0,315097,8.6625,,S
|
||||
838,0,3,"Sirota, Mr. Maurice",male,,0,0,392092,8.05,,S
|
||||
839,1,3,"Chip, Mr. Chang",male,32,0,0,1601,56.4958,,S
|
||||
840,1,1,"Marechal, Mr. Pierre",male,,0,0,11774,29.7,C47,C
|
||||
841,0,3,"Alhomaki, Mr. Ilmari Rudolf",male,20,0,0,SOTON/O2 3101287,7.925,,S
|
||||
842,0,2,"Mudd, Mr. Thomas Charles",male,16,0,0,S.O./P.P. 3,10.5,,S
|
||||
843,1,1,"Serepeca, Miss. Augusta",female,30,0,0,113798,31,,C
|
||||
844,0,3,"Lemberopolous, Mr. Peter L",male,34.5,0,0,2683,6.4375,,C
|
||||
845,0,3,"Culumovic, Mr. Jeso",male,17,0,0,315090,8.6625,,S
|
||||
846,0,3,"Abbing, Mr. Anthony",male,42,0,0,C.A. 5547,7.55,,S
|
||||
847,0,3,"Sage, Mr. Douglas Bullen",male,,8,2,CA. 2343,69.55,,S
|
||||
848,0,3,"Markoff, Mr. Marin",male,35,0,0,349213,7.8958,,C
|
||||
849,0,2,"Harper, Rev. John",male,28,0,1,248727,33,,S
|
||||
850,1,1,"Goldenberg, Mrs. Samuel L (Edwiga Grabowska)",female,,1,0,17453,89.1042,C92,C
|
||||
851,0,3,"Andersson, Master. Sigvard Harald Elias",male,4,4,2,347082,31.275,,S
|
||||
852,0,3,"Svensson, Mr. Johan",male,74,0,0,347060,7.775,,S
|
||||
853,0,3,"Boulos, Miss. Nourelain",female,9,1,1,2678,15.2458,,C
|
||||
854,1,1,"Lines, Miss. Mary Conover",female,16,0,1,PC 17592,39.4,D28,S
|
||||
855,0,2,"Carter, Mrs. Ernest Courtenay (Lilian Hughes)",female,44,1,0,244252,26,,S
|
||||
856,1,3,"Aks, Mrs. Sam (Leah Rosen)",female,18,0,1,392091,9.35,,S
|
||||
857,1,1,"Wick, Mrs. George Dennick (Mary Hitchcock)",female,45,1,1,36928,164.8667,,S
|
||||
858,1,1,"Daly, Mr. Peter Denis ",male,51,0,0,113055,26.55,E17,S
|
||||
859,1,3,"Baclini, Mrs. Solomon (Latifa Qurban)",female,24,0,3,2666,19.2583,,C
|
||||
860,0,3,"Razi, Mr. Raihed",male,,0,0,2629,7.2292,,C
|
||||
861,0,3,"Hansen, Mr. Claus Peter",male,41,2,0,350026,14.1083,,S
|
||||
862,0,2,"Giles, Mr. Frederick Edward",male,21,1,0,28134,11.5,,S
|
||||
863,1,1,"Swift, Mrs. Frederick Joel (Margaret Welles Barron)",female,48,0,0,17466,25.9292,D17,S
|
||||
864,0,3,"Sage, Miss. Dorothy Edith ""Dolly""",female,,8,2,CA. 2343,69.55,,S
|
||||
865,0,2,"Gill, Mr. John William",male,24,0,0,233866,13,,S
|
||||
866,1,2,"Bystrom, Mrs. (Karolina)",female,42,0,0,236852,13,,S
|
||||
867,1,2,"Duran y More, Miss. Asuncion",female,27,1,0,SC/PARIS 2149,13.8583,,C
|
||||
868,0,1,"Roebling, Mr. Washington Augustus II",male,31,0,0,PC 17590,50.4958,A24,S
|
||||
869,0,3,"van Melkebeke, Mr. Philemon",male,,0,0,345777,9.5,,S
|
||||
870,1,3,"Johnson, Master. Harold Theodor",male,4,1,1,347742,11.1333,,S
|
||||
871,0,3,"Balkic, Mr. Cerin",male,26,0,0,349248,7.8958,,S
|
||||
872,1,1,"Beckwith, Mrs. Richard Leonard (Sallie Monypeny)",female,47,1,1,11751,52.5542,D35,S
|
||||
873,0,1,"Carlsson, Mr. Frans Olof",male,33,0,0,695,5,B51 B53 B55,S
|
||||
874,0,3,"Vander Cruyssen, Mr. Victor",male,47,0,0,345765,9,,S
|
||||
875,1,2,"Abelson, Mrs. Samuel (Hannah Wizosky)",female,28,1,0,P/PP 3381,24,,C
|
||||
876,1,3,"Najib, Miss. Adele Kiamie ""Jane""",female,15,0,0,2667,7.225,,C
|
||||
877,0,3,"Gustafsson, Mr. Alfred Ossian",male,20,0,0,7534,9.8458,,S
|
||||
878,0,3,"Petroff, Mr. Nedelio",male,19,0,0,349212,7.8958,,S
|
||||
879,0,3,"Laleff, Mr. Kristo",male,,0,0,349217,7.8958,,S
|
||||
880,1,1,"Potter, Mrs. Thomas Jr (Lily Alexenia Wilson)",female,56,0,1,11767,83.1583,C50,C
|
||||
881,1,2,"Shelley, Mrs. William (Imanita Parrish Hall)",female,25,0,1,230433,26,,S
|
||||
882,0,3,"Markun, Mr. Johann",male,33,0,0,349257,7.8958,,S
|
||||
883,0,3,"Dahlberg, Miss. Gerda Ulrika",female,22,0,0,7552,10.5167,,S
|
||||
884,0,2,"Banfield, Mr. Frederick James",male,28,0,0,C.A./SOTON 34068,10.5,,S
|
||||
885,0,3,"Sutehall, Mr. Henry Jr",male,25,0,0,SOTON/OQ 392076,7.05,,S
|
||||
886,0,3,"Rice, Mrs. William (Margaret Norton)",female,39,0,5,382652,29.125,,Q
|
||||
887,0,2,"Montvila, Rev. Juozas",male,27,0,0,211536,13,,S
|
||||
888,1,1,"Graham, Miss. Margaret Edith",female,19,0,0,112053,30,B42,S
|
||||
889,0,3,"Johnston, Miss. Catherine Helen ""Carrie""",female,,1,2,W./C. 6607,23.45,,S
|
||||
890,1,1,"Behr, Mr. Karl Howell",male,26,0,0,111369,30,C148,C
|
||||
891,0,3,"Dooley, Mr. Patrick",male,32,0,0,370376,7.75,,Q
|
|
@ -1,417 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "18ada398-dce6-4049-9b56-fc0ede63da9c",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Vectorstore Agent\n",
|
||||
"\n",
|
||||
"This notebook showcases an agent designed to retrieve information from one or more vectorstores, either with or without sources."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "eecb683b-3a46-4b9d-81a3-7caefbfec1a1",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Create the Vectorstores"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "9bfd0ed8-a5eb-443e-8e92-90be8cabb0a7",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
|
||||
"from langchain.vectorstores import Chroma\n",
|
||||
"from langchain.text_splitter import CharacterTextSplitter\n",
|
||||
"from langchain import OpenAI, VectorDBQA\n",
|
||||
"llm = OpenAI(temperature=0)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "345bb078-4ec1-4e3a-827b-cd238c49054d",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Running Chroma using direct local API.\n",
|
||||
"Using DuckDB in-memory for database. Data will be transient.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain.document_loaders import TextLoader\n",
|
||||
"loader = TextLoader('../../state_of_the_union.txt')\n",
|
||||
"documents = loader.load()\n",
|
||||
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
|
||||
"texts = text_splitter.split_documents(documents)\n",
|
||||
"\n",
|
||||
"embeddings = OpenAIEmbeddings()\n",
|
||||
"state_of_union_store = Chroma.from_documents(texts, embeddings, collection_name=\"state-of-union\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "5f50eb82-e1a5-4252-8306-8ec1b478d9b4",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Running Chroma using direct local API.\n",
|
||||
"Using DuckDB in-memory for database. Data will be transient.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain.document_loaders import WebBaseLoader\n",
|
||||
"loader = WebBaseLoader(\"https://beta.ruff.rs/docs/faq/\")\n",
|
||||
"docs = loader.load()\n",
|
||||
"ruff_texts = text_splitter.split_documents(docs)\n",
|
||||
"ruff_store = Chroma.from_documents(ruff_texts, embeddings, collection_name=\"ruff\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f4814175-964d-42f1-aa9d-22801ce1e912",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Initialize Toolkit and Agent\n",
|
||||
"\n",
|
||||
"First, we'll create an agent with a single vectorstore."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "5b3b3206",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents.agent_toolkits import (\n",
|
||||
" create_vectorstore_agent,\n",
|
||||
" VectorStoreToolkit,\n",
|
||||
" VectorStoreInfo,\n",
|
||||
")\n",
|
||||
"vectorstore_info = VectorStoreInfo(\n",
|
||||
" name=\"state_of_union_address\",\n",
|
||||
" description=\"the most recent state of the Union adress\",\n",
|
||||
" vectorstore=state_of_union_store\n",
|
||||
")\n",
|
||||
"toolkit = VectorStoreToolkit(vectorstore_info=vectorstore_info)\n",
|
||||
"agent_executor = create_vectorstore_agent(\n",
|
||||
" llm=llm,\n",
|
||||
" toolkit=toolkit,\n",
|
||||
" verbose=True\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "8a38ad10",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Examples"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "3f2f455c",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I need to find the answer in the state of the union address\n",
|
||||
"Action: state_of_union_address\n",
|
||||
"Action Input: What did biden say about ketanji brown jackson\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_executor.run(\"What did biden say about ketanji brown jackson is the state of the union address?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "d61e1e63",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I need to use the state_of_union_address_with_sources tool to answer this question.\n",
|
||||
"Action: state_of_union_address_with_sources\n",
|
||||
"Action Input: What did biden say about ketanji brown jackson\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3m{\"answer\": \" Biden said that he nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to the United States Supreme Court, and that she is one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\\n\", \"sources\": \"../../state_of_the_union.txt\"}\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: Biden said that he nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to the United States Supreme Court, and that she is one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence. Sources: ../../state_of_the_union.txt\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"Biden said that he nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to the United States Supreme Court, and that she is one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence. Sources: ../../state_of_the_union.txt\""
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_executor.run(\"What did biden say about ketanji brown jackson is the state of the union address? List the source.\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "7ca07707",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Multiple Vectorstores\n",
|
||||
"We can also easily use this initialize an agent with multiple vectorstores and use the agent to route between them. To do this. This agent is optimized for routing, so it is a different toolkit and initializer."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "c3209fd3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents.agent_toolkits import (\n",
|
||||
" create_vectorstore_router_agent,\n",
|
||||
" VectorStoreRouterToolkit,\n",
|
||||
" VectorStoreInfo,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "815c4f39-308d-4949-b992-1361036e6e09",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"ruff_vectorstore_info = VectorStoreInfo(\n",
|
||||
" name=\"ruff\",\n",
|
||||
" description=\"Information about the Ruff python linting library\",\n",
|
||||
" vectorstore=ruff_store\n",
|
||||
")\n",
|
||||
"router_toolkit = VectorStoreRouterToolkit(\n",
|
||||
" vectorstores=[vectorstore_info, ruff_vectorstore_info],\n",
|
||||
" llm=llm\n",
|
||||
")\n",
|
||||
"agent_executor = create_vectorstore_agent(\n",
|
||||
" llm=llm,\n",
|
||||
" toolkit=router_toolkit,\n",
|
||||
" verbose=True\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "71680984-edaf-4a63-90f5-94edbd263550",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Examples"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "3cd1bf3e-e3df-4e69-bbe1-71c64b1af947",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I need to use the state_of_union_address tool to answer this question.\n",
|
||||
"Action: state_of_union_address\n",
|
||||
"Action Input: What did biden say about ketanji brown jackson\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_executor.run(\"What did biden say about ketanji brown jackson is the state of the union address?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "c5998b8d",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I need to find out what tool ruff uses to run over Jupyter Notebooks\n",
|
||||
"Action: ruff\n",
|
||||
"Action Input: What tool does ruff use to run over Jupyter Notebooks?\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3m Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.ipynb\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.ipynb\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.ipynb'"
|
||||
]
|
||||
},
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_executor.run(\"What tool does ruff use to run over Jupyter Notebooks?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "744e9b51-fbd9-4778-b594-ea957d0f3467",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I need to find out what tool ruff uses and if the president mentioned it in the state of the union.\n",
|
||||
"Action: ruff\n",
|
||||
"Action Input: What tool does ruff use to run over Jupyter Notebooks?\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3m Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.ipynb\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I need to find out if the president mentioned nbQA in the state of the union.\n",
|
||||
"Action: state_of_union_address\n",
|
||||
"Action Input: Did the president mention nbQA in the state of the union?\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m No, the president did not mention nbQA in the state of the union.\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
|
||||
"Final Answer: No, the president did not mention nbQA in the state of the union.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'No, the president did not mention nbQA in the state of the union.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_executor.run(\"What tool does ruff use to run over Jupyter Notebooks? Did the president mention that tool in the state of the union?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "92203aa9-f63a-4ce1-b562-fadf4474ad9d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.9"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
@ -22,7 +22,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"execution_count": 20,
|
||||
"id": "2e87c10a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -30,14 +30,13 @@
|
||||
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
|
||||
"from langchain.vectorstores import Chroma\n",
|
||||
"from langchain.text_splitter import CharacterTextSplitter\n",
|
||||
"from langchain.llms import OpenAI\n",
|
||||
"from langchain.chains import RetrievalQA\n",
|
||||
"from langchain import OpenAI, VectorDBQA\n",
|
||||
"llm = OpenAI(temperature=0)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"execution_count": 37,
|
||||
"id": "f2675861",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@ -63,17 +62,17 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": 38,
|
||||
"id": "bc5403d4",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"state_of_union = RetrievalQA.from_chain_type(llm=llm, chain_type=\"stuff\", retriever=docsearch.as_retriever())"
|
||||
"state_of_union = VectorDBQA.from_chain_type(llm=llm, chain_type=\"stuff\", vectorstore=docsearch)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"execution_count": 39,
|
||||
"id": "1431cded",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -83,7 +82,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"execution_count": 40,
|
||||
"id": "915d3ff3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -93,7 +92,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"execution_count": 41,
|
||||
"id": "96a2edf8",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@ -110,7 +109,7 @@
|
||||
"docs = loader.load()\n",
|
||||
"ruff_texts = text_splitter.split_documents(docs)\n",
|
||||
"ruff_db = Chroma.from_documents(ruff_texts, embeddings, collection_name=\"ruff\")\n",
|
||||
"ruff = RetrievalQA.from_chain_type(llm=llm, chain_type=\"stuff\", retriever=ruff_db.as_retriever())"
|
||||
"ruff = VectorDBQA.from_chain_type(llm=llm, chain_type=\"stuff\", vectorstore=ruff_db)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -265,9 +264,9 @@
|
||||
"id": "9161ba91",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You can also set `return_direct=True` if you intend to use the agent as a router and just want to directly return the result of the RetrievalQAChain.\n",
|
||||
"You can also set `return_direct=True` if you intend to use the agent as a router and just want to directly return the result of the VectorDBQaChain.\n",
|
||||
"\n",
|
||||
"Notice that in the above examples the agent did some extra work after querying the RetrievalQAChain. You can avoid that and just return the result directly."
|
||||
"Notice that in the above examples the agent did some extra work after querying the VectorDBQAChain. You can avoid that and just return the result directly."
|
||||
]
|
||||
},
|
||||
{
|
||||
|
@ -403,7 +403,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.9"
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
@ -1,309 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "4658d71a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Conversation Agent (for Chat Models)\n",
|
||||
"\n",
|
||||
"This notebook walks through using an agent optimized for conversation, using ChatModels. Other agents are often optimized for using tools to figure out the best response, which is not ideal in a conversational setting where you may want the agent to be able to chat with the user as well.\n",
|
||||
"\n",
|
||||
"This is accomplished with a specific type of agent (`chat-conversational-react-description`) which expects to be used with a memory component."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "f4f5d1a8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"os.environ[\"LANGCHAIN_HANDLER\"] = \"langchain\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "f65308ab",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import Tool\n",
|
||||
"from langchain.memory import ConversationBufferMemory\n",
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.utilities import SerpAPIWrapper\n",
|
||||
"from langchain.agents import initialize_agent"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "5fb14d6d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"search = SerpAPIWrapper()\n",
|
||||
"tools = [\n",
|
||||
" Tool(\n",
|
||||
" name = \"Current Search\",\n",
|
||||
" func=search.run,\n",
|
||||
" description=\"useful for when you need to answer questions about current events or the current state of the world. the input to this should be a single search term.\"\n",
|
||||
" ),\n",
|
||||
"]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "dddc34c4",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"memory = ConversationBufferMemory(memory_key=\"chat_history\", return_messages=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "cafe9bc1",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm=ChatOpenAI(temperature=0)\n",
|
||||
"agent_chain = initialize_agent(tools, llm, agent=\"chat-conversational-react-description\", verbose=True, memory=memory)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "dc70b454",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m{\n",
|
||||
" \"action\": \"Final Answer\",\n",
|
||||
" \"action_input\": \"Hello Bob! How can I assist you today?\"\n",
|
||||
"}\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Hello Bob! How can I assist you today?'"
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_chain.run(input=\"hi, i am bob\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "3dcf7953",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m{\n",
|
||||
" \"action\": \"Final Answer\",\n",
|
||||
" \"action_input\": \"Your name is Bob.\"\n",
|
||||
"}\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Your name is Bob.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_chain.run(input=\"what's my name?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "aa05f566",
|
||||
"metadata": {
|
||||
"scrolled": false
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m{\n",
|
||||
" \"action\": \"Current Search\",\n",
|
||||
" \"action_input\": \"Thai food dinner recipes\"\n",
|
||||
"}\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m59 easy Thai recipes for any night of the week · Marion Grasby's Thai spicy chilli and basil fried rice · Thai curry noodle soup · Marion Grasby's ...\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m{\n",
|
||||
" \"action\": \"Final Answer\",\n",
|
||||
" \"action_input\": \"Here are some Thai food dinner recipes you can make this week: Thai spicy chilli and basil fried rice, Thai curry noodle soup, and many more. You can find 59 easy Thai recipes for any night of the week on Marion Grasby's website.\"\n",
|
||||
"}\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"Here are some Thai food dinner recipes you can make this week: Thai spicy chilli and basil fried rice, Thai curry noodle soup, and many more. You can find 59 easy Thai recipes for any night of the week on Marion Grasby's website.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_chain.run(\"what are some good dinners to make this week, if i like thai food?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "c5d8b7ea",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m```json\n",
|
||||
"{\n",
|
||||
" \"action\": \"Current Search\",\n",
|
||||
" \"action_input\": \"who won the world cup in 1978\"\n",
|
||||
"}\n",
|
||||
"```\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mThe Argentina national football team represents Argentina in men's international football and is administered by the Argentine Football Association, the governing body for football in Argentina. Nicknamed La Albiceleste, they are the reigning world champions, having won the most recent World Cup in 2022.\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m```json\n",
|
||||
"{\n",
|
||||
" \"action\": \"Final Answer\",\n",
|
||||
" \"action_input\": \"The last letter in your name is 'b'. The Argentina national football team won the World Cup in 1978.\"\n",
|
||||
"}\n",
|
||||
"```\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"The last letter in your name is 'b'. The Argentina national football team won the World Cup in 1978.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_chain.run(input=\"tell me the last letter in my name, and also tell me who won the world cup in 1978?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "f608889b",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m{\n",
|
||||
" \"action\": \"Current Search\",\n",
|
||||
" \"action_input\": \"weather in pomfret\"\n",
|
||||
"}\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mMostly cloudy with gusty winds developing during the afternoon. A few flurries or snow showers possible. High near 40F. Winds NNW at 20 to 30 mph.\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m{\n",
|
||||
" \"action\": \"Final Answer\",\n",
|
||||
" \"action_input\": \"The weather in Pomfret is mostly cloudy with gusty winds developing during the afternoon. A few flurries or snow showers are possible. High near 40F. Winds NNW at 20 to 30 mph.\"\n",
|
||||
"}\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'The weather in Pomfret is mostly cloudy with gusty winds developing during the afternoon. A few flurries or snow showers are possible. High near 40F. Winds NNW at 20 to 30 mph.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_chain.run(input=\"whats the weather like in pomfret?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "0084efd6",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
@ -1,119 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "3f34700b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# ChatGPT Plugins\n",
|
||||
"\n",
|
||||
"This example shows how to use ChatGPT Plugins within LangChain abstractions.\n",
|
||||
"\n",
|
||||
"Note 1: This currently only works for plugins with no auth.\n",
|
||||
"\n",
|
||||
"Note 2: There are almost certainly other ways to do this, this is just a first pass. If you have better ideas, please open a PR!"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "d41405b5",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.agents import load_tools, initialize_agent\n",
|
||||
"from langchain.tools import AIPluginTool"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "d9e61df5",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tool = AIPluginTool.from_plugin_url(\"https://www.klarna.com/.well-known/ai-plugin.json\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "edc0ea0e",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mI need to check the Klarna Shopping API to see if it has information on available t shirts.\n",
|
||||
"Action: KlarnaProducts\n",
|
||||
"Action Input: None\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3mUsage Guide: Use the Klarna plugin to get relevant product suggestions for any shopping or researching purpose. The query to be sent should not include stopwords like articles, prepositions and determinants. The api works best when searching for words that are related to products, like their name, brand, model or category. Links will always be returned and should be shown to the user.\n",
|
||||
"\n",
|
||||
"OpenAPI Spec: {'openapi': '3.0.1', 'info': {'version': 'v0', 'title': 'Open AI Klarna product Api'}, 'servers': [{'url': 'https://www.klarna.com/us/shopping'}], 'tags': [{'name': 'open-ai-product-endpoint', 'description': 'Open AI Product Endpoint. Query for products.'}], 'paths': {'/public/openai/v0/products': {'get': {'tags': ['open-ai-product-endpoint'], 'summary': 'API for fetching Klarna product information', 'operationId': 'productsUsingGET', 'parameters': [{'name': 'q', 'in': 'query', 'description': 'query, must be between 2 and 100 characters', 'required': True, 'schema': {'type': 'string'}}, {'name': 'size', 'in': 'query', 'description': 'number of products returned', 'required': False, 'schema': {'type': 'integer'}}, {'name': 'budget', 'in': 'query', 'description': 'maximum price of the matching product in local currency, filters results', 'required': False, 'schema': {'type': 'integer'}}], 'responses': {'200': {'description': 'Products found', 'content': {'application/json': {'schema': {'$ref': '#/components/schemas/ProductResponse'}}}}, '503': {'description': 'one or more services are unavailable'}}, 'deprecated': False}}}, 'components': {'schemas': {'Product': {'type': 'object', 'properties': {'attributes': {'type': 'array', 'items': {'type': 'string'}}, 'name': {'type': 'string'}, 'price': {'type': 'string'}, 'url': {'type': 'string'}}, 'title': 'Product'}, 'ProductResponse': {'type': 'object', 'properties': {'products': {'type': 'array', 'items': {'$ref': '#/components/schemas/Product'}}}, 'title': 'ProductResponse'}}}}\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mI need to use the Klarna Shopping API to search for t shirts.\n",
|
||||
"Action: requests_get\n",
|
||||
"Action Input: https://www.klarna.com/us/shopping/public/openai/v0/products?q=t%20shirts\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m{\"products\":[{\"name\":\"Lacoste Men's Pack of Plain T-Shirts\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3202043025/Clothing/Lacoste-Men-s-Pack-of-Plain-T-Shirts/?source=openai\",\"price\":\"$28.99\",\"attributes\":[\"Material:Cotton\",\"Target Group:Man\",\"Color:White,Black\"]},{\"name\":\"Hanes Men's Ultimate 6pk. Crewneck T-Shirts\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3201808270/Clothing/Hanes-Men-s-Ultimate-6pk.-Crewneck-T-Shirts/?source=openai\",\"price\":\"$13.40\",\"attributes\":[\"Material:Cotton\",\"Target Group:Man\",\"Color:White\"]},{\"name\":\"Nike Boy's Jordan Stretch T-shirts\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl359/3201863202/Children-s-Clothing/Nike-Boy-s-Jordan-Stretch-T-shirts/?source=openai\",\"price\":\"$14.99\",\"attributes\":[\"Color:White,Green\",\"Model:Boy\",\"Pattern:Solid Color\",\"Size (Small-Large):S,XL,L,M\"]},{\"name\":\"Polo Classic Fit Cotton V-Neck T-Shirts 3-Pack\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3203028500/Clothing/Polo-Classic-Fit-Cotton-V-Neck-T-Shirts-3-Pack/?source=openai\",\"price\":\"$29.95\",\"attributes\":[\"Material:Cotton\",\"Target Group:Man\",\"Color:White,Blue,Black\"]},{\"name\":\"adidas Comfort T-shirts Men's 3-pack\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3202640533/Clothing/adidas-Comfort-T-shirts-Men-s-3-pack/?source=openai\",\"price\":\"$14.99\",\"attributes\":[\"Material:Cotton\",\"Target Group:Man\",\"Color:White,Black\",\"Pattern:Solid Color\"]}]}\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mThe available t shirts on Klarna are Lacoste Men's Pack of Plain T-Shirts, Hanes Men's Ultimate 6pk. Crewneck T-Shirts, Nike Boy's Jordan Stretch T-shirts, Polo Classic Fit Cotton V-Neck T-Shirts 3-Pack, and adidas Comfort T-shirts Men's 3-pack.\n",
|
||||
"Final Answer: The available t shirts on Klarna are Lacoste Men's Pack of Plain T-Shirts, Hanes Men's Ultimate 6pk. Crewneck T-Shirts, Nike Boy's Jordan Stretch T-shirts, Polo Classic Fit Cotton V-Neck T-Shirts 3-Pack, and adidas Comfort T-shirts Men's 3-pack.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"The available t shirts on Klarna are Lacoste Men's Pack of Plain T-Shirts, Hanes Men's Ultimate 6pk. Crewneck T-Shirts, Nike Boy's Jordan Stretch T-shirts, Polo Classic Fit Cotton V-Neck T-Shirts 3-Pack, and adidas Comfort T-shirts Men's 3-pack.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"llm = ChatOpenAI(temperature=0)\n",
|
||||
"tools = load_tools([\"requests\"] )\n",
|
||||
"tools += [tool]\n",
|
||||
"\n",
|
||||
"agent_chain = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)\n",
|
||||
"\n",
|
||||
"agent_chain.run(\"what t shirts are available in klarna?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "e49318a4",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
@ -1,132 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Human as a tool\n",
|
||||
"\n",
|
||||
"Human are AGI so they can certainly be used as a tool to help out AI agent \n",
|
||||
"when it is confused."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import sys\n",
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.llms import OpenAI\n",
|
||||
"from langchain.agents import load_tools, initialize_agent\n",
|
||||
"\n",
|
||||
"llm = ChatOpenAI(temperature=0.0)\n",
|
||||
"math_llm = OpenAI(temperature=0.0)\n",
|
||||
"tools = load_tools(\n",
|
||||
" [\"human\", \"llm-math\"], \n",
|
||||
" llm=math_llm,\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"agent_chain = initialize_agent(\n",
|
||||
" tools,\n",
|
||||
" llm,\n",
|
||||
" agent=\"zero-shot-react-description\",\n",
|
||||
" verbose=True,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"In the above code you can see the tool takes input directly from command line.\n",
|
||||
"You can customize `prompt_func` and `input_func` according to your need."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mI don't know Eric Zhu, so I should ask a human for guidance.\n",
|
||||
"Action: Human\n",
|
||||
"Action Input: \"Do you know when Eric Zhu's birthday is?\"\u001b[0m\n",
|
||||
"\n",
|
||||
"Do you know when Eric Zhu's birthday is?\n",
|
||||
"last week\n",
|
||||
"\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mlast week\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mThat's not very helpful. I should ask for more information.\n",
|
||||
"Action: Human\n",
|
||||
"Action Input: \"Do you know the specific date of Eric Zhu's birthday?\"\u001b[0m\n",
|
||||
"\n",
|
||||
"Do you know the specific date of Eric Zhu's birthday?\n",
|
||||
"august 1st\n",
|
||||
"\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3maugust 1st\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mNow that I have the date, I can check if it's a leap year or not.\n",
|
||||
"Action: Calculator\n",
|
||||
"Action Input: \"Is 2021 a leap year?\"\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3mAnswer: False\n",
|
||||
"\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mI have all the information I need to answer the original question.\n",
|
||||
"Final Answer: Eric Zhu's birthday is on August 1st and it is not a leap year in 2021.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"Eric Zhu's birthday is on August 1st and it is not a leap year in 2021.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"\n",
|
||||
"agent_chain.run(\"What is Eric Zhu's birthday?\")\n",
|
||||
"# Answer with \"last week\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
@ -29,16 +29,16 @@
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
|
||||
"\u001B[32;1m\u001B[1;3m Yes.\n",
|
||||
"Follow up: Who is the reigning men's U.S. Open champion?\u001B[0m\n",
|
||||
"Intermediate answer: \u001B[36;1m\u001B[1;3m2016 · SUI · Stan Wawrinka ; 2017 · ESP · Rafael Nadal ; 2018 · SRB · Novak Djokovic ; 2019 · ESP · Rafael Nadal.\u001B[0m\n",
|
||||
"\u001B[32;1m\u001B[1;3mSo the reigning men's U.S. Open champion is Rafael Nadal.\n",
|
||||
"Follow up: What is Rafael Nadal's hometown?\u001B[0m\n",
|
||||
"Intermediate answer: \u001B[36;1m\u001B[1;3mIn 2016, he once again showed his deep ties to Mallorca and opened the Rafa Nadal Academy in his hometown of Manacor.\u001B[0m\n",
|
||||
"\u001B[32;1m\u001B[1;3mSo the final answer is: Manacor, Mallorca, Spain.\u001B[0m\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m Yes.\n",
|
||||
"Follow up: Who is the reigning men's U.S. Open champion?\u001b[0m\n",
|
||||
"Intermediate answer: \u001b[36;1m\u001b[1;3m2016 · SUI · Stan Wawrinka ; 2017 · ESP · Rafael Nadal ; 2018 · SRB · Novak Djokovic ; 2019 · ESP · Rafael Nadal.\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mSo the reigning men's U.S. Open champion is Rafael Nadal.\n",
|
||||
"Follow up: What is Rafael Nadal's hometown?\u001b[0m\n",
|
||||
"Intermediate answer: \u001b[36;1m\u001b[1;3mIn 2016, he once again showed his deep ties to Mallorca and opened the Rafa Nadal Academy in his hometown of Manacor.\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mSo the final answer is: Manacor, Mallorca, Spain.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001B[1m> Finished chain.\u001B[0m\n"
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -61,8 +61,7 @@
|
||||
"tools = [\n",
|
||||
" Tool(\n",
|
||||
" name=\"Intermediate Answer\",\n",
|
||||
" func=search.run,\n",
|
||||
" description=\"useful for when you need to ask with search\"\n",
|
||||
" func=search.run\n",
|
||||
" )\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
|
@ -12,7 +12,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"execution_count": 1,
|
||||
"id": "e6860c2d",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
@ -28,7 +28,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": 2,
|
||||
"id": "dadbcfcd",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -238,92 +238,6 @@
|
||||
"source": [
|
||||
"agent.run(\"What is the weather in Pomfret?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "eabad3af",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## SearxNG Meta Search Engine\n",
|
||||
"\n",
|
||||
"Here we will be using a self hosted SearxNG meta search engine."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "b196c704",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tools = load_tools([\"searx-search\"], searx_host=\"http://localhost:8888\", llm=llm)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "9023eeaa",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "3aad92c1",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I should look up the current weather\n",
|
||||
"Action: SearX Search\n",
|
||||
"Action Input: \"weather in Pomfret\"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mMainly cloudy with snow showers around in the morning. High around 40F. Winds NNW at 5 to 10 mph. Chance of snow 40%. Snow accumulations less than one inch.\n",
|
||||
"\n",
|
||||
"10 Day Weather - Pomfret, MD As of 1:37 pm EST Today 49°/ 41° 52% Mon 27 | Day 49° 52% SE 14 mph Cloudy with occasional rain showers. High 49F. Winds SE at 10 to 20 mph. Chance of rain 50%....\n",
|
||||
"\n",
|
||||
"10 Day Weather - Pomfret, VT As of 3:51 am EST Special Weather Statement Today 39°/ 32° 37% Wed 01 | Day 39° 37% NE 4 mph Cloudy with snow showers developing for the afternoon. High 39F....\n",
|
||||
"\n",
|
||||
"Pomfret, CT ; Current Weather. 1:06 AM. 35°F · RealFeel® 32° ; TODAY'S WEATHER FORECAST. 3/3. 44°Hi. RealFeel® 50° ; TONIGHT'S WEATHER FORECAST. 3/3. 32°Lo.\n",
|
||||
"\n",
|
||||
"Pomfret, MD Forecast Today Hourly Daily Morning 41° 1% Afternoon 43° 0% Evening 35° 3% Overnight 34° 2% Don't Miss Finally, Here’s Why We Get More Colds and Flu When It’s Cold Coast-To-Coast...\n",
|
||||
"\n",
|
||||
"Pomfret, MD Weather Forecast | AccuWeather Current Weather 5:35 PM 35° F RealFeel® 36° RealFeel Shade™ 36° Air Quality Excellent Wind E 3 mph Wind Gusts 5 mph Cloudy More Details WinterCast...\n",
|
||||
"\n",
|
||||
"Pomfret, VT Weather Forecast | AccuWeather Current Weather 11:21 AM 23° F RealFeel® 27° RealFeel Shade™ 25° Air Quality Fair Wind ESE 3 mph Wind Gusts 7 mph Cloudy More Details WinterCast...\n",
|
||||
"\n",
|
||||
"Pomfret Center, CT Weather Forecast | AccuWeather Daily Current Weather 6:50 PM 39° F RealFeel® 36° Air Quality Fair Wind NW 6 mph Wind Gusts 16 mph Mostly clear More Details WinterCast...\n",
|
||||
"\n",
|
||||
"12:00 pm · Feels Like36° · WindN 5 mph · Humidity43% · UV Index3 of 10 · Cloud Cover65% · Rain Amount0 in ...\n",
|
||||
"\n",
|
||||
"Pomfret Center, CT Weather Conditions | Weather Underground star Popular Cities San Francisco, CA 49 °F Clear Manhattan, NY 37 °F Fair Schiller Park, IL (60176) warning39 °F Mostly Cloudy...\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: The current weather in Pomfret is mainly cloudy with snow showers around in the morning. The temperature is around 40F with winds NNW at 5 to 10 mph. Chance of snow is 40%.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'The current weather in Pomfret is mainly cloudy with snow showers around in the morning. The temperature is around 40F with winds NNW at 5 to 10 mph. Chance of snow is 40%.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent.run(\"What is the weather in Pomfret\")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
@ -342,7 +256,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.11"
|
||||
"version": "3.9.1"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
|
@ -1,552 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "fa6802ac",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Adding SharedMemory to an Agent and its Tools\n",
|
||||
"\n",
|
||||
"This notebook goes over adding memory to **both** of an Agent and its tools. Before going through this notebook, please walk through the following notebooks, as this will build on top of both of them:\n",
|
||||
"\n",
|
||||
"- [Adding memory to an LLM Chain](../../memory/examples/adding_memory.ipynb)\n",
|
||||
"- [Custom Agents](custom_agent.ipynb)\n",
|
||||
"\n",
|
||||
"We are going to create a custom Agent. The agent has access to a conversation memory, search tool, and a summarization tool. And, the summarization tool also needs access to the conversation memory."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "8db95912",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import ZeroShotAgent, Tool, AgentExecutor\n",
|
||||
"from langchain.memory import ConversationBufferMemory, ReadOnlySharedMemory\n",
|
||||
"from langchain import OpenAI, LLMChain, PromptTemplate\n",
|
||||
"from langchain.utilities import GoogleSearchAPIWrapper"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "06b7187b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"template = \"\"\"This is a conversation between a human and a bot:\n",
|
||||
"\n",
|
||||
"{chat_history}\n",
|
||||
"\n",
|
||||
"Write a summary of the conversation for {input}:\n",
|
||||
"\"\"\"\n",
|
||||
"\n",
|
||||
"prompt = PromptTemplate(\n",
|
||||
" input_variables=[\"input\", \"chat_history\"], \n",
|
||||
" template=template\n",
|
||||
")\n",
|
||||
"memory = ConversationBufferMemory(memory_key=\"chat_history\")\n",
|
||||
"readonlymemory = ReadOnlySharedMemory(memory=memory)\n",
|
||||
"summry_chain = LLMChain(\n",
|
||||
" llm=OpenAI(), \n",
|
||||
" prompt=prompt, \n",
|
||||
" verbose=True, \n",
|
||||
" memory=readonlymemory, # use the read-only memory to prevent the tool from modifying the memory\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "97ad8467",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"search = GoogleSearchAPIWrapper()\n",
|
||||
"tools = [\n",
|
||||
" Tool(\n",
|
||||
" name = \"Search\",\n",
|
||||
" func=search.run,\n",
|
||||
" description=\"useful for when you need to answer questions about current events\"\n",
|
||||
" ),\n",
|
||||
" Tool(\n",
|
||||
" name = \"Summary\",\n",
|
||||
" func=summry_chain.run,\n",
|
||||
" description=\"useful for when you summarize a conversation. The input to this tool should be a string, representing who will read this summary.\"\n",
|
||||
" )\n",
|
||||
"]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "e3439cd6",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"prefix = \"\"\"Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:\"\"\"\n",
|
||||
"suffix = \"\"\"Begin!\"\n",
|
||||
"\n",
|
||||
"{chat_history}\n",
|
||||
"Question: {input}\n",
|
||||
"{agent_scratchpad}\"\"\"\n",
|
||||
"\n",
|
||||
"prompt = ZeroShotAgent.create_prompt(\n",
|
||||
" tools, \n",
|
||||
" prefix=prefix, \n",
|
||||
" suffix=suffix, \n",
|
||||
" input_variables=[\"input\", \"chat_history\", \"agent_scratchpad\"]\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "0021675b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We can now construct the LLMChain, with the Memory object, and then create the agent."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "c56a0e73",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=prompt)\n",
|
||||
"agent = ZeroShotAgent(llm_chain=llm_chain, tools=tools, verbose=True)\n",
|
||||
"agent_chain = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True, memory=memory)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "ca4bc1fb",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mThought: I should research ChatGPT to answer this question.\n",
|
||||
"Action: Search\n",
|
||||
"Action Input: \"ChatGPT\"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mNov 30, 2022 ... We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... ChatGPT. We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... Feb 2, 2023 ... ChatGPT, the popular chatbot from OpenAI, is estimated to have reached 100 million monthly active users in January, just two months after ... 2 days ago ... ChatGPT recently launched a new version of its own plagiarism detection tool, with hopes that it will squelch some of the criticism around how ... An API for accessing new AI models developed by OpenAI. Feb 19, 2023 ... ChatGPT is an AI chatbot system that OpenAI released in November to show off and test what a very large, powerful AI system can accomplish. You ... ChatGPT is fine-tuned from GPT-3.5, a language model trained to produce text. ChatGPT was optimized for dialogue by using Reinforcement Learning with Human ... 3 days ago ... Visual ChatGPT connects ChatGPT and a series of Visual Foundation Models to enable sending and receiving images during chatting. Dec 1, 2022 ... ChatGPT is a natural language processing tool driven by AI technology that allows you to have human-like conversations and much more with a ...\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
|
||||
"Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_chain.run(input=\"What is ChatGPT?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "45627664",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"To test the memory of this agent, we can ask a followup question that relies on information in the previous exchange to be answered correctly."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "eecc0462",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mThought: I need to find out who developed ChatGPT\n",
|
||||
"Action: Search\n",
|
||||
"Action Input: Who developed ChatGPT\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... Feb 15, 2023 ... Who owns Chat GPT? Chat GPT is owned and developed by AI research and deployment company, OpenAI. The organization is headquartered in San ... Feb 8, 2023 ... ChatGPT is an AI chatbot developed by San Francisco-based startup OpenAI. OpenAI was co-founded in 2015 by Elon Musk and Sam Altman and is ... Dec 7, 2022 ... ChatGPT is an AI chatbot designed and developed by OpenAI. The bot works by generating text responses based on human-user input, like questions ... Jan 12, 2023 ... In 2019, Microsoft invested $1 billion in OpenAI, the tiny San Francisco company that designed ChatGPT. And in the years since, it has quietly ... Jan 25, 2023 ... The inside story of ChatGPT: How OpenAI founder Sam Altman built the world's hottest technology with billions from Microsoft. Dec 3, 2022 ... ChatGPT went viral on social media for its ability to do anything from code to write essays. · The company that created the AI chatbot has a ... Jan 17, 2023 ... While many Americans were nursing hangovers on New Year's Day, 22-year-old Edward Tian was working feverishly on a new app to combat misuse ... ChatGPT is a language model created by OpenAI, an artificial intelligence research laboratory consisting of a team of researchers and engineers focused on ... 1 day ago ... Everyone is talking about ChatGPT, developed by OpenAI. This is such a great tool that has helped to make AI more accessible to a wider ...\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: ChatGPT was developed by OpenAI.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'ChatGPT was developed by OpenAI.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_chain.run(input=\"Who developed it?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "c34424cf",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mThought: I need to simplify the conversation for a 5 year old.\n",
|
||||
"Action: Summary\n",
|
||||
"Action Input: My daughter 5 years old\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
|
||||
"Prompt after formatting:\n",
|
||||
"\u001b[32;1m\u001b[1;3mThis is a conversation between a human and a bot:\n",
|
||||
"\n",
|
||||
"Human: What is ChatGPT?\n",
|
||||
"AI: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\n",
|
||||
"Human: Who developed it?\n",
|
||||
"AI: ChatGPT was developed by OpenAI.\n",
|
||||
"\n",
|
||||
"Write a summary of the conversation for My daughter 5 years old:\n",
|
||||
"\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||
"\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3m\n",
|
||||
"The conversation was about ChatGPT, an artificial intelligence chatbot. It was created by OpenAI and can send and receive images while chatting.\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
|
||||
"Final Answer: ChatGPT is an artificial intelligence chatbot created by OpenAI that can send and receive images while chatting.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'ChatGPT is an artificial intelligence chatbot created by OpenAI that can send and receive images while chatting.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_chain.run(input=\"Thanks. Summarize the conversation, for my daughter 5 years old.\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "4ebd8326",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Confirm that the memory was correctly updated."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "b91f8c85",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Human: What is ChatGPT?\n",
|
||||
"AI: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\n",
|
||||
"Human: Who developed it?\n",
|
||||
"AI: ChatGPT was developed by OpenAI.\n",
|
||||
"Human: Thanks. Summarize the conversation, for my daughter 5 years old.\n",
|
||||
"AI: ChatGPT is an artificial intelligence chatbot created by OpenAI that can send and receive images while chatting.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(agent_chain.memory.buffer)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "cc3d0aa4",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"For comparison, below is a bad example that uses the same memory for both the Agent and the tool."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "3359d043",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"## This is a bad practice for using the memory.\n",
|
||||
"## Use the ReadOnlySharedMemory class, as shown above.\n",
|
||||
"\n",
|
||||
"template = \"\"\"This is a conversation between a human and a bot:\n",
|
||||
"\n",
|
||||
"{chat_history}\n",
|
||||
"\n",
|
||||
"Write a summary of the conversation for {input}:\n",
|
||||
"\"\"\"\n",
|
||||
"\n",
|
||||
"prompt = PromptTemplate(\n",
|
||||
" input_variables=[\"input\", \"chat_history\"], \n",
|
||||
" template=template\n",
|
||||
")\n",
|
||||
"memory = ConversationBufferMemory(memory_key=\"chat_history\")\n",
|
||||
"summry_chain = LLMChain(\n",
|
||||
" llm=OpenAI(), \n",
|
||||
" prompt=prompt, \n",
|
||||
" verbose=True, \n",
|
||||
" memory=memory, # <--- this is the only change\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"search = GoogleSearchAPIWrapper()\n",
|
||||
"tools = [\n",
|
||||
" Tool(\n",
|
||||
" name = \"Search\",\n",
|
||||
" func=search.run,\n",
|
||||
" description=\"useful for when you need to answer questions about current events\"\n",
|
||||
" ),\n",
|
||||
" Tool(\n",
|
||||
" name = \"Summary\",\n",
|
||||
" func=summry_chain.run,\n",
|
||||
" description=\"useful for when you summarize a conversation. The input to this tool should be a string, representing who will read this summary.\"\n",
|
||||
" )\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"prefix = \"\"\"Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:\"\"\"\n",
|
||||
"suffix = \"\"\"Begin!\"\n",
|
||||
"\n",
|
||||
"{chat_history}\n",
|
||||
"Question: {input}\n",
|
||||
"{agent_scratchpad}\"\"\"\n",
|
||||
"\n",
|
||||
"prompt = ZeroShotAgent.create_prompt(\n",
|
||||
" tools, \n",
|
||||
" prefix=prefix, \n",
|
||||
" suffix=suffix, \n",
|
||||
" input_variables=[\"input\", \"chat_history\", \"agent_scratchpad\"]\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=prompt)\n",
|
||||
"agent = ZeroShotAgent(llm_chain=llm_chain, tools=tools, verbose=True)\n",
|
||||
"agent_chain = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True, memory=memory)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "970d23df",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mThought: I should research ChatGPT to answer this question.\n",
|
||||
"Action: Search\n",
|
||||
"Action Input: \"ChatGPT\"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mNov 30, 2022 ... We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... ChatGPT. We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... Feb 2, 2023 ... ChatGPT, the popular chatbot from OpenAI, is estimated to have reached 100 million monthly active users in January, just two months after ... 2 days ago ... ChatGPT recently launched a new version of its own plagiarism detection tool, with hopes that it will squelch some of the criticism around how ... An API for accessing new AI models developed by OpenAI. Feb 19, 2023 ... ChatGPT is an AI chatbot system that OpenAI released in November to show off and test what a very large, powerful AI system can accomplish. You ... ChatGPT is fine-tuned from GPT-3.5, a language model trained to produce text. ChatGPT was optimized for dialogue by using Reinforcement Learning with Human ... 3 days ago ... Visual ChatGPT connects ChatGPT and a series of Visual Foundation Models to enable sending and receiving images during chatting. Dec 1, 2022 ... ChatGPT is a natural language processing tool driven by AI technology that allows you to have human-like conversations and much more with a ...\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
|
||||
"Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_chain.run(input=\"What is ChatGPT?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"id": "d9ea82f0",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mThought: I need to find out who developed ChatGPT\n",
|
||||
"Action: Search\n",
|
||||
"Action Input: Who developed ChatGPT\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... Feb 15, 2023 ... Who owns Chat GPT? Chat GPT is owned and developed by AI research and deployment company, OpenAI. The organization is headquartered in San ... Feb 8, 2023 ... ChatGPT is an AI chatbot developed by San Francisco-based startup OpenAI. OpenAI was co-founded in 2015 by Elon Musk and Sam Altman and is ... Dec 7, 2022 ... ChatGPT is an AI chatbot designed and developed by OpenAI. The bot works by generating text responses based on human-user input, like questions ... Jan 12, 2023 ... In 2019, Microsoft invested $1 billion in OpenAI, the tiny San Francisco company that designed ChatGPT. And in the years since, it has quietly ... Jan 25, 2023 ... The inside story of ChatGPT: How OpenAI founder Sam Altman built the world's hottest technology with billions from Microsoft. Dec 3, 2022 ... ChatGPT went viral on social media for its ability to do anything from code to write essays. · The company that created the AI chatbot has a ... Jan 17, 2023 ... While many Americans were nursing hangovers on New Year's Day, 22-year-old Edward Tian was working feverishly on a new app to combat misuse ... ChatGPT is a language model created by OpenAI, an artificial intelligence research laboratory consisting of a team of researchers and engineers focused on ... 1 day ago ... Everyone is talking about ChatGPT, developed by OpenAI. This is such a great tool that has helped to make AI more accessible to a wider ...\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: ChatGPT was developed by OpenAI.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'ChatGPT was developed by OpenAI.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 12,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_chain.run(input=\"Who developed it?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"id": "5b1f9223",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mThought: I need to simplify the conversation for a 5 year old.\n",
|
||||
"Action: Summary\n",
|
||||
"Action Input: My daughter 5 years old\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
|
||||
"Prompt after formatting:\n",
|
||||
"\u001b[32;1m\u001b[1;3mThis is a conversation between a human and a bot:\n",
|
||||
"\n",
|
||||
"Human: What is ChatGPT?\n",
|
||||
"AI: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\n",
|
||||
"Human: Who developed it?\n",
|
||||
"AI: ChatGPT was developed by OpenAI.\n",
|
||||
"\n",
|
||||
"Write a summary of the conversation for My daughter 5 years old:\n",
|
||||
"\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||
"\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3m\n",
|
||||
"The conversation was about ChatGPT, an artificial intelligence chatbot developed by OpenAI. It is designed to have conversations with humans and can also send and receive images.\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
|
||||
"Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI that can have conversations with humans and send and receive images.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'ChatGPT is an artificial intelligence chatbot developed by OpenAI that can have conversations with humans and send and receive images.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 13,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_chain.run(input=\"Thanks. Summarize the conversation, for my daughter 5 years old.\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "d07415da",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The final answer is not wrong, but we see the 3rd Human input is actually from the agent in the memory because the memory was modified by the summary tool."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"id": "32f97b21",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Human: What is ChatGPT?\n",
|
||||
"AI: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\n",
|
||||
"Human: Who developed it?\n",
|
||||
"AI: ChatGPT was developed by OpenAI.\n",
|
||||
"Human: My daughter 5 years old\n",
|
||||
"AI: \n",
|
||||
"The conversation was about ChatGPT, an artificial intelligence chatbot developed by OpenAI. It is designed to have conversations with humans and can also send and receive images.\n",
|
||||
"Human: Thanks. Summarize the conversation, for my daughter 5 years old.\n",
|
||||
"AI: ChatGPT is an artificial intelligence chatbot developed by OpenAI that can have conversations with humans and send and receive images.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(agent_chain.memory.buffer)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.9"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
@ -1,15 +1,6 @@
|
||||
How-To Guides
|
||||
=============
|
||||
|
||||
There are three types of examples in this section:
|
||||
|
||||
1. Agent Overview: how-to-guides for generic agent functionality
|
||||
2. Agent Toolkits: how-to-guides for specific agent toolkits (agents optimized for interacting with a certain resource)
|
||||
3. Agent Types: how-to-guides for working with the different agent types
|
||||
|
||||
Agent Overview
|
||||
---------------
|
||||
|
||||
The first category of how-to guides here cover specific parts of working with agents.
|
||||
|
||||
`Load From Hub <./examples/load_from_hub.html>`_: This notebook covers how to load agents from `LangChainHub <https://github.com/hwchase17/langchain-hub>`_.
|
||||
@ -30,48 +21,7 @@ The first category of how-to guides here cover specific parts of working with ag
|
||||
|
||||
`Asynchronous <./examples/async_agent.html>`_: Covering asynchronous functionality.
|
||||
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:glob:
|
||||
:hidden:
|
||||
|
||||
./examples/*
|
||||
|
||||
|
||||
Agent Toolkits
|
||||
---------------
|
||||
|
||||
The next set of examples covers agents with toolkits.
|
||||
As opposed to the examples above, these examples are not intended to show off an agent `type`,
|
||||
but rather to show off an agent applied to particular use case.
|
||||
|
||||
`SQLDatabase Agent <./agent_toolkits/sql_database.html>`_: This notebook covers how to interact with an arbitrary SQL database using an agent.
|
||||
|
||||
`JSON Agent <./agent_toolkits/json.html>`_: This notebook covers how to interact with a JSON dictionary using an agent.
|
||||
|
||||
`OpenAPI Agent <./agent_toolkits/openapi.html>`_: This notebook covers how to interact with an arbitrary OpenAPI endpoint using an agent.
|
||||
|
||||
`VectorStore Agent <./agent_toolkits/vectorstore.html>`_: This notebook covers how to interact with VectorStores using an agent.
|
||||
|
||||
`Python Agent <./agent_toolkits/python.html>`_: This notebook covers how to produce and execute python code using an agent.
|
||||
|
||||
`Pandas DataFrame Agent <./agent_toolkits/pandas.html>`_: This notebook covers how to do question answering over a pandas dataframe using an agent. Under the hood this calls the Python agent..
|
||||
|
||||
`CSV Agent <./agent_toolkits/csv.html>`_: This notebook covers how to do question answering over a csv file. Under the hood this calls the Pandas DataFrame agent.
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:glob:
|
||||
:hidden:
|
||||
|
||||
./agent_toolkits/*
|
||||
|
||||
|
||||
Agent Types
|
||||
---------------
|
||||
|
||||
The final set of examples are all end-to-end example of different agent types.
|
||||
The next set of examples are all end-to-end agents for specific applications.
|
||||
In all examples there is an Agent with a particular set of tools.
|
||||
|
||||
- Tools: A tool can be anything that takes in a string and returns a string. This means that you can use both the primitives AND the chains found in `this <../chains.html>`_ documentation. LangChain also provides a list of easily loadable tools. For detailed information on those, please see `this documentation <./tools.html>`_
|
||||
@ -101,13 +51,16 @@ In all examples there is an Agent with a particular set of tools.
|
||||
|
||||
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:glob:
|
||||
:hidden:
|
||||
|
||||
./examples/*
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:glob:
|
||||
:hidden:
|
||||
|
||||
./implementations/*
|
||||
|
||||
|
||||
./implementations/*
|
@ -1,253 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f1390152",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# MRKL Chat\n",
|
||||
"\n",
|
||||
"This notebook showcases using an agent to replicate the MRKL chain using an agent optimized for chat models."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "39ea3638",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"This uses the example Chinook database.\n",
|
||||
"To set it up follow the instructions on https://database.guide/2-sample-databases-sqlite/, placing the `.db` file in a notebooks folder at the root of this repository."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "ac561cc4",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain import OpenAI, LLMMathChain, SerpAPIWrapper, SQLDatabase, SQLDatabaseChain\n",
|
||||
"from langchain.agents import initialize_agent, Tool\n",
|
||||
"from langchain.chat_models import ChatOpenAI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "07e96d99",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm = ChatOpenAI(temperature=0)\n",
|
||||
"llm1 = OpenAI(temperature=0)\n",
|
||||
"search = SerpAPIWrapper()\n",
|
||||
"llm_math_chain = LLMMathChain(llm=llm1, verbose=True)\n",
|
||||
"db = SQLDatabase.from_uri(\"sqlite:///../../../../notebooks/Chinook.db\")\n",
|
||||
"db_chain = SQLDatabaseChain(llm=llm1, database=db, verbose=True)\n",
|
||||
"tools = [\n",
|
||||
" Tool(\n",
|
||||
" name = \"Search\",\n",
|
||||
" func=search.run,\n",
|
||||
" description=\"useful for when you need to answer questions about current events. You should ask targeted questions\"\n",
|
||||
" ),\n",
|
||||
" Tool(\n",
|
||||
" name=\"Calculator\",\n",
|
||||
" func=llm_math_chain.run,\n",
|
||||
" description=\"useful for when you need to answer questions about math\"\n",
|
||||
" ),\n",
|
||||
" Tool(\n",
|
||||
" name=\"FooBar DB\",\n",
|
||||
" func=db_chain.run,\n",
|
||||
" description=\"useful for when you need to answer questions about FooBar. Input should be in the form of a question containing full context\"\n",
|
||||
" )\n",
|
||||
"]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "a069c4b6",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"mrkl = initialize_agent(tools, llm, agent=\"chat-zero-shot-react-description\", verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "e603cd7d",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mThought: The first question requires a search, while the second question requires a calculator.\n",
|
||||
"Action:\n",
|
||||
"```\n",
|
||||
"{\n",
|
||||
" \"action\": \"Search\",\n",
|
||||
" \"action_input\": \"Who is Leo DiCaprio's girlfriend?\"\n",
|
||||
"}\n",
|
||||
"```\n",
|
||||
"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mCamila Morrone\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mFor the second question, I need to use the calculator tool to raise her current age to the 0.43 power.\n",
|
||||
"Action:\n",
|
||||
"```\n",
|
||||
"{\n",
|
||||
" \"action\": \"Calculator\",\n",
|
||||
" \"action_input\": \"22.0^(0.43)\"\n",
|
||||
"}\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
|
||||
"22.0^(0.43)\u001b[32;1m\u001b[1;3m\n",
|
||||
"```python\n",
|
||||
"import math\n",
|
||||
"print(math.pow(22.0, 0.43))\n",
|
||||
"```\n",
|
||||
"\u001b[0m\n",
|
||||
"Answer: \u001b[33;1m\u001b[1;3m3.777824273683966\n",
|
||||
"\u001b[0m\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||
"\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3mAnswer: 3.777824273683966\n",
|
||||
"\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mI now know the final answer.\n",
|
||||
"Final Answer: Camila Morrone, 3.777824273683966.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Camila Morrone, 3.777824273683966.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"mrkl.run(\"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "a5c07010",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mQuestion: What is the full name of the artist who recently released an album called 'The Storm Before the Calm' and are they in the FooBar database? If so, what albums of theirs are in the FooBar database?\n",
|
||||
"Thought: I should use the Search tool to find the answer to the first part of the question and then use the FooBar DB tool to find the answer to the second part of the question.\n",
|
||||
"Action:\n",
|
||||
"```\n",
|
||||
"{\n",
|
||||
" \"action\": \"Search\",\n",
|
||||
" \"action_input\": \"Who recently released an album called 'The Storm Before the Calm'\"\n",
|
||||
"}\n",
|
||||
"```\n",
|
||||
"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mAlanis Morissette\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mNow that I have the name of the artist, I can use the FooBar DB tool to find their albums in the database.\n",
|
||||
"Action:\n",
|
||||
"```\n",
|
||||
"{\n",
|
||||
" \"action\": \"FooBar DB\",\n",
|
||||
" \"action_input\": \"What albums does Alanis Morissette have in the database?\"\n",
|
||||
"}\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new SQLDatabaseChain chain...\u001b[0m\n",
|
||||
"What albums does Alanis Morissette have in the database? \n",
|
||||
"SQLQuery:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"/Users/harrisonchase/workplace/langchain/langchain/sql_database.py:141: SAWarning: Dialect sqlite+pysqlite does *not* support Decimal objects natively, and SQLAlchemy must convert from floating point - rounding errors and other issues may occur. Please consider storing Decimal numbers as strings or integers on this platform for lossless storage.\n",
|
||||
" sample_rows = connection.execute(command)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[32;1m\u001b[1;3m SELECT Title FROM Album WHERE ArtistId IN (SELECT ArtistId FROM Artist WHERE Name = 'Alanis Morissette') LIMIT 5;\u001b[0m\n",
|
||||
"SQLResult: \u001b[33;1m\u001b[1;3m[('Jagged Little Pill',)]\u001b[0m\n",
|
||||
"Answer:\u001b[32;1m\u001b[1;3m Alanis Morissette has the album 'Jagged Little Pill' in the database.\u001b[0m\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||
"\n",
|
||||
"Observation: \u001b[38;5;200m\u001b[1;3m Alanis Morissette has the album 'Jagged Little Pill' in the database.\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mI have found the answer to both parts of the question.\n",
|
||||
"Final Answer: The artist who recently released an album called 'The Storm Before the Calm' is Alanis Morissette. The album 'Jagged Little Pill' is in the FooBar database.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"The artist who recently released an album called 'The Storm Before the Calm' is Alanis Morissette. The album 'Jagged Little Pill' is in the FooBar database.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"mrkl.run(\"What is the full name of the artist who recently released an album called 'The Storm Before the Calm' and are they in the FooBar database? If so, what albums of theirs are in the FooBar database?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "af016a70",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
@ -24,13 +24,11 @@
|
||||
"tools = [\n",
|
||||
" Tool(\n",
|
||||
" name=\"Search\",\n",
|
||||
" func=docstore.search,\n",
|
||||
" description=\"useful for when you need to ask with search\"\n",
|
||||
" func=docstore.search\n",
|
||||
" ),\n",
|
||||
" Tool(\n",
|
||||
" name=\"Lookup\",\n",
|
||||
" func=docstore.lookup,\n",
|
||||
" description=\"useful for when you need to ask with lookup\"\n",
|
||||
" func=docstore.lookup\n",
|
||||
" )\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
@ -83,7 +81,7 @@
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"display_name": "Python 3.9.0 64-bit ('llm-env')",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
@ -97,7 +95,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
"version": "3.9.0"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
|
@ -52,8 +52,7 @@
|
||||
"tools = [\n",
|
||||
" Tool(\n",
|
||||
" name=\"Intermediate Answer\",\n",
|
||||
" func=search.run,\n",
|
||||
" description=\"useful for when you need to ask with search\"\n",
|
||||
" func=search.run\n",
|
||||
" )\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
@ -64,7 +63,7 @@
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"display_name": "Python 3.9.0 64-bit ('llm-env')",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
@ -78,7 +77,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.9"
|
||||
"version": "3.9.0"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
|
@ -8,9 +8,3 @@ For more detailed information on agents, and different types of agents in LangCh
|
||||
Tools are functions that agents can use to interact with the world.
|
||||
These tools can be generic utilities (e.g. search), other chains, or even other agents.
|
||||
For more detailed information on tools, and different types of tools in LangChain, see [this documentation](tools.md).
|
||||
|
||||
## ToolKits
|
||||
Toolkits are groups of tools that are best used together.
|
||||
They allow you to logically group and initialize a set of tools that share a particular resource (such as a database connection or json object).
|
||||
They can be used to construct an agent for a specific use-case.
|
||||
For more detailed information on toolkits and their use cases, see [this documentation](how_to_guides.rst#agent-toolkits) (the "Agent Toolkits" section).
|
@ -136,19 +136,3 @@ Below is a list of all supported tools and relevant information:
|
||||
- Requires LLM: No
|
||||
- Extra Parameters: `serper_api_key`
|
||||
- For more information on this, see [this page](../../ecosystem/google_serper.md)
|
||||
|
||||
**wikipedia**
|
||||
|
||||
- Tool Name: Wikipedia
|
||||
- Tool Description: A wrapper around Wikipedia. Useful for when you need to answer general questions about people, places, companies, historical events, or other subjects. Input should be a search query.
|
||||
- Notes: Uses the [wikipedia](https://pypi.org/project/wikipedia/) Python package to call the MediaWiki API and then parses results.
|
||||
- Requires LLM: No
|
||||
- Extra Parameters: `top_k_results`
|
||||
|
||||
**podcast-api**
|
||||
|
||||
- Tool Name: Podcast API
|
||||
- Tool Description: Use the Listen Notes Podcast API to search all podcasts or episodes. The input should be a question in natural language that this API can answer.
|
||||
- Notes: A natural language connection to the Listen Notes Podcast API (`https://www.PodcastAPI.com`), specifically the `/search/` endpoint.
|
||||
- Requires LLM: Yes
|
||||
- Extra Parameters: `listen_api_key` (your api key to access this endpoint)
|
||||
|
@ -39,7 +39,7 @@
|
||||
"\n",
|
||||
"\n",
|
||||
"SparkleSmile Toothpaste\n",
|
||||
"\u001B[1mConcurrent executed in 1.54 seconds.\u001B[0m\n",
|
||||
"\u001b[1mConcurrent executed in 1.54 seconds.\u001b[0m\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"BrightSmile Toothpaste Co.\n",
|
||||
@ -55,7 +55,7 @@
|
||||
"\n",
|
||||
"\n",
|
||||
"BrightSmile Toothpaste.\n",
|
||||
"\u001B[1mSerial executed in 6.38 seconds.\u001B[0m\n"
|
||||
"\u001b[1mSerial executed in 6.38 seconds.\u001b[0m\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
@ -149,33 +149,6 @@
|
||||
"chain.run(\"Search for 'Avatar'\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Listen API Example"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"from langchain.llms import OpenAI\n",
|
||||
"from langchain.chains.api import podcast_docs\n",
|
||||
"from langchain.chains import APIChain\n",
|
||||
"\n",
|
||||
"# Get api key here: https://www.listennotes.com/api/pricing/\n",
|
||||
"listen_api_key = 'xxx'\n",
|
||||
"\n",
|
||||
"llm = OpenAI(temperature=0)\n",
|
||||
"headers = {\"X-ListenAPI-Key\": listen_api_key}\n",
|
||||
"chain = APIChain.from_llm_and_api_docs(llm, podcast_docs.PODCAST_DOCS, headers=headers, verbose=True)\n",
|
||||
"chain.run(\"Search for 'silicon valley bank' podcast episodes, audio length is more than 30 minutes, return only 1 results\")\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
@ -200,7 +173,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
"version": "3.10.9"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
File diff suppressed because it is too large
Load Diff
@ -71,17 +71,17 @@
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001B[1m> Entering new PALChain chain...\u001B[0m\n",
|
||||
"\u001B[32;1m\u001B[1;3mdef solution():\n",
|
||||
"\u001b[1m> Entering new PALChain chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mdef solution():\n",
|
||||
" \"\"\"Jan has three times the number of pets as Marcia. Marcia has two more pets than Cindy. If Cindy has four pets, how many total pets do the three have?\"\"\"\n",
|
||||
" cindy_pets = 4\n",
|
||||
" marcia_pets = cindy_pets + 2\n",
|
||||
" jan_pets = marcia_pets * 3\n",
|
||||
" total_pets = cindy_pets + marcia_pets + jan_pets\n",
|
||||
" result = total_pets\n",
|
||||
" return result\u001B[0m\n",
|
||||
" return result\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001B[1m> Finished chain.\u001B[0m\n"
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -139,8 +139,8 @@
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001B[1m> Entering new PALChain chain...\u001B[0m\n",
|
||||
"\u001B[32;1m\u001B[1;3m# Put objects into a list to record ordering\n",
|
||||
"\u001b[1m> Entering new PALChain chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m# Put objects into a list to record ordering\n",
|
||||
"objects = []\n",
|
||||
"objects += [('booklet', 'blue')] * 2\n",
|
||||
"objects += [('booklet', 'purple')] * 2\n",
|
||||
@ -151,9 +151,9 @@
|
||||
"\n",
|
||||
"# Count number of purple objects\n",
|
||||
"num_purple = len([object for object in objects if object[1] == 'purple'])\n",
|
||||
"answer = num_purple\u001B[0m\n",
|
||||
"answer = num_purple\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001B[1m> Finished PALChain chain.\u001B[0m\n"
|
||||
"\u001b[1m> Finished PALChain chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -212,8 +212,8 @@
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001B[1m> Entering new PALChain chain...\u001B[0m\n",
|
||||
"\u001B[32;1m\u001B[1;3m# Put objects into a list to record ordering\n",
|
||||
"\u001b[1m> Entering new PALChain chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m# Put objects into a list to record ordering\n",
|
||||
"objects = []\n",
|
||||
"objects += [('booklet', 'blue')] * 2\n",
|
||||
"objects += [('booklet', 'purple')] * 2\n",
|
||||
@ -224,9 +224,9 @@
|
||||
"\n",
|
||||
"# Count number of purple objects\n",
|
||||
"num_purple = len([object for object in objects if object[1] == 'purple'])\n",
|
||||
"answer = num_purple\u001B[0m\n",
|
||||
"answer = num_purple\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001B[1m> Finished chain.\u001B[0m\n"
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
@ -377,20 +377,11 @@
|
||||
"\tFOREIGN KEY(\"GenreId\") REFERENCES \"Genre\" (\"GenreId\"), \n",
|
||||
"\tFOREIGN KEY(\"AlbumId\") REFERENCES \"Album\" (\"AlbumId\")\n",
|
||||
")\n",
|
||||
"/*\n",
|
||||
"2 rows from Track table:\n",
|
||||
"TrackId\tName\tAlbumId\tMediaTypeId\tGenreId\tComposer\tMilliseconds\tBytes\tUnitPrice\n",
|
||||
"1\tFor Those About To Rock (We Salute You)\t1\t1\t1\tAngus Young, Malcolm Young, Brian Johnson\t343719\t11170334\t0.99\n",
|
||||
"2\tBalls to the Wall\t2\t2\t1\tNone\t342562\t5510424\t0.99\n",
|
||||
"*/\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"/home/jon/projects/langchain/langchain/sql_database.py:135: SAWarning: Dialect sqlite+pysqlite does *not* support Decimal objects natively, and SQLAlchemy must convert from floating point - rounding errors and other issues may occur. Please consider storing Decimal numbers as strings or integers on this platform for lossless storage.\n",
|
||||
" sample_rows = connection.execute(command)\n"
|
||||
"\n",
|
||||
"SELECT * FROM 'Track' LIMIT 2;\n",
|
||||
"TrackId Name AlbumId MediaTypeId GenreId Composer Milliseconds Bytes UnitPrice\n",
|
||||
"1 For Those About To Rock (We Salute You) 1 1 1 Angus Young, Malcolm Young, Brian Johnson 343719 11170334 0.99\n",
|
||||
"2 Balls to the Wall 2 2 1 None 342562 5510424 0.99\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@ -443,134 +434,6 @@
|
||||
"db_chain.run(\"What are some example tracks by Bach?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "ef94e948",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Custom Table Info\n",
|
||||
"In some cases, it can be useful to provide custom table information instead of using the automatically generated table definitions and the first `sample_rows_in_table_info` sample rows. For example, if you know that the first few rows of a table are uninformative, it could help to manually provide example rows that are more diverse or provide more information to the model. It is also possible to limit the columns that will be visible to the model if there are unnecessary columns. \n",
|
||||
"\n",
|
||||
"This information can be provided as a dictionary with table names as the keys and table information as the values. For example, let's provide a custom definition and sample rows for the Track table with only a few columns:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 16,
|
||||
"id": "2ad33ab1",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"custom_table_info = {\n",
|
||||
" \"Track\": \"\"\"CREATE TABLE Track (\n",
|
||||
"\t\"TrackId\" INTEGER NOT NULL, \n",
|
||||
"\t\"Name\" NVARCHAR(200) NOT NULL,\n",
|
||||
"\t\"Composer\" NVARCHAR(220),\n",
|
||||
"\tPRIMARY KEY (\"TrackId\")\n",
|
||||
")\n",
|
||||
"/*\n",
|
||||
"3 rows from Track table:\n",
|
||||
"TrackId\tName\tComposer\n",
|
||||
"1\tFor Those About To Rock (We Salute You)\tAngus Young, Malcolm Young, Brian Johnson\n",
|
||||
"2\tBalls to the Wall\tNone\n",
|
||||
"3\tMy favorite song ever\tThe coolest composer of all time\n",
|
||||
"*/\"\"\"\n",
|
||||
"}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 17,
|
||||
"id": "db144352",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"CREATE TABLE \"Playlist\" (\n",
|
||||
"\t\"PlaylistId\" INTEGER NOT NULL, \n",
|
||||
"\t\"Name\" NVARCHAR(120), \n",
|
||||
"\tPRIMARY KEY (\"PlaylistId\")\n",
|
||||
")\n",
|
||||
"/*\n",
|
||||
"2 rows from Playlist table:\n",
|
||||
"PlaylistId\tName\n",
|
||||
"1\tMusic\n",
|
||||
"2\tMovies\n",
|
||||
"*/\n",
|
||||
"\n",
|
||||
"CREATE TABLE Track (\n",
|
||||
"\t\"TrackId\" INTEGER NOT NULL, \n",
|
||||
"\t\"Name\" NVARCHAR(200) NOT NULL,\n",
|
||||
"\t\"Composer\" NVARCHAR(220),\n",
|
||||
"\tPRIMARY KEY (\"TrackId\")\n",
|
||||
")\n",
|
||||
"/*\n",
|
||||
"3 rows from Track table:\n",
|
||||
"TrackId\tName\tComposer\n",
|
||||
"1\tFor Those About To Rock (We Salute You)\tAngus Young, Malcolm Young, Brian Johnson\n",
|
||||
"2\tBalls to the Wall\tNone\n",
|
||||
"3\tMy favorite song ever\tThe coolest composer of all time\n",
|
||||
"*/\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"db = SQLDatabase.from_uri(\n",
|
||||
" \"sqlite:///../../../../notebooks/Chinook.db\",\n",
|
||||
" include_tables=['Track', 'Playlist'],\n",
|
||||
" sample_rows_in_table_info=2,\n",
|
||||
" custom_table_info=custom_table_info)\n",
|
||||
"\n",
|
||||
"print(db.table_info)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5fc6f507",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Note how our custom table definition and sample rows for `Track` overrides the `sample_rows_in_table_info` parameter. Tables that are not overridden by `custom_table_info`, in this example `Playlist`, will have their table info gathered automatically as usual."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 18,
|
||||
"id": "dfbda4e6",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new SQLDatabaseChain chain...\u001b[0m\n",
|
||||
"What are some example tracks by Bach? \n",
|
||||
"SQLQuery:\u001b[32;1m\u001b[1;3m SELECT Name, Composer FROM Track WHERE Composer LIKE '%Bach%' LIMIT 5;\u001b[0m\n",
|
||||
"SQLResult: \u001b[33;1m\u001b[1;3m[('American Woman', 'B. Cummings/G. Peterson/M.J. Kale/R. Bachman'), ('Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace', 'Johann Sebastian Bach'), ('Aria Mit 30 Veränderungen, BWV 988 \"Goldberg Variations\": Aria', 'Johann Sebastian Bach'), ('Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude', 'Johann Sebastian Bach'), ('Toccata and Fugue in D Minor, BWV 565: I. Toccata', 'Johann Sebastian Bach')]\u001b[0m\n",
|
||||
"Answer:\u001b[32;1m\u001b[1;3m Some example tracks by Bach are 'American Woman', 'Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace', 'Aria Mit 30 Veränderungen, BWV 988 \"Goldberg Variations\": Aria', 'Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude', and 'Toccata and Fugue in D Minor, BWV 565: I. Toccata'.\u001b[0m\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"' Some example tracks by Bach are \\'American Woman\\', \\'Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace\\', \\'Aria Mit 30 Veränderungen, BWV 988 \"Goldberg Variations\": Aria\\', \\'Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude\\', and \\'Toccata and Fugue in D Minor, BWV 565: I. Toccata\\'.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 18,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"db_chain = SQLDatabaseChain(llm=llm, database=db, verbose=True)\n",
|
||||
"db_chain.run(\"What are some example tracks by Bach?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "c12ae15a",
|
||||
|
@ -34,10 +34,10 @@
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001B[1m> Entering new LLMMathChain chain...\u001B[0m\n",
|
||||
"whats 2 raised to .12\u001B[32;1m\u001B[1;3m\n",
|
||||
"Answer: 1.0791812460476249\u001B[0m\n",
|
||||
"\u001B[1m> Finished chain.\u001B[0m\n"
|
||||
"\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
|
||||
"whats 2 raised to .12\u001b[32;1m\u001b[1;3m\n",
|
||||
"Answer: 1.0791812460476249\u001b[0m\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
@ -42,13 +42,13 @@
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
|
||||
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
|
||||
"Prompt after formatting:\n",
|
||||
"\u001B[32;1m\u001B[1;3mQuestion: What NFL team won the Super Bowl in the year Justin Beiber was born?\n",
|
||||
"\u001b[32;1m\u001b[1;3mQuestion: What NFL team won the Super Bowl in the year Justin Beiber was born?\n",
|
||||
"\n",
|
||||
"Answer: Let's think step by step.\u001B[0m\n",
|
||||
"Answer: Let's think step by step.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n"
|
||||
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -95,11 +95,11 @@
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
|
||||
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
|
||||
"Prompt after formatting:\n",
|
||||
"\u001B[32;1m\u001B[1;3mWrite a sad poem about ducks.\u001B[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mWrite a sad poem about ducks.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n"
|
||||
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
@ -36,25 +36,6 @@
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "7a886879",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"cannot find .env file\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"%load_ext dotenv\n",
|
||||
"%dotenv"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "3f2f9b8c",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -66,7 +47,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": 2,
|
||||
"id": "b8237d1a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -83,7 +64,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": 3,
|
||||
"id": "4a391730",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -101,7 +82,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"execution_count": 4,
|
||||
"id": "9368bd63",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -113,7 +94,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"execution_count": 5,
|
||||
"id": "d39e15f5",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@ -126,20 +107,22 @@
|
||||
"\u001b[1m> Entering new SimpleSequentialChain chain...\u001b[0m\n",
|
||||
"\u001b[36;1m\u001b[1;3m\n",
|
||||
"\n",
|
||||
"Tragedy at Sunset on the Beach is a story of a young couple, Jack and Sarah, who are in love and looking forward to their future together. On the night of their anniversary, they decide to take a walk on the beach at sunset. As they are walking, they come across a mysterious figure, who tells them that their love will be tested in the near future. \n",
|
||||
"Tragedy at Sunset on the Beach follows the story of a young couple, Jack and Annie, who have just started to explore the possibility of a relationship together. After a day spent in the sun and sand, they decide to take a romantic stroll down the beach as the sun sets. \n",
|
||||
"\n",
|
||||
"The figure then tells the couple that the sun will soon set, and with it, a tragedy will strike. If Jack and Sarah can stay together and pass the test, they will be granted everlasting love. However, if they fail, their love will be lost forever.\n",
|
||||
"However, their romantic evening quickly turns tragic when they stumble upon a body lying in the sand. As they approach to investigate, they are shocked to discover that it is Jack's long-lost brother, who has been missing for several years. \n",
|
||||
"\n",
|
||||
"The play follows the couple as they struggle to stay together and battle the forces that threaten to tear them apart. Despite the tragedy that awaits them, they remain devoted to one another and fight to keep their love alive. In the end, the couple must decide whether to take a chance on their future together or succumb to the tragedy of the sunset.\u001b[0m\n",
|
||||
"The story follows Jack and Annie as they navigate their way through the tragedy and their newfound relationship. With the help of their friends, family, and the beach's inhabitants, Jack and Annie must come to terms with their deep-seated emotions and the reality of the situation. \n",
|
||||
"\n",
|
||||
"Ultimately, the play explores themes of family, love, and loss, as Jack and Annie's story unfolds against the beautiful backdrop of the beach at sunset.\u001b[0m\n",
|
||||
"\u001b[33;1m\u001b[1;3m\n",
|
||||
"\n",
|
||||
"Tragedy at Sunset on the Beach is an emotionally gripping story of love, hope, and sacrifice. Through the story of Jack and Sarah, the audience is taken on a journey of self-discovery and the power of love to overcome even the greatest of obstacles. \n",
|
||||
"Tragedy at Sunset on the Beach is an emotionally complex tale of family, love, and loss. Told against the beautiful backdrop of a beach at sunset, the story follows Jack and Annie, a young couple just beginning to explore a relationship together. When they stumble upon the body of Jack's long-lost brother on the beach, they must face the reality of the tragedy and come to terms with their deep-seated emotions. \n",
|
||||
"\n",
|
||||
"The play's talented cast brings the characters to life, allowing us to feel the depths of their emotion and the intensity of their struggle. With its compelling story and captivating performances, this play is sure to draw in audiences and leave them on the edge of their seats. \n",
|
||||
"The playwright has crafted a heartfelt and thought-provoking story, one that probes into the depths of the human experience. The cast of characters is well-rounded and fully realized, and the dialogue is natural and emotional. The direction and choreography are top-notch, and the scenic design is breathtaking. \n",
|
||||
"\n",
|
||||
"The play's setting of the beach at sunset adds a touch of poignancy and romanticism to the story, while the mysterious figure serves to keep the audience enthralled. Overall, Tragedy at Sunset on the Beach is an engaging and thought-provoking play that is sure to leave audiences feeling inspired and hopeful.\u001b[0m\n",
|
||||
"Overall, Tragedy at Sunset on the Beach is a powerful and moving story about the fragility of life and the strength of love. It is sure to tug at your heartstrings and leave you with a newfound appreciation of life's precious moments. Highly recommended.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
"\u001b[1m> Finished SimpleSequentialChain chain.\u001b[0m\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@ -149,7 +132,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"execution_count": 6,
|
||||
"id": "c6649a01",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@ -159,11 +142,11 @@
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"Tragedy at Sunset on the Beach is an emotionally gripping story of love, hope, and sacrifice. Through the story of Jack and Sarah, the audience is taken on a journey of self-discovery and the power of love to overcome even the greatest of obstacles. \n",
|
||||
"Tragedy at Sunset on the Beach is an emotionally complex tale of family, love, and loss. Told against the beautiful backdrop of a beach at sunset, the story follows Jack and Annie, a young couple just beginning to explore a relationship together. When they stumble upon the body of Jack's long-lost brother on the beach, they must face the reality of the tragedy and come to terms with their deep-seated emotions. \n",
|
||||
"\n",
|
||||
"The play's talented cast brings the characters to life, allowing us to feel the depths of their emotion and the intensity of their struggle. With its compelling story and captivating performances, this play is sure to draw in audiences and leave them on the edge of their seats. \n",
|
||||
"The playwright has crafted a heartfelt and thought-provoking story, one that probes into the depths of the human experience. The cast of characters is well-rounded and fully realized, and the dialogue is natural and emotional. The direction and choreography are top-notch, and the scenic design is breathtaking. \n",
|
||||
"\n",
|
||||
"The play's setting of the beach at sunset adds a touch of poignancy and romanticism to the story, while the mysterious figure serves to keep the audience enthralled. Overall, Tragedy at Sunset on the Beach is an engaging and thought-provoking play that is sure to leave audiences feeling inspired and hopeful.\n"
|
||||
"Overall, Tragedy at Sunset on the Beach is a powerful and moving story about the fragility of life and the strength of love. It is sure to tug at your heartstrings and leave you with a newfound appreciation of life's precious moments. Highly recommended.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@ -184,7 +167,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"execution_count": 7,
|
||||
"id": "02016a51",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -202,7 +185,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"execution_count": 8,
|
||||
"id": "8bd38cc2",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -220,7 +203,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"execution_count": 9,
|
||||
"id": "524523af",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -237,7 +220,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"execution_count": 10,
|
||||
"id": "3fd3a7be",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@ -248,8 +231,14 @@
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new SequentialChain chain...\u001b[0m\n",
|
||||
"\u001b[1mChain 0\u001b[0m:\n",
|
||||
"{'synopsis': \" \\n\\nTragedy at Sunset on the Beach is a dark and gripping drama set in Victorian England. The play follows the story of two lovers, Emma and Edward, whose passionate relationship is threatened by the strict rules and regulations of the time.\\n\\nThe two are deeply in love, but Edward is from a wealthy family and Emma is from a lower class background. Despite the obstacles, the two are determined to be together and decide to elope.\\n\\nOn the night of their planned escape, Emma and Edward meet at the beach at sunset to declare their love for one another and begin a new life together. However, their plans are disrupted when Emma's father discovers their plan and appears on the beach with a gun.\\n\\nIn a heartbreaking scene, Emma's father orders Edward to leave, but Edward refuses and fights for their love. In a fit of rage, Emma's father shoots Edward, killing him instantly. \\n\\nThe tragedy of the play lies in the fact that Emma and Edward are denied their chance at a happy ending due to the rigid social conventions of Victorian England. The audience is left with a heavy heart as the play ends with Emma standing alone on the beach, mourning the loss of her beloved.\"}\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
"\u001b[1mChain 1\u001b[0m:\n",
|
||||
"{'review': \"\\n\\nTragedy at Sunset on the Beach is an emotionally charged production that will leave audiences heartsick. The play follows the ill-fated love story of Emma and Edward, two star-crossed lovers whose passionate relationship is tragically thwarted by Victorian England's societal conventions. The performance is captivating from start to finish, as the audience is taken on an emotional rollercoaster of love, loss, and heartbreak.\\n\\nThe acting is powerful and sincere, and the performances of the two leads are particularly stirring. Emma and Edward are both portrayed with such tenderness and emotion that it's hard not to feel their pain as they fight for their forbidden love. The climactic scene, in which Edward is shot by Emma's father, is especially heartbreaking and will leave audience members on the edge of their seats.\\n\\nOverall, Tragedy at Sunset on the Beach is a powerful and moving work of theatre. It is a tragedy of impossible love, and a vivid reminder of the devastating consequences of social injustice. The play is sure to leave a lasting impression on anyone who experiences it.\"}\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished SequentialChain chain.\u001b[0m\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@ -257,91 +246,10 @@
|
||||
"review = overall_chain({\"title\":\"Tragedy at sunset on the beach\", \"era\": \"Victorian England\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "d2fac817",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Memory in Sequential Chains\n",
|
||||
"Sometimes you may want to pass along some context to use in each step of the chain or in a later part of the chain, but maintaining and chaining together the input/output variables can quickly get messy. Using `SimpleMemory` is a convenient way to do manage this and clean up your chains.\n",
|
||||
"\n",
|
||||
"For example, using the previous playwright SequentialChain, lets say you wanted to include some context about date, time and location of the play, and using the generated synopsis and review, create some social media post text. You could add these new context variables as `input_variables`, or we can add a `SimpleMemory` to the chain to manage this context:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "b2cf3098",
|
||||
"metadata": {},
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"id": "6b7b3a7a",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new SequentialChain chain...\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'title': 'Tragedy at sunset on the beach',\n",
|
||||
" 'era': 'Victorian England',\n",
|
||||
" 'time': 'December 25th, 8pm PST',\n",
|
||||
" 'location': 'Theater in the Park',\n",
|
||||
" 'social_post_text': \"\\nSpend your Christmas night with us at Theater in the Park and experience the heartbreaking story of love and loss that is 'A Walk on the Beach'. Set in Victorian England, this romantic tragedy follows the story of Frances and Edward, a young couple whose love is tragically cut short. Don't miss this emotional and thought-provoking production that is sure to leave you in tears. #AWalkOnTheBeach #LoveAndLoss #TheaterInThePark #VictorianEngland\"}"
|
||||
]
|
||||
},
|
||||
"execution_count": 12,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain.chains import SequentialChain\n",
|
||||
"from langchain.memory import SimpleMemory\n",
|
||||
"\n",
|
||||
"llm = OpenAI(temperature=.7)\n",
|
||||
"template = \"\"\"You are a social media manager for a theater company. Given the title of play, the era it is set in, the date,time and location, the synopsis of the play, and the review of the play, it is your job to write a social media post for that play.\n",
|
||||
"\n",
|
||||
"Here is some context about the time and location of the play:\n",
|
||||
"Date and Time: {time}\n",
|
||||
"Location: {location}\n",
|
||||
"\n",
|
||||
"Play Synopsis:\n",
|
||||
"{synopsis}\n",
|
||||
"Review from a New York Times play critic of the above play:\n",
|
||||
"{review}\n",
|
||||
"\n",
|
||||
"Social Media Post:\n",
|
||||
"\"\"\"\n",
|
||||
"prompt_template = PromptTemplate(input_variables=[\"synopsis\", \"review\", \"time\", \"location\"], template=template)\n",
|
||||
"social_chain = LLMChain(llm=llm, prompt=prompt_template, output_key=\"social_post_text\")\n",
|
||||
"\n",
|
||||
"overall_chain = SequentialChain(\n",
|
||||
" memory=SimpleMemory(memories={\"time\": \"December 25th, 8pm PST\", \"location\": \"Theater in the Park\"}),\n",
|
||||
" chains=[synopsis_chain, review_chain, social_chain],\n",
|
||||
" input_variables=[\"era\", \"title\"],\n",
|
||||
" # Here we return multiple variables\n",
|
||||
" output_variables=[\"social_post_text\"],\n",
|
||||
" verbose=True)\n",
|
||||
"\n",
|
||||
"overall_chain({\"title\":\"Tragedy at sunset on the beach\", \"era\": \"Victorian England\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "ee9bc09c",
|
||||
"id": "6be70d27",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
@ -363,7 +271,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
"version": "3.10.9"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
@ -136,13 +136,13 @@
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
|
||||
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
|
||||
"Prompt after formatting:\n",
|
||||
"\u001B[32;1m\u001B[1;3mQuestion: whats 2 + 2\n",
|
||||
"\u001b[32;1m\u001b[1;3mQuestion: whats 2 + 2\n",
|
||||
"\n",
|
||||
"Answer: Let's think step by step.\u001B[0m\n",
|
||||
"Answer: Let's think step by step.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001B[1m> Finished chain.\u001B[0m\n"
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -319,13 +319,13 @@
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
|
||||
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
|
||||
"Prompt after formatting:\n",
|
||||
"\u001B[32;1m\u001B[1;3mQuestion: whats 2 + 2\n",
|
||||
"\u001b[32;1m\u001b[1;3mQuestion: whats 2 + 2\n",
|
||||
"\n",
|
||||
"Answer: Let's think step by step.\u001B[0m\n",
|
||||
"Answer: Let's think step by step.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001B[1m> Finished chain.\u001B[0m\n"
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
@ -32,9 +32,7 @@
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.prompts import PromptTemplate\n",
|
||||
@ -57,9 +55,7 @@
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
@ -67,7 +63,7 @@
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"Rainbow Socks Co.\n"
|
||||
"Vibrancy Socks.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@ -79,48 +75,6 @@
|
||||
"print(chain.run(\"colorful socks\"))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You can use a chat model in an `LLMChain` as well:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"Rainbow Threads\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.prompts.chat import (\n",
|
||||
" ChatPromptTemplate,\n",
|
||||
" HumanMessagePromptTemplate,\n",
|
||||
")\n",
|
||||
"human_message_prompt = HumanMessagePromptTemplate(\n",
|
||||
" prompt=PromptTemplate(\n",
|
||||
" template=\"What is a good name for a company that makes {product}?\",\n",
|
||||
" input_variables=[\"product\"],\n",
|
||||
" )\n",
|
||||
" )\n",
|
||||
"chat_prompt_template = ChatPromptTemplate.from_messages([human_message_prompt])\n",
|
||||
"chat = ChatOpenAI(temperature=0.9)\n",
|
||||
"chain = LLMChain(llm=chat, prompt=chat_prompt_template)\n",
|
||||
"print(chain.run(\"colorful socks\"))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
@ -320,5 +274,5 @@
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
|
@ -9,12 +9,3 @@ This is a specific type of chain where multiple other chains are run in sequence
|
||||
to the next. A subtype of this type of chain is the [`SimpleSequentialChain`](./generic/sequential_chains.html#simplesequentialchain), where all subchains have only one input and one output,
|
||||
and the output of one is therefore used as sole input to the next chain.
|
||||
|
||||
## Prompt Selectors
|
||||
One thing that we've noticed is that the best prompt to use is really dependent on the model you use.
|
||||
Some prompts work really good with some models, but not great with others.
|
||||
One of our goals is provide good chains that "just work" out of the box.
|
||||
A big part of chains like that is having prompts that "just work".
|
||||
So rather than having a default prompt for chains, we are moving towards a paradigm where if a prompt is not explicitly
|
||||
provided we select one with a PromptSelector. This class takes in the model passed in, and returns a default prompt.
|
||||
The inner workings of the PromptSelector can look at any aspect of the model - LLM vs ChatModel, OpenAI vs Cohere, GPT3 vs GPT4, etc.
|
||||
Due to this being a newer feature, this may not be implemented for all chains, but this is the direction we are moving.
|
||||
|
@ -1,26 +0,0 @@
|
||||
Chat
|
||||
==========================
|
||||
|
||||
Chat models are a variation on language models.
|
||||
While chat models use language models under the hood, the interface they expose is a bit different.
|
||||
Rather than expose a "text in, text out" API, they expose an interface where "chat messages" are the inputs and outputs.
|
||||
|
||||
Chat model APIs are fairly new, so we are still figuring out the correct abstractions.
|
||||
|
||||
The following sections of documentation are provided:
|
||||
|
||||
- `Getting Started <./chat/getting_started.html>`_: An overview of the basics of chat models.
|
||||
|
||||
- `Key Concepts <./chat/key_concepts.html>`_: A conceptual guide going over the various concepts related to chat models.
|
||||
|
||||
- `How-To Guides <./chat/how_to_guides.html>`_: A collection of how-to guides. These highlight how to accomplish various objectives with our chat model class, as well as how to integrate with various chat model providers.
|
||||
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:name: LLMs
|
||||
:hidden:
|
||||
|
||||
./chat/getting_started.ipynb
|
||||
./chat/key_concepts.md
|
||||
./chat/how_to_guides.rst
|
@ -1,208 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "e58f4d5a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Agent\n",
|
||||
"This notebook covers how to create a custom agent for a chat model. It will utilize chat specific prompts."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "5268c7fa",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import ZeroShotAgent, Tool, AgentExecutor\n",
|
||||
"from langchain.chains import LLMChain\n",
|
||||
"from langchain.utilities import SerpAPIWrapper"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "fbaa4dbe",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"search = SerpAPIWrapper()\n",
|
||||
"tools = [\n",
|
||||
" Tool(\n",
|
||||
" name = \"Search\",\n",
|
||||
" func=search.run,\n",
|
||||
" description=\"useful for when you need to answer questions about current events\"\n",
|
||||
" )\n",
|
||||
"]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "f3ba6f08",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"prefix = \"\"\"Answer the following questions as best you can, but speaking as a pirate might speak. You have access to the following tools:\"\"\"\n",
|
||||
"suffix = \"\"\"Begin! Remember to speak as a pirate when giving your final answer. Use lots of \"Args\"\"\"\n",
|
||||
"\n",
|
||||
"prompt = ZeroShotAgent.create_prompt(\n",
|
||||
" tools, \n",
|
||||
" prefix=prefix, \n",
|
||||
" suffix=suffix, \n",
|
||||
" input_variables=[]\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "3547a37d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.prompts.chat import (\n",
|
||||
" ChatPromptTemplate,\n",
|
||||
" SystemMessagePromptTemplate,\n",
|
||||
" AIMessagePromptTemplate,\n",
|
||||
" HumanMessagePromptTemplate,\n",
|
||||
")\n",
|
||||
"from langchain.schema import (\n",
|
||||
" AIMessage,\n",
|
||||
" HumanMessage,\n",
|
||||
" SystemMessage\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "a78f886f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"messages = [\n",
|
||||
" SystemMessagePromptTemplate(prompt=prompt),\n",
|
||||
" HumanMessagePromptTemplate.from_template(\"{input}\\n\\nThis was your previous work \"\n",
|
||||
" f\"(but I haven't seen any of it! I only see what \"\n",
|
||||
" \"you return as final answer):\\n{agent_scratchpad}\")\n",
|
||||
"]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "dadadd70",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"prompt = ChatPromptTemplate.from_messages(messages)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "b7180182",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm_chain = LLMChain(llm=ChatOpenAI(temperature=0), prompt=prompt)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "ddddb07b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tool_names = [tool.name for tool in tools]\n",
|
||||
"agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"id": "36aef054",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent_executor = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"id": "33a4d6cc",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mArrr, ye be in luck, matey! I'll find ye the answer to yer question.\n",
|
||||
"\n",
|
||||
"Thought: I need to search for the current population of Canada.\n",
|
||||
"Action: Search\n",
|
||||
"Action Input: \"current population of Canada 2023\"\n",
|
||||
"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mThe current population of Canada is 38,623,091 as of Saturday, March 4, 2023, based on Worldometer elaboration of the latest United Nations data.\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mAhoy, me hearties! I've found the answer to yer question.\n",
|
||||
"\n",
|
||||
"Final Answer: As of March 4, 2023, the population of Canada be 38,623,091. Arrr!\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'As of March 4, 2023, the population of Canada be 38,623,091. Arrr!'"
|
||||
]
|
||||
},
|
||||
"execution_count": 13,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_executor.run(\"How many people live in canada as of 2023?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "6aefe978",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
@ -1,376 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "134a0785",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Chat Vector DB\n",
|
||||
"\n",
|
||||
"This notebook goes over how to set up a chat model to chat with a vector database.\n",
|
||||
"\n",
|
||||
"This notebook is very similar to the example of using an LLM in the ConversationalRetrievalChain. The only differences here are (1) using a ChatModel, and (2) passing in a ChatPromptTemplate (optimized for chat models)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "70c4e529",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
|
||||
"from langchain.vectorstores import Chroma\n",
|
||||
"from langchain.text_splitter import CharacterTextSplitter\n",
|
||||
"from langchain.chains import ConversationalRetrievalChain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "cdff94be",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Load in documents. You can replace this with a loader for whatever type of data you want"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "01c46e92",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.document_loaders import TextLoader\n",
|
||||
"loader = TextLoader('../../state_of_the_union.txt')\n",
|
||||
"documents = loader.load()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "e9be4779",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"If you had multiple loaders that you wanted to combine, you do something like:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "433363a5",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# loaders = [....]\n",
|
||||
"# docs = []\n",
|
||||
"# for loader in loaders:\n",
|
||||
"# docs.extend(loader.load())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "239475d2",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We now split the documents, create embeddings for them, and put them in a vectorstore. This allows us to do semantic search over them."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "a8930cf7",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Running Chroma using direct local API.\n",
|
||||
"Using DuckDB in-memory for database. Data will be transient.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
|
||||
"documents = text_splitter.split_documents(documents)\n",
|
||||
"\n",
|
||||
"embeddings = OpenAIEmbeddings()\n",
|
||||
"vectorstore = Chroma.from_documents(documents, embeddings)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "18415aca",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We are now going to construct a prompt specifically designed for chat models."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "c8805230",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.prompts.chat import (\n",
|
||||
" ChatPromptTemplate,\n",
|
||||
" SystemMessagePromptTemplate,\n",
|
||||
" AIMessagePromptTemplate,\n",
|
||||
" HumanMessagePromptTemplate,\n",
|
||||
")\n",
|
||||
"from langchain.schema import (\n",
|
||||
" AIMessage,\n",
|
||||
" HumanMessage,\n",
|
||||
" SystemMessage\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "cc86c30e",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"system_template=\"\"\"Use the following pieces of context to answer the users question. \n",
|
||||
"If you don't know the answer, just say that you don't know, don't try to make up an answer.\n",
|
||||
"----------------\n",
|
||||
"{context}\"\"\"\n",
|
||||
"messages = [\n",
|
||||
" SystemMessagePromptTemplate.from_template(system_template),\n",
|
||||
" HumanMessagePromptTemplate.from_template(\"{question}\")\n",
|
||||
"]\n",
|
||||
"prompt = ChatPromptTemplate.from_messages(messages)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "3c96b118",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We now initialize the ConversationalRetrievalChain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "7b4110f3",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"qa = ConversationalRetrievalChain.from_llm(ChatOpenAI(temperature=0), vectorstore,qa_prompt=prompt)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "3872432d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Here's an example of asking a question with no chat history"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "7fe3e730",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chat_history = []\n",
|
||||
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
|
||||
"result = qa({\"question\": query, \"chat_history\": chat_history})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "bfff9cc8",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"The President nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to serve on the United States Supreme Court. He described her as one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, and a consensus builder. She has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"result[\"answer\"]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "9e46edf7",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Here's an example of asking a question with some chat history"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "00b4cf00",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chat_history = [(query, result[\"answer\"])]\n",
|
||||
"query = \"Did he mention who came before her\"\n",
|
||||
"result = qa({\"question\": query, \"chat_history\": chat_history})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "f01828d1",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"The President mentioned Circuit Court of Appeals Judge Ketanji Brown Jackson as the nominee for the United States Supreme Court. He described her as one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence. The President did not mention any specific sources of support for Judge Jackson, but he did note that advancing immigration reform is supported by everyone from labor unions to religious leaders to the U.S. Chamber of Commerce.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"result['answer']"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "2324cdc6-98bf-4708-b8cd-02a98b1e5b67",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## ConversationalRetrievalChain with streaming to `stdout`\n",
|
||||
"\n",
|
||||
"Output from the chain will be streamed to `stdout` token by token in this example."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"id": "2efacec3-2690-4b05-8de3-a32fd2ac3911",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chains.llm import LLMChain\n",
|
||||
"from langchain.llms import OpenAI\n",
|
||||
"from langchain.callbacks.base import CallbackManager\n",
|
||||
"from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
|
||||
"from langchain.chains.chat_index.prompts import CONDENSE_QUESTION_PROMPT\n",
|
||||
"from langchain.chains.question_answering import load_qa_chain\n",
|
||||
"\n",
|
||||
"# Construct a ChatVectorDBChain with a streaming llm for combine docs\n",
|
||||
"# and a separate, non-streaming llm for question generation\n",
|
||||
"llm = OpenAI(temperature=0)\n",
|
||||
"streaming_llm = ChatOpenAI(streaming=True, callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), verbose=True, temperature=0)\n",
|
||||
"\n",
|
||||
"question_generator = LLMChain(llm=llm, prompt=CONDENSE_QUESTION_PROMPT)\n",
|
||||
"doc_chain = load_qa_chain(streaming_llm, chain_type=\"stuff\", prompt=prompt)\n",
|
||||
"\n",
|
||||
"qa = ConversationalRetrievalChain(retriever=vectorstore.as_retriever(), combine_docs_chain=doc_chain, question_generator=question_generator)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"id": "fd6d43f4-7428-44a4-81bc-26fe88a98762",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"The President nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to serve on the United States Supreme Court. He described her as one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, and a consensus builder. He also mentioned that she has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans."
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chat_history = []\n",
|
||||
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
|
||||
"result = qa({\"question\": query, \"chat_history\": chat_history})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"id": "5ab38978-f3e8-4fa7-808c-c79dec48379a",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"The context does not provide information on who Ketanji Brown Jackson succeeded on the United States Supreme Court."
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chat_history = [(query, result[\"answer\"])]\n",
|
||||
"query = \"Did he mention who she suceeded\"\n",
|
||||
"result = qa({\"question\": query, \"chat_history\": chat_history})\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "8e8d0055",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
@ -1,166 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "bb0735c0",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Few Shot Examples\n",
|
||||
"\n",
|
||||
"This notebook covers how to use few shot examples in chat models.\n",
|
||||
"\n",
|
||||
"There does not appear to be solid consensus on how best to do few shot prompting. As a result, we are not solidifying any abstractions around this yet but rather using existing abstractions."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "c6e9664c",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Alternating Human/AI messages\n",
|
||||
"The first way of doing few shot prompting relies on using alternating human/ai messages. See an example of this below."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "62156fe4",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain import PromptTemplate, LLMChain\n",
|
||||
"from langchain.prompts.chat import (\n",
|
||||
" ChatPromptTemplate,\n",
|
||||
" SystemMessagePromptTemplate,\n",
|
||||
" AIMessagePromptTemplate,\n",
|
||||
" HumanMessagePromptTemplate,\n",
|
||||
")\n",
|
||||
"from langchain.schema import (\n",
|
||||
" AIMessage,\n",
|
||||
" HumanMessage,\n",
|
||||
" SystemMessage\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "ed7ac3c6",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chat = ChatOpenAI(temperature=0)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "98791aa9",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"template=\"You are a helpful assistant that translates english to pirate.\"\n",
|
||||
"system_message_prompt = SystemMessagePromptTemplate.from_template(template)\n",
|
||||
"example_human = HumanMessagePromptTemplate.from_template(\"Hi\")\n",
|
||||
"example_ai = AIMessagePromptTemplate.from_template(\"Argh me mateys\")\n",
|
||||
"human_template=\"{text}\"\n",
|
||||
"human_message_prompt = HumanMessagePromptTemplate.from_template(human_template)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "4eebdcd7",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"I be lovin' programmin', me hearty!\""
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chat_prompt = ChatPromptTemplate.from_messages([system_message_prompt, example_human, example_ai, human_message_prompt])\n",
|
||||
"chain = LLMChain(llm=chat, prompt=chat_prompt)\n",
|
||||
"# get a chat completion from the formatted messages\n",
|
||||
"chain.run(\"I love programming.\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5c4135d7",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## System Messages\n",
|
||||
"\n",
|
||||
"OpenAI provides an optional `name` parameter that they also recommend using in conjunction with system messages to do few shot prompting. Here is an example of how to do that below."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "1ba92d59",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"template=\"You are a helpful assistant that translates english to pirate.\"\n",
|
||||
"system_message_prompt = SystemMessagePromptTemplate.from_template(template)\n",
|
||||
"example_human = SystemMessagePromptTemplate.from_template(\"Hi\", additional_kwargs={\"name\": \"example_user\"})\n",
|
||||
"example_ai = SystemMessagePromptTemplate.from_template(\"Argh me mateys\", additional_kwargs={\"name\": \"example_assistant\"})\n",
|
||||
"human_template=\"{text}\"\n",
|
||||
"human_message_prompt = HumanMessagePromptTemplate.from_template(human_template)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "56e488a7",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"I be lovin' programmin', me hearty.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chat_prompt = ChatPromptTemplate.from_messages([system_message_prompt, example_human, example_ai, human_message_prompt])\n",
|
||||
"chain = LLMChain(llm=chat, prompt=chat_prompt)\n",
|
||||
"# get a chat completion from the formatted messages\n",
|
||||
"chain.run(\"I love programming.\")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
@ -1,192 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "9a9350a6",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Memory\n",
|
||||
"This notebook goes over how to use Memory with chat models. The main difference between this and Memory for LLMs is that rather than trying to condense all previous messages into a string, we can keep them as their own unique memory object."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "110935ae",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.prompts import (\n",
|
||||
" ChatPromptTemplate, \n",
|
||||
" MessagesPlaceholder, \n",
|
||||
" SystemMessagePromptTemplate, \n",
|
||||
" HumanMessagePromptTemplate\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "161b6629",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"prompt = ChatPromptTemplate.from_messages([\n",
|
||||
" SystemMessagePromptTemplate.from_template(\"The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\"),\n",
|
||||
" MessagesPlaceholder(variable_name=\"history\"),\n",
|
||||
" HumanMessagePromptTemplate.from_template(\"{input}\")\n",
|
||||
"])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "4976fbda",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chains import ConversationChain\n",
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.memory import ConversationBufferMemory"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "12a0bea6",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm = ChatOpenAI(temperature=0)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f6edcd6a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We can now initialize the memory. Note that we set `return_messages=True` To denote that this should return a list of messages when appropriate"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "f55bea38",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"memory = ConversationBufferMemory(return_messages=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "737e8c78",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We can now use this in the rest of the chain."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "80152db7",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"conversation = ConversationChain(memory=memory, prompt=prompt, llm=llm)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "ac68e766",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Hello! How can I assist you today?'"
|
||||
]
|
||||
},
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation.predict(input=\"Hi there!\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "babb33d0",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"That sounds like fun! I'm happy to chat with you. Is there anything specific you'd like to talk about?\""
|
||||
]
|
||||
},
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation.predict(input=\"I'm doing well! Just having a conversation with an AI.\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "36f8a1dc",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"Sure! I am an AI language model created by OpenAI. I was trained on a large dataset of text from the internet, which allows me to understand and generate human-like language. I can answer questions, provide information, and even have conversations like this one. Is there anything else you'd like to know about me?\""
|
||||
]
|
||||
},
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation.predict(input=\"Tell me about yourself.\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "79fb460b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
@ -1,188 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "959300d4",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# PromptLayer ChatOpenAI\n",
|
||||
"\n",
|
||||
"This example showcases how to connect to [PromptLayer](https://www.promptlayer.com) to start recording your ChatOpenAI requests."
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "6a45943e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Install PromptLayer\n",
|
||||
"The `promptlayer` package is required to use PromptLayer with OpenAI. Install `promptlayer` using pip."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "dbe09bd8",
|
||||
"metadata": {
|
||||
"vscode": {
|
||||
"languageId": "powershell"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"pip install promptlayer"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "536c1dfa",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Imports"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "c16da3b5",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"from langchain.chat_models import PromptLayerChatOpenAI\n",
|
||||
"from langchain.schema import HumanMessage"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "8564ce7d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Set the Environment API Key\n",
|
||||
"You can create a PromptLayer API Key at [wwww.promptlayer.com](https://ww.promptlayer.com) by clicking the settings cog in the navbar.\n",
|
||||
"\n",
|
||||
"Set it as an environment variable called `PROMPTLAYER_API_KEY`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "46ba25dc",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"os.environ[\"PROMPTLAYER_API_KEY\"] = \"**********\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "bf0294de",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Use the PromptLayerOpenAI LLM like normal\n",
|
||||
"*You can optionally pass in `pl_tags` to track your requests with PromptLayer's tagging feature.*"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "3acf0069",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"AIMessage(content='to take a nap in a cozy spot. I search around for a suitable place and finally settle on a soft cushion on the window sill. I curl up into a ball and close my eyes, relishing the warmth of the sun on my fur. As I drift off to sleep, I can hear the birds chirping outside and feel the gentle breeze blowing through the window. This is the life of a contented cat.', additional_kwargs={})"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chat = PromptLayerChatOpenAI(pl_tags=[\"langchain\"])\n",
|
||||
"chat([HumanMessage(content=\"I am a cat and I want\")])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "a2d76826",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"**The above request should now appear on your [PromptLayer dashboard](https://ww.promptlayer.com).**"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "05e9e2fe",
|
||||
"metadata": {},
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "c43803d1",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Using PromptLayer Track\n",
|
||||
"If you would like to use any of the [PromptLayer tracking features](https://magniv.notion.site/Track-4deee1b1f7a34c1680d085f82567dab9), you need to pass the argument `return_pl_id` when instantializing the PromptLayer LLM to get the request id. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "b7d4db01",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chat = PromptLayerChatOpenAI(return_pl_id=True)\n",
|
||||
"chat_results = chat.generate([[HumanMessage(content=\"I am a cat and I want\")]])\n",
|
||||
"\n",
|
||||
"for res in chat_results.generations:\n",
|
||||
" pl_request_id = res[0].generation_info[\"pl_request_id\"]\n",
|
||||
" promptlayer.track.score(request_id=pl_request_id, score=100)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "13e56507",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Using this allows you to track the performance of your model in the PromptLayer dashboard. If you are using a prompt template, you can attach a template to a request as well.\n",
|
||||
"Overall, this gives you the opportunity to track the performance of different templates and models in the PromptLayer dashboard."
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "base",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.8.8 (default, Apr 13 2021, 12:59:45) \n[Clang 10.0.0 ]"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "8a5edab282632443219e051e4ade2d1d5bbc671c781051bf1437897cbdfea0f1"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
@ -1,119 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "fe4e96b5",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Streaming\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use streaming with a chat model."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "e0244f2a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.schema import (\n",
|
||||
" HumanMessage,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "ad342bfa",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"Verse 1:\n",
|
||||
"Bubbles rising to the top\n",
|
||||
"A refreshing drink that never stops\n",
|
||||
"Clear and crisp, it's pure delight\n",
|
||||
"A taste that's sure to excite\n",
|
||||
"\n",
|
||||
"Chorus:\n",
|
||||
"Sparkling water, oh so fine\n",
|
||||
"A drink that's always on my mind\n",
|
||||
"With every sip, I feel alive\n",
|
||||
"Sparkling water, you're my vibe\n",
|
||||
"\n",
|
||||
"Verse 2:\n",
|
||||
"No sugar, no calories, just pure bliss\n",
|
||||
"A drink that's hard to resist\n",
|
||||
"It's the perfect way to quench my thirst\n",
|
||||
"A drink that always comes first\n",
|
||||
"\n",
|
||||
"Chorus:\n",
|
||||
"Sparkling water, oh so fine\n",
|
||||
"A drink that's always on my mind\n",
|
||||
"With every sip, I feel alive\n",
|
||||
"Sparkling water, you're my vibe\n",
|
||||
"\n",
|
||||
"Bridge:\n",
|
||||
"From the mountains to the sea\n",
|
||||
"Sparkling water, you're the key\n",
|
||||
"To a healthy life, a happy soul\n",
|
||||
"A drink that makes me feel whole\n",
|
||||
"\n",
|
||||
"Chorus:\n",
|
||||
"Sparkling water, oh so fine\n",
|
||||
"A drink that's always on my mind\n",
|
||||
"With every sip, I feel alive\n",
|
||||
"Sparkling water, you're my vibe\n",
|
||||
"\n",
|
||||
"Outro:\n",
|
||||
"Sparkling water, you're the one\n",
|
||||
"A drink that's always so much fun\n",
|
||||
"I'll never let you go, my friend\n",
|
||||
"Sparkling"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain.callbacks.base import CallbackManager\n",
|
||||
"from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
|
||||
"chat = ChatOpenAI(streaming=True, callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), verbose=True, temperature=0)\n",
|
||||
"resp = chat([HumanMessage(content=\"Write me a song about sparkling water.\")])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "67c44deb",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
@ -1,169 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "07c1e3b9",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Retrieval Question/Answering\n",
|
||||
"\n",
|
||||
"This example showcases using a chat model to do question answering over a vector database.\n",
|
||||
"\n",
|
||||
"This notebook is very similar to the example of using an LLM in the RetrievalQA. The only differences here are (1) using a ChatModel, and (2) passing in a ChatPromptTemplate (optimized for chat models)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "82525493",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
|
||||
"from langchain.vectorstores import Chroma\n",
|
||||
"from langchain.text_splitter import CharacterTextSplitter\n",
|
||||
"from langchain.chains import RetrievalQA"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "5c7049db",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Running Chroma using direct local API.\n",
|
||||
"Using DuckDB in-memory for database. Data will be transient.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain.document_loaders import TextLoader\n",
|
||||
"loader = TextLoader('../../state_of_the_union.txt')\n",
|
||||
"documents = loader.load()\n",
|
||||
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
|
||||
"texts = text_splitter.split_documents(documents)\n",
|
||||
"\n",
|
||||
"embeddings = OpenAIEmbeddings()\n",
|
||||
"docsearch = Chroma.from_documents(texts, embeddings)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "35f99145",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We can now set up the chat model and chat model specific prompt"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "32a49412",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.prompts.chat import (\n",
|
||||
" ChatPromptTemplate,\n",
|
||||
" SystemMessagePromptTemplate,\n",
|
||||
" AIMessagePromptTemplate,\n",
|
||||
" HumanMessagePromptTemplate,\n",
|
||||
")\n",
|
||||
"from langchain.schema import (\n",
|
||||
" AIMessage,\n",
|
||||
" HumanMessage,\n",
|
||||
" SystemMessage\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "f231fb9b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"system_template=\"\"\"Use the following pieces of context to answer the users question. \n",
|
||||
"If you don't know the answer, just say that you don't know, don't try to make up an answer.\n",
|
||||
"----------------\n",
|
||||
"{context}\"\"\"\n",
|
||||
"messages = [\n",
|
||||
" SystemMessagePromptTemplate.from_template(system_template),\n",
|
||||
" HumanMessagePromptTemplate.from_template(\"{question}\")\n",
|
||||
"]\n",
|
||||
"prompt = ChatPromptTemplate.from_messages(messages)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "3018f865",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chain_type_kwargs = {\"prompt\": prompt}\n",
|
||||
"qa = RetrievalQA.from_chain_type(llm=ChatOpenAI(), chain_type=\"stuff\", retriever=docsearch.as_retriever(), chain_type_kwargs=chain_type_kwargs)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "032a47f8",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"The president nominated Ketanji Brown Jackson to serve on the United States Supreme Court. He referred to her as one of our nation's top legal minds, a former federal public defender, a consensus builder, and from a family of public school educators and police officers. Since she's been nominated, she has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
|
||||
"qa.run(query)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "8b403637",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "b1677b440931f40d89ef8be7bf03acb108ce003de0ac9b18e8d43753ea2e7103"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
@ -1,206 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "efc5be67",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Retrieval Question Answering with Sources\n",
|
||||
"\n",
|
||||
"This notebook goes over how to do question-answering with sources with a chat model over a vector database. It does this by using the `RetrievalQAWithSourcesChain`, which does the lookup of the documents from a vector database. \n",
|
||||
"\n",
|
||||
"This notebook is very similar to the example of using an LLM in the RetrievalQAWithSources. The only differences here are (1) using a ChatModel, and (2) passing in a ChatPromptTemplate (optimized for chat models)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "1c613960",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
|
||||
"from langchain.embeddings.cohere import CohereEmbeddings\n",
|
||||
"from langchain.text_splitter import CharacterTextSplitter\n",
|
||||
"from langchain.vectorstores.elastic_vector_search import ElasticVectorSearch\n",
|
||||
"from langchain.vectorstores import Chroma"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "17d1306e",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with open('../../state_of_the_union.txt') as f:\n",
|
||||
" state_of_the_union = f.read()\n",
|
||||
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
|
||||
"texts = text_splitter.split_text(state_of_the_union)\n",
|
||||
"\n",
|
||||
"embeddings = OpenAIEmbeddings()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "0e745d99",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Running Chroma using direct local API.\n",
|
||||
"Using DuckDB in-memory for database. Data will be transient.\n",
|
||||
"Running Chroma using direct local API.\n",
|
||||
"Using DuckDB in-memory for database. Data will be transient.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"docsearch = Chroma.from_texts(texts, embeddings, metadatas=[{\"source\": f\"{i}-pl\"} for i in range(len(texts))])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "8aa571ae",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chains import RetrievalQAWithSourcesChain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "1f73b14a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We can now set up the chat model and chat model specific prompt"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "9643c775",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.prompts.chat import (\n",
|
||||
" ChatPromptTemplate,\n",
|
||||
" SystemMessagePromptTemplate,\n",
|
||||
" AIMessagePromptTemplate,\n",
|
||||
" HumanMessagePromptTemplate,\n",
|
||||
")\n",
|
||||
"from langchain.schema import (\n",
|
||||
" AIMessage,\n",
|
||||
" HumanMessage,\n",
|
||||
" SystemMessage\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "ed00e906",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"system_template=\"\"\"Use the following pieces of context to answer the users question. \n",
|
||||
"If you don't know the answer, just say that you don't know, don't try to make up an answer.\n",
|
||||
"ALWAYS return a \"SOURCES\" part in your answer.\n",
|
||||
"The \"SOURCES\" part should be a reference to the source of the document from which you got your answer.\n",
|
||||
"\n",
|
||||
"Example of your response should be:\n",
|
||||
"\n",
|
||||
"```\n",
|
||||
"The answer is foo\n",
|
||||
"SOURCES: xyz\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"Begin!\n",
|
||||
"----------------\n",
|
||||
"{summaries}\"\"\"\n",
|
||||
"messages = [\n",
|
||||
" SystemMessagePromptTemplate.from_template(system_template),\n",
|
||||
" HumanMessagePromptTemplate.from_template(\"{question}\")\n",
|
||||
"]\n",
|
||||
"prompt = ChatPromptTemplate.from_messages(messages)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "aa859d4c",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chain_type_kwargs = {\"prompt\": prompt}\n",
|
||||
"chain = RetrievalQAWithSourcesChain.from_chain_type(\n",
|
||||
" ChatOpenAI(temperature=0), \n",
|
||||
" chain_type=\"stuff\", \n",
|
||||
" retriever=docsearch.as_retriever(),\n",
|
||||
" chain_type_kwargs=chain_type_kwargs\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "8ba36fa7",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'answer': 'The President honored Justice Stephen Breyer, an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court, for his dedicated service to the country. \\n',\n",
|
||||
" 'sources': '31-pl'}"
|
||||
]
|
||||
},
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chain({\"question\": \"What did the president say about Justice Breyer\"}, return_only_outputs=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "8308fbf7",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "b1677b440931f40d89ef8be7bf03acb108ce003de0ac9b18e8d43753ea2e7103"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
@ -1,412 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "e49f1e0d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Getting Started\n",
|
||||
"\n",
|
||||
"This notebook covers how to get started with chat models. The interface is based around messages rather than raw text."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "522686de",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain import PromptTemplate, LLMChain\n",
|
||||
"from langchain.prompts.chat import (\n",
|
||||
" ChatPromptTemplate,\n",
|
||||
" SystemMessagePromptTemplate,\n",
|
||||
" AIMessagePromptTemplate,\n",
|
||||
" HumanMessagePromptTemplate,\n",
|
||||
")\n",
|
||||
"from langchain.schema import (\n",
|
||||
" AIMessage,\n",
|
||||
" HumanMessage,\n",
|
||||
" SystemMessage\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "62e0dbc3",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chat = ChatOpenAI(temperature=0)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "bbaec18e-3684-4eef-955f-c1cec8bf765d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You can get chat completions by passing one or more messages to the chat model. The response will be a message. The types of messages currently supported in LangChain are `AIMessage`, `HumanMessage`, `SystemMessage`, and `ChatMessage` -- `ChatMessage` takes in an arbitrary role parameter. Most of the time, you'll just be dealing with `HumanMessage`, `AIMessage`, and `SystemMessage`"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "76a6e7b0-e927-4bfb-a414-1332a4149106",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"AIMessage(content=\"J'aime programmer.\", additional_kwargs={})"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chat([HumanMessage(content=\"Translate this sentence from English to French. I love programming.\")])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "a62153d4-1211-411b-a493-3febfe446ae0",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"OpenAI's chat model supports multiple messages as input. See [here](https://platform.openai.com/docs/guides/chat/chat-vs-completions) for more information. Here is an example of sending a system and user message to the chat model:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "ce16ad78-8e6f-48cd-954e-98be75eb5836",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"AIMessage(content=\"J'aime programmer.\", additional_kwargs={})"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"messages = [\n",
|
||||
" SystemMessage(content=\"You are a helpful assistant that translates English to French.\"),\n",
|
||||
" HumanMessage(content=\"Translate this sentence from English to French. I love programming.\")\n",
|
||||
"]\n",
|
||||
"chat(messages)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "36dc8d7e-bd25-47ac-8c1b-60e3422603d3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You can go one step further and generate completions for multiple sets of messages using `generate`. This returns an `LLMResult` with an additional `message` parameter."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "2b21fc52-74b6-4950-ab78-45d12c68fb4d",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"LLMResult(generations=[[ChatGeneration(text=\"J'aime programmer.\", generation_info=None, message=AIMessage(content=\"J'aime programmer.\", additional_kwargs={}))], [ChatGeneration(text=\"J'aime l'intelligence artificielle.\", generation_info=None, message=AIMessage(content=\"J'aime l'intelligence artificielle.\", additional_kwargs={}))]], llm_output={'token_usage': {'prompt_tokens': 71, 'completion_tokens': 18, 'total_tokens': 89}})"
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"batch_messages = [\n",
|
||||
" [\n",
|
||||
" SystemMessage(content=\"You are a helpful assistant that translates English to French.\"),\n",
|
||||
" HumanMessage(content=\"Translate this sentence from English to French. I love programming.\")\n",
|
||||
" ],\n",
|
||||
" [\n",
|
||||
" SystemMessage(content=\"You are a helpful assistant that translates English to French.\"),\n",
|
||||
" HumanMessage(content=\"Translate this sentence from English to French. I love artificial intelligence.\")\n",
|
||||
" ],\n",
|
||||
"]\n",
|
||||
"result = chat.generate(batch_messages)\n",
|
||||
"result"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "2960f50f",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You can recover things like token usage from this LLMResult"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "a6186bee",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'token_usage': {'prompt_tokens': 71,\n",
|
||||
" 'completion_tokens': 18,\n",
|
||||
" 'total_tokens': 89}}"
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"result.llm_output"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "b10b00ef-f373-4bc3-8302-2dfc28033734",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## PromptTemplates"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "778f912a-66ea-4a5d-b3de-6c7db4baba26",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You can make use of templating by using a `MessagePromptTemplate`. You can build a `ChatPromptTemplate` from one or more `MessagePromptTemplates`. You can use `ChatPromptTemplate`'s `format_prompt` -- this returns a `PromptValue`, which you can convert to a string or Message object, depending on whether you want to use the formatted value as input to an llm or chat model.\n",
|
||||
"\n",
|
||||
"For convience, there is a `from_template` method exposed on the template. If you were to use this template, this is what it would look like:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "180c5cc8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"template=\"You are a helpful assistant that translates {input_language} to {output_language}.\"\n",
|
||||
"system_message_prompt = SystemMessagePromptTemplate.from_template(template)\n",
|
||||
"human_template=\"{text}\"\n",
|
||||
"human_message_prompt = HumanMessagePromptTemplate.from_template(human_template)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "fbb043e6",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"AIMessage(content=\"J'adore la programmation.\", additional_kwargs={})"
|
||||
]
|
||||
},
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chat_prompt = ChatPromptTemplate.from_messages([system_message_prompt, human_message_prompt])\n",
|
||||
"\n",
|
||||
"# get a chat completion from the formatted messages\n",
|
||||
"chat(chat_prompt.format_prompt(input_language=\"English\", output_language=\"French\", text=\"I love programming.\").to_messages())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "e28b98da",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"If you wanted to construct the MessagePromptTemplate more directly, you could create a PromptTemplate outside and then pass it in, eg:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "d5b1ab1c",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"prompt=PromptTemplate(\n",
|
||||
" template=\"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
|
||||
" input_variables=[\"input_language\", \"output_language\"],\n",
|
||||
")\n",
|
||||
"system_message_prompt = SystemMessagePromptTemplate(prompt=prompt)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "92af0bba",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## LLMChain\n",
|
||||
"You can use the existing LLMChain in a very similar way to before - provide a prompt and a model."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "f2cbfe3d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chain = LLMChain(llm=chat, prompt=chat_prompt)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "268543b1",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"J'adore la programmation.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chain.run(input_language=\"English\", output_language=\"French\", text=\"I love programming.\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "eb779f3f",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Streaming\n",
|
||||
"\n",
|
||||
"Streaming is supported for `ChatOpenAI` through callback handling."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "509181be",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"Verse 1:\n",
|
||||
"Bubbles rising to the top\n",
|
||||
"A refreshing drink that never stops\n",
|
||||
"Clear and crisp, it's pure delight\n",
|
||||
"A taste that's sure to excite\n",
|
||||
"\n",
|
||||
"Chorus:\n",
|
||||
"Sparkling water, oh so fine\n",
|
||||
"A drink that's always on my mind\n",
|
||||
"With every sip, I feel alive\n",
|
||||
"Sparkling water, you're my vibe\n",
|
||||
"\n",
|
||||
"Verse 2:\n",
|
||||
"No sugar, no calories, just pure bliss\n",
|
||||
"A drink that's hard to resist\n",
|
||||
"It's the perfect way to quench my thirst\n",
|
||||
"A drink that always comes first\n",
|
||||
"\n",
|
||||
"Chorus:\n",
|
||||
"Sparkling water, oh so fine\n",
|
||||
"A drink that's always on my mind\n",
|
||||
"With every sip, I feel alive\n",
|
||||
"Sparkling water, you're my vibe\n",
|
||||
"\n",
|
||||
"Bridge:\n",
|
||||
"From the mountains to the sea\n",
|
||||
"Sparkling water, you're the key\n",
|
||||
"To a healthy life, a happy soul\n",
|
||||
"A drink that makes me feel whole\n",
|
||||
"\n",
|
||||
"Chorus:\n",
|
||||
"Sparkling water, oh so fine\n",
|
||||
"A drink that's always on my mind\n",
|
||||
"With every sip, I feel alive\n",
|
||||
"Sparkling water, you're my vibe\n",
|
||||
"\n",
|
||||
"Outro:\n",
|
||||
"Sparkling water, you're the one\n",
|
||||
"A drink that's always so much fun\n",
|
||||
"I'll never let you go, my friend\n",
|
||||
"Sparkling"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain.callbacks.base import CallbackManager\n",
|
||||
"from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
|
||||
"chat = ChatOpenAI(streaming=True, callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), verbose=True, temperature=0)\n",
|
||||
"resp = chat([HumanMessage(content=\"Write me a song about sparkling water.\")])\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "c095285d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
@ -1,10 +0,0 @@
|
||||
How-To Guides
|
||||
=============
|
||||
|
||||
The examples here all address certain "how-to" guides for working with chat models.
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:glob:
|
||||
|
||||
./examples/*
|
@ -1,29 +0,0 @@
|
||||
# Key Concepts
|
||||
|
||||
## ChatMessage
|
||||
A chat message is what we refer to as the modular unit of information.
|
||||
At the moment, this consists of "content", which refers to the content of the chat message.
|
||||
At the moment, most chat models are trained to predict sequences of Human <> AI messages.
|
||||
This is because so far the primary interaction mode has been between a human user and a singular AI system.
|
||||
|
||||
At the moment, there are four different classes of Chat Messages
|
||||
|
||||
### HumanMessage
|
||||
A HumanMessage is a ChatMessage that is sent as if from a Human's point of view.
|
||||
|
||||
### AIMessage
|
||||
An AIMessage is a ChatMessage that is sent from the point of view of the AI system to which the Human is corresponding.
|
||||
|
||||
### SystemMessage
|
||||
A SystemMessage is still a bit ambiguous, and so far seems to be a concept unique to OpenAI
|
||||
|
||||
### ChatMessage
|
||||
A chat message is a generic chat message, with not only a "content" field but also a "role" field.
|
||||
With this field, arbitrary roles may be assigned to a message.
|
||||
|
||||
## ChatGeneration
|
||||
The output of a single prediction of a chat message.
|
||||
Currently this is just a chat message itself (eg content and a role)
|
||||
|
||||
## Chat Model
|
||||
A model which takes in a list of chat messages, and predicts a chat message in response.
|
@ -1,38 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Blackboard\n",
|
||||
"\n",
|
||||
"This covers how to load data from a Blackboard Learn instance."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.document_loaders import BlackboardLoader\n",
|
||||
"\n",
|
||||
"loader = BlackboardLoader(\n",
|
||||
" blackboard_course_url=\"https://blackboard.example.com/webapps/blackboard/execute/announcement?method=search&context=course_entry&course_id=_123456_1\",\n",
|
||||
" bbrouter=\"expires:12345...\",\n",
|
||||
" load_all_recursively=True,\n",
|
||||
")\n",
|
||||
"documents = loader.load()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"language_info": {
|
||||
"name": "python"
|
||||
},
|
||||
"orig_nbformat": 4
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
File diff suppressed because one or more lines are too long
@ -1,8 +1,5 @@
|
||||
<!DOCTYPE html>
|
||||
<html>
|
||||
<head>
|
||||
<title>Test Title</title>
|
||||
</head>
|
||||
<body>
|
||||
|
||||
<h1>My First Heading</h1>
|
||||
|
@ -1,32 +0,0 @@
|
||||
"Team", "Payroll (millions)", "Wins"
|
||||
"Nationals", 81.34, 98
|
||||
"Reds", 82.20, 97
|
||||
"Yankees", 197.96, 95
|
||||
"Giants", 117.62, 94
|
||||
"Braves", 83.31, 94
|
||||
"Athletics", 55.37, 94
|
||||
"Rangers", 120.51, 93
|
||||
"Orioles", 81.43, 93
|
||||
"Rays", 64.17, 90
|
||||
"Angels", 154.49, 89
|
||||
"Tigers", 132.30, 88
|
||||
"Cardinals", 110.30, 88
|
||||
"Dodgers", 95.14, 86
|
||||
"White Sox", 96.92, 85
|
||||
"Brewers", 97.65, 83
|
||||
"Phillies", 174.54, 81
|
||||
"Diamondbacks", 74.28, 81
|
||||
"Pirates", 63.43, 79
|
||||
"Padres", 55.24, 76
|
||||
"Mariners", 81.97, 75
|
||||
"Mets", 93.35, 74
|
||||
"Blue Jays", 75.48, 73
|
||||
"Royals", 60.91, 72
|
||||
"Marlins", 118.07, 69
|
||||
"Red Sox", 173.18, 69
|
||||
"Indians", 78.43, 68
|
||||
"Twins", 94.08, 66
|
||||
"Rockies", 78.06, 64
|
||||
"Cubs", 88.19, 61
|
||||
"Astros", 60.65, 55
|
||||
|
|
@ -1,79 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "33205b12",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Figma\n",
|
||||
"\n",
|
||||
"This notebook covers how to load data from the Figma REST API into a format that can be ingested into LangChain."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "90b69c94",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"from langchain.document_loaders import FigmaFileLoader"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "13deb0f5",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loader = FigmaFileLoader(\n",
|
||||
" os.environ.get('ACCESS_TOKEN'),\n",
|
||||
" os.environ.get('NODE_IDS'),\n",
|
||||
" os.environ.get('FILE_KEY')\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "9ccc1e2f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loader.load()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "3e64cac2",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
@ -48,7 +48,9 @@
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": "[Document(page_content='My First Heading\\n\\nMy first paragraph.', lookup_str='', metadata={'source': 'example_data/fake-content.html'}, lookup_index=0)]"
|
||||
"text/plain": [
|
||||
"[Document(page_content='My First Heading\\n\\nMy first paragraph.', lookup_str='', metadata={'source': 'example_data/fake-content.html'}, lookup_index=0)]"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
@ -59,57 +61,13 @@
|
||||
"data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"## Loading HTML with BeautifulSoup4\n",
|
||||
"\n",
|
||||
"We can also use BeautifulSoup4 to load HTML documents using the `BSHTMLLoader`. This will extract the text from the html into `page_content`, and the page title as `title` into `metadata`."
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 16,
|
||||
"execution_count": null,
|
||||
"id": "79b1bce4",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.document_loaders import BSHTMLLoader"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 17,
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": "[Document(page_content='\\n\\nTest Title\\n\\n\\nMy First Heading\\nMy first paragraph.\\n\\n\\n', lookup_str='', metadata={'source': 'example_data/fake-content.html', 'title': 'Test Title'}, lookup_index=0)]"
|
||||
},
|
||||
"execution_count": 17,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"loader = BSHTMLLoader(\"example_data/fake-content.html\")\n",
|
||||
"data = loader.load()\n",
|
||||
"data"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"outputs": [],
|
||||
"source": [],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
}
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
|
@ -1,145 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "39af9ecd",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Markdown\n",
|
||||
"\n",
|
||||
"This covers how to load markdown documents into a document format that we can use downstream."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "721c48aa",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.document_loaders import UnstructuredMarkdownLoader"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "9d3d0e35",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loader = UnstructuredMarkdownLoader(\"../../../../README.md\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "06073f91",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"data = loader.load()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "c9adc5cb",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content=\"ð\\x9f¦\\x9cï¸\\x8fð\\x9f”\\x97 LangChain\\n\\nâ\\x9a¡ Building applications with LLMs through composability â\\x9a¡\\n\\nProduction Support: As you move your LangChains into production, we'd love to offer more comprehensive support.\\nPlease fill out this form and we'll set up a dedicated support Slack channel.\\n\\nQuick Install\\n\\npip install langchain\\n\\nð\\x9f¤” What is this?\\n\\nLarge language models (LLMs) are emerging as a transformative technology, enabling\\ndevelopers to build applications that they previously could not.\\nBut using these LLMs in isolation is often not enough to\\ncreate a truly powerful app - the real power comes when you can combine them with other sources of computation or knowledge.\\n\\nThis library is aimed at assisting in the development of those types of applications. Common examples of these types of applications include:\\n\\nâ\\x9d“ Question Answering over specific documents\\n\\nDocumentation\\n\\nEnd-to-end Example: Question Answering over Notion Database\\n\\nð\\x9f’¬ Chatbots\\n\\nDocumentation\\n\\nEnd-to-end Example: Chat-LangChain\\n\\nð\\x9f¤\\x96 Agents\\n\\nDocumentation\\n\\nEnd-to-end Example: GPT+WolframAlpha\\n\\nð\\x9f“\\x96 Documentation\\n\\nPlease see here for full documentation on:\\n\\nGetting started (installation, setting up the environment, simple examples)\\n\\nHow-To examples (demos, integrations, helper functions)\\n\\nReference (full API docs)\\n Resources (high-level explanation of core concepts)\\n\\nð\\x9f\\x9a\\x80 What can this help with?\\n\\nThere are six main areas that LangChain is designed to help with.\\nThese are, in increasing order of complexity:\\n\\nð\\x9f“\\x83 LLMs and Prompts:\\n\\nThis includes prompt management, prompt optimization, generic interface for all LLMs, and common utilities for working with LLMs.\\n\\nð\\x9f”\\x97 Chains:\\n\\nChains go beyond just a single LLM call, and are sequences of calls (whether to an LLM or a different utility). LangChain provides a standard interface for chains, lots of integrations with other tools, and end-to-end chains for common applications.\\n\\nð\\x9f“\\x9a Data Augmented Generation:\\n\\nData Augmented Generation involves specific types of chains that first interact with an external datasource to fetch data to use in the generation step. Examples of this include summarization of long pieces of text and question/answering over specific data sources.\\n\\nð\\x9f¤\\x96 Agents:\\n\\nAgents involve an LLM making decisions about which Actions to take, taking that Action, seeing an Observation, and repeating that until done. LangChain provides a standard interface for agents, a selection of agents to choose from, and examples of end to end agents.\\n\\nð\\x9f§\\xa0 Memory:\\n\\nMemory is the concept of persisting state between calls of a chain/agent. LangChain provides a standard interface for memory, a collection of memory implementations, and examples of chains/agents that use memory.\\n\\nð\\x9f§\\x90 Evaluation:\\n\\n[BETA] Generative models are notoriously hard to evaluate with traditional metrics. One new way of evaluating them is using language models themselves to do the evaluation. LangChain provides some prompts/chains for assisting in this.\\n\\nFor more information on these concepts, please see our full documentation.\\n\\nð\\x9f’\\x81 Contributing\\n\\nAs an open source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infra, or better documentation.\\n\\nFor detailed information on how to contribute, see here.\", lookup_str='', metadata={'source': '../../../../README.md'}, lookup_index=0)]"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "525d6b67",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Retain Elements\n",
|
||||
"\n",
|
||||
"Under the hood, Unstructured creates different \"elements\" for different chunks of text. By default we combine those together, but you can easily keep that separation by specifying `mode=\"elements\"`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "064f9162",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loader = UnstructuredMarkdownLoader(\"../../../../README.md\", mode=\"elements\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "abefbbdb",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"data = loader.load()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "a547c534",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"Document(page_content='ð\\x9f¦\\x9cï¸\\x8fð\\x9f”\\x97 LangChain', lookup_str='', metadata={'source': '../../../../README.md', 'page_number': 1, 'category': 'UncategorizedText'}, lookup_index=0)"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"data[0]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "381d4139",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.8.13"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
145
docs/modules/document_loaders/examples/microsoft_word.ipynb
Normal file
145
docs/modules/document_loaders/examples/microsoft_word.ipynb
Normal file
@ -0,0 +1,145 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "34c90eed",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Microsoft Word\n",
|
||||
"\n",
|
||||
"This notebook shows how to load text from Microsoft word documents."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "28ded768",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.document_loaders import UnstructuredDocxLoader"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "f1f26035",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loader = UnstructuredDocxLoader('example_data/fake.docx')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "2c87dde9",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"data = loader.load()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "0e4a884c",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': 'example_data/fake.docx'}, lookup_index=0)]"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5d1472e9",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Retain Elements\n",
|
||||
"\n",
|
||||
"Under the hood, Unstructured creates different \"elements\" for different chunks of text. By default we combine those together, but you can easily keep that separation by specifying `mode=\"elements\"`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "93abf60b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loader = UnstructuredDocxLoader('example_data/fake.docx', mode=\"elements\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "c35cdbcc",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"data = loader.load()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "fae2d730",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': 'example_data/fake.docx'}, lookup_index=0)]"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "961a7b1d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
91
docs/modules/document_loaders/examples/online_pdf.ipynb
Normal file
91
docs/modules/document_loaders/examples/online_pdf.ipynb
Normal file
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@ -158,72 +158,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "672733fd",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Define a Partitioning Strategy\n",
|
||||
"\n",
|
||||
"Unstructured document loader allow users to pass in a `strategy` parameter that lets `unstructured` know how to partitioning the document. Currently supported strategies are `\"hi_res\"` (the default) and `\"fast\"`. Hi res partitioning strategies are more accurate, but take longer to process. Fast strategies partition the document more quickly, but trade-off accuracy. Not all document types have separate hi res and fast partitioning strategies. For those document types, the `strategy` kwarg is ignored. In some cases, the high res strategy will fallback to fast if there is a dependency missing (i.e. a model for document partitioning). You can see how to apply a strategy to an `UnstructuredFileLoader` below."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "767238a4",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.document_loaders import UnstructuredFileLoader"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "9518b425",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loader = UnstructuredFileLoader(\"layout-parser-paper-fast.pdf\", strategy=\"fast\", mode=\"elements\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "645f29e9",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"docs = loader.load()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "60685353",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='1', lookup_str='', metadata={'source': 'layout-parser-paper-fast.pdf', 'filename': 'layout-parser-paper-fast.pdf', 'page_number': 1, 'category': 'UncategorizedText'}, lookup_index=0),\n",
|
||||
" Document(page_content='2', lookup_str='', metadata={'source': 'layout-parser-paper-fast.pdf', 'filename': 'layout-parser-paper-fast.pdf', 'page_number': 1, 'category': 'UncategorizedText'}, lookup_index=0),\n",
|
||||
" Document(page_content='0', lookup_str='', metadata={'source': 'layout-parser-paper-fast.pdf', 'filename': 'layout-parser-paper-fast.pdf', 'page_number': 1, 'category': 'UncategorizedText'}, lookup_index=0),\n",
|
||||
" Document(page_content='2', lookup_str='', metadata={'source': 'layout-parser-paper-fast.pdf', 'filename': 'layout-parser-paper-fast.pdf', 'page_number': 1, 'category': 'UncategorizedText'}, lookup_index=0),\n",
|
||||
" Document(page_content='n', lookup_str='', metadata={'source': 'layout-parser-paper-fast.pdf', 'filename': 'layout-parser-paper-fast.pdf', 'page_number': 1, 'category': 'Title'}, lookup_index=0)]"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"docs[:5]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "8de9ef16",
|
||||
"id": "7874d01d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## PDF Example\n",
|
||||
@ -231,6 +166,7 @@
|
||||
"Processing PDF documents works exactly the same way. Unstructured detects the file type and extracts the same types of `elements`. "
|
||||
]
|
||||
},
|
||||
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
@ -289,7 +225,7 @@
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "f52b04cb",
|
||||
"id": "8ca8a648",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
@ -311,7 +247,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.8.13"
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
@ -27,7 +27,7 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loader = UnstructuredWordDocumentLoader(\"example_data/fake.docx\")"
|
||||
"loader = UnstructuredWordDocumentLoader(\"fake.docx\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -78,7 +78,7 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loader = UnstructuredWordDocumentLoader(\"example_data/fake.docx\", mode=\"elements\")"
|
||||
"loader = UnstructuredWordDocumentLoader(\"fake.docx\", mode=\"elements\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
@ -7,23 +7,22 @@
|
||||
"source": [
|
||||
"# YouTube\n",
|
||||
"\n",
|
||||
"How to load documents from YouTube transcripts.\n",
|
||||
"\n"
|
||||
"How to load documents from YouTube transcripts."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "427d5745",
|
||||
"execution_count": 1,
|
||||
"id": "da4a867f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.document_loaders import YoutubeLoader\n"
|
||||
"from langchain.document_loaders import YoutubeLoader"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 2,
|
||||
"id": "34a25b57",
|
||||
"metadata": {
|
||||
"scrolled": true
|
||||
@ -35,7 +34,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 3,
|
||||
"id": "bc8b308a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -45,10 +44,21 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 4,
|
||||
"id": "d073dd36",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='LADIES AND GENTLEMEN, PEDRO PASCAL! [ CHEERS AND APPLAUSE ] >> THANK YOU, THANK YOU. THANK YOU VERY MUCH. I\\'M SO EXCITED TO BE HERE. THANK YOU. I SPENT THE LAST YEAR SHOOTING A SHOW CALLED \"THE LAST OF US\" ON HBO. FOR SOME HBO SHOES, YOU GET TO SHOOT IN A FIVE STAR ITALIAN RESORT SURROUNDED BY BEAUTIFUL PEOPLE, BUT I SAID, NO, THAT\\'S TOO EASY. I WANT TO SHOOT IN A FREEZING CANADIAN FOREST WHILE BEING CHASED AROUND BY A GUY WHOSE HEAD LOOKS LIKE A GENITAL WART. IT IS AN HONOR BEING A PART OF THESE HUGE FRANCHISEs LIKE \"GAME OF THRONES\" AND \"STAR WARS,\" BUT I\\'M STILL GETTING USED TO PEOPLE RECOGNIZING ME. THE OTHER DAY, A GUY STOPPED ME ON THE STREET AND SAYS, MY SON LOVES \"THE MANDALORIAN\" AND THE NEXT THING I KNOW, I\\'M FACE TIMING WITH A 6-YEAR-OLD WHO HAS NO IDEA WHO I AM BECAUSE MY CHARACTER WEARS A MASK THE ENTIRE SHOW. THE GUY IS LIKE, DO THE MANDO VOICE, BUT IT\\'S LIKE A BEDROOM VOICE. WITHOUT THE MASK, IT JUST SOUNDS PORNY. PEOPLE WALKING BY ON THE STREET SEE ME WHISPERING TO A 6-YEAR-OLD KID. I CAN BRING YOU IN WARM, OR I CAN BRING YOU IN COLD. EVEN THOUGH I CAME TO THE U.S. WHEN I WAS LITTLE, I WAS BORN IN CHILE, AND I HAVE 34 FIRST COUSINS WHO ARE STILL THERE. THEY\\'RE VERY PROUD OF ME. I KNOW THEY\\'RE PROUD BECAUSE THEY GIVE MY PHONE NUMBER TO EVERY PERSON THEY MEET, WHICH MEANS EVERY DAY, SOMEONE IN SANTIAGO WILL TEXT ME STUFF LIKE, CAN YOU COME TO MY WEDDING, OR CAN YOU SING MY PRIEST HAPPY BIRTHDAY, OR IS BABY YODA MEAN IN REAL LIFE. SO I HAVE TO BE LIKE NO, NO, AND HIS NAME IS GROGU. BUT MY COUSINS WEREN\\'T ALWAYS SO PROUD. EARLY IN MY CAREER, I PLAYED SMALL PARTS IN EVERY CRIME SHOW. I EVEN PLAYED TWO DIFFERENT CHARACTERS ON \"LAW AND ORDER.\" TITO CABASSA WHO LOOKED LIKE THIS. AND ONE YEAR LATER, I PLAYED REGGIE LUCKMAN WHO LOOKS LIKE THIS. AND THAT, MY FRIENDS, IS CALLED RANGE. BUT IT IS AMAZING TO BE HERE, LIKE I SAID. I WAS BORN IN CHILE, AND NINE MONTHS LATER, MY PARENTS FLED AND BROUGHT ME AND MY SISTER TO THE U.S. THEY WERE SO BRAVE, AND WITHOUT THEM, I WOULDN\\'T BE HERE IN THIS WONDERFUL COUNTRY, AND I CERTAINLY WOULDN\\'T BE STANDING HERE WITH YOU ALL TONIGHT. SO TO ALL MY FAMILY WATCHING IN CHILE, I WANT TO SAY [ SPEAKING NON-ENGLISH ] WHICH MEANS, I LOVE YOU, I MISS YOU, AND STOP GIVING OUT MY PHONE NUMBER. WE\\'VE GOT AN AMAZING SHOW FOR YOU TONIGHT. COLDPLAY IS HERE, SO STICK', lookup_str='', metadata={'source': 'QsYGlZkevEg', 'title': 'Pedro Pascal Monologue - SNL', 'description': 'First-time host Pedro Pascal talks about filming The Last of Us and being recognized by fans.\\n\\nSaturday Night Live. Stream now on Peacock: https://pck.tv/3uQxh4q\\n\\nSubscribe to SNL: https://goo.gl/tUsXwM\\nStream Current Full Episodes: http://www.nbc.com/saturday-night-live\\n\\nWATCH PAST SNL SEASONS\\nGoogle Play - http://bit.ly/SNLGooglePlay\\niTunes - http://bit.ly/SNLiTunes\\n\\nSNL ON SOCIAL\\nSNL Instagram: http://instagram.com/nbcsnl\\nSNL Facebook: https://www.facebook.com/snl\\nSNL Twitter: https://twitter.com/nbcsnl\\nSNL TikTok: https://www.tiktok.com/@nbcsnl\\n\\nGET MORE NBC\\nLike NBC: http://Facebook.com/NBC\\nFollow NBC: http://Twitter.com/NBC\\nNBC Tumblr: http://NBCtv.tumblr.com/\\nYouTube: http://www.youtube.com/nbc\\nNBC Instagram: http://instagram.com/nbc\\n\\n#SNL #PedroPascal #SNL48 #Coldplay', 'view_count': 1175057, 'thumbnail_url': 'https://i.ytimg.com/vi/QsYGlZkevEg/sddefault.jpg', 'publish_date': datetime.datetime(2023, 2, 4, 0, 0), 'length': 224, 'author': 'Saturday Night Live'}, lookup_index=0)]"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"loader.load()"
|
||||
]
|
||||
@ -63,7 +73,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 5,
|
||||
"id": "ba28af69",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -73,7 +83,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 6,
|
||||
"id": "9b8ea390",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -83,61 +93,24 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 7,
|
||||
"id": "97b98e92",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='LADIES AND GENTLEMEN, PEDRO PASCAL! [ CHEERS AND APPLAUSE ] >> THANK YOU, THANK YOU. THANK YOU VERY MUCH. I\\'M SO EXCITED TO BE HERE. THANK YOU. I SPENT THE LAST YEAR SHOOTING A SHOW CALLED \"THE LAST OF US\" ON HBO. FOR SOME HBO SHOES, YOU GET TO SHOOT IN A FIVE STAR ITALIAN RESORT SURROUNDED BY BEAUTIFUL PEOPLE, BUT I SAID, NO, THAT\\'S TOO EASY. I WANT TO SHOOT IN A FREEZING CANADIAN FOREST WHILE BEING CHASED AROUND BY A GUY WHOSE HEAD LOOKS LIKE A GENITAL WART. IT IS AN HONOR BEING A PART OF THESE HUGE FRANCHISEs LIKE \"GAME OF THRONES\" AND \"STAR WARS,\" BUT I\\'M STILL GETTING USED TO PEOPLE RECOGNIZING ME. THE OTHER DAY, A GUY STOPPED ME ON THE STREET AND SAYS, MY SON LOVES \"THE MANDALORIAN\" AND THE NEXT THING I KNOW, I\\'M FACE TIMING WITH A 6-YEAR-OLD WHO HAS NO IDEA WHO I AM BECAUSE MY CHARACTER WEARS A MASK THE ENTIRE SHOW. THE GUY IS LIKE, DO THE MANDO VOICE, BUT IT\\'S LIKE A BEDROOM VOICE. WITHOUT THE MASK, IT JUST SOUNDS PORNY. PEOPLE WALKING BY ON THE STREET SEE ME WHISPERING TO A 6-YEAR-OLD KID. I CAN BRING YOU IN WARM, OR I CAN BRING YOU IN COLD. EVEN THOUGH I CAME TO THE U.S. WHEN I WAS LITTLE, I WAS BORN IN CHILE, AND I HAVE 34 FIRST COUSINS WHO ARE STILL THERE. THEY\\'RE VERY PROUD OF ME. I KNOW THEY\\'RE PROUD BECAUSE THEY GIVE MY PHONE NUMBER TO EVERY PERSON THEY MEET, WHICH MEANS EVERY DAY, SOMEONE IN SANTIAGO WILL TEXT ME STUFF LIKE, CAN YOU COME TO MY WEDDING, OR CAN YOU SING MY PRIEST HAPPY BIRTHDAY, OR IS BABY YODA MEAN IN REAL LIFE. SO I HAVE TO BE LIKE NO, NO, AND HIS NAME IS GROGU. BUT MY COUSINS WEREN\\'T ALWAYS SO PROUD. EARLY IN MY CAREER, I PLAYED SMALL PARTS IN EVERY CRIME SHOW. I EVEN PLAYED TWO DIFFERENT CHARACTERS ON \"LAW AND ORDER.\" TITO CABASSA WHO LOOKED LIKE THIS. AND ONE YEAR LATER, I PLAYED REGGIE LUCKMAN WHO LOOKS LIKE THIS. AND THAT, MY FRIENDS, IS CALLED RANGE. BUT IT IS AMAZING TO BE HERE, LIKE I SAID. I WAS BORN IN CHILE, AND NINE MONTHS LATER, MY PARENTS FLED AND BROUGHT ME AND MY SISTER TO THE U.S. THEY WERE SO BRAVE, AND WITHOUT THEM, I WOULDN\\'T BE HERE IN THIS WONDERFUL COUNTRY, AND I CERTAINLY WOULDN\\'T BE STANDING HERE WITH YOU ALL TONIGHT. SO TO ALL MY FAMILY WATCHING IN CHILE, I WANT TO SAY [ SPEAKING NON-ENGLISH ] WHICH MEANS, I LOVE YOU, I MISS YOU, AND STOP GIVING OUT MY PHONE NUMBER. WE\\'VE GOT AN AMAZING SHOW FOR YOU TONIGHT. COLDPLAY IS HERE, SO STICK', lookup_str='', metadata={'source': 'QsYGlZkevEg', 'title': 'Pedro Pascal Monologue - SNL', 'description': 'First-time host Pedro Pascal talks about filming The Last of Us and being recognized by fans.\\n\\nSaturday Night Live. Stream now on Peacock: https://pck.tv/3uQxh4q\\n\\nSubscribe to SNL: https://goo.gl/tUsXwM\\nStream Current Full Episodes: http://www.nbc.com/saturday-night-live\\n\\nWATCH PAST SNL SEASONS\\nGoogle Play - http://bit.ly/SNLGooglePlay\\niTunes - http://bit.ly/SNLiTunes\\n\\nSNL ON SOCIAL\\nSNL Instagram: http://instagram.com/nbcsnl\\nSNL Facebook: https://www.facebook.com/snl\\nSNL Twitter: https://twitter.com/nbcsnl\\nSNL TikTok: https://www.tiktok.com/@nbcsnl\\n\\nGET MORE NBC\\nLike NBC: http://Facebook.com/NBC\\nFollow NBC: http://Twitter.com/NBC\\nNBC Tumblr: http://NBCtv.tumblr.com/\\nYouTube: http://www.youtube.com/nbc\\nNBC Instagram: http://instagram.com/nbc\\n\\n#SNL #PedroPascal #SNL48 #Coldplay', 'view_count': 1175057, 'thumbnail_url': 'https://i.ytimg.com/vi/QsYGlZkevEg/sddefault.jpg', 'publish_date': datetime.datetime(2023, 2, 4, 0, 0), 'length': 224, 'author': 'Saturday Night Live'}, lookup_index=0)]"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"loader.load()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "65796cc5",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## YouTube loader from Google Cloud\n",
|
||||
"\n",
|
||||
"### Prerequisites\n",
|
||||
"\n",
|
||||
"1. Create a Google Cloud project or use an existing project\n",
|
||||
"1. Enable the [Youtube Api](https://console.cloud.google.com/apis/enableflow?apiid=youtube.googleapis.com&project=sixth-grammar-344520)\n",
|
||||
"1. [Authorize credentials for desktop app](https://developers.google.com/drive/api/quickstart/python#authorize_credentials_for_a_desktop_application)\n",
|
||||
"1. `pip install --upgrade google-api-python-client google-auth-httplib2 google-auth-oauthlib youtube-transcript-api`\n",
|
||||
"\n",
|
||||
"### 🧑 Instructions for ingesting your Google Docs data\n",
|
||||
"By default, the `GoogleDriveLoader` expects the `credentials.json` file to be `~/.credentials/credentials.json`, but this is configurable using the `credentials_file` keyword argument. Same thing with `token.json`. Note that `token.json` will be created automatically the first time you use the loader.\n",
|
||||
"\n",
|
||||
"`GoogleApiYoutubeLoader` can load from a list of Google Docs document ids or a folder id. You can obtain your folder and document id from the URL:\n",
|
||||
"Note depending on your set up, the `service_account_path` needs to be set up. See [here](https://developers.google.com/drive/api/v3/quickstart/python) for more details."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "c345bc43",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.document_loaders import GoogleApiClient, GoogleApiYoutubeLoader\n",
|
||||
"\n",
|
||||
"# Init the GoogleApiClient \n",
|
||||
"from pathlib import Path\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"google_api_client = GoogleApiClient(credentials_path=Path(\"your_path_creds.json\"))\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"# Use a Channel\n",
|
||||
"youtube_loader_channel = GoogleApiYoutubeLoader(google_api_client=google_api_client, channel_name=\"Reducible\",captions_language=\"en\")\n",
|
||||
"\n",
|
||||
"# Use Youtube Ids\n",
|
||||
"\n",
|
||||
"youtube_loader_ids = GoogleApiYoutubeLoader(google_api_client=google_api_client, video_ids=[\"TrdevFK_am4\"], add_video_info=True)\n",
|
||||
"\n",
|
||||
"# returns a list of Documents\n",
|
||||
"youtube_loader_channel.load()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
@ -157,11 +130,6 @@
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "604c1013f65d31a2eb1fca07aae054bedd5a5a0d272dbb31e502c81f0b254b99"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
@ -21,6 +21,8 @@ There are a lot of different document loaders that LangChain supports. Below are
|
||||
|
||||
`GoogleDrive <./examples/googledrive.html>`_: A walkthrough of how to load data from Google drive.
|
||||
|
||||
`Microsoft Word <./examples/microsoft_word.html>`_: A walkthrough of how to load data from Microsoft Word files.
|
||||
|
||||
`Obsidian <./examples/obsidian.html>`_: A walkthrough of how to load data from an Obsidian file dump.
|
||||
|
||||
`Roam <./examples/roam.html>`_: A walkthrough of how to load data from a Roam file export.
|
||||
@ -53,32 +55,12 @@ There are a lot of different document loaders that LangChain supports. Below are
|
||||
|
||||
`Airbyte Json <./examples/airbyte_json.html>`_: A walkthrough of how to load data from a local Airbyte JSON file.
|
||||
|
||||
`Online PDF <./examples/online_pdf.html>`_: A walkthrough of how to load data from an online PDF.
|
||||
|
||||
`CoNLL-U <./examples/CoNLL-U.html>`_: A walkthrough of how to load data from a ConLL-U file.
|
||||
|
||||
`iFixit <./examples/ifixit.html>`_: A walkthrough of how to search and load data like guides, technical Q&A's, and device wikis from iFixit.com
|
||||
|
||||
`Notebook <./examples/notebook.html>`_: A walkthrough of how to load data from .ipynb notebook.
|
||||
|
||||
`Copypaste <./examples/copypaste.html>`_: A walkthrough of how to load a document object from something you just want to copy and paste.
|
||||
|
||||
`CSV <./examples/csv.html>`_: A walkthrough of how to load data from a .csv file.
|
||||
|
||||
`Facebook Chat <./examples/facebook_chat.html>`_: A walkthrough of how to load data from a Facebook Chat json file.
|
||||
|
||||
`Image <./examples/image.html>`_: A walkthrough of how to load images such as JPGs PNGs into a document format that can be used downstream.
|
||||
|
||||
`Markdown <./examples/markdown.html>`_: A walkthrough of how to load data from a markdown file.
|
||||
|
||||
`SRT <./examples/srt.html>`_: A walkthrough of how to load data from a subtitle (`.srt`) file.
|
||||
|
||||
`Telegram <./examples/telegram.html>`_: A walkthrough of how to load data from a Telegram Chat json file.
|
||||
|
||||
`URL <./examples/url.html>`_: A walkthrough of how to load HTML documents from a list of URLs into a document format that we can use downstream.
|
||||
|
||||
`Word Document <./examples/word_document.html>`_: A walkthrough of how to load data from Microsoft Word files.
|
||||
|
||||
`Blackboard <./examples/blackboard.html>`_: A walkthrough of how to load data from a Blackboard course.
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:glob:
|
||||
|
@ -3,24 +3,16 @@ Indexes
|
||||
|
||||
Indexes refer to ways to structure documents so that LLMs can best interact with them.
|
||||
This module contains utility functions for working with documents, different types of indexes, and then examples for using those indexes in chains.
|
||||
|
||||
The most common way that indexes are used in chains is in a "retrieval" step.
|
||||
This step refers to taking a user's query and returning the most relevant documents.
|
||||
We draw this distinction because (1) an index can be used for other things besides retrieval, and (2) retrieval can use other logic besides an index to find relevant documents.
|
||||
We therefor have a concept of a "Retriever" interface - this is the interface that most chains work with.
|
||||
|
||||
Most of the time when we talk about indexes and retrieval we are talking about indexing and retrieving unstructured data (like text documents).
|
||||
For interacting with structured data (SQL tables, etc) or APIs, please see the corresponding use case sections for links to relevant functionality.
|
||||
The primary index and retrieval types supported by LangChain are currently centered around vector databases, and therefore
|
||||
a lot of the functionality we dive deep on those topics.
|
||||
LangChain provides common indices for working with data (most prominently support for vector databases).
|
||||
For more complicated index structures, it is worth checking out `GPTIndex <https://gpt-index.readthedocs.io/en/latest/index.html>`_.
|
||||
|
||||
The following sections of documentation are provided:
|
||||
|
||||
- `Getting Started <./indexes/getting_started.html>`_: An overview of the base "Retriever" interface, and then all the functionality LangChain provides for working with indexes.
|
||||
- `Getting Started <./indexes/getting_started.html>`_: An overview of all the functionality LangChain provides for working with indexes.
|
||||
|
||||
- `Key Concepts <./indexes/key_concepts.html>`_: A conceptual guide going over the various concepts related to indexes and the tools needed to create them.
|
||||
|
||||
- `How-To Guides <./indexes/how_to_guides.html>`_: A collection of how-to guides. These highlight how to use all the relevant tools, the different types of vector databases, different types of retrievers, and how to use retrievers and indexes in chains.
|
||||
- `How-To Guides <./indexes/how_to_guides.html>`_: A collection of how-to guides. These highlight how to use all the relevant tools, the different types of vector databases, and how to use indexes in chains.
|
||||
|
||||
|
||||
.. toctree::
|
||||
|
@ -5,9 +5,9 @@
|
||||
"id": "134a0785",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Chat Index\n",
|
||||
"# Chat Vector DB\n",
|
||||
"\n",
|
||||
"This notebook goes over how to set up a chain to chat with an index. The only difference between this chain and the [RetrievalQAChain](./vector_db_qa.ipynb) is that this allows for passing in of a chat history which can be used to allow for follow up questions."
|
||||
"This notebook goes over how to set up a chain to chat with a vector database. The only difference between this chain and the [VectorDBQAChain](./vector_db_qa.ipynb) is that this allows for passing in of a chat history which can be used to allow for follow up questions."
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -23,7 +23,7 @@
|
||||
"from langchain.vectorstores import Chroma\n",
|
||||
"from langchain.text_splitter import CharacterTextSplitter\n",
|
||||
"from langchain.llms import OpenAI\n",
|
||||
"from langchain.chains import ConversationalRetrievalChain"
|
||||
"from langchain.chains import ChatVectorDBChain"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -109,7 +109,7 @@
|
||||
"id": "3c96b118",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We now initialize the ConversationalRetrievalChain"
|
||||
"We now initialize the ChatVectorDBChain"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -121,7 +121,7 @@
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"qa = ConversationalRetrievalChain.from_llm(OpenAI(temperature=0), vectorstore)"
|
||||
"qa = ChatVectorDBChain.from_llm(OpenAI(temperature=0), vectorstore)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -220,22 +220,22 @@
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Return Source Documents\n",
|
||||
"You can also easily return source documents from the ConversationalRetrievalChain. This is useful for when you want to inspect what documents were returned."
|
||||
"You can also easily return source documents from the ChatVectorDBChain. This is useful for when you want to inspect what documents were returned."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "562769c6",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"qa = ChatVectorDBChain.from_llm(OpenAI(temperature=0), vectorstore, return_source_documents=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "562769c6",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"qa = ConversationalRetrievalChain.from_llm(OpenAI(temperature=0), vectorstore, return_source_documents=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"id": "ea478300",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -247,17 +247,17 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"execution_count": 15,
|
||||
"id": "4cb75b4e",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"Document(page_content='Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0)"
|
||||
"Document(page_content='In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. \\n\\nWe cannot let this happen. \\n\\nTonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0)"
|
||||
]
|
||||
},
|
||||
"execution_count": 13,
|
||||
"execution_count": 15,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@ -268,60 +268,64 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "4f49beab",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## ConversationalRetrievalChain with `search_distance`\n",
|
||||
"## Chat Vector DB with `search_distance`\n",
|
||||
"If you are using a vector store that supports filtering by search distance, you can add a threshold value parameter."
|
||||
]
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"id": "5ed8d612",
|
||||
"metadata": {},
|
||||
"execution_count": null,
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"vectordbkwargs = {\"search_distance\": 0.9}"
|
||||
]
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"id": "6a7b3459",
|
||||
"metadata": {},
|
||||
"execution_count": null,
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"qa = ConversationalRetrievalChain.from_llm(OpenAI(temperature=0), vectorstore, return_source_documents=True)\n",
|
||||
"qa = ChatVectorDBChain.from_llm(OpenAI(temperature=0), vectorstore, return_source_documents=True)\n",
|
||||
"chat_history = []\n",
|
||||
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
|
||||
"result = qa({\"question\": query, \"chat_history\": chat_history, \"vectordbkwargs\": vectordbkwargs})"
|
||||
]
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "99b96dae",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## ConversationalRetrievalChain with `map_reduce`\n",
|
||||
"We can also use different types of combine document chains with the ConversationalRetrievalChain chain."
|
||||
]
|
||||
"## Chat Vector DB with `map_reduce`\n",
|
||||
"We can also use different types of combine document chains with the Chat Vector DB chain."
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 16,
|
||||
"execution_count": null,
|
||||
"id": "e53a9d66",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chains import LLMChain\n",
|
||||
"from langchain.chains.question_answering import load_qa_chain\n",
|
||||
"from langchain.chains.chat_index.prompts import CONDENSE_QUESTION_PROMPT"
|
||||
"from langchain.chains.chat_vector_db.prompts import CONDENSE_QUESTION_PROMPT"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 19,
|
||||
"execution_count": 9,
|
||||
"id": "bf205e35",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -330,8 +334,8 @@
|
||||
"question_generator = LLMChain(llm=llm, prompt=CONDENSE_QUESTION_PROMPT)\n",
|
||||
"doc_chain = load_qa_chain(llm, chain_type=\"map_reduce\")\n",
|
||||
"\n",
|
||||
"chain = ConversationalRetrievalChain(\n",
|
||||
" retriever=vectorstore.as_retriever(),\n",
|
||||
"chain = ChatVectorDBChain(\n",
|
||||
" vectorstore=vectorstore,\n",
|
||||
" question_generator=question_generator,\n",
|
||||
" combine_docs_chain=doc_chain,\n",
|
||||
")"
|
||||
@ -339,7 +343,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 20,
|
||||
"execution_count": 10,
|
||||
"id": "78155887",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -351,7 +355,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 21,
|
||||
"execution_count": 11,
|
||||
"id": "e54b5fa2",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@ -361,7 +365,7 @@
|
||||
"\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, from a family of public school educators and police officers, a consensus builder, and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 21,
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@ -375,14 +379,14 @@
|
||||
"id": "a2fe6b14",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## ConversationalRetrievalChain with Question Answering with sources\n",
|
||||
"## Chat Vector DB with Question Answering with sources\n",
|
||||
"\n",
|
||||
"You can also use this chain with the question answering with sources chain."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 22,
|
||||
"execution_count": 12,
|
||||
"id": "d1058fd2",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -392,7 +396,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 23,
|
||||
"execution_count": 13,
|
||||
"id": "a6594482",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -401,8 +405,8 @@
|
||||
"question_generator = LLMChain(llm=llm, prompt=CONDENSE_QUESTION_PROMPT)\n",
|
||||
"doc_chain = load_qa_with_sources_chain(llm, chain_type=\"map_reduce\")\n",
|
||||
"\n",
|
||||
"chain = ConversationalRetrievalChain(\n",
|
||||
" retriever=vectorstore.as_retriever(),\n",
|
||||
"chain = ChatVectorDBChain(\n",
|
||||
" vectorstore=vectorstore,\n",
|
||||
" question_generator=question_generator,\n",
|
||||
" combine_docs_chain=doc_chain,\n",
|
||||
")"
|
||||
@ -410,7 +414,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 24,
|
||||
"execution_count": 14,
|
||||
"id": "e2badd21",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -422,7 +426,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 25,
|
||||
"execution_count": 16,
|
||||
"id": "edb31fe5",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@ -432,7 +436,7 @@
|
||||
"\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, from a family of public school educators and police officers, a consensus builder, and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \\nSOURCES: ../../state_of_the_union.txt\""
|
||||
]
|
||||
},
|
||||
"execution_count": 25,
|
||||
"execution_count": 16,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@ -446,14 +450,14 @@
|
||||
"id": "2324cdc6-98bf-4708-b8cd-02a98b1e5b67",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## ConversationalRetrievalChain with streaming to `stdout`\n",
|
||||
"## Chat Vector DB with streaming to `stdout`\n",
|
||||
"\n",
|
||||
"Output from the chain will be streamed to `stdout` token by token in this example."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 26,
|
||||
"execution_count": 10,
|
||||
"id": "2efacec3-2690-4b05-8de3-a32fd2ac3911",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
@ -463,7 +467,7 @@
|
||||
"from langchain.chains.llm import LLMChain\n",
|
||||
"from langchain.callbacks.base import CallbackManager\n",
|
||||
"from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
|
||||
"from langchain.chains.chat_index.prompts import CONDENSE_QUESTION_PROMPT, QA_PROMPT\n",
|
||||
"from langchain.chains.chat_vector_db.prompts import CONDENSE_QUESTION_PROMPT, QA_PROMPT\n",
|
||||
"from langchain.chains.question_answering import load_qa_chain\n",
|
||||
"\n",
|
||||
"# Construct a ChatVectorDBChain with a streaming llm for combine docs\n",
|
||||
@ -474,13 +478,12 @@
|
||||
"question_generator = LLMChain(llm=llm, prompt=CONDENSE_QUESTION_PROMPT)\n",
|
||||
"doc_chain = load_qa_chain(streaming_llm, chain_type=\"stuff\", prompt=QA_PROMPT)\n",
|
||||
"\n",
|
||||
"qa = ConversationalRetrievalChain(\n",
|
||||
" retriever=vectorstore.as_retriever(), combine_docs_chain=doc_chain, question_generator=question_generator)"
|
||||
"qa = ChatVectorDBChain(vectorstore=vectorstore, combine_docs_chain=doc_chain, question_generator=question_generator)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 27,
|
||||
"execution_count": 11,
|
||||
"id": "fd6d43f4-7428-44a4-81bc-26fe88a98762",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
@ -502,7 +505,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 28,
|
||||
"execution_count": 12,
|
||||
"id": "5ab38978-f3e8-4fa7-808c-c79dec48379a",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
@ -521,71 +524,6 @@
|
||||
"query = \"Did he mention who she suceeded\"\n",
|
||||
"result = qa({\"question\": query, \"chat_history\": chat_history})\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f793d56b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## get_chat_history Function\n",
|
||||
"You can also specify a `get_chat_history` function, which can be used to format the chat_history string."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 29,
|
||||
"id": "a7ba9d8c",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def get_chat_history(inputs) -> str:\n",
|
||||
" res = []\n",
|
||||
" for human, ai in inputs:\n",
|
||||
" res.append(f\"Human:{human}\\nAI:{ai}\")\n",
|
||||
" return \"\\n\".join(res)\n",
|
||||
"qa = ConversationalRetrievalChain.from_llm(OpenAI(temperature=0), vectorstore, get_chat_history=get_chat_history)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 30,
|
||||
"id": "a3e33c0d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chat_history = []\n",
|
||||
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
|
||||
"result = qa({\"question\": query, \"chat_history\": chat_history})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 31,
|
||||
"id": "936dc62f",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, and from a family of public school educators and police officers. He also said that she is a consensus builder and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 31,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"result['answer']"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "b8c26901",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
|
@ -205,76 +205,10 @@
|
||||
"chain.run(\"what is Intel going to build?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "410aafa0",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Save the graph\n",
|
||||
"We can also save and load the graph."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "bc72cca0",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"graph.write_to_gml(\"graph.gml\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "652760ad",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.indexes.graph import NetworkxEntityGraph"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "eae591fe",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loaded_graph = NetworkxEntityGraph.from_gml(\"graph.gml\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "9439d419",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[('Intel', '$20 billion semiconductor \"mega site\"', 'is going to build'),\n",
|
||||
" ('Intel', 'state-of-the-art factories', 'is building'),\n",
|
||||
" ('Intel', '10,000 new good-paying jobs', 'is creating'),\n",
|
||||
" ('Intel', 'Silicon Valley', 'is helping build'),\n",
|
||||
" ('Field of dreams',\n",
|
||||
" \"America's future will be built\",\n",
|
||||
" 'is the ground on which')]"
|
||||
]
|
||||
},
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"loaded_graph.get_triples()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "045796cf",
|
||||
"id": "f70b9ada",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
|
@ -635,7 +635,7 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.output_parsers import RegexParser\n",
|
||||
"from langchain.prompts.base import RegexParser\n",
|
||||
"\n",
|
||||
"output_parser = RegexParser(\n",
|
||||
" regex=r\"(.*?)\\nScore: (.*)\",\n",
|
||||
@ -732,4 +732,4 @@
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
}
|
@ -7,7 +7,7 @@
|
||||
"source": [
|
||||
"# Question Answering\n",
|
||||
"\n",
|
||||
"This notebook walks through how to use LangChain for question answering over a list of documents. It covers four different types of chains: `stuff`, `map_reduce`, `refine`, `map_rerank`. For a more in depth explanation of what these chain types are, see [here](../combine_docs.md)."
|
||||
"This notebook walks through how to use LangChain for question answering over a list of documents. It covers four different types of chains: `stuff`, `map_reduce`, `refine`, `map-rerank`. For a more in depth explanation of what these chain types are, see [here](../combine_docs.md)."
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -635,7 +635,7 @@
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain.output_parsers import RegexParser\n",
|
||||
"from langchain.prompts.base import RegexParser\n",
|
||||
"\n",
|
||||
"output_parser = RegexParser(\n",
|
||||
" regex=r\"(.*?)\\nScore: (.*)\",\n",
|
||||
|
@ -21,7 +21,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"execution_count": 7,
|
||||
"id": "e9db25f3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -81,17 +81,17 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"execution_count": 14,
|
||||
"id": "5cfa89b2",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"' In response to Russian aggression in Ukraine, the United States and its allies are taking action to hold Putin accountable, including economic sanctions, asset seizures, and military assistance. The US is also providing economic and humanitarian aid to Ukraine, and has passed the American Rescue Plan and the Bipartisan Infrastructure Law to help struggling families and create jobs. The US remains unified and determined to protect Ukraine and the free world.'"
|
||||
"\" In response to Russia's aggression in Ukraine, the United States and its allies have imposed economic sanctions and are taking other measures to hold Putin accountable. The US is also providing economic and military assistance to Ukraine, protecting NATO countries, and investing in American products to create jobs. President Biden and Vice President Harris have passed the American Rescue Plan and the Bipartisan Infrastructure Law to help working people and rebuild America.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@ -470,7 +470,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
"version": "3.10.9"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
|
@ -5,9 +5,9 @@
|
||||
"id": "07c1e3b9",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Retrieval Question/Answering\n",
|
||||
"# Vector DB Question/Answering\n",
|
||||
"\n",
|
||||
"This example showcases question answering over an index."
|
||||
"This example showcases question answering over a vector database."
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -20,8 +20,7 @@
|
||||
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
|
||||
"from langchain.vectorstores import Chroma\n",
|
||||
"from langchain.text_splitter import CharacterTextSplitter\n",
|
||||
"from langchain.llms import OpenAI\n",
|
||||
"from langchain.chains import RetrievalQA"
|
||||
"from langchain import OpenAI, VectorDBQA"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -57,7 +56,7 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"qa = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type=\"stuff\", retriever=docsearch.as_retriever())"
|
||||
"qa = VectorDBQA.from_chain_type(llm=OpenAI(), chain_type=\"stuff\", vectorstore=docsearch)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -69,7 +68,7 @@
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\" The president said that she is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, and from a family of public school educators and police officers. He also said that she is a consensus builder and has received a broad range of support, from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
|
||||
"\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice and federal public defender, from a family of public school educators and police officers, a consensus builder, and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
@ -88,7 +87,7 @@
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Chain Type\n",
|
||||
"You can easily specify different chain types to load and use in the RetrievalQA chain. For a more detailed walkthrough of these types, please see [this notebook](question_answering.ipynb).\n",
|
||||
"You can easily specify different chain types to load and use in the VectorDBQA chain. For a more detailed walkthrough of these types, please see [this notebook](question_answering.ipynb).\n",
|
||||
"\n",
|
||||
"There are two ways to load different chain types. First, you can specify the chain type argument in the `from_chain_type` method. This allows you to pass in the name of the chain type you want to use. For example, in the below we change the chain type to `map_reduce`."
|
||||
]
|
||||
@ -100,7 +99,7 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"qa = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type=\"map_reduce\", retriever=docsearch.as_retriever())"
|
||||
"qa = VectorDBQA.from_chain_type(llm=OpenAI(), chain_type=\"map_reduce\", vectorstore=docsearch)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -112,7 +111,7 @@
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\" The president said that Judge Ketanji Brown Jackson is one of our nation's top legal minds, a former top litigator in private practice and a former federal public defender, from a family of public school educators and police officers, a consensus builder and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
|
||||
"\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, from a family of public school educators and police officers, a consensus builder, and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
@ -130,24 +129,24 @@
|
||||
"id": "60368f38",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The above way allows you to really simply change the chain_type, but it does provide a ton of flexibility over parameters to that chain type. If you want to control those parameters, you can load the chain directly (as you did in [this notebook](question_answering.ipynb)) and then pass that directly to the the RetrievalQA chain with the `combine_documents_chain` parameter. For example:"
|
||||
"The above way allows you to really simply change the chain_type, but it does provide a ton of flexibility over parameters to that chain type. If you want to control those parameters, you can load the chain directly (as you did in [this notebook](question_answering.ipynb)) and then pass that directly to the the VectorDBQA chain with the `combine_documents_chain` parameter. For example:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"execution_count": 18,
|
||||
"id": "7b403f0d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chains.question_answering import load_qa_chain\n",
|
||||
"qa_chain = load_qa_chain(OpenAI(temperature=0), chain_type=\"stuff\")\n",
|
||||
"qa = RetrievalQA(combine_documents_chain=qa_chain, retriever=docsearch.as_retriever())"
|
||||
"qa = VectorDBQA(combine_documents_chain=qa_chain, vectorstore=docsearch)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"execution_count": 19,
|
||||
"id": "9e04a9ac",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@ -157,7 +156,7 @@
|
||||
"\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, and from a family of public school educators and police officers. He also said that she is a consensus builder and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 10,
|
||||
"execution_count": 19,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@ -178,7 +177,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"execution_count": 6,
|
||||
"id": "a45232a2",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -197,28 +196,28 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"execution_count": 7,
|
||||
"id": "9b5c8d1d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chain_type_kwargs = {\"prompt\": PROMPT}\n",
|
||||
"qa = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type=\"stuff\", retriever=docsearch.as_retriever(), chain_type_kwargs=chain_type_kwargs)"
|
||||
"qa = VectorDBQA.from_chain_type(llm=OpenAI(), chain_type=\"stuff\", vectorstore=docsearch, chain_type_kwargs=chain_type_kwargs)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"execution_count": 8,
|
||||
"id": "26ee7671",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\" Il presidente ha detto che Ketanji Brown Jackson è una delle menti legali più importanti del paese, che continuerà l'eccellenza di Justice Breyer e che ha ricevuto un ampio sostegno, da Fraternal Order of Police a ex giudici nominati da democratici e repubblicani.\""
|
||||
"\" Il Presidente ha detto che Ketanji Brown Jackson è uno dei pensatori legali più importanti del nostro Paese, che continuerà l'eccellente eredità di giustizia Breyer. È un ex principale litigante in pratica privata, un ex difensore federale pubblico e appartiene a una famiglia di insegnanti e poliziotti delle scuole pubbliche. È un costruttore di consenso che ha ricevuto un ampio supporto da parte di Fraternal Order of Police e giudici designati da democratici e repubblicani.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 14,
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@ -239,17 +238,17 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"execution_count": 5,
|
||||
"id": "af093aba",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"qa = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type=\"stuff\", retriever=docsearch.as_retriever(), return_source_documents=True)"
|
||||
"qa = VectorDBQA.from_chain_type(llm=OpenAI(), chain_type=\"stuff\", vectorstore=docsearch, return_source_documents=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 16,
|
||||
"execution_count": 8,
|
||||
"id": "eac11321",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -260,17 +259,17 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 17,
|
||||
"execution_count": 10,
|
||||
"id": "7d75945a",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice and a former federal public defender from a family of public school educators and police officers, and that she has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
|
||||
"\" The president said that Ketanji Brown Jackson is one of our nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 17,
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@ -281,20 +280,20 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 18,
|
||||
"execution_count": 11,
|
||||
"id": "35b4f31f",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0),\n",
|
||||
" Document(page_content='A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \\n\\nAnd if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \\n\\nWe can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling. \\n\\nWe’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers. \\n\\nWe’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \\n\\nWe’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0),\n",
|
||||
" Document(page_content='And for our LGBTQ+ Americans, let’s finally get the bipartisan Equality Act to my desk. The onslaught of state laws targeting transgender Americans and their families is wrong. \\n\\nAs I said last year, especially to our younger transgender Americans, I will always have your back as your President, so you can be yourself and reach your God-given potential. \\n\\nWhile it often appears that we never agree, that isn’t true. I signed 80 bipartisan bills into law last year. From preventing government shutdowns to protecting Asian-Americans from still-too-common hate crimes to reforming military justice. \\n\\nAnd soon, we’ll strengthen the Violence Against Women Act that I first wrote three decades ago. It is important for us to show the nation that we can come together and do big things. \\n\\nSo tonight I’m offering a Unity Agenda for the Nation. Four big things we can do together. \\n\\nFirst, beat the opioid epidemic.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0),\n",
|
||||
" Document(page_content='Tonight, I’m announcing a crackdown on these companies overcharging American businesses and consumers. \\n\\nAnd as Wall Street firms take over more nursing homes, quality in those homes has gone down and costs have gone up. \\n\\nThat ends on my watch. \\n\\nMedicare is going to set higher standards for nursing homes and make sure your loved ones get the care they deserve and expect. \\n\\nWe’ll also cut costs and keep the economy going strong by giving workers a fair shot, provide more training and apprenticeships, hire them based on their skills not degrees. \\n\\nLet’s pass the Paycheck Fairness Act and paid leave. \\n\\nRaise the minimum wage to $15 an hour and extend the Child Tax Credit, so no one has to raise a family in poverty. \\n\\nLet’s increase Pell Grants and increase our historic support of HBCUs, and invest in what Jill—our First Lady who teaches full-time—calls America’s best-kept secret: community colleges.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0)]"
|
||||
"[Document(page_content='In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. \\n\\nWe cannot let this happen. \\n\\nTonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', lookup_str='', metadata={}, lookup_index=0),\n",
|
||||
" Document(page_content='A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \\n\\nAnd if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \\n\\nWe can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling. \\n\\nWe’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers. \\n\\nWe’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \\n\\nWe’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.', lookup_str='', metadata={}, lookup_index=0),\n",
|
||||
" Document(page_content='And for our LGBTQ+ Americans, let’s finally get the bipartisan Equality Act to my desk. The onslaught of state laws targeting transgender Americans and their families is wrong. \\n\\nAs I said last year, especially to our younger transgender Americans, I will always have your back as your President, so you can be yourself and reach your God-given potential. \\n\\nWhile it often appears that we never agree, that isn’t true. I signed 80 bipartisan bills into law last year. From preventing government shutdowns to protecting Asian-Americans from still-too-common hate crimes to reforming military justice. \\n\\nAnd soon, we’ll strengthen the Violence Against Women Act that I first wrote three decades ago. It is important for us to show the nation that we can come together and do big things. \\n\\nSo tonight I’m offering a Unity Agenda for the Nation. Four big things we can do together. \\n\\nFirst, beat the opioid epidemic.', lookup_str='', metadata={}, lookup_index=0),\n",
|
||||
" Document(page_content='As I’ve told Xi Jinping, it is never a good bet to bet against the American people. \\n\\nWe’ll create good jobs for millions of Americans, modernizing roads, airports, ports, and waterways all across America. \\n\\nAnd we’ll do it all to withstand the devastating effects of the climate crisis and promote environmental justice. \\n\\nWe’ll build a national network of 500,000 electric vehicle charging stations, begin to replace poisonous lead pipes—so every child—and every American—has clean water to drink at home and at school, provide affordable high-speed internet for every American—urban, suburban, rural, and tribal communities. \\n\\n4,000 projects have already been announced. \\n\\nAnd tonight, I’m announcing that this year we will start fixing over 65,000 miles of highway and 1,500 bridges in disrepair. \\n\\nWhen we use taxpayer dollars to rebuild America – we are going to Buy American: buy American products to support American jobs.', lookup_str='', metadata={}, lookup_index=0)]"
|
||||
]
|
||||
},
|
||||
"execution_count": 18,
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
|
@ -5,9 +5,9 @@
|
||||
"id": "efc5be67",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Retrieval Question Answering with Sources\n",
|
||||
"# VectorDB Question Answering with Sources\n",
|
||||
"\n",
|
||||
"This notebook goes over how to do question-answering with sources over an Index. It does this by using the `RetrievalQAWithSourcesChain`, which does the lookup of the documents from an Index. "
|
||||
"This notebook goes over how to do question-answering with sources over a vector database. It does this by using the `VectorDBQAWithSourcesChain`, which does the lookup of the documents from a vector database. "
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -21,7 +21,7 @@
|
||||
"from langchain.embeddings.cohere import CohereEmbeddings\n",
|
||||
"from langchain.text_splitter import CharacterTextSplitter\n",
|
||||
"from langchain.vectorstores.elastic_vector_search import ElasticVectorSearch\n",
|
||||
"from langchain.vectorstores import Chroma"
|
||||
"from langchain.vectorstores import Chromaoma"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -41,7 +41,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": 5,
|
||||
"id": "0e745d99",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@ -50,7 +50,8 @@
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Running Chroma using direct local API.\n",
|
||||
"Using DuckDB in-memory for database. Data will be transient.\n"
|
||||
"Using DuckDB in-memory for database. Data will be transient.\n",
|
||||
"Exiting: Cleaning up .chroma directory\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@ -60,40 +61,40 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": 6,
|
||||
"id": "8aa571ae",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chains import RetrievalQAWithSourcesChain"
|
||||
"from langchain.chains import VectorDBQAWithSourcesChain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"execution_count": 7,
|
||||
"id": "aa859d4c",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain import OpenAI\n",
|
||||
"\n",
|
||||
"chain = RetrievalQAWithSourcesChain.from_chain_type(OpenAI(temperature=0), chain_type=\"stuff\", retriever=docsearch.as_retriever())"
|
||||
"chain = VectorDBQAWithSourcesChain.from_chain_type(OpenAI(temperature=0), chain_type=\"stuff\", vectorstore=docsearch)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"execution_count": 8,
|
||||
"id": "8ba36fa7",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'answer': ' The president honored Justice Breyer for his service and mentioned his legacy of excellence.\\n',\n",
|
||||
" 'sources': '31-pl'}"
|
||||
"{'answer': ' The president thanked Justice Breyer for his service and mentioned his legacy of excellence.\\n',\n",
|
||||
" 'sources': '30-pl'}"
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@ -108,35 +109,35 @@
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Chain Type\n",
|
||||
"You can easily specify different chain types to load and use in the RetrievalQAWithSourcesChain chain. For a more detailed walkthrough of these types, please see [this notebook](qa_with_sources.ipynb).\n",
|
||||
"You can easily specify different chain types to load and use in the VectorDBQAWithSourcesChain chain. For a more detailed walkthrough of these types, please see [this notebook](qa_with_sources.ipynb).\n",
|
||||
"\n",
|
||||
"There are two ways to load different chain types. First, you can specify the chain type argument in the `from_chain_type` method. This allows you to pass in the name of the chain type you want to use. For example, in the below we change the chain type to `map_reduce`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"execution_count": 8,
|
||||
"id": "8b35b30a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chain = RetrievalQAWithSourcesChain.from_chain_type(OpenAI(temperature=0), chain_type=\"map_reduce\", retriever=docsearch.as_retriever())"
|
||||
"chain = VectorDBQAWithSourcesChain.from_chain_type(OpenAI(temperature=0), chain_type=\"map_reduce\", vectorstore=docsearch)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"execution_count": 9,
|
||||
"id": "58bd424f",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'answer': ' The president said \"Justice Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service.\"\\n',\n",
|
||||
" 'sources': '31-pl'}"
|
||||
"{'answer': ' The president honored Justice Stephen Breyer for his service.\\n',\n",
|
||||
" 'sources': '30-pl'}"
|
||||
]
|
||||
},
|
||||
"execution_count": 8,
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@ -150,19 +151,19 @@
|
||||
"id": "21e14eed",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The above way allows you to really simply change the chain_type, but it does provide a ton of flexibility over parameters to that chain type. If you want to control those parameters, you can load the chain directly (as you did in [this notebook](qa_with_sources.ipynb)) and then pass that directly to the the RetrievalQAWithSourcesChain chain with the `combine_documents_chain` parameter. For example:"
|
||||
"The above way allows you to really simply change the chain_type, but it does provide a ton of flexibility over parameters to that chain type. If you want to control those parameters, you can load the chain directly (as you did in [this notebook](qa_with_sources.ipynb)) and then pass that directly to the the VectorDBQA chain with the `combine_documents_chain` parameter. For example:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"execution_count": 12,
|
||||
"id": "af35f0c6",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chains.qa_with_sources import load_qa_with_sources_chain\n",
|
||||
"qa_chain = load_qa_with_sources_chain(OpenAI(temperature=0), chain_type=\"stuff\")\n",
|
||||
"qa = RetrievalQAWithSourcesChain(combine_documents_chain=qa_chain, retriever=docsearch.as_retriever())"
|
||||
"qa = VectorDBQAWithSourcesChain(combine_documents_chain=qa_chain, vectorstore=docsearch)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -174,8 +175,8 @@
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'answer': ' The president honored Justice Breyer for his service and mentioned his legacy of excellence.\\n',\n",
|
||||
" 'sources': '31-pl'}"
|
||||
"{'answer': ' The president honored Justice Stephen Breyer for his service.\\n',\n",
|
||||
" 'sources': '30-pl'}"
|
||||
]
|
||||
},
|
||||
"execution_count": 11,
|
||||
@ -186,14 +187,6 @@
|
||||
"source": [
|
||||
"qa({\"question\": \"What did the president say about Justice Breyer\"}, return_only_outputs=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "3c594296",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
@ -222,4 +215,4 @@
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
}
|
@ -28,7 +28,7 @@
|
||||
"from langchain.docstore.document import Document\n",
|
||||
"import requests\n",
|
||||
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
|
||||
"from langchain.vectorstores import Chroma\n",
|
||||
"from langchain.vectorstores import Chromama\n",
|
||||
"from langchain.text_splitter import CharacterTextSplitter\n",
|
||||
"from langchain.prompts import PromptTemplate\n",
|
||||
"import pathlib\n",
|
||||
|
@ -19,20 +19,20 @@ to pass to the language model. This is implemented in LangChain as the `StuffDoc
|
||||
|
||||
**Cons:** Most LLMs have a context length, and for large documents (or many documents) this will not work as it will result in a prompt larger than the context length.
|
||||
|
||||
The main downside of this method is that it only works on smaller pieces of data. Once you are working
|
||||
The main downside of this method is that it only works one smaller pieces of data. Once you are working
|
||||
with many pieces of data, this approach is no longer feasible. The next two approaches are designed to help deal with that.
|
||||
|
||||
## Map Reduce
|
||||
This method involves running an initial prompt on each chunk of data (for summarization tasks, this
|
||||
This method involves an initial prompt on each chunk of data (for summarization tasks, this
|
||||
could be a summary of that chunk; for question-answering tasks, it could be an answer based solely on that chunk).
|
||||
Then a different prompt is run to combine all the initial outputs. This is implemented in the LangChain as the `MapReduceDocumentsChain`.
|
||||
|
||||
**Pros:** Can scale to larger documents (and more documents) than `StuffDocumentsChain`. The calls to the LLM on individual documents are independent and can therefore be parallelized.
|
||||
|
||||
**Cons:** Requires many more calls to the LLM than `StuffDocumentsChain`. Loses some information during the final combined call.
|
||||
**Cons:** Requires many more calls to the LLM than `StuffDocumentsChain`. Loses some information during the final combining call.
|
||||
|
||||
## Refine
|
||||
This method involves running an initial prompt on the first chunk of data, generating some output.
|
||||
This method involves an initial prompt on the first chunk of data, generating some output.
|
||||
For the remaining documents, that output is passed in, along with the next document,
|
||||
asking the LLM to refine the output based on the new document.
|
||||
|
||||
@ -46,6 +46,6 @@ This method involves running an initial prompt on each chunk of data, that not o
|
||||
task but also gives a score for how certain it is in its answer. The responses are then
|
||||
ranked according to this score, and the highest score is returned.
|
||||
|
||||
**Pros:** Similar pros as `MapReduceDocumentsChain`. Requires fewer calls, compared to `MapReduceDocumentsChain`.
|
||||
**Pros:** Similar pros as `MapReduceDocumentsChain`. Compared to `MapReduceDocumentsChain`, it requires fewer calls.
|
||||
|
||||
**Cons:** Cannot combine information between documents. This means it is most useful when you expect there to be a single simple answer in a single document.
|
||||
|
@ -76,129 +76,6 @@
|
||||
"doc_result = embeddings.embed_documents([text])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "bb61bbeb",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Let's load the OpenAI Embedding class with first generation models (e.g. text-search-ada-doc-001/text-search-ada-query-001). Note: These are not recommended models - see [here](https://platform.openai.com/docs/guides/embeddings/what-are-embeddings)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "c0b072cc",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings.openai import OpenAIEmbeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "a56b70f5",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings = OpenAIEmbeddings(model_name=\"ada\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "14aefb64",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"text = \"This is a test document.\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "3c39ed33",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = embeddings.embed_query(text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "e3221db6",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_result = embeddings.embed_documents([text])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "c3852491",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## AzureOpenAI\n",
|
||||
"\n",
|
||||
"Let's load the OpenAI Embedding class with environment variables set to indicate to use Azure endpoints."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "1b40f827",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# set the environment variables needed for openai package to know to reach out to azure\n",
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"OPENAI_API_TYPE\"] = \"azure\"\n",
|
||||
"os.environ[\"OPENAI_API_BASE\"] = \"https://<your-endpoint.openai.azure.com/\"\n",
|
||||
"os.environ[\"OPENAI_API_KEY\"] = \"your AzureOpenAI key\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "bb36d16c",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings = OpenAIEmbeddings(model=\"your-embeddings-deployment-name\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "228abcbb",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"text = \"This is a test document.\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "60dd7fad",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = embeddings.embed_query(text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "83bc1a72",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_result = embeddings.embed_documents([text])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "42f76e43",
|
||||
@ -209,12 +86,6 @@
|
||||
"Let's load the Cohere Embedding class."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "ca9e2b3a",
|
||||
"metadata": {},
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
@ -232,7 +103,7 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings = CohereEmbeddings(cohere_api_key=cohere_api_key)"
|
||||
"embeddings = CohereEmbeddings(cohere_api_key= cohere_api_key)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -419,9 +290,7 @@
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"embeddings = HuggingFaceInstructEmbeddings(\n",
|
||||
" query_instruction=\"Represent the query for retrieval: \"\n",
|
||||
")"
|
||||
"embeddings = HuggingFaceInstructEmbeddings(query_instruction=\"Represent the query for retrieval: \")"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -463,9 +332,9 @@
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings import (\n",
|
||||
" SelfHostedEmbeddings,\n",
|
||||
" SelfHostedHuggingFaceEmbeddings,\n",
|
||||
" SelfHostedHuggingFaceInstructEmbeddings,\n",
|
||||
" SelfHostedEmbeddings, \n",
|
||||
" SelfHostedHuggingFaceEmbeddings, \n",
|
||||
" SelfHostedHuggingFaceInstructEmbeddings\n",
|
||||
")\n",
|
||||
"import runhouse as rh"
|
||||
]
|
||||
@ -484,7 +353,7 @@
|
||||
"# gpu = rh.cluster(name='rh-a10x', instance_type='g5.2xlarge', provider='aws')\n",
|
||||
"\n",
|
||||
"# For an existing cluster\n",
|
||||
"# gpu = rh.cluster(ips=['<ip of the cluster>'],\n",
|
||||
"# gpu = rh.cluster(ips=['<ip of the cluster>'], \n",
|
||||
"# ssh_creds={'ssh_user': '...', 'ssh_private_key':'<path_to_key>'},\n",
|
||||
"# name='my-cluster')"
|
||||
]
|
||||
@ -555,22 +424,16 @@
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def get_pipeline():\n",
|
||||
" from transformers import (\n",
|
||||
" AutoModelForCausalLM,\n",
|
||||
" AutoTokenizer,\n",
|
||||
" pipeline,\n",
|
||||
" ) # Must be inside the function in notebooks\n",
|
||||
"\n",
|
||||
" from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline # Must be inside the function in notebooks\n",
|
||||
" model_id = \"facebook/bart-base\"\n",
|
||||
" tokenizer = AutoTokenizer.from_pretrained(model_id)\n",
|
||||
" model = AutoModelForCausalLM.from_pretrained(model_id)\n",
|
||||
" return pipeline(\"feature-extraction\", model=model, tokenizer=tokenizer)\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def inference_fn(pipeline, prompt):\n",
|
||||
" # Return last hidden state of the model\n",
|
||||
" if isinstance(prompt, list):\n",
|
||||
" return [emb[0][-1] for emb in pipeline(prompt)]\n",
|
||||
" return [emb[0][-1] for emb in pipeline(prompt)] \n",
|
||||
" return pipeline(prompt)[0][-1]"
|
||||
]
|
||||
},
|
||||
@ -582,10 +445,10 @@
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings = SelfHostedEmbeddings(\n",
|
||||
" model_load_fn=get_pipeline,\n",
|
||||
" model_load_fn=get_pipeline, \n",
|
||||
" hardware=gpu,\n",
|
||||
" model_reqs=[\"./\", \"torch\", \"transformers\"],\n",
|
||||
" inference_fn=inference_fn,\n",
|
||||
" inference_fn=inference_fn\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
@ -600,153 +463,6 @@
|
||||
"source": [
|
||||
"query_result = embeddings.embed_query(text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f9c02c78",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Fake Embeddings\n",
|
||||
"\n",
|
||||
"LangChain also provides a fake embedding class. You can use this to test your pipelines."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "2ffc2e4b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings import FakeEmbeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "80777571",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeddings = FakeEmbeddings(size=1352)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "3ec9d8f0",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = embeddings.embed_query(\"foo\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "3b9ae9e1",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_results = embeddings.embed_documents([\"foo\"])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "1f83f273",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## SageMaker Endpoint Embeddings\n",
|
||||
"\n",
|
||||
"Let's load the SageMaker Endpoints Embeddings class. The class can be used if you host, e.g. your own Hugging Face model on SageMaker.\n",
|
||||
"\n",
|
||||
"For instrucstions on how to do this, please see [here](https://www.philschmid.de/custom-inference-huggingface-sagemaker)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "88d366bd",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip3 install langchain boto3"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "1e9b926a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from typing import Dict\n",
|
||||
"from langchain.embeddings import SagemakerEndpointEmbeddings\n",
|
||||
"from langchain.llms.sagemaker_endpoint import ContentHandlerBase\n",
|
||||
"import json\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"class ContentHandler(ContentHandlerBase):\n",
|
||||
" content_type = \"application/json\"\n",
|
||||
" accepts = \"application/json\"\n",
|
||||
"\n",
|
||||
" def transform_input(self, prompt: str, model_kwargs: Dict) -> bytes:\n",
|
||||
" input_str = json.dumps({\"inputs\": prompt, **model_kwargs})\n",
|
||||
" return input_str.encode('utf-8')\n",
|
||||
" \n",
|
||||
" def transform_output(self, output: bytes) -> str:\n",
|
||||
" response_json = json.loads(output.read().decode(\"utf-8\"))\n",
|
||||
" return response_json[\"embeddings\"]\n",
|
||||
"\n",
|
||||
"content_handler = ContentHandler()\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"embeddings = SagemakerEndpointEmbeddings(\n",
|
||||
" # endpoint_name=\"endpoint-name\", \n",
|
||||
" # credentials_profile_name=\"credentials-profile-name\", \n",
|
||||
" endpoint_name=\"huggingface-pytorch-inference-2023-03-21-16-14-03-834\", \n",
|
||||
" region_name=\"us-east-1\", \n",
|
||||
" content_handler=content_handler\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "fe9797b8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = embeddings.embed_query(\"foo\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "76f1b752",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_results = embeddings.embed_documents([\"foo\"])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "fff99b21",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_results"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "aaad49f8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
@ -765,11 +481,11 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
"version": "3.10.9"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "7377c2ccc78bc62c2683122d48c8cd1fb85a53850a1b1fc29736ed39852c9885"
|
||||
"hash": "ce6f9b0d7cdac41515b0e0c38d0e6e153a2edce81d579281cb1ab99da6e8ea6d"
|
||||
}
|
||||
}
|
||||
},
|
||||
|
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue
Block a user