cr

.dockerignore

@@ -1,144 +0,0 @@
-.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

.flake8

@@ -1,6 +1,5 @@
 [flake8]
 exclude =
-    venv
     .venv
     __pycache__
     notebooks

.github/workflows/linkcheck.yml

@@ -1,36 +0,0 @@
-name: linkcheck
-
-on:
-  push:
-    branches: [master]
-  pull_request:
-
-env:
-  POETRY_VERSION: "1.3.1"
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.11"
-    steps:
-      - uses: actions/checkout@v3
-      - name: Install poetry
-        run: |
-          pipx install poetry==$POETRY_VERSION
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: poetry
-      - name: Install dependencies
-        run: |
-          poetry install --with docs
-      - name: Build the docs
-        run: |
-          make docs_build
-      - name: Analyzing the docs with linkcheck
-        run: |
-          make docs_linkcheck

.github/workflows/lint.yml

@@ -1,36 +1,23 @@
 name: lint
 
-on:
-  push:
-    branches: [master]
-  pull_request:
-
-env:
-  POETRY_VERSION: "1.3.1"
+on: [push, pull_request]
 
 jobs:
   build:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
+        python-version: ["3.7"]
     steps:
     - uses: actions/checkout@v3
-      - name: Install poetry
-        run: |
-          pipx install poetry==$POETRY_VERSION
     - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
+      uses: actions/setup-python@v3
       with:
         python-version: ${{ matrix.python-version }}
-          cache: poetry
     - name: Install dependencies
       run: |
-          poetry install
+        python -m pip install --upgrade pip
+        pip install -r test_requirements.txt
     - name: Analysing the code with our lint
       run: |
         make lint

.github/workflows/release.yml

@@ -1,49 +0,0 @@
-name: release
-
-on:
-  pull_request:
-    types:
-      - closed
-    branches:
-      - master
-    paths:
-      - 'pyproject.toml'
-
-env:
-  POETRY_VERSION: "1.3.1"
-
-jobs:
-  if_release:
-    if: |
-        ${{ github.event.pull_request.merged == true }}
-        && ${{ contains(github.event.pull_request.labels.*.name, 'release') }}
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-      - name: Install poetry
-        run: pipx install poetry==$POETRY_VERSION
-      - name: Set up Python 3.10
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.10"
-          cache: "poetry"
-      - name: Build project for distribution
-        run: poetry build
-      - name: Check Version
-        id: check-version
-        run: |
-          echo version=$(poetry version --short) >> $GITHUB_OUTPUT
-      - name: Create Release
-        uses: ncipollo/release-action@v1
-        with:
-          artifacts: "dist/*"
-          token: ${{ secrets.GITHUB_TOKEN }}
-          draft: false
-          generateReleaseNotes: true
-          tag: v${{ steps.check-version.outputs.version }}
-          commit: master
-      - name: Publish to PyPI
-        env:
-          POETRY_PYPI_TOKEN_PYPI: ${{ secrets.PYPI_API_TOKEN }}
-        run: | 
-          poetry publish

.github/workflows/test.yml

@@ -1,34 +1,23 @@
 name: test
 
-on:
-  push:
-    branches: [master]
-  pull_request:
-
-env:
-  POETRY_VERSION: "1.3.1"
+on: [push, pull_request]
 
 jobs:
   build:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
+        python-version: ["3.7"]
     steps:
     - uses: actions/checkout@v3
-      - name: Install poetry
-        run: pipx install poetry==$POETRY_VERSION
     - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
+      uses: actions/setup-python@v3
       with:
         python-version: ${{ matrix.python-version }}
-          cache: "poetry"
     - name: Install dependencies
-        run: poetry install
+      run: |
+        python -m pip install --upgrade pip
+        pip install -r test_requirements.txt
     - name: Run unit tests
       run: |
-          make test
+        make tests

.gitignore

@@ -1,5 +1,4 @@
 .vscode/
-.idea/
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
@@ -106,9 +105,7 @@ celerybeat.pid
 
 # Environments
 .env
-!docker/.env
 .venv
-.venvs
 env/
 venv/
 ENV/
@@ -132,7 +129,3 @@ dmypy.json
 
 # Pyre type checker
 .pyre/
-
-# macOS display setting files
-.DS_Store
-docker.build

CITATION.cff

@@ -1,8 +0,0 @@
-cff-version: 1.2.0
-message: "If you use this software, please cite it as below."
-authors:
-- family-names: "Chase"
-  given-names: "Harrison"
-title: "LangChain"
-date-released: 2022-10-17
-url: "https://github.com/hwchase17/langchain"

CONTRIBUTING.md

@@ -1,186 +0,0 @@
-# Contributing to LangChain
-
-Hi there! Thank you for even being interested in contributing to LangChain.
-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.
-
-To contribute to this project, please follow a ["fork and pull request"](https://docs.github.com/en/get-started/quickstart/contributing-to-projects) workflow.
-Please do not try to push directly to this repo unless you are maintainer.
-
-## 🗺️Contributing Guidelines
-
-### 🚩GitHub Issues
-
-Our [issues](https://github.com/hwchase17/langchain/issues) page is kept up to date
-with bugs, improvements, and feature requests. There is a taxonomy of labels to help
-with sorting and discovery of issues of interest. These include:
-
-- prompts: related to prompt tooling/infra.
-- llms: related to LLM wrappers/tooling/infra.
-- chains
-- utilities: related to different types of utilities to integrate with (Python, SQL, etc.).
-- agents
-- memory
-- applications: related to example applications to build
-
-If you start working on an issue, please assign it to yourself.
-
-If you are adding an issue, please try to keep it focused on a single modular bug/improvement/feature.
-If the two issues are related, or blocking, please link them rather than keep them as one single one.
-
-We will try to keep these issues as up to date as possible, though
-with the rapid rate of develop in this field some may get out of date.
-If you notice this happening, please just let us know.
-
-### 🙋Getting Help
-
-Although we try to have a developer setup to make it as easy as possible for others to contribute (see below)
-it is possible that some pain point may arise around environment setup, linting, documentation, or other.
-Should that occur, please contact a maintainer! Not only do we want to help get you unblocked,
-but we also want to make sure that the process is smooth for future contributors.
-
-In a similar vein, we do enforce certain linting, formatting, and documentation standards in the codebase.
-If you are finding these difficult (or even just annoying) to work with,
-feel free to contact a maintainer for help - we do not want these to get in the way of getting
-good code into the codebase.
-
-### 🏭Release process
-
-As of now, LangChain has an ad hoc release process: releases are cut with high frequency via by
-a developer and published to [PyPI](https://pypi.org/project/langchain/).
-
-LangChain follows the [semver](https://semver.org/) versioning standard. However, as pre-1.0 software,
-even patch releases may contain [non-backwards-compatible changes](https://semver.org/#spec-item-4).
-
-If your contribution has made its way into a release, we will want to give you credit on Twitter (only if you want though)!
-If you have a Twitter account you would like us to mention, please let us know in the PR or in another manner.
-
-## 🚀Quick Start
-
-This project uses [Poetry](https://python-poetry.org/) as a dependency manager. Check out Poetry's [documentation on how to install it](https://python-poetry.org/docs/#installation) on your system before proceeding.
-
-❗Note: If you use `Conda` or `Pyenv` as your environment / package manager, avoid dependency conflicts by doing the following first:
-1. *Before installing Poetry*, create and activate a new Conda env (e.g. `conda create -n langchain python=3.9`)
-2. Install Poetry (see above)
-3. Tell Poetry to use the virtualenv python environment (`poetry config virtualenvs.prefer-active-python true`)
-4. Continue with the following steps.
-
-To install requirements:
-
-```bash
-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.
-
-Now, you should be able to run the common tasks in the following section.
-
-## ✅Common Tasks
-
-Type `make` for a list of common tasks.
-
-### Code Formatting
-
-Formatting for this project is done via a combination of [Black](https://black.readthedocs.io/en/stable/) and [isort](https://pycqa.github.io/isort/).
-
-To run formatting for this project:
-
-```bash
-make format
-```
-
-### Linting
-
-Linting for this project is done via a combination of [Black](https://black.readthedocs.io/en/stable/), [isort](https://pycqa.github.io/isort/), [flake8](https://flake8.pycqa.org/en/latest/), and [mypy](http://mypy-lang.org/).
-
-To run linting for this project:
-
-```bash
-make lint
-```
-
-We recognize linting can be annoying - if you do not want to do it, please contact a project maintainer, and they can help you with it. We do not want this to be a blocker for good code getting contributed.
-
-### Coverage
-
-Code coverage (i.e. the amount of code that is covered by unit tests) helps identify areas of the code that are potentially more or less brittle.
-
-To get a report of current coverage, run the following:
-
-```bash
-make coverage
-```
-
-### Testing
-
-Unit tests cover modular logic that does not require calls to outside APIs.
-
-To run unit tests:
-
-```bash
-make test
-```
-
-If you add new logic, please add a unit test.
-
-Integration tests cover logic that requires making calls to outside APIs (often integration with other services).
-
-To run integration tests:
-
-```bash
-make integration_tests
-```
-
-If you add support for a new external API, please add a new integration test.
-
-### Adding a Jupyter Notebook
-
-If you are adding a Jupyter notebook example, you'll want to install the optional `dev` dependencies.
-
-To install dev dependencies:
-
-```bash
-poetry install --with dev
-```
-
-Launch a notebook:
-
-```bash
-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
-
-Docs are largely autogenerated by [sphinx](https://www.sphinx-doc.org/en/master/) from the code.
-
-For that reason, we ask that you add good documentation to all classes and methods.
-
-Similar to linting, we recognize documentation can be annoying. If you do not want to do it, please contact a project maintainer, and they can help you with it. We do not want this to be a blocker for good code getting contributed.
-
-### Build Documentation Locally
-
-Before building the documentation, it is always a good idea to clean the build directory:
-
-```bash
-make docs_clean
-```
-
-Next, you can run the linkchecker to make sure all links are valid:
-
-```bash
-make docs_linkcheck
-```
-
-Finally, you can build the documentation as outlined below:
-
-```bash
-make docs_build
-```

MANIFEST.in

@@ -0,0 +1,3 @@
+include langchain/py.typed
+include langchain/VERSION
+include LICENSE

Makefile

@@ -1,73 +1,17 @@
-.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:
-	poetry run pytest --cov \
-		--cov-config=.coveragerc \
-		--cov-report xml \
-		--cov-report term-missing:skip-covered
-
-clean: docs_clean
-
-docs_build:
-	cd docs && poetry run make html
-
-docs_clean:
-	cd docs && poetry run make clean
-
-docs_linkcheck:
-	poetry run linkchecker docs/_build/html/index.html
+.PHONY: format lint tests integration_tests
 
 format:
-	poetry run black .
-	poetry run ruff --select I --fix .
+	black .
+	isort .
 
 lint:
-	poetry run mypy .
-	poetry run black . --check
-	poetry run ruff .
+	mypy .
+	black . --check
+	isort . --check
+	flake8 .
 
-test:
-	poetry run pytest tests/unit_tests
-
-tests: test
-
-test_watch:
-	poetry run ptw --now . -- tests/unit_tests
+tests:
+	pytest tests/unit_tests
 
 integration_tests:
-	poetry run pytest tests/integration_tests
-
-help:
-	@echo '----'
-	@echo 'coverage            - run unit tests and generate coverage report'
-	@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
-	
+	pytest tests/integration_tests

README.md

@@ -1,15 +1,8 @@
-# 🦜️🔗 LangChain - Docker
+# 🦜️🔗 LangChain
 
-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.
+⚡ Building applications with LLMs through composability ⚡
 
-Currently exploring the following:
-
--  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.
+[![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) [![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)
 
 ## Quick Install
 
@@ -20,67 +13,79 @@ Currently exploring the following:
 Large language models (LLMs) are emerging as a transformative technology, enabling
 developers to build applications that they previously could not.
 But using these LLMs in isolation is often not enough to
-create a truly powerful app - the real power comes when you can combine them with other sources of computation or knowledge.
+create a truly powerful app - the real power comes when you are able to
+combine them with other sources of computation or knowledge.
 
-This library is aimed at assisting in the development of those types of applications. Common examples of these types of applications include:
-
-**❓ Question Answering over specific documents**
-
-- [Documentation](https://langchain.readthedocs.io/en/latest/use_cases/question_answering.html)
-- End-to-end Example: [Question Answering over Notion Database](https://github.com/hwchase17/notion-qa)
-
-**💬 Chatbots**
-
-- [Documentation](https://langchain.readthedocs.io/en/latest/use_cases/chatbots.html)
-- End-to-end Example: [Chat-LangChain](https://github.com/hwchase17/chat-langchain)
-
-**🤖 Agents**
-
-- [Documentation](https://langchain.readthedocs.io/en/latest/use_cases/agents.html)
-- End-to-end Example: [GPT+WolframAlpha](https://huggingface.co/spaces/JavaFXpert/Chat-GPT-LangChain)
+This library is aimed at assisting in the development of those types of applications.
 
 ## 📖 Documentation
 
 Please see [here](https://langchain.readthedocs.io/en/latest/?) for full documentation on:
-
-- Getting started (installation, setting up the environment, simple examples)
+- Getting started (installation, setting up 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?
 
-There are six main areas that LangChain is designed to help with.
+There are three main areas (with a forth coming soon) that LangChain is designed to help with.
 These are, in increasing order of complexity:
+1. LLM and Prompt usage
+2. Chaining LLMs with other tools in a deterministic manner
+3. Having a router LLM which uses other tools as needed
+4. (Coming Soon) Memory
 
-**📃 LLMs and Prompts:**
+### LLMs and Prompts
+Calling out to an LLM once is pretty easy, with most of them being behind well documented APIs.
+However, there are still some challenges going from that to an application running in production that LangChain attempts to address:
+- Easy switching costs: by exposing a standard interface for all the top LLM providers, LangChain makes it easy to switch from one provider to another, whether it be for production use cases or just for testing stuff out.
+- Prompt management: managing your prompts is easy when you only have one simple one, but can get tricky when you have a bunch or when they start to get more complex. LangChain provides a standard way for storing, constructing, and referencing prompts.
+- Prompt optimization: despite the underlying models getting better and better, there is still currently a need for carefully constructing prompts. 
+- More coming soon
 
-This includes prompt management, prompt optimization, generic interface for all LLMs, and common utilities for working with LLMs.
+### Chains
+Using an LLM in isolation is fine for some simple applications, but many more complex ones require chaining LLMs - either with eachother or with other tools.
+LangChain provides several parts to help with that:
+- Standard interface for working with Chains
+- Easy way to construct chains of LLMs
+- Lots of integrations with other tools that you may want to use in conjunction with LLMs (search, databases, Python REPL, etc)
+- End-to-end chains for common workflows (database question/answer, recursive summarization, etc)
 
-**🔗 Chains:**
+### Routing Chains
+Some applications will require not just a predetermined chain of calls to LLMs/other tools, but potentially an unknown chain that depends on the user input.
+In these types of chains, there is a "router" LLM chain which has access to a suite of tools.
+Depending on the user input, the router can then decide which, if any, of these tools to call.
+To help develop applications like these, LangChain provides:
+- Standard router and router chain interfaces
+- Common router LLM chains from literature
+- Common chains that can be used as tools
 
-Chains 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.
+### Memory
+Coming soon.
 
-**📚 Data Augmented Generation:**
+## 🤖 Developer Guide
 
-Data 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.
+To begin developing on this project, first clone to the repo locally.
+To install requirements, run `pip install -r requirements.txt`.
+This will install all requirements for running the package, examples, linting, formatting, and tests.
 
-**🤖 Agents:**
+Formatting for this project is a combination of [Black](https://black.readthedocs.io/en/stable/) and [isort](https://pycqa.github.io/isort/).
+To run formatting for this project, run `make format`.
 
-Agents 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.
+Linting for this project is a combination of [Black](https://black.readthedocs.io/en/stable/), [isort](https://pycqa.github.io/isort/), [flake8](https://flake8.pycqa.org/en/latest/), and [mypy](http://mypy-lang.org/).
+To run linting for this project, run `make lint`.
+We recognize linting can be annoying - if you do not want to do it, please contact a project maintainer and they can help you with it. We do not want this to be a blocker for good code getting contributed.
 
-**🧠 Memory:**
+Unit tests cover modular logic that does not require calls to outside apis.
+To run unit tests, run `make tests`.
+If you add new logic, please add a unit test.
 
-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.
+Integration tests cover logic that requires making calls to outside APIs (often integration with other services).
+To run integration tests, run `make integration_tests`.
+If you add support for a new external API, please add a new integration test.
 
-**🧐 Evaluation:**
+If you are adding a Jupyter notebook example, you can run `pip install -e .` to build the langchain package from your local changes, so your new logic can be imported into the notebook.
 
-[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.
-
-For more information on these concepts, please see our [full documentation](https://langchain.readthedocs.io/en/latest/?).
-
-## 💁 Contributing
-
-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](CONTRIBUTING.md).
+Docs are largely autogenerated by [sphinx](https://www.sphinx-doc.org/en/master/) from the code.
+For that reason, we ask that you add good documentation to all classes and methods.
+Similar to linting, we recognize documentation can be annoying - if you do not want to do it, please contact a project maintainer and they can help you with it. We do not want this to be a blocker for good code getting contributed.

docker/.env

@@ -1,13 +0,0 @@
-# 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:-}

docker/DOCKER.md

@@ -1,53 +0,0 @@
-# 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`.
-
-

docker/Dockerfile

@@ -1,104 +0,0 @@
-# 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"]

docker/Makefile

@@ -1,84 +0,0 @@
-#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 ... "

docker/assets/entry.sh

@@ -1,10 +0,0 @@
-#!/usr/bin/env bash
-
-export PATH=$HOME/.local/bin:$PATH
-
-if [ -z "$1" ]; then
-    cat /etc/motd
-    exec /bin/bash
-fi
-
-exec "$@"

docker/assets/etc/motd

@@ -1,8 +0,0 @@
-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.

docker/docker-compose.yml

@@ -1,17 +0,0 @@
-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

docs/_static/css/custom.css

@@ -1,13 +0,0 @@
-pre {
-  white-space: break-spaces;
-}
-
-@media (min-width: 1200px) {
-  .container,
-  .container-lg,
-  .container-md,
-  .container-sm,
-  .container-xl {
-    max-width: 2560px !important;
-  }
-}

docs/conf.py

@@ -15,21 +15,16 @@
 # import sys
 # sys.path.insert(0, os.path.abspath('.'))
 
-import toml
-
-with open("../pyproject.toml") as f:
-    data = toml.load(f)
+import langchain
 
 # -- Project information -----------------------------------------------------
 
-project = "🦜🔗 LangChain"
+project = "LangChain"
 copyright = "2022, Harrison Chase"
 author = "Harrison Chase"
 
-version = data["tool"]["poetry"]["version"]
-release = version
-
-html_title = project + " " + version
+version = langchain.__version__
+release = langchain.__version__
 
 
 # -- General configuration ---------------------------------------------------
@@ -44,11 +39,11 @@ extensions = [
     "sphinx.ext.napoleon",
     "sphinx.ext.viewcode",
     "sphinxcontrib.autodoc_pydantic",
-    "myst_nb",
+    "myst_parser",
+    "nbsphinx",
     "sphinx_panels",
-    "IPython.sphinxext.ipython_console_highlighting",
 ]
-source_suffix = [".ipynb", ".html", ".md", ".rst"]
+
 
 autodoc_pydantic_model_show_json = False
 autodoc_pydantic_field_list_validators = False
@@ -75,13 +70,8 @@ exclude_patterns = ["_build", "Thumbs.db", ".DS_Store"]
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
-html_theme = "sphinx_book_theme"
-
-html_theme_options = {
-    "path_to_docs": "docs",
-    "repository_url": "https://github.com/hwchase17/langchain",
-    "use_repository_button": True,
-}
+html_theme = "sphinx_rtd_theme"
+# html_theme = "sphinx_typlog_theme"
 
 html_context = {
     "display_github": True,  # Integrate GitHub
@@ -94,12 +84,4 @@ html_context = {
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ["_static"]
-
-# These paths are either relative to html_static_path
-# or fully qualified paths (eg. https://...)
-html_css_files = [
-    "css/custom.css",
-]
-nb_execution_mode = "off"
-myst_enable_extensions = ["colon_fence"]
+html_static_path: list = []

docs/deployments.md

@@ -1,39 +0,0 @@
-# Deployments
-
-So you've made a really cool chain - now what? How do you deploy it and make it easily sharable with the world?
-
-This section covers several options for that.
-Note that these are meant as quick deployment options for prototypes and demos, and not for production systems.
-If you are looking for help with deployment of a production system, please contact us directly.
-
-What follows is a list of template GitHub repositories aimed that are intended to be
-very easy to fork and modify to use your chain.
-This is far from an exhaustive list of options, and we are EXTREMELY open to contributions here.
-
-## [Streamlit](https://github.com/hwchase17/langchain-streamlit-template)
-
-This repo serves as a template for how to deploy a LangChain with Streamlit.
-It implements a chatbot interface.
-It also contains instructions for how to deploy this app on the Streamlit platform.
-
-## [Gradio (on Hugging Face)](https://github.com/hwchase17/langchain-gradio-template)
-
-This repo serves as a template for how deploy a LangChain with Gradio.
-It implements a chatbot interface, with a "Bring-Your-Own-Token" approach (nice for not wracking up big bills).
-It also contains instructions for how to deploy this app on the Hugging Face platform.
-This is heavily influenced by James Weaver's [excellent examples](https://huggingface.co/JavaFXpert).
-
-## [Beam](https://github.com/slai-labs/get-beam/tree/main/examples/langchain-question-answering)
-
-This repo serves as a template for how deploy a LangChain with [Beam](https://beam.cloud).
-
-It implements a Question Answering app and contains instructions for deploying the app as a serverless REST API.
-
-## [Vercel](https://github.com/homanp/vercel-langchain)
-
-A minimal example on how to run LangChain on Vercel using Flask.
-
-
-## [SteamShip](https://github.com/steamship-core/steamship-langchain/)
-This repository contains LangChain adapters for Steamship, enabling LangChain developers to rapidly deploy their apps on Steamship.
-This includes: production ready endpoints, horizontal scaling across dependencies, persistant storage of app state, multi-tenancy support, etc.

docs/ecosystem.rst

@@ -1,10 +0,0 @@
-LangChain Ecosystem
-===================
-
-Guides for how other companies/products can be used with LangChain
-
-.. toctree::
-   :maxdepth: 1
-   :glob:
-
-   ecosystem/*

docs/ecosystem/ai21.md

@@ -1,16 +0,0 @@
-# AI21 Labs
-
-This page covers how to use the AI21 ecosystem within LangChain.
-It is broken into two parts: installation and setup, and then references to specific AI21 wrappers.
-
-## Installation and Setup
-- Get an AI21 api key and set it as an environment variable (`AI21_API_KEY`)
-
-## Wrappers
-
-### LLM
-
-There exists an AI21 LLM wrapper, which you can access with 
-```python
-from langchain.llms import AI21
-```

docs/ecosystem/atlas.md

@@ -1,25 +0,0 @@
-# AtlasDB
-
-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 Nomic docs](https://docs.nomic.ai/atlas_api.html) for more detailed information.
-
-
-
-To import this vectorstore:
-```python
-from langchain.vectorstores import AtlasDB
-```
-
-For a more detailed walkthrough of the Chroma wrapper, see [this notebook](../modules/indexes/examples/vectorstores.ipynb)

docs/ecosystem/bananadev.md

@@ -1,79 +0,0 @@
-# Banana
-
-This page covers how to use the Banana ecosystem within LangChain.
-It is broken into two parts: installation and setup, and then references to specific Banana wrappers.
-
-## Installation and Setup
-
-- 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
-
-If you want to use an available language model template you can find one [here](https://app.banana.dev/templates/conceptofmind/serverless-template-palmyra-base).
-This template uses the Palmyra-Base model by [Writer](https://writer.com/product/api/).
-You can check out an example Banana repository [here](https://github.com/conceptofmind/serverless-template-palmyra-base).
-
-## Build the Banana app
-
-Banana Apps must include the "output" key in the return json. 
-There is a rigid response structure.
-
-```python
-# Return the results as a dictionary
-result = {'output': result}
-```
-
-An example inference function would be:
-
-```python
-def inference(model_inputs:dict) -> dict:
-    global model
-    global tokenizer
-
-    # Parse out your arguments
-    prompt = model_inputs.get('prompt', None)
-    if prompt == None:
-        return {'message': "No prompt provided"}
-
-    # Run the model
-    input_ids = tokenizer.encode(prompt, return_tensors='pt').cuda()
-    output = model.generate(
-        input_ids,
-        max_length=100,
-        do_sample=True,
-        top_k=50,
-        top_p=0.95,
-        num_return_sequences=1,
-        temperature=0.9,
-        early_stopping=True,
-        no_repeat_ngram_size=3,
-        num_beams=5,
-        length_penalty=1.5,
-        repetition_penalty=1.5,
-        bad_words_ids=[[tokenizer.encode(' ', add_prefix_space=True)[0]]]
-        )
-
-    result = tokenizer.decode(output[0], skip_special_tokens=True)
-    # Return the results as a dictionary
-    result = {'output': result}
-    return result
-```
-
-You can find a full example of a Banana app [here](https://github.com/conceptofmind/serverless-template-palmyra-base/blob/main/app.py).
-
-## Wrappers
-
-### LLM
-
-There exists an Banana LLM wrapper, which you can access with
-
-```python
-from langchain.llms import Banana
-```
-
-You need to provide a model key located in the dashboard:
-
-```python
-llm = Banana(model_key="YOUR_MODEL_KEY")
-```

docs/ecosystem/cerebriumai.md

@@ -1,17 +0,0 @@
-# CerebriumAI
-
-This page covers how to use the CerebriumAI ecosystem within LangChain.
-It is broken into two parts: installation and setup, and then references to specific CerebriumAI wrappers.
-
-## Installation and Setup
-- Install with `pip install cerebrium`
-- Get an CerebriumAI api key and set it as an environment variable (`CEREBRIUMAI_API_KEY`)
-
-## Wrappers
-
-### LLM
-
-There exists an CerebriumAI LLM wrapper, which you can access with 
-```python
-from langchain.llms import CerebriumAI
-```

docs/ecosystem/chroma.md

@@ -1,20 +0,0 @@
-# Chroma
-
-This page covers how to use the Chroma ecosystem within LangChain.
-It is broken into two parts: installation and setup, and then references to specific Chroma wrappers.
-
-## Installation and Setup
-- Install the Python package with `pip install chromadb`
-## Wrappers
-
-### VectorStore
-
-There exists a wrapper around Chroma 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 import Chroma
-```
-
-For a more detailed walkthrough of the Chroma wrapper, see [this notebook](../modules/indexes/examples/vectorstores.ipynb)

docs/ecosystem/cohere.md

@@ -1,25 +0,0 @@
-# Cohere
-
-This page covers how to use the Cohere ecosystem within LangChain.
-It is broken into two parts: installation and setup, and then references to specific Cohere wrappers.
-
-## Installation and Setup
-- Install the Python SDK with `pip install cohere`
-- Get an Cohere api key and set it as an environment variable (`COHERE_API_KEY`)
-
-## Wrappers
-
-### LLM
-
-There exists an Cohere LLM wrapper, which you can access with 
-```python
-from langchain.llms import Cohere
-```
-
-### Embeddings
-
-There exists an Cohere Embeddings wrapper, which you can access with 
-```python
-from langchain.embeddings import CohereEmbeddings
-```
-For a more detailed walkthrough of this, see [this notebook](../modules/indexes/examples/embeddings.ipynb)

docs/ecosystem/deepinfra.md

@@ -1,17 +0,0 @@
-# DeepInfra
-
-This page covers how to use the DeepInfra ecosystem within LangChain.
-It is broken into two parts: installation and setup, and then references to specific DeepInfra wrappers.
-
-## Installation and Setup
-- Get your DeepInfra api key from this link [here](https://deepinfra.com/).
-- Get an DeepInfra api key and set it as an environment variable (`DEEPINFRA_API_TOKEN`)
-
-## Wrappers
-
-### LLM
-
-There exists an DeepInfra LLM wrapper, which you can access with
-```python
-from langchain.llms import DeepInfra
-```

docs/ecosystem/deeplake.md

@@ -1,25 +0,0 @@
-# Deep Lake
-
-This page covers how to use the Deep Lake ecosystem within LangChain.
-It is broken into two parts: installation and setup, and then references to specific Deep Lake wrappers. For more information.
-
-1. Here is [whitepaper](https://www.deeplake.ai/whitepaper) and [academic paper](https://arxiv.org/pdf/2209.10785.pdf) for Deep Lake
-
-2. Here is a set of additional resources available for review: [Deep Lake](https://github.com/activeloopai/deeplake), [Getting Started](https://docs.activeloop.ai/getting-started) and [Tutorials](https://docs.activeloop.ai/hub-tutorials)
-
-## Installation and Setup
-- Install the Python package with `pip install deeplake`
-
-## Wrappers
-
-### VectorStore
-
-There exists a wrapper around Deep Lake, a data lake for Deep Learning applications, allowing you to use it as a vectorstore (for now), whether for semantic search or example selection.
-
-To import this vectorstore:
-```python
-from langchain.vectorstores import DeepLake
-```
-
-
-For a more detailed walkthrough of the Deep Lake wrapper, see [this notebook](../modules/indexes/vectorstore_examples/deeplake.ipynb)

docs/ecosystem/forefrontai.md

@@ -1,16 +0,0 @@
-# ForefrontAI
-
-This page covers how to use the ForefrontAI ecosystem within LangChain.
-It is broken into two parts: installation and setup, and then references to specific ForefrontAI wrappers.
-
-## Installation and Setup
-- Get an ForefrontAI api key and set it as an environment variable (`FOREFRONTAI_API_KEY`)
-
-## Wrappers
-
-### LLM
-
-There exists an ForefrontAI LLM wrapper, which you can access with 
-```python
-from langchain.llms import ForefrontAI
-```

docs/ecosystem/google_search.md

@@ -1,32 +0,0 @@
-# Google Search Wrapper
-
-This page covers how to use the Google Search API within LangChain.
-It is broken into two parts: installation and setup, and then references to the specific Google Search wrapper.
-
-## Installation and Setup
-- Install requirements with `pip install google-api-python-client`
-- Set up a Custom Search Engine, following [these instructions](https://stackoverflow.com/questions/37083058/programmatically-searching-google-in-python-using-custom-search)
-- Get an API Key and Custom Search Engine ID from the previous step, and set them as environment variables `GOOGLE_API_KEY` and `GOOGLE_CSE_ID` respectively
-
-## Wrappers
-
-### Utility
-
-There exists a GoogleSearchAPIWrapper utility which wraps this API. To import this utility:
-
-```python
-from langchain.utilities import GoogleSearchAPIWrapper
-```
-
-For a more detailed walkthrough of this wrapper, see [this notebook](../modules/utils/examples/google_search.ipynb).
-
-### Tool
-
-You can also easily load this wrapper as a Tool (to use with an Agent).
-You can do this with:
-```python
-from langchain.agents import load_tools
-tools = load_tools(["google-search"])
-```
-
-For more information on this, see [this page](../modules/agents/tools.md)

docs/ecosystem/google_serper.md

@@ -1,71 +0,0 @@
-# Google Serper Wrapper
-
-This page covers how to use the [Serper](https://serper.dev) Google Search API within LangChain. Serper is a low-cost Google Search API that can be used to add answer box, knowledge graph, and organic results data from Google Search. 
-It is broken into two parts: setup, and then references to the specific Google Serper wrapper.
-
-## Setup
-- Go to [serper.dev](https://serper.dev) to sign up for a free account
-- Get the api key and set it as an environment variable (`SERPER_API_KEY`)
-
-## Wrappers
-
-### Utility
-
-There exists a GoogleSerperAPIWrapper utility which wraps this API. To import this utility:
-
-```python
-from langchain.utilities import GoogleSerperAPIWrapper
-```
-
-You can use it as part of a Self Ask chain:
-
-```python
-from langchain.utilities import GoogleSerperAPIWrapper
-from langchain.llms.openai import OpenAI
-from langchain.agents import initialize_agent, Tool
-
-import os
-
-os.environ["SERPER_API_KEY"] = ""
-os.environ['OPENAI_API_KEY'] = ""
-
-llm = OpenAI(temperature=0)
-search = GoogleSerperAPIWrapper()
-tools = [
-    Tool(
-        name="Intermediate Answer",
-        func=search.run
-    )
-]
-
-self_ask_with_search = initialize_agent(tools, llm, agent="self-ask-with-search", verbose=True)
-self_ask_with_search.run("What is the hometown of the reigning men's U.S. Open champion?")
-```
-
-#### Output
-```
-Entering new AgentExecutor chain...
- Yes.
-Follow up: Who is the reigning men's U.S. Open champion?
-Intermediate answer: Current champions Carlos Alcaraz, 2022 men's singles champion.
-Follow up: Where is Carlos Alcaraz from?
-Intermediate answer: El Palmar, Spain
-So the final answer is: El Palmar, Spain
-
-> Finished chain.
-
-'El Palmar, Spain'
-```
-
-For a more detailed walkthrough of this wrapper, see [this notebook](../modules/utils/examples/google_serper.ipynb).
-
-### Tool
-
-You can also easily load this wrapper as a Tool (to use with an Agent).
-You can do this with:
-```python
-from langchain.agents import load_tools
-tools = load_tools(["google-serper"])
-```
-
-For more information on this, see [this page](../modules/agents/tools.md)

docs/ecosystem/gooseai.md

@@ -1,23 +0,0 @@
-# GooseAI
-
-This page covers how to use the GooseAI ecosystem within LangChain.
-It is broken into two parts: installation and setup, and then references to specific GooseAI wrappers.
-
-## Installation and Setup
-- Install the Python SDK with `pip install openai`
-- Get your GooseAI api key from this link [here](https://goose.ai/).
-- Set the environment variable (`GOOSEAI_API_KEY`).
-
-```python
-import os
-os.environ["GOOSEAI_API_KEY"] = "YOUR_API_KEY"
-```
-
-## Wrappers
-
-### LLM
-
-There exists an GooseAI LLM wrapper, which you can access with: 
-```python
-from langchain.llms import GooseAI
-```

docs/ecosystem/graphsignal.md

@@ -1,38 +0,0 @@
-# Graphsignal
-
-This page covers how to use the Graphsignal to trace and monitor LangChain.
-
-## Installation and Setup
-
-- Install the Python library with `pip install graphsignal`
-- Create free Graphsignal account [here](https://graphsignal.com)
-- Get an API key and set it as an environment variable (`GRAPHSIGNAL_API_KEY`)
-
-## Tracing and Monitoring
-
-Graphsignal automatically instruments and starts tracing and monitoring chains. Traces, metrics and errors are then available in your [Graphsignal dashboard](https://app.graphsignal.com/). No prompts or other sensitive data are sent to Graphsignal cloud, only statistics and metadata.
-
-Initialize the tracer by providing a deployment name:
-
-```python
-import graphsignal
-
-graphsignal.configure(deployment='my-langchain-app-prod')
-```
-
-In order to trace full runs and see a breakdown by chains and tools, you can wrap the calling routine or use a decorator:
-
-```python
-with graphsignal.start_trace('my-chain'):
-    chain.run("some initial text")
-```
-
-Optionally, enable profiling to record function-level statistics for each trace.
-
-```python
-with graphsignal.start_trace(
-        'my-chain', options=graphsignal.TraceOptions(enable_profiling=True)):
-    chain.run("some initial text")
-```
-
-See the [Quick Start](https://graphsignal.com/docs/guides/quick-start/) guide for complete setup instructions.

docs/ecosystem/hazy_research.md

@@ -1,19 +0,0 @@
-# Hazy Research
-
-This page covers how to use the Hazy Research ecosystem within LangChain.
-It is broken into two parts: installation and setup, and then references to specific Hazy Research wrappers.
-
-## Installation and Setup
-- To use the `manifest`, install it with `pip install manifest-ml`
-
-## Wrappers
-
-### LLM
-
-There exists an LLM wrapper around Hazy Research's `manifest` library. 
-`manifest` is a python library which is itself a wrapper around many model providers, and adds in caching, history, and more.
-
-To use this wrapper:
-```python
-from langchain.llms.manifest import ManifestWrapper
-```

docs/ecosystem/helicone.md

@@ -1,53 +0,0 @@
-# Helicone
-
-This page covers how to use the [Helicone](https://helicone.ai) within LangChain.
-
-## What is Helicone?
-
-Helicone is an [open source](https://github.com/Helicone/helicone) observability platform that proxies your OpenAI traffic and provides you key insights into your spend, latency and usage.
-
-![Helicone](../_static/HeliconeDashboard.png)
-
-## Quick start
-
-With your LangChain environment you can just add the following parameter.
-
-```bash
-export OPENAI_API_BASE="https://oai.hconeai.com/v1"
-```
-
-Now head over to [helicone.ai](https://helicone.ai/onboarding?step=2) to create your account, and add your OpenAI API key within our dashboard to view your logs.
-
-![Helicone](../_static/HeliconeKeys.png)
-
-## How to enable Helicone caching
-
-```python
-from langchain.llms import OpenAI
-import openai
-openai.api_base = "https://oai.hconeai.com/v1"
-
-llm = OpenAI(temperature=0.9, headers={"Helicone-Cache-Enabled": "true"})
-text = "What is a helicone?"
-print(llm(text))
-```
-
-[Helicone caching docs](https://docs.helicone.ai/advanced-usage/caching)
-
-## How to use Helicone custom properties
-
-```python
-from langchain.llms import OpenAI
-import openai
-openai.api_base = "https://oai.hconeai.com/v1"
-
-llm = OpenAI(temperature=0.9, headers={
-        "Helicone-Property-Session": "24",
-        "Helicone-Property-Conversation": "support_issue_2",
-        "Helicone-Property-App": "mobile",
-      })
-text = "What is a helicone?"
-print(llm(text))
-```
-
-[Helicone property docs](https://docs.helicone.ai/advanced-usage/custom-properties)

docs/ecosystem/huggingface.md

@@ -1,69 +0,0 @@
-# Hugging Face
-
-This page covers how to use the Hugging Face ecosystem (including the [Hugging Face Hub](https://huggingface.co)) within LangChain.
-It is broken into two parts: installation and setup, and then references to specific Hugging Face wrappers.
-
-## Installation and Setup
-
-If you want to work with the Hugging Face Hub:
-- Install the Hub client library with `pip install huggingface_hub`
-- Create a Hugging Face account (it's free!)
-- Create an [access token](https://huggingface.co/docs/hub/security-tokens) and set it as an environment variable (`HUGGINGFACEHUB_API_TOKEN`)
-
-If you want work with the Hugging Face Python libraries:
-- Install `pip install transformers` for working with models and tokenizers
-- Install `pip install datasets` for working with datasets
-
-## Wrappers
-
-### LLM
-
-There exists two Hugging Face LLM wrappers, one for a local pipeline and one for a model hosted on Hugging Face Hub.
-Note that these wrappers only work for models that support the following tasks: [`text2text-generation`](https://huggingface.co/models?library=transformers&pipeline_tag=text2text-generation&sort=downloads), [`text-generation`](https://huggingface.co/models?library=transformers&pipeline_tag=text-classification&sort=downloads)
-
-To use the local pipeline wrapper:
-```python
-from langchain.llms import HuggingFacePipeline
-```
-
-To use a the wrapper for a model hosted on Hugging Face Hub:
-```python
-from langchain.llms import HuggingFaceHub
-```
-For a more detailed walkthrough of the Hugging Face Hub wrapper, see [this notebook](../modules/llms/integrations/huggingface_hub.ipynb)
-
-
-### Embeddings
-
-There exists two Hugging Face Embeddings wrappers, one for a local model and one for a model hosted on Hugging Face Hub.
-Note that these wrappers only work for [`sentence-transformers` models](https://huggingface.co/models?library=sentence-transformers&sort=downloads).
-
-To use the local pipeline wrapper:
-```python
-from langchain.embeddings import HuggingFaceEmbeddings
-```
-
-To use a the wrapper for a model hosted on Hugging Face Hub:
-```python
-from langchain.embeddings import HuggingFaceHubEmbeddings
-```
-For a more detailed walkthrough of this, see [this notebook](../modules/indexes/examples/embeddings.ipynb)
-
-### Tokenizer
-
-There are several places you can use tokenizers available through the `transformers` package.
-By default, it is used to count tokens for all LLMs.
-
-You can also use it to count tokens when splitting documents with 
-```python
-from langchain.text_splitter import CharacterTextSplitter
-CharacterTextSplitter.from_huggingface_tokenizer(...)
-```
-For a more detailed walkthrough of this, see [this notebook](../modules/indexes/examples/textsplitter.ipynb)
-
-
-### Datasets
-
-The Hugging Face Hub has lots of great [datasets](https://huggingface.co/datasets) that can be used to evaluate your LLM chains.
-
-For a detailed walkthrough of how to use them to do so, see [this notebook](../use_cases/evaluation/huggingface_datasets.ipynb)

docs/ecosystem/modal.md

@@ -1,66 +0,0 @@
-# Modal
-
-This page covers how to use the Modal ecosystem within LangChain.
-It is broken into two parts: installation and setup, and then references to specific Modal wrappers.
-
-## Installation and Setup
-- Install with `pip install modal-client`
-- Run `modal token new`
-
-## Define your Modal Functions and Webhooks
-
-You must include a prompt. There is a rigid response structure.
-
-```python
-class Item(BaseModel):
-    prompt: str
-
-@stub.webhook(method="POST")
-def my_webhook(item: Item):
-    return {"prompt": my_function.call(item.prompt)}
-```
-
-An example with GPT2:
-
-```python
-from pydantic import BaseModel
-
-import modal
-
-stub = modal.Stub("example-get-started")
-
-volume = modal.SharedVolume().persist("gpt2_model_vol")
-CACHE_PATH = "/root/model_cache"
-
-@stub.function(
-    gpu="any",
-    image=modal.Image.debian_slim().pip_install(
-        "tokenizers", "transformers", "torch", "accelerate"
-    ),
-    shared_volumes={CACHE_PATH: volume},
-    retries=3,
-)
-def run_gpt2(text: str):
-    from transformers import GPT2Tokenizer, GPT2LMHeadModel
-    tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
-    model = GPT2LMHeadModel.from_pretrained('gpt2')
-    encoded_input = tokenizer(text, return_tensors='pt').input_ids
-    output = model.generate(encoded_input, max_length=50, do_sample=True)
-    return tokenizer.decode(output[0], skip_special_tokens=True)
-
-class Item(BaseModel):
-    prompt: str
-
-@stub.webhook(method="POST")
-def get_text(item: Item):
-    return {"prompt": run_gpt2.call(item.prompt)}
-```
-
-## Wrappers
-
-### LLM
-
-There exists an Modal LLM wrapper, which you can access with 
-```python
-from langchain.llms import Modal
-```

docs/ecosystem/nlpcloud.md

@@ -1,17 +0,0 @@
-# NLPCloud
-
-This page covers how to use the NLPCloud ecosystem within LangChain.
-It is broken into two parts: installation and setup, and then references to specific NLPCloud wrappers.
-
-## Installation and Setup
-- Install the Python SDK with `pip install nlpcloud`
-- Get an NLPCloud api key and set it as an environment variable (`NLPCLOUD_API_KEY`)
-
-## Wrappers
-
-### LLM
-
-There exists an NLPCloud LLM wrapper, which you can access with 
-```python
-from langchain.llms import NLPCloud
-```

docs/ecosystem/openai.md

@@ -1,55 +0,0 @@
-# OpenAI
-
-This page covers how to use the OpenAI ecosystem within LangChain.
-It is broken into two parts: installation and setup, and then references to specific OpenAI wrappers.
-
-## Installation and Setup
-- Install the Python SDK with `pip install openai`
-- Get an OpenAI api key and set it as an environment variable (`OPENAI_API_KEY`)
-- If you want to use OpenAI's tokenizer (only available for Python 3.9+), install it with `pip install tiktoken`
-
-## Wrappers
-
-### LLM
-
-There exists an OpenAI LLM wrapper, which you can access with 
-```python
-from langchain.llms import OpenAI
-```
-
-If you are using a model hosted on Azure, you should use different wrapper for that:
-```python
-from langchain.llms import AzureOpenAI
-```
-For a more detailed walkthrough of the Azure wrapper, see [this notebook](../modules/llms/integrations/azure_openai_example.ipynb)
-
-
-
-### Embeddings
-
-There exists an OpenAI Embeddings wrapper, which you can access with 
-```python
-from langchain.embeddings import OpenAIEmbeddings
-```
-For a more detailed walkthrough of this, see [this notebook](../modules/indexes/examples/embeddings.ipynb)
-
-
-### Tokenizer
-
-There are several places you can use the `tiktoken` tokenizer. By default, it is used to count tokens
-for OpenAI LLMs.
-
-You can also use it to count tokens when splitting documents with 
-```python
-from langchain.text_splitter import CharacterTextSplitter
-CharacterTextSplitter.from_tiktoken_encoder(...)
-```
-For a more detailed walkthrough of this, see [this notebook](../modules/indexes/examples/textsplitter.ipynb)
-
-### Moderation
-You can also access the OpenAI content moderation endpoint with
-
-```python
-from langchain.chains import OpenAIModerationChain
-```
-For a more detailed walkthrough of this, see [this notebook](../modules/chains/examples/moderation.ipynb)

docs/ecosystem/opensearch.md

@@ -1,21 +0,0 @@
-# OpenSearch
-
-This page covers how to use the OpenSearch ecosystem within LangChain.
-It is broken into two parts: installation and setup, and then references to specific OpenSearch wrappers.
-
-## Installation and Setup
-- Install the Python package with `pip install opensearch-py`
-## Wrappers
-
-### VectorStore
-
-There exists a wrapper around OpenSearch vector databases, allowing you to use it as a vectorstore 
-for semantic search using approximate vector search powered by lucene, nmslib and faiss engines 
-or using painless scripting and script scoring functions for bruteforce vector search.
-
-To import this vectorstore:
-```python
-from langchain.vectorstores import OpenSearchVectorSearch
-```
-
-For a more detailed walkthrough of the OpenSearch wrapper, see [this notebook](../modules/indexes/vectorstore_examples/opensearch.ipynb)

docs/ecosystem/petals.md

@@ -1,17 +0,0 @@
-# Petals
-
-This page covers how to use the Petals ecosystem within LangChain.
-It is broken into two parts: installation and setup, and then references to specific Petals wrappers.
-
-## Installation and Setup
-- Install with `pip install petals`
-- Get a Hugging Face api key and set it as an environment variable (`HUGGINGFACE_API_KEY`)
-
-## Wrappers
-
-### LLM
-
-There exists an Petals LLM wrapper, which you can access with 
-```python
-from langchain.llms import Petals
-```

docs/ecosystem/pinecone.md

@@ -1,20 +0,0 @@
-# Pinecone
-
-This page covers how to use the Pinecone ecosystem within LangChain.
-It is broken into two parts: installation and setup, and then references to specific Pinecone wrappers.
-
-## Installation and Setup
-- Install the Python SDK with `pip install pinecone-client`
-## Wrappers
-
-### VectorStore
-
-There exists a wrapper around Pinecone 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 Pinecone
-```
-
-For a more detailed walkthrough of the Pinecone wrapper, see [this notebook](../modules/indexes/examples/vectorstores.ipynb)

docs/ecosystem/promptlayer.md

@@ -1,31 +0,0 @@
-# PromptLayer
-
-This page covers how to use [PromptLayer](https://www.promptlayer.com) within LangChain.
-It is broken into two parts: installation and setup, and then references to specific PromptLayer wrappers.
-
-## Installation and Setup
-
-If you want to work with PromptLayer:
-- Install the promptlayer python library `pip install promptlayer`
-- Create a PromptLayer account
-- Create an api token and set it as an environment variable (`PROMPTLAYER_API_KEY`)
-
-## Wrappers
-
-### LLM
-
-There exists an PromptLayer OpenAI LLM wrapper, which you can access with
-```python
-from langchain.llms import PromptLayerOpenAI
-```
-
-To tag your requests, use the argument `pl_tags` when instanializing the LLM
-```python
-from langchain.llms import PromptLayerOpenAI
-llm = PromptLayerOpenAI(pl_tags=["langchain-requests", "chatbot"])
-```
-
-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
-

docs/ecosystem/runhouse.md

@@ -1,31 +0,0 @@
-# Runhouse
-
-This page covers how to use the [Runhouse](https://github.com/run-house/runhouse) ecosystem within LangChain.
-It is broken into three parts: installation and setup, LLMs, and Embeddings.
-
-## Installation and Setup
-- Install the Python SDK with `pip install runhouse`
-- If you'd like to use on-demand cluster, check your cloud credentials with `sky check`
-
-## Self-hosted LLMs
-For a basic self-hosted LLM, you can use the `SelfHostedHuggingFaceLLM` class. For more
-custom LLMs, you can use the `SelfHostedPipeline` parent class.
-
-```python
-from langchain.llms import SelfHostedPipeline, SelfHostedHuggingFaceLLM
-```
-
-For a more detailed walkthrough of the Self-hosted LLMs, see [this notebook](../modules/llms/integrations/self_hosted_examples.ipynb)
-
-## Self-hosted Embeddings
-There are several ways to use self-hosted embeddings with LangChain via Runhouse.
-
-For a basic self-hosted embedding from a Hugging Face Transformers model, you can use 
-the `SelfHostedEmbedding` class.
-```python
-from langchain.llms import SelfHostedPipeline, SelfHostedHuggingFaceLLM
-```
-
-For a more detailed walkthrough of the Self-hosted Embeddings, see [this notebook](../modules/indexes/examples/embeddings.ipynb)
-
-##

docs/ecosystem/searx.md

@@ -1,35 +0,0 @@
-# SearxNG Search API
-
-This page covers how to use the SearxNG search API within LangChain.
-It is broken into two parts: installation and setup, and then references to the specific SearxNG API wrapper.
-
-## Installation and Setup
-
-- 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
-
-You can use the wrapper to get results from a SearxNG instance. 
-
-```python
-from langchain.utilities import SearxSearchWrapper
-```
-
-### Tool
-
-You can also easily load this wrapper as a Tool (to use with an Agent).
-You can do this with:
-
-```python
-from langchain.agents import load_tools
-tools = load_tools(["searx-search"], searx_host="https://searx.example.com")
-```
-
-For more information on this, see [this page](../modules/agents/tools.md)

docs/ecosystem/serpapi.md

@@ -1,31 +0,0 @@
-# SerpAPI
-
-This page covers how to use the SerpAPI search APIs within LangChain.
-It is broken into two parts: installation and setup, and then references to the specific SerpAPI wrapper.
-
-## Installation and Setup
-- Install requirements with `pip install google-search-results`
-- Get a SerpAPI api key and either set it as an environment variable (`SERPAPI_API_KEY`)
-
-## Wrappers
-
-### Utility
-
-There exists a SerpAPI utility which wraps this API. To import this utility:
-
-```python
-from langchain.utilities import SerpAPIWrapper
-```
-
-For a more detailed walkthrough of this wrapper, see [this notebook](../modules/utils/examples/serpapi.ipynb).
-
-### Tool
-
-You can also easily load this wrapper as a Tool (to use with an Agent).
-You can do this with:
-```python
-from langchain.agents import load_tools
-tools = load_tools(["serpapi"])
-```
-
-For more information on this, see [this page](../modules/agents/tools.md)

docs/ecosystem/stochasticai.md

@@ -1,17 +0,0 @@
-# StochasticAI
-
-This page covers how to use the StochasticAI ecosystem within LangChain.
-It is broken into two parts: installation and setup, and then references to specific StochasticAI wrappers.
-
-## Installation and Setup
-- Install with `pip install stochasticx`
-- Get an StochasticAI api key and set it as an environment variable (`STOCHASTICAI_API_KEY`)
-
-## Wrappers
-
-### LLM
-
-There exists an StochasticAI LLM wrapper, which you can access with 
-```python
-from langchain.llms import StochasticAI
-```

docs/ecosystem/unstructured.md

@@ -1,41 +0,0 @@
-# Unstructured
-
-This page covers how to use the [`unstructured`](https://github.com/Unstructured-IO/unstructured)
-ecosystem within LangChain. The `unstructured` package from
-[Unstructured.IO](https://www.unstructured.io/) extracts clean text from raw source documents like
-PDFs and Word documents.
-
-
-This page is broken into two parts: installation and setup, and then references to specific
-`unstructured` wrappers.
-
-## Installation and Setup
-- Install the Python SDK with `pip install "unstructured[local-inference]"`
-- Install the following system dependencies if they are not already available on your system.
-  Depending on what document types you're parsing, you may not need all of these.
-    - `libmagic-dev`
-    - `poppler-utils`
-    - `tesseract-ocr`
-    - `libreoffice`
-- 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"`
-
-## Wrappers
-
-### Data Loaders
-
-The primary `unstructured` wrappers within `langchain` are data loaders. The following
-shows how to use the most basic unstructured data loader. There are other file-specific
-data loaders available in the `langchain.document_loaders` module.
-
-```python
-from langchain.document_loaders import UnstructuredFileLoader
-
-loader = UnstructuredFileLoader("state_of_the_union.txt")
-loader.load()
-```
-
-If you instantiate the loader with `UnstructuredFileLoader(mode="elements")`, the loader
-will track additional metadata like the page number and text type (i.e. title, narrative text)
-when that information is available.

docs/ecosystem/weaviate.md

@@ -1,33 +0,0 @@
-# Weaviate
-
-This page covers how to use the Weaviate ecosystem within LangChain.
-
-What is Weaviate?
-
-**Weaviate in a nutshell:**
-- Weaviate is an open-source ​database of the type ​vector search engine.
-- Weaviate allows you to store JSON documents in a class property-like fashion while attaching machine learning vectors to these documents to represent them in vector space.
-- Weaviate can be used stand-alone (aka bring your vectors) or with a variety of modules that can do the vectorization for you and extend the core capabilities.
-- Weaviate has a GraphQL-API to access your data easily.
-- We aim to bring your vector search set up to production to query in mere milliseconds (check our [open source benchmarks](https://weaviate.io/developers/weaviate/current/benchmarks/) to see if Weaviate fits your use case).
-- Get to know Weaviate in the [basics getting started guide](https://weaviate.io/developers/weaviate/current/core-knowledge/basics.html) in under five minutes.
-
-**Weaviate in detail:**
-
-Weaviate is a low-latency vector search engine with out-of-the-box support for different media types (text, images, etc.). It offers Semantic Search, Question-Answer Extraction, Classification, Customizable Models (PyTorch/TensorFlow/Keras), etc. Built from scratch in Go, Weaviate stores both objects and vectors, allowing for combining vector search with structured filtering and the fault tolerance of a cloud-native database. It is all accessible through GraphQL, REST, and various client-side programming languages.
-
-## Installation and Setup
-- Install the Python SDK with `pip install weaviate-client`
-## Wrappers
-
-### VectorStore
-
-There exists a wrapper around Weaviate 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 Weaviate
-```
-
-For a more detailed walkthrough of the Weaviate wrapper, see [this notebook](../modules/indexes/examples/vectorstores.ipynb)

docs/ecosystem/wolfram_alpha.md

@@ -1,34 +0,0 @@
-# Wolfram Alpha Wrapper
-
-This page covers how to use the Wolfram Alpha API within LangChain.
-It is broken into two parts: installation and setup, and then references to specific Wolfram Alpha wrappers.
-
-## Installation and Setup
-- Install requirements with `pip install wolframalpha`
-- Go to wolfram alpha and sign up for a developer account [here](https://developer.wolframalpha.com/)
-- Create an app and get your APP ID
-- Set your APP ID as an environment variable `WOLFRAM_ALPHA_APPID`
-
-
-## Wrappers
-
-### Utility
-
-There exists a WolframAlphaAPIWrapper utility which wraps this API. To import this utility:
-
-```python
-from langchain.utilities.wolfram_alpha import WolframAlphaAPIWrapper
-```
-
-For a more detailed walkthrough of this wrapper, see [this notebook](../modules/utils/examples/wolfram_alpha.ipynb).
-
-### Tool
-
-You can also easily load this wrapper as a Tool (to use with an Agent).
-You can do this with:
-```python
-from langchain.agents import load_tools
-tools = load_tools(["wolfram-alpha"])
-```
-
-For more information on this, see [this page](../modules/agents/tools.md)

docs/ecosystem/writer.md

@@ -1,16 +0,0 @@
-# Writer
-
-This page covers how to use the Writer ecosystem within LangChain.
-It is broken into two parts: installation and setup, and then references to specific Writer wrappers.
-
-## Installation and Setup
-- Get an Writer api key and set it as an environment variable (`WRITER_API_KEY`)
-
-## Wrappers
-
-### LLM
-
-There exists an Writer LLM wrapper, which you can access with 
-```python
-from langchain.llms import Writer
-```

docs/examples/demos.rst

@@ -0,0 +1,25 @@
+Demos
+=====
+
+The examples here are all end-to-end chains of specific applications.
+They are separated into normal chains and then routing chains.
+
+.. toctree::
+   :maxdepth: 1
+   :glob:
+   :caption: Chains
+
+   demos/llm_math.ipynb
+   demos/map_reduce.ipynb
+   demos/simple_prompts.ipynb
+   demos/sqlite.ipynb
+   demos/vector_db_qa.ipynb
+
+.. toctree::
+   :maxdepth: 1
+   :glob:
+   :caption: Routing Chains
+
+   demos/mrkl.ipynb
+   demos/react.ipynb
+   demos/self_ask_with_search.ipynb

docs/examples/demos/custom_routing_chains.ipynb

@@ -0,0 +1,183 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "0af33207",
+   "metadata": {},
+   "source": [
+    "# Custom Routing Chains\n",
+    "\n",
+    "This covers how to implement a custom routing chain. That problem really reduces to how to implement a custom router. This also acts as a design doc of sorts for routers."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "16773dc8",
+   "metadata": {},
+   "source": [
+    "## Terminology\n",
+    "\n",
+    "Before going through any code, let's align on some terminology.\n",
+    "- Tool: A function that performs a specific duty. This can be things like: Google Search, Database lookup, Python REPL. The interface for a tool is currently a function that is expected to have a string as an input, with a string as an output.\n",
+    "- Tool Input: The input string to a tool.\n",
+    "- Observation: The output from calling a tool on a particular input.\n",
+    "- Router: The object responsible for deciding which tools to call and when. Exposes a `route` method, which takes in a string and returns a Router Output.\n",
+    "- Router Output: The object returned from calling `Router.route` on a string. Consists of:\n",
+    "    - The tool to use\n",
+    "    - The input to that tool\n",
+    "    - A log of the router's thinking.\n",
+    "- Routing Chain: A chain which is made up of a router and suite of tools. When passed a string, the Routing Chain will iterative call tools as needed until it arrives at a Final Answer.\n",
+    "- Final Answer: The final output of a Routing Chain."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6eaca15e",
+   "metadata": {},
+   "source": [
+    "## Router\n",
+    "A central piece of this chain is the router. The router is responsible for taking user input and deciding which tools, if any, to use. Although it doesn't necessarily have to be backed by a language model (LLM), for pretty much all current use cases it is. LLMs make great routers because they are really good at understanding human intent, which makes them perfect for choosing which tools to use (and for interpreting the output of those tools).\n",
+    "\n",
+    "Below is the interface we expect routers to expose, along with the RouterOutput definition.\n",
+    "\n",
+    "```python\n",
+    "\n",
+    "class RouterOutput(NamedTuple):\n",
+    "    \"\"\"Output of a router.\"\"\"\n",
+    "\n",
+    "    tool: str\n",
+    "    tool_input: str\n",
+    "    log: str\n",
+    "        \n",
+    "\n",
+    "class Router(ABC):\n",
+    "    \"\"\"Chain responsible for deciding the action to take.\"\"\"\n",
+    "\n",
+    "    @abstractmethod\n",
+    "    def route(self, text: str) -> RouterOutput:\n",
+    "        \"\"\"Given input, decided how to route it.\n",
+    "\n",
+    "        Args:\n",
+    "            text: input string\n",
+    "\n",
+    "        Returns:\n",
+    "            RouterOutput specifying what tool to use.\n",
+    "        \"\"\"\n",
+    "\n",
+    "    @property\n",
+    "    @abstractmethod\n",
+    "    def observation_prefix(self) -> str:\n",
+    "        \"\"\"Prefix to append the observation with before calling the router again.\"\"\"\n",
+    "\n",
+    "    @property\n",
+    "    @abstractmethod\n",
+    "    def router_prefix(self) -> str:\n",
+    "        \"\"\"Prefix to prepend the router call with.\"\"\"\n",
+    "\n",
+    "    @property\n",
+    "    def finish_tool_name(self) -> str:\n",
+    "        \"\"\"Name of the tool to use to finish the chain.\"\"\"\n",
+    "        return \"Final Answer\"\n",
+    "\n",
+    "    @property\n",
+    "    def starter_string(self) -> str:\n",
+    "        \"\"\"Put this string after user input but before first router call.\"\"\"\n",
+    "        return \"\\n\"\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "471389be",
+   "metadata": {},
+   "source": [
+    "In order to understand why the router interface is what it is, let's take a look at how it is used in the RoutingChain class:\n",
+    "\n",
+    "```python\n",
+    "def _call(self, inputs: Dict[str, str]) -> Dict[str, str]:\n",
+    "    # Construct a mapping of tool name to tool for easy lookup\n",
+    "    name_to_tool_map = {tc.tool_name: tc.tool for tc in self.tool_configs}\n",
+    "    # Construct the initial string to pass into the router. This is made up\n",
+    "    # of the user input, the special starter string, and then the router prefix.\n",
+    "    # The starter string is a special string that may be used by a router to\n",
+    "    # immediately follow the user input. The router prefix is a string that\n",
+    "    # prompts the router to start routing.\n",
+    "    starter_string = (\n",
+    "        inputs[self.input_key]\n",
+    "        + self.router.starter_string\n",
+    "        + self.router.router_prefix\n",
+    "    )\n",
+    "    # We use the ChainedInput class to iteratively add to the input over time.\n",
+    "    chained_input = ChainedInput(starter_string, verbose=self.verbose)\n",
+    "    # We construct a mapping from each tool to a color, used for logging.\n",
+    "    color_mapping = get_color_mapping(\n",
+    "        [c.tool_name for c in self.tool_configs], excluded_colors=[\"green\"]\n",
+    "    )\n",
+    "    # We now enter the router loop (until it returns something).\n",
+    "    while True:\n",
+    "        # Call the router to see what to do.\n",
+    "        output = self.router.route(chained_input.input)\n",
+    "        # Add the log to the Chained Input.\n",
+    "        chained_input.add(output.log, color=\"green\")\n",
+    "        # If the tool chosen is the finishing tool, then we end and return.\n",
+    "        if output.tool == self.router.finish_tool_name:\n",
+    "            return {self.output_key: output.tool_input}\n",
+    "        # Otherwise we lookup the tool\n",
+    "        chain = name_to_tool_map[output.tool]\n",
+    "        # We then call the tool on the tool input to get an observation\n",
+    "        observation = chain(output.tool_input)\n",
+    "        # We then log the observation\n",
+    "        chained_input.add(f\"\\n{self.router.observation_prefix}\")\n",
+    "        chained_input.add(observation, color=color_mapping[output.tool])\n",
+    "        # We then add the router prefix into the prompt to get the router to start\n",
+    "        # thinking, and start the loop all over.\n",
+    "        chained_input.add(f\"\\n{self.router.router_prefix}\")\n",
+    "\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d9f6ca91",
+   "metadata": {},
+   "source": [
+    "Once we have the custom router written, it is pretty easy to construct the routing chain:\n",
+    "\n",
+    "```python\n",
+    "tools: List[ToolConfig] = ...\n",
+    "router = CustomRouter(....)\n",
+    "routing_chain = RoutingChain(tools=tools, router=router, verbose=True)\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5d0c7662",
+   "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": "3.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/examples/demos/llm_math.ipynb

@@ -0,0 +1,91 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "e71e720f",
+   "metadata": {},
+   "source": [
+    "# LLM Math\n",
+    "\n",
+    "This notebook showcases using LLMs and Python REPLs to do complex word math problems."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "44e9ba31",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new chain...\u001b[0m\n",
+      "How many of the integers between 0 and 99 inclusive are divisible by 8?\u001b[102m\n",
+      "\n",
+      "```python\n",
+      "count = 0\n",
+      "for i in range(100):\n",
+      "    if i % 8 == 0:\n",
+      "        count += 1\n",
+      "print(count)\n",
+      "```\n",
+      "\u001b[0m\n",
+      "Answer: \u001b[103m13\n",
+      "\u001b[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'Answer: 13\\n'"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain import OpenAI, LLMMathChain\n",
+    "\n",
+    "llm = OpenAI(temperature=0)\n",
+    "llm_math = LLMMathChain(llm=llm, verbose=True)\n",
+    "\n",
+    "llm_math.run(\"How many of the integers between 0 and 99 inclusive are divisible by 8?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f62f0c75",
+   "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": "3.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/examples/demos/map_reduce.ipynb

@@ -0,0 +1,93 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "d9a0131f",
+   "metadata": {},
+   "source": [
+    "# Map Reduce\n",
+    "\n",
+    "This notebok showcases an example of map-reduce chains: recursive summarization."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "e9db25f3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain import OpenAI, PromptTemplate, LLMChain\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain.chains.mapreduce import MapReduceChain\n",
+    "\n",
+    "llm = OpenAI(temperature=0)\n",
+    "\n",
+    "_prompt = \"\"\"Write a concise summary of the following:\n",
+    "\n",
+    "\n",
+    "{text}\n",
+    "\n",
+    "\n",
+    "CONCISE SUMMARY:\"\"\"\n",
+    "prompt = PromptTemplate(template=_prompt, input_variables=[\"text\"])\n",
+    "\n",
+    "text_splitter = CharacterTextSplitter()\n",
+    "\n",
+    "mp_chain = MapReduceChain.from_params(llm, prompt, text_splitter)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "99bbe19b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"\\n\\nThe President discusses the recent aggression by Russia, and the response by the United States and its allies. He announces new sanctions against Russia, and says that the free world is united in holding Putin accountable. The President also discusses the American Rescue Plan, the Bipartisan Infrastructure Law, and the Bipartisan Innovation Act. Finally, the President addresses the need for women's rights and equality for LGBTQ+ Americans.\""
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "with open('../state_of_the_union.txt') as f:\n",
+    "    state_of_the_union = f.read()\n",
+    "mp_chain.run(state_of_the_union)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b581501e",
+   "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": "3.8.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/examples/demos/mrkl.ipynb

@@ -0,0 +1,226 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "f1390152",
+   "metadata": {},
+   "source": [
+    "# MRKL\n",
+    "\n",
+    "This notebook showcases using the MRKL chain to route between tasks"
+   ]
+  },
+  {
+   "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 LLMMathChain, OpenAI, SerpAPIChain, MRKLChain, SQLDatabase, SQLDatabaseChain\n",
+    "from langchain.routing_chains.mrkl.base import ChainConfig"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "07e96d99",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(temperature=0)\n",
+    "search = SerpAPIChain()\n",
+    "llm_math_chain = LLMMathChain(llm=llm, verbose=True)\n",
+    "db = SQLDatabase.from_uri(\"sqlite:///../../../notebooks/Chinook.db\")\n",
+    "db_chain = SQLDatabaseChain(llm=llm, database=db, verbose=True)\n",
+    "chains = [\n",
+    "    ChainConfig(\n",
+    "        action_name = \"Search\",\n",
+    "        action=search.run,\n",
+    "        action_description=\"useful for when you need to answer questions about current events\"\n",
+    "    ),\n",
+    "    ChainConfig(\n",
+    "        action_name=\"Calculator\",\n",
+    "        action=llm_math_chain.run,\n",
+    "        action_description=\"useful for when you need to answer questions about math\"\n",
+    "    ),\n",
+    "    \n",
+    "    ChainConfig(\n",
+    "        action_name=\"FooBar DB\",\n",
+    "        action=db_chain.run,\n",
+    "        action_description=\"useful for when you need to answer questions about FooBar. Input should be in the form of a question\"\n",
+    "    )\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "a069c4b6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mrkl = MRKLChain.from_chains(llm, chains, verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "e603cd7d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new chain...\u001b[0m\n",
+      "What is the age of Olivia Wilde's boyfriend raised to the 0.23 power?\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to find the age of Olivia Wilde's boyfriend\n",
+      "Action: Search\n",
+      "Action Input: \"Olivia Wilde's boyfriend\"\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mOlivia Wilde started dating Harry Styles after ending her years-long engagement to Jason Sudeikis — see their relationship timeline.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to find the age of Harry Styles\n",
+      "Action: Search\n",
+      "Action Input: \"Harry Styles age\"\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3m28 years\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to calculate 28 to the 0.23 power\n",
+      "Action: Calculator\n",
+      "Action Input: 28^0.23\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Entering new chain...\u001b[0m\n",
+      "28^0.23\u001b[32;1m\u001b[1;3m\n",
+      "\n",
+      "```python\n",
+      "print(28**0.23)\n",
+      "```\n",
+      "\u001b[0m\n",
+      "Answer: \u001b[33;1m\u001b[1;3m2.1520202182226886\n",
+      "\u001b[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\n",
+      "Observation: \u001b[33;1m\u001b[1;3mAnswer: 2.1520202182226886\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: 2.1520202182226886\u001b[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'2.1520202182226886'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mrkl.run(\"What is the age of Olivia Wilde's boyfriend raised to the 0.23 power?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "a5c07010",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new chain...\u001b[0m\n",
+      "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:\u001b[32;1m\u001b[1;3m I need to find an album called 'The Storm Before the Calm'\n",
+      "Action: Search\n",
+      "Action Input: \"The Storm Before the Calm album\"\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mThe Storm Before the Calm (stylized in all lowercase) is the tenth (and eighth international) studio album by Canadian-American singer-songwriter Alanis ...\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to check if Alanis is in the FooBar database\n",
+      "Action: FooBar DB\n",
+      "Action Input: \"Does Alanis Morissette exist in the FooBar database?\"\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Entering new chain...\u001b[0m\n",
+      "Does Alanis Morissette exist in the FooBar database?\n",
+      "SQLQuery:\u001b[32;1m\u001b[1;3m SELECT * FROM Artist WHERE Name = 'Alanis Morissette'\u001b[0m\n",
+      "SQLResult: \u001b[33;1m\u001b[1;3m[(4, 'Alanis Morissette')]\u001b[0m\n",
+      "Answer:\u001b[32;1m\u001b[1;3m Yes\u001b[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\n",
+      "Observation: \u001b[38;5;200m\u001b[1;3m Yes\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to find out what albums of Alanis's are in the FooBar database\n",
+      "Action: FooBar DB\n",
+      "Action Input: \"What albums by Alanis Morissette are in the FooBar database?\"\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Entering new chain...\u001b[0m\n",
+      "What albums by Alanis Morissette are in the FooBar database?\n",
+      "SQLQuery:\u001b[32;1m\u001b[1;3m SELECT Album.Title FROM Album JOIN Artist ON Album.ArtistId = Artist.ArtistId WHERE Artist.Name = \"Alanis Morissette\"\u001b[0m\n",
+      "SQLResult: \u001b[33;1m\u001b[1;3m[('Jagged Little Pill',)]\u001b[0m\n",
+      "Answer:\u001b[32;1m\u001b[1;3m Jagged Little Pill\u001b[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\n",
+      "Observation: \u001b[38;5;200m\u001b[1;3m Jagged Little Pill\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: The album is by Alanis Morissette and the albums in the FooBar database by her are Jagged Little Pill\u001b[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'The album is by Alanis Morissette and the albums in the FooBar database by her are Jagged Little Pill'"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mrkl.run(\"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": "d7c2e6ac",
+   "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": "3.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/examples/demos/natbot.py

@@ -2,7 +2,7 @@
 import time
 
 from langchain.chains.natbot.base import NatBotChain
-from langchain.chains.natbot.crawler import Crawler
+from langchain.chains.natbot.crawler import Crawler  # type: ignore
 
 
 def run_cmd(cmd: str, _crawler: Crawler) -> None:
@@ -33,6 +33,7 @@ def run_cmd(cmd: str, _crawler: Crawler) -> None:
 
 
 if __name__ == "__main__":
+
     objective = "Make a reservation for 2 at 7pm at bistro vida in menlo park"
     print("\nWelcome to natbot! What is your objective?")
     i = input()

docs/examples/demos/react.ipynb

@@ -7,38 +7,25 @@
    "source": [
     "# ReAct\n",
     "\n",
-    "This notebook showcases using an agent to implement the ReAct logic."
+    "This notebook showcases the implementation of the ReAct chain logic."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 1,
    "id": "4e272b47",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain import OpenAI, Wikipedia\n",
-    "from langchain.agents import initialize_agent, Tool\n",
-    "from langchain.agents.react.base import DocstoreExplorer\n",
-    "docstore=DocstoreExplorer(Wikipedia())\n",
-    "tools = [\n",
-    "    Tool(\n",
-    "        name=\"Search\",\n",
-    "        func=docstore.search\n",
-    "    ),\n",
-    "    Tool(\n",
-    "        name=\"Lookup\",\n",
-    "        func=docstore.lookup\n",
-    "    )\n",
-    "]\n",
+    "from langchain import OpenAI, ReActChain, Wikipedia\n",
     "\n",
-    "llm = OpenAI(temperature=0, model_name=\"text-davinci-002\")\n",
-    "react = initialize_agent(tools, llm, agent=\"react-docstore\", verbose=True)"
+    "llm = OpenAI(temperature=0)\n",
+    "react = ReActChain(llm=llm, docstore=Wikipedia(), verbose=True)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 2,
    "id": "8078c8f1",
    "metadata": {},
    "outputs": [
@@ -48,18 +35,20 @@
      "text": [
       "\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m\n",
-      "Thought 1: I need to search David Chanoff and find the U.S. Navy admiral he collaborated\n",
+      "\u001b[1m> Entering new chain...\u001b[0m\n",
+      "Author David Chanoff has collaborated with a U.S. Navy admiral who served as the ambassador to the United Kingdom under which President?\n",
+      "Thought 1:\u001b[32;1m\u001b[1;3m I need to search David Chanoff and find the U.S. Navy admiral he collaborated\n",
       "with.\n",
       "Action 1: Search[David Chanoff]\u001b[0m\n",
       "Observation 1: \u001b[36;1m\u001b[1;3mDavid Chanoff is a noted author of non-fiction work. His work has typically involved collaborations with the principal protagonist of the work concerned. His collaborators have included; Augustus A. White, Joycelyn Elders, Đoàn Văn Toại, William J. Crowe, Ariel Sharon, Kenneth Good and Felix Zandman. He has also written about a wide range of subjects including literary history, education and foreign for The Washington Post, The New Republic and The New York Times Magazine. He has published more than twelve books.\u001b[0m\n",
-      "Thought 2:\u001b[32;1m\u001b[1;3m The U.S. Navy admiral David Chanoff collaborated with is William J. Crowe.\n",
+      "Thought 2:\u001b[32;1m\u001b[1;3m The U.S. Navy admiral David Chanoff collaborated with is William J. Crowe. I\n",
+      "need to search him next.\n",
       "Action 2: Search[William J. Crowe]\u001b[0m\n",
       "Observation 2: \u001b[36;1m\u001b[1;3mWilliam James Crowe Jr. (January 2, 1925 – October 18, 2007) was a United States Navy admiral and diplomat who served as the 11th chairman of the Joint Chiefs of Staff under Presidents Ronald Reagan and George H. W. Bush, and as the ambassador to the United Kingdom and Chair of the Intelligence Oversight Board under President Bill Clinton.\u001b[0m\n",
-      "Thought 3:\u001b[32;1m\u001b[1;3m The President William J. Crowe served as the ambassador to the United Kingdom under is Bill Clinton.\n",
+      "Thought 3:\u001b[32;1m\u001b[1;3m William J. Crowe served as the ambassador to the United Kingdom under\n",
+      "President Bill Clinton. So the answer is Bill Clinton.\n",
       "Action 3: Finish[Bill Clinton]\u001b[0m\n",
-      "\u001b[1m> Finished AgentExecutor chain.\u001b[0m\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
@@ -68,7 +57,7 @@
        "'Bill Clinton'"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -77,11 +66,19 @@
     "question = \"Author David Chanoff has collaborated with a U.S. Navy admiral who served as the ambassador to the United Kingdom under which President?\"\n",
     "react.run(question)"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4ff64e81",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3.9.0 64-bit ('llm-env')",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -95,12 +92,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.0"
-  },
-  "vscode": {
-   "interpreter": {
-    "hash": "b1677b440931f40d89ef8be7bf03acb108ce003de0ac9b18e8d43753ea2e7103"
-   }
+   "version": "3.7.6"
   }
  },
  "nbformat": 4,

docs/examples/demos/routing_chains.ipynb

@@ -0,0 +1,195 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "5436020b",
+   "metadata": {},
+   "source": [
+    "# Routing Chains\n",
+    "Some applications will require not just a predetermined chain of calls to LLMs/other tools, but potentially an unknown chain that depends on the user input. In these types of chains, there is a \"router\" LLM chain which has access to a suite of tools. Depending on the user input, the router can then decide which, if any, of these tools to call.\n",
+    "\n",
+    "These types of chains are called Routing Chains. When used correctly these can be extremely powerful. The purpose of this notebook is to show you how to easily use routing chains through the simplest, highest level API. If you want more low level control over various components, check out the documentation for custom routing chains."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3c6226b9",
+   "metadata": {},
+   "source": [
+    "## Concepts\n",
+    "\n",
+    "In order to understand routing chains, you should understand the following concepts:\n",
+    "- Tool: A function that performs a specific duty. This can be things like: Google Search, Database lookup, Python REPL, other chains. The interface for a tool is currently a function that is expected to have a string as an input, with a string as an output.\n",
+    "- LLM: The language model responsible for doing the router.\n",
+    "- RouterType: The type of the router to use. This should be a string (see more on the allowed router types below). Because this notebook focuses on the simplest, highest level API, this only covers using the standard supported routers. If you want to implement a custom router, see the documentation for custom routing chains."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "05d4b21e",
+   "metadata": {},
+   "source": [
+    "## Tools\n",
+    "When constructing your own Routing Chain, you will need to provide it with a list of tools that it can use. This is done with a list of Tools. The Tools are used not only to create the Routing Chain, but is also sometimes used to create the router itself (often, the router logic depends on the tools available). \n",
+    "\n",
+    "```python\n",
+    "class Tool(NamedTuple):\n",
+    "    \"\"\"Interface for tools.\"\"\"\n",
+    "\n",
+    "    name: str\n",
+    "    func: Callable[[str], str]\n",
+    "    description: Optional[str] = None\n",
+    "```\n",
+    "\n",
+    "The two required components of a ToolConfig are the name and then the tool itself. A tool description is optional, as it is needed for some routers but not all."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2558a02d",
+   "metadata": {},
+   "source": [
+    "## Loading the chains\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "36ed392e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Import things that are needed generically\n",
+    "from langchain.routing_chains import load_routing_chain, Tool\n",
+    "from langchain.llms import OpenAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "56ff7670",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Load the tool configs that are needed.\n",
+    "from langchain import LLMMathChain, SerpAPIChain\n",
+    "llm = OpenAI(temperature=0)\n",
+    "search = SerpAPIChain()\n",
+    "llm_math_chain = LLMMathChain(llm=llm, 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\"\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",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "5b93047d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Construct the routing chain. We will use the default router type here.\n",
+    "# See documentation for a full list of options.\n",
+    "router_llm = OpenAI(temperature=0)\n",
+    "chain = load_routing_chain(tools, router_llm, verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "6f96a891",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new chain...\u001b[0m\n",
+      "What is the age of Olivia Wilde's boyfriend raised to the 0.23 power?\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to find the age of Olivia Wilde's boyfriend\n",
+      "Action: Search\n",
+      "Action Input: \"Olivia Wilde's boyfriend\"\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mOlivia Wilde started dating Harry Styles after ending her years-long engagement to Jason Sudeikis — see their relationship timeline.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to find the age of Harry Styles\n",
+      "Action: Search\n",
+      "Action Input: \"Harry Styles age\"\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3m28 years\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to calculate 28 to the 0.23 power\n",
+      "Action: Calculator\n",
+      "Action Input: 28^0.23\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Entering new chain...\u001b[0m\n",
+      "28^0.23\u001b[32;1m\u001b[1;3m\n",
+      "\n",
+      "```python\n",
+      "print(28**0.23)\n",
+      "```\n",
+      "\u001b[0m\n",
+      "Answer: \u001b[33;1m\u001b[1;3m2.1520202182226886\n",
+      "\u001b[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\n",
+      "Observation: \u001b[33;1m\u001b[1;3mAnswer: 2.1520202182226886\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: 2.1520202182226886\u001b[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'2.1520202182226886'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.run(\"What is the age of Olivia Wilde's boyfriend raised to the 0.23 power?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2f0852ff",
+   "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": "3.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/examples/demos/self_ask_with_search.ipynb

@@ -12,7 +12,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "id": "7e3b513e",
    "metadata": {},
    "outputs": [
@@ -22,14 +22,15 @@
      "text": [
       "\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m Yes.\n",
+      "\u001b[1m> Entering new chain...\u001b[0m\n",
+      "What is the hometown of the reigning men's U.S. Open champion?\n",
+      "Are follow up questions needed here:\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;3mCarlos Alcaraz won the 2022 Men's single title while Poland's Iga Swiatek won the Women's single title defeating Tunisian's Ons Jabeur.\u001b[0m\n",
+      "Intermediate answer: \u001b[36;1m\u001b[1;3mCarlos Alcaraz\u001b[0m\n",
       "\u001b[32;1m\u001b[1;3mFollow up: Where is Carlos Alcaraz from?\u001b[0m\n",
       "Intermediate answer: \u001b[36;1m\u001b[1;3mEl Palmar, Spain\u001b[0m\n",
       "\u001b[32;1m\u001b[1;3mSo the final answer is: El Palmar, Spain\u001b[0m\n",
-      "\u001b[1m> Finished AgentExecutor chain.\u001b[0m\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
@@ -38,32 +39,34 @@
        "'El Palmar, Spain'"
       ]
      },
-     "execution_count": 2,
+     "execution_count": 1,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "from langchain import OpenAI, SerpAPIWrapper\n",
-    "from langchain.agents import initialize_agent, Tool\n",
+    "from langchain import SelfAskWithSearchChain, OpenAI, SerpAPIChain\n",
     "\n",
     "llm = OpenAI(temperature=0)\n",
-    "search = SerpAPIWrapper()\n",
-    "tools = [\n",
-    "    Tool(\n",
-    "        name=\"Intermediate Answer\",\n",
-    "        func=search.run\n",
-    "    )\n",
-    "]\n",
+    "search = SerpAPIChain()\n",
+    "\n",
+    "self_ask_with_search = SelfAskWithSearchChain(llm=llm, search_chain=search, verbose=True)\n",
     "\n",
-    "self_ask_with_search = initialize_agent(tools, llm, agent=\"self-ask-with-search\", verbose=True)\n",
     "self_ask_with_search.run(\"What is the hometown of the reigning men's U.S. Open champion?\")"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "683d69e7",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3.9.0 64-bit ('llm-env')",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -77,12 +80,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.0"
-  },
-  "vscode": {
-   "interpreter": {
-    "hash": "b1677b440931f40d89ef8be7bf03acb108ce003de0ac9b18e8d43753ea2e7103"
-   }
+   "version": "3.7.6"
   }
  },
  "nbformat": 4,

docs/examples/demos/sequential_chains.ipynb

@@ -104,25 +104,15 @@
      "text": [
       "\n",
       "\n",
-      "\u001b[1m> Entering new SimpleSequentialChain chain...\u001b[0m\n",
+      "\u001b[1m> Entering new chain...\u001b[0m\n",
       "\u001b[36;1m\u001b[1;3m\n",
       "\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",
-      "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 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",
+      "A young couple, John and Mary, are enjoying a day at the beach. As the sun sets, they share a romantic moment. However, their happiness is short-lived, as a tragic accident claims John's life. Mary is left devastated by the loss of her husband.\u001b[0m\n",
       "\u001b[33;1m\u001b[1;3m\n",
       "\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",
+      "\"A young couple's happiness is cut short by tragedy in this moving play. Mary is left devastated by the loss of her husband, John, in a freak accident. The play captures the pain and grief of loss, as well as the strength of love. A must-see for fans of theater.\"\u001b[0m\n",
       "\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",
-      "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 SimpleSequentialChain chain.\u001b[0m\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     }
    ],
@@ -142,11 +132,7 @@
      "text": [
       "\n",
       "\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 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",
-      "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"
+      "\"A young couple's happiness is cut short by tragedy in this moving play. Mary is left devastated by the loss of her husband, John, in a freak accident. The play captures the pain and grief of loss, as well as the strength of love. A must-see for fans of theater.\"\n"
      ]
     }
    ],
@@ -230,15 +216,15 @@
      "text": [
       "\n",
       "\n",
-      "\u001b[1m> Entering new SequentialChain chain...\u001b[0m\n",
+      "\u001b[1m> Entering new 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",
+      "{'synopsis': \"\\n\\nThe play is set in Victorian England and follows the tragic story of a young woman who drowns while swimming at sunset on the beach. Her body is found the next morning by a fisherman who raises the alarm. The young woman's family and friends are devastated by her death and the play ends with their mourning her loss.\"}\n",
       "\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",
+      "{'review': '\\n\\n\"The play is a tragedy, pure and simple. It is the story of a young woman\\'s death, told through the eyes of those who loved her. It is a sad, beautiful play that will stay with you long after you\\'ve seen it. The acting is superb, and the writing is exquisite. If you are looking for a play that will touch your heart and make you think, this is it.\"'}\n",
       "\n",
       "\n",
-      "\u001b[1m> Finished SequentialChain chain.\u001b[0m\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     }
    ],
@@ -271,7 +257,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.7.6"
   }
  },
  "nbformat": 4,

docs/examples/demos/simple_prompts.ipynb

@@ -0,0 +1,89 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "d8a5c5d4",
+   "metadata": {},
+   "source": [
+    "# Simple Example\n",
+    "\n",
+    "This notebook showcases a simple chain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "51a54c4d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new 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",
+      "\n",
+      "Answer: Let's think step by step.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "' The year Justin Beiber was born was 1994. In 1994, the Dallas Cowboys won the Super Bowl.'"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain import PromptTemplate, OpenAI, LLMChain\n",
+    "\n",
+    "template = \"\"\"Question: {question}\n",
+    "\n",
+    "Answer: Let's think step by step.\"\"\"\n",
+    "prompt = PromptTemplate(template=template, input_variables=[\"question\"])\n",
+    "llm_chain = LLMChain(prompt=prompt, llm=OpenAI(temperature=0), verbose=True)\n",
+    "\n",
+    "question = \"What NFL team won the Super Bowl in the year Justin Beiber was born?\"\n",
+    "\n",
+    "llm_chain.run(question)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "03dd6918",
+   "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": "3.8.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/examples/demos/sqlite.ipynb

@@ -0,0 +1,129 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "0ed6aab1",
+   "metadata": {
+    "pycharm": {
+     "name": "#%% md\n"
+    }
+   },
+   "source": [
+    "# SQLite example\n",
+    "\n",
+    "This example showcases hooking up an LLM to answer questions over a database."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b2f66479",
+   "metadata": {
+    "pycharm": {
+     "name": "#%% md\n"
+    }
+   },
+   "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": "d0e27d88",
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from langchain import OpenAI, SQLDatabase, SQLDatabaseChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "72ede462",
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "db = SQLDatabase.from_uri(\"sqlite:///../../../notebooks/Chinook.db\")\n",
+    "llm = OpenAI(temperature=0)\n",
+    "db_chain = SQLDatabaseChain(llm=llm, database=db, verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "15ff81df",
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new chain...\u001b[0m\n",
+      "How many employees are there?\n",
+      "SQLQuery:\u001b[102m SELECT COUNT(*) FROM Employee\u001b[0m\n",
+      "SQLResult: \u001b[103m[(8,)]\u001b[0m\n",
+      "Answer:\u001b[102m 8\u001b[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "' 8'"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "db_chain.run(\"How many employees are there?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "61d91b85",
+   "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": "3.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/examples/demos/vector_db_qa.ipynb

@@ -2,80 +2,79 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "683953b3",
+   "id": "07c1e3b9",
    "metadata": {},
    "source": [
-    "# Qdrant\n",
+    "# Vector DB Question/Answering\n",
     "\n",
-    "This notebook shows how to use functionality related to the Qdrant vector database."
+    "This example showcases question answering over a vector database."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 1,
-   "id": "aac9563e",
+   "id": "82525493",
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "from langchain.vectorstores.faiss import FAISS\n",
     "from langchain.text_splitter import CharacterTextSplitter\n",
-    "from langchain.vectorstores import Qdrant\n",
-    "from langchain.document_loaders import TextLoader"
+    "from langchain import OpenAI, VectorDBQA"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
-   "id": "a3c3999a",
+   "execution_count": 3,
+   "id": "5c7049db",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.document_loaders import TextLoader\n",
-    "loader = TextLoader('../../state_of_the_union.txt')\n",
-    "documents = loader.load()\n",
+    "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",
-    "docs = text_splitter.split_documents(documents)\n",
+    "texts = text_splitter.split_text(state_of_the_union)\n",
     "\n",
-    "embeddings = OpenAIEmbeddings()"
+    "embeddings = OpenAIEmbeddings()\n",
+    "docsearch = FAISS.from_texts(texts, embeddings)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "dcf88bdf",
+   "execution_count": 4,
+   "id": "3018f865",
    "metadata": {},
    "outputs": [],
    "source": [
-    "host = \"<---host name here --->\"\n",
-    "api_key = \"<---api key here--->\"\n",
-    "qdrant = Qdrant.from_documents(docs, embeddings, host=host, prefer_grpc=True, api_key=api_key)\n",
-    "query = \"What did the president say about Ketanji Brown Jackson\""
+    "qa = VectorDBQA(llm=OpenAI(), vectorstore=docsearch)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "a8c513ab",
+   "execution_count": 5,
+   "id": "032a47f8",
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "docs = qdrant.similarity_search(query)"
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "' The President said that Ketanji Brown Jackson is a consensus builder and has received a broad range of support since she was nominated.'"
       ]
      },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "fc516993",
+     "execution_count": 5,
      "metadata": {},
-   "outputs": [],
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "docs[0]"
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "qa.run(query)"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "a359ed74",
+   "id": "f0f20b92",
    "metadata": {},
    "outputs": [],
    "source": []
@@ -97,7 +96,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.7.6"
   }
  },
  "nbformat": 4,

docs/examples/integrations.rst

@@ -0,0 +1,10 @@
+Integrations
+============
+
+The examples here all highlight a specific type of integration.
+
+.. toctree::
+   :maxdepth: 1
+   :glob:
+
+   integrations/*

docs/examples/integrations/embeddings.ipynb

@@ -0,0 +1,177 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "7ef4d402-6662-4a26-b612-35b542066487",
+   "metadata": {
+    "pycharm": {
+     "name": "#%% md\n"
+    }
+   },
+   "source": [
+    "#  Embeddings & VectorStores\n",
+    "\n",
+    "This notebook show cases how to use embeddings to create a VectorStore"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "965eecee",
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain.vectorstores.elastic_vector_search import ElasticVectorSearch\n",
+    "from langchain.vectorstores.faiss import FAISS"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "68481687",
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "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": "015f4ff5",
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "docsearch = FAISS.from_texts(texts, embeddings)\n",
+    "\n",
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "docs = docsearch.similarity_search(query)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "67baf32e",
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Tonight, 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",
+      "\n",
+      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
+      "\n",
+      "And 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. \n",
+      "\n",
+      "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",
+      "\n",
+      "And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \n"
+     ]
+    }
+   ],
+   "source": [
+    "print(docs[0].page_content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "eea6e627",
+   "metadata": {},
+   "source": [
+    "## Requires having ElasticSearch setup"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "4906b8a3",
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "docsearch = ElasticVectorSearch.from_texts(texts, embeddings, elasticsearch_url=\"http://localhost:9200\")\n",
+    "\n",
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "docs = docsearch.similarity_search(query)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "95f9eee9",
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Tonight, 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",
+      "\n",
+      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
+      "\n",
+      "And 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. \n",
+      "\n",
+      "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",
+      "\n",
+      "And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \n"
+     ]
+    }
+   ],
+   "source": [
+    "print(docs[0].page_content)"
+   ]
+  }
+ ],
+ "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": "3.8.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/examples/integrations/huggingface_hub.ipynb

@@ -5,14 +5,14 @@
    "id": "959300d4",
    "metadata": {},
    "source": [
-    "# Hugging Face Hub\n",
+    "# HuggingFace Hub\n",
     "\n",
-    "This example showcases how to connect to the Hugging Face Hub."
+    "This example showcases how to connect to the HuggingFace Hub."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 1,
    "id": "3acf0069",
    "metadata": {},
    "outputs": [
@@ -20,7 +20,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "The Seattle Seahawks won the Super Bowl in 2010. Justin Beiber was born in 2010. The final answer: Seattle Seahawks.\n"
+      "The Seattle Seahawks won the Super Bowl in 2010. Justin Beiber was born in 2010. The\n"
      ]
     }
    ],
@@ -31,7 +31,7 @@
     "\n",
     "Answer: Let's think step by step.\"\"\"\n",
     "prompt = PromptTemplate(template=template, input_variables=[\"question\"])\n",
-    "llm_chain = LLMChain(prompt=prompt, llm=HuggingFaceHub(repo_id=\"google/flan-t5-xl\", model_kwargs={\"temperature\":0, \"max_length\":64}))\n",
+    "llm_chain = LLMChain(prompt=prompt, llm=HuggingFaceHub(repo_id=\"google/flan-t5-xl\", model_kwargs={\"temperature\":1e-10}))\n",
     "\n",
     "question = \"What NFL team won the Super Bowl in the year Justin Beiber was born?\"\n",
     "\n",
@@ -63,7 +63,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.8.7"
   }
  },
  "nbformat": 4,

docs/examples/integrations/huggingface_tokenizer_text_splitter.ipynb

@@ -0,0 +1,180 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "b118c9dc",
+   "metadata": {},
+   "source": [
+    "# HuggingFace Tokenizers\n",
+    "\n",
+    "This notebook show cases how to use HuggingFace tokenizers to split text."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "e82c4685",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.text_splitter import CharacterTextSplitter"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "a8ce51d5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from transformers import GPT2TokenizerFast\n",
+    "\n",
+    "tokenizer = GPT2TokenizerFast.from_pretrained(\"gpt2\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "ca5e72c0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open('../state_of_the_union.txt') as f:\n",
+    "    state_of_the_union = f.read()\n",
+    "text_splitter = CharacterTextSplitter.from_huggingface_tokenizer(tokenizer, chunk_size=1000, chunk_overlap=0)\n",
+    "texts = text_splitter.split_text(state_of_the_union)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "37cdfbeb",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans.  \n",
+      "\n",
+      "Last year COVID-19 kept us apart. This year we are finally together again. \n",
+      "\n",
+      "Tonight, we meet as Democrats Republicans and Independents. But most importantly as Americans. \n",
+      "\n",
+      "With a duty to one another to the American people to the Constitution. \n",
+      "\n",
+      "And with an unwavering resolve that freedom will always triumph over tyranny. \n",
+      "\n",
+      "Six days ago, Russia’s Vladimir Putin sought to shake the foundations of the free world thinking he could make it bend to his menacing ways. But he badly miscalculated. \n",
+      "\n",
+      "He thought he could roll into Ukraine and the world would roll over. Instead he met a wall of strength he never imagined. \n",
+      "\n",
+      "He met the Ukrainian people. \n",
+      "\n",
+      "From President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world. \n",
+      "\n",
+      "Groups of citizens blocking tanks with their bodies. Everyone from students to retirees teachers turned soldiers defending their homeland. \n",
+      "\n",
+      "In this struggle as President Zelenskyy said in his speech to the European Parliament “Light will win over darkness.” The Ukrainian Ambassador to the United States is here tonight. \n",
+      "\n",
+      "Let each of us here tonight in this Chamber send an unmistakable signal to Ukraine and to the world. \n",
+      "\n",
+      "Please rise if you are able and show that, Yes, we the United States of America stand with the Ukrainian people. \n",
+      "\n",
+      "Throughout our history we’ve learned this lesson when dictators do not pay a price for their aggression they cause more chaos.   \n",
+      "\n",
+      "They keep moving.   \n",
+      "\n",
+      "And the costs and the threats to America and the world keep rising.   \n",
+      "\n",
+      "That’s why the NATO Alliance was created to secure peace and stability in Europe after World War 2. \n",
+      "\n",
+      "The United States is a member along with 29 other nations. \n",
+      "\n",
+      "It matters. American diplomacy matters. American resolve matters. \n",
+      "\n",
+      "Putin’s latest attack on Ukraine was premeditated and unprovoked. \n",
+      "\n",
+      "He rejected repeated efforts at diplomacy. \n",
+      "\n",
+      "He thought the West and NATO wouldn’t respond. And he thought he could divide us at home. Putin was wrong. We were ready.  Here is what we did.   \n",
+      "\n",
+      "We prepared extensively and carefully. \n",
+      "\n",
+      "We spent months building a coalition of other freedom-loving nations from Europe and the Americas to Asia and Africa to confront Putin. \n",
+      "\n",
+      "I spent countless hours unifying our European allies. We shared with the world in advance what we knew Putin was planning and precisely how he would try to falsely justify his aggression.  \n",
+      "\n",
+      "We countered Russia’s lies with truth.   \n",
+      "\n",
+      "And now that he has acted the free world is holding him accountable. \n",
+      "\n",
+      "Along with twenty-seven members of the European Union including France, Germany, Italy, as well as countries like the United Kingdom, Canada, Japan, Korea, Australia, New Zealand, and many others, even Switzerland. \n",
+      "\n",
+      "We are inflicting pain on Russia and supporting the people of Ukraine. Putin is now isolated from the world more than ever. \n",
+      "\n",
+      "Together with our allies –we are right now enforcing powerful economic sanctions. \n",
+      "\n",
+      "We are cutting off Russia’s largest banks from the international financial system.  \n",
+      "\n",
+      "Preventing Russia’s central bank from defending the Russian Ruble making Putin’s $630 Billion “war fund” worthless.   \n",
+      "\n",
+      "We are choking off Russia’s access to technology that will sap its economic strength and weaken its military for years to come.  \n",
+      "\n",
+      "Tonight I say to the Russian oligarchs and corrupt leaders who have bilked billions of dollars off this violent regime no more. \n",
+      "\n",
+      "The U.S. Department of Justice is assembling a dedicated task force to go after the crimes of Russian oligarchs.  \n",
+      "\n",
+      "We are joining with our European allies to find and seize your yachts your luxury apartments your private jets. We are coming for your ill-begotten gains. \n",
+      "\n",
+      "And tonight I am announcing that we will join our allies in closing off American air space to all Russian flights – further isolating Russia – and adding an additional squeeze –on their economy. The Ruble has lost 30% of its value. \n",
+      "\n",
+      "The Russian stock market has lost 40% of its value and trading remains suspended. Russia’s economy is reeling and Putin alone is to blame. \n",
+      "\n",
+      "Together with our allies we are providing support to the Ukrainians in their fight for freedom. Military assistance. Economic assistance. Humanitarian assistance. \n",
+      "\n",
+      "We are giving more than $1 Billion in direct assistance to Ukraine. \n",
+      "\n",
+      "And we will continue to aid the Ukrainian people as they defend their country and to help ease their suffering.  \n",
+      "\n",
+      "Let me be clear, our forces are not engaged and will not engage in conflict with Russian forces in Ukraine.  \n",
+      "\n",
+      "Our forces are not going to Europe to fight in Ukraine, but to defend our NATO Allies – in the event that Putin decides to keep moving west.  \n"
+     ]
+    }
+   ],
+   "source": [
+    "print(texts[0])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d214aec2",
+   "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": "3.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/examples/model_laboratory.ipynb

@@ -5,11 +5,9 @@
    "id": "920a3c1a",
    "metadata": {},
    "source": [
-    "# Model Comparison\n",
+    "# Model Laboratory\n",
     "\n",
-    "Constructing your language model application will likely involved choosing between many different options of prompts, models, and even chains to use. When doing so, you will want to compare these different options on different inputs in an easy, flexible, and intuitive way. \n",
-    "\n",
-    "LangChain provides the concept of a ModelLaboratory to test out and try different models."
+    "This example goes over basic functionality of how to use the ModelLaboratory to test out and try different models."
    ]
   },
   {
@@ -137,14 +135,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain import SelfAskWithSearchChain, SerpAPIWrapper\n",
+    "from langchain import SelfAskWithSearchChain, SerpAPIChain\n",
     "\n",
     "open_ai_llm = OpenAI(temperature=0)\n",
-    "search = SerpAPIWrapper()\n",
+    "search = SerpAPIChain()\n",
     "self_ask_with_search_openai = SelfAskWithSearchChain(llm=open_ai_llm, search_chain=search, verbose=True)\n",
     "\n",
     "cohere_llm = Cohere(temperature=0, model=\"command-xlarge-20221108\")\n",
-    "search = SerpAPIWrapper()\n",
+    "search = SerpAPIChain()\n",
     "self_ask_with_search_cohere = SelfAskWithSearchChain(llm=cohere_llm, search_chain=search, verbose=True)"
    ]
   },
@@ -248,7 +246,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.8.7"
   }
  },
  "nbformat": 4,

docs/examples/prompts.rst

@@ -0,0 +1,10 @@
+Prompts
+=======
+
+The examples here all highlight how to work with prompts.
+
+.. toctree::
+   :maxdepth: 1
+   :glob:
+
+   prompts/*

docs/examples/prompts/few shot examples.ipynb

@@ -0,0 +1,306 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "f8b01b97",
+   "metadata": {},
+   "source": [
+    "# Few Shot Prompt examples\n",
+    "Notebook showing off how canonical prompts in LangChain can be recreated as FewShotPrompts"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "18c67cc9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.prompts.few_shot import FewShotPromptTemplate\n",
+    "from langchain.prompts.prompt import PromptTemplate"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "2a729c9f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Self Ask with Search\n",
+    "\n",
+    "examples = [\n",
+    "  {\n",
+    "    \"question\": \"Who lived longer, Muhammad Ali or Alan Turing?\",\n",
+    "    \"answer\": \"Are follow up questions needed here: Yes.\\nFollow up: How old was Muhammad Ali when he died?\\nIntermediate answer: Muhammad Ali was 74 years old when he died.\\nFollow up: How old was Alan Turing when he died?\\nIntermediate answer: Alan Turing was 41 years old when he died.\\nSo the final answer is: Muhammad Ali\"\n",
+    "  },\n",
+    "  {\n",
+    "    \"question\": \"When was the founder of craigslist born?\",\n",
+    "    \"answer\": \"Are follow up questions needed here: Yes.\\nFollow up: Who was the founder of craigslist?\\nIntermediate answer: Craigslist was founded by Craig Newmark.\\nFollow up: When was Craig Newmark born?\\nIntermediate answer: Craig Newmark was born on December 6, 1952.\\nSo the final answer is: December 6, 1952\"\n",
+    "  },\n",
+    "  {\n",
+    "    \"question\": \"Who was the maternal grandfather of George Washington?\",\n",
+    "    \"answer\": \"Are follow up questions needed here: Yes.\\nFollow up: Who was the mother of George Washington?\\nIntermediate answer: The mother of George Washington was Mary Ball Washington.\\nFollow up: Who was the father of Mary Ball Washington?\\nIntermediate answer: The father of Mary Ball Washington was Joseph Ball.\\nSo the final answer is: Joseph Ball\"\n",
+    "  },\n",
+    "  {\n",
+    "    \"question\": \"Are both the directors of Jaws and Casino Royale from the same country?\",\n",
+    "    \"answer\": \"Are follow up questions needed here: Yes.\\nFollow up: Who is the director of Jaws?\\nIntermediate Answer: The director of Jaws is Steven Spielberg.\\nFollow up: Where is Steven Spielberg from?\\nIntermediate Answer: The United States.\\nFollow up: Who is the director of Casino Royale?\\nIntermediate Answer: The director of Casino Royale is Martin Campbell.\\nFollow up: Where is Martin Campbell from?\\nIntermediate Answer: New Zealand.\\nSo the final answer is: No\"\n",
+    "  }\n",
+    "]\n",
+    "example_prompt = PromptTemplate(input_variables=[\"question\", \"answer\"], template=\"Question: {question}\\n{answer}\")\n",
+    "\n",
+    "prompt = FewShotPromptTemplate(\n",
+    "    examples=examples, \n",
+    "    example_prompt=example_prompt, \n",
+    "    suffix=\"Question: {input}\", \n",
+    "    input_variables=[\"input\"]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "95fc0059",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# ReAct\n",
+    "\n",
+    "examples = [\n",
+    "  {\n",
+    "    \"question\": \"What is the elevation range for the area that the eastern sector of the Colorado orogeny extends into?\",\n",
+    "    \"answer\": \"Thought 1: I need to search Colorado orogeny, find the area that the eastern sector of the Colorado orogeny extends into, then find the elevation range of that area.\\nAction 1: Search[Colorado orogeny]\\nObservation 1: The Colorado orogeny was an episode of mountain building (an orogeny) in Colorado and surrounding areas.\\nThought 2: It does not mention the eastern sector. So I need to look up eastern sector.\\nAction 2: Lookup[eastern sector]\\nObservation 2: (Result 1 / 1) The eastern sector extends into the High Plains and is called the Central Plains orogeny.\\nThought 3: The eastern sector of Colorado orogeny extends into the High Plains. So I need to search High Plains and find its elevation range.\\nAction 3: Search[High Plains]\\nObservation 3: High Plains refers to one of two distinct land regions\\nThought 4: I need to instead search High Plains (United States).\\nAction 4: Search[High Plains (United States)]\\nObservation 4: The High Plains are a subregion of the Great Plains. From east to west, the High Plains rise in elevation from around 1,800 to 7,000 ft (550 to 2,130 m).[3]\\nThought 5: High Plains rise in elevation from around 1,800 to 7,000 ft, so the answer is 1,800 to 7,000 ft.\\nAction 5: Finish[1,800 to 7,000 ft]\"\n",
+    "  },\n",
+    "  {\n",
+    "    \"question\": \"Musician and satirist Allie Goertz wrote a song about the \\\"The Simpsons\\\" character Milhouse, who Matt Groening named after who?\",\n",
+    "    \"answer\": \"Thought 1: The question simplifies to \\\"The Simpsons\\\" character Milhouse is named after who. I only need to search Milhouse and find who it is named after.\\nAction 1: Search[Milhouse]\\nObservation 1: Milhouse Mussolini Van Houten is a recurring character in the Fox animated television series The Simpsons voiced by Pamela Hayden and created by Matt Groening.\\nThought 2: The paragraph does not tell who Milhouse is named after, maybe I can look up \\\"named after\\\".\\nAction 2: Lookup[named after]\\nObservation 2: (Result 1 / 1) Milhouse was named after U.S. president Richard Nixon, whose middle name was Milhous.\\nThought 3: Milhouse was named after U.S. president Richard Nixon, so the answer is Richard Nixon.\\nAction 3: Finish[Richard Nixon]\"\n",
+    "  },\n",
+    "  {\n",
+    "    \"question\": \"Which documentary is about Finnish rock groups, Adam Clayton Powell or The Saimaa Gesture?\",\n",
+    "    \"answer\": \"Thought 1: I need to search Adam Clayton Powell and The Saimaa Gesture, and find which documentary is about Finnish rock groups.\\nAction 1: Search[Adam Clayton Powell]\\nObservation 1 Could not find [Adam Clayton Powell]. Similar: [’Adam Clayton Powell III’, ’Seventh Avenue (Manhattan)’, ’Adam Clayton Powell Jr. State Office Building’, ’Isabel Washington Powell’, ’Adam Powell’, ’Adam Clayton Powell (film)’, ’Giancarlo Esposito’].\\nThought 2: To find the documentary, I can search Adam Clayton Powell (film).\\nAction 2: Search[Adam Clayton Powell (film)]\\nObservation 2: Adam Clayton Powell is a 1989 American documentary film directed by Richard Kilberg. The film is about the rise and fall of influential African-American politician Adam Clayton Powell Jr.[3][4] It was later aired as part of the PBS series The American Experience.\\nThought 3: Adam Clayton Powell (film) is a documentary about an African-American politician, not Finnish rock groups. So the documentary about Finnish rock groups must instead be The Saimaa Gesture.\\nAction 3: Finish[The Saimaa Gesture]\"\n",
+    "  },\n",
+    "  {\n",
+    "    \"question\": \"What profession does Nicholas Ray and Elia Kazan have in common?\",\n",
+    "    \"answer\": \"Thought 1: I need to search Nicholas Ray and Elia Kazan, find their professions, then find the profession they have in common.\\nAction 1: Search[Nicholas Ray]\\nObservation 1: Nicholas Ray (born Raymond Nicholas Kienzle Jr., August 7, 1911 - June 16, 1979) was an American film director, screenwriter, and actor best known for the 1955 film Rebel Without a Cause.\\nThought 2: Professions of Nicholas Ray are director, screenwriter, and actor. I need to search Elia Kazan next and find his professions.\\nAction 2: Search[Elia Kazan]\\nObservation 2: Elia Kazan was an American film and theatre director, producer, screenwriter and actor.\\nThought 3: Professions of Elia Kazan are director, producer, screenwriter, and actor. So profession Nicholas Ray and Elia Kazan have in common is director, screenwriter, and actor.\\nAction 3: Finish[director, screenwriter, actor]\"\n",
+    "  },\n",
+    "  {\n",
+    "    \"question\": \"Which magazine was started first Arthur’s Magazine or First for Women?\",\n",
+    "    \"answer\": \"Thought 1: I need to search Arthur’s Magazine and First for Women, and find which was started first.\\nAction 1: Search[Arthur’s Magazine]\\nObservation 1: Arthur’s Magazine (1844-1846) was an American literary periodical published in Philadelphia in the 19th century.\\nThought 2: Arthur’s Magazine was started in 1844. I need to search First for Women next.\\nAction 2: Search[First for Women]\\nObservation 2: First for Women is a woman’s magazine published by Bauer Media Group in the USA.[1] The magazine was started in 1989.\\nThought 3: First for Women was started in 1989. 1844 (Arthur’s Magazine) < 1989 (First for Women), so Arthur’s Magazine was started first.\\nAction 3: Finish[Arthur’s Magazine]\"\n",
+    "  },\n",
+    "  {\n",
+    "    \"question\": \"Were Pavel Urysohn and Leonid Levin known for the same type of work?\",\n",
+    "    \"answer\": \"Thought 1: I need to search Pavel Urysohn and Leonid Levin, find their types of work, then find if they are the same.\\nAction 1: Search[Pavel Urysohn]\\nObservation 1: Pavel Samuilovich Urysohn (February 3, 1898 - August 17, 1924) was a Soviet mathematician who is best known for his contributions in dimension theory.\\nThought 2: Pavel Urysohn is a mathematician. I need to search Leonid Levin next and find its type of work.\\nAction 2: Search[Leonid Levin]\\nObservation 2: Leonid Anatolievich Levin is a Soviet-American mathematician and computer scientist.\\nThought 3: Leonid Levin is a mathematician and computer scientist. So Pavel Urysohn and Leonid Levin have the same type of work.\\nAction 3: Finish[yes]\"\n",
+    "  }\n",
+    "]\n",
+    "example_prompt = PromptTemplate(input_variables=[\"question\", \"answer\"], template=\"Question: {question}\\n{answer}\")\n",
+    "\n",
+    "prompt = FewShotPromptTemplate(\n",
+    "    examples=examples, \n",
+    "    example_prompt=example_prompt, \n",
+    "    suffix=\"Question: {input}\", \n",
+    "    input_variables=[\"input\"]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "897d4e08",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# LLM Math\n",
+    "examples = [\n",
+    "  {\n",
+    "    \"question\": \"What is 37593 * 67?\",\n",
+    "    \"answer\": \"```python\\nprint(37593 * 67)\\n```\\n```output\\n2518731\\n```\\nAnswer: 2518731\"\n",
+    "  }\n",
+    "]\n",
+    "example_prompt = PromptTemplate(input_variables=[\"question\", \"answer\"], template=\"Question: {question}\\n\\n{answer}\")\n",
+    "\n",
+    "prompt = FewShotPromptTemplate(\n",
+    "    examples=examples, \n",
+    "    example_prompt=example_prompt, \n",
+    "    suffix=\"Question: {input}\", \n",
+    "    input_variables=[\"input\"]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "7ab7379f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# NatBot\n",
+    "example_seperator = \"==================================================\"\n",
+    "content_1 = \"\"\"<link id=1>About</link>\n",
+    "<link id=2>Store</link>\n",
+    "<link id=3>Gmail</link>\n",
+    "<link id=4>Images</link>\n",
+    "<link id=5>(Google apps)</link>\n",
+    "<link id=6>Sign in</link>\n",
+    "<img id=7 alt=\"(Google)\"/>\n",
+    "<input id=8 alt=\"Search\"></input>\n",
+    "<button id=9>(Search by voice)</button>\n",
+    "<button id=10>(Google Search)</button>\n",
+    "<button id=11>(I'm Feeling Lucky)</button>\n",
+    "<link id=12>Advertising</link>\n",
+    "<link id=13>Business</link>\n",
+    "<link id=14>How Search works</link>\n",
+    "<link id=15>Carbon neutral since 2007</link>\n",
+    "<link id=16>Privacy</link>\n",
+    "<link id=17>Terms</link>\n",
+    "<text id=18>Settings</text>\"\"\"\n",
+    "content_2 = \"\"\"<link id=1>About</link>\n",
+    "<link id=2>Store</link>\n",
+    "<link id=3>Gmail</link>\n",
+    "<link id=4>Images</link>\n",
+    "<link id=5>(Google apps)</link>\n",
+    "<link id=6>Sign in</link>\n",
+    "<img id=7 alt=\"(Google)\"/>\n",
+    "<input id=8 alt=\"Search\"></input>\n",
+    "<button id=9>(Search by voice)</button>\n",
+    "<button id=10>(Google Search)</button>\n",
+    "<button id=11>(I'm Feeling Lucky)</button>\n",
+    "<link id=12>Advertising</link>\n",
+    "<link id=13>Business</link>\n",
+    "<link id=14>How Search works</link>\n",
+    "<link id=15>Carbon neutral since 2007</link>\n",
+    "<link id=16>Privacy</link>\n",
+    "<link id=17>Terms</link>\n",
+    "<text id=18>Settings</text>\"\"\"\n",
+    "content_3 = \"\"\"<button id=1>For Businesses</button>\n",
+    "<button id=2>Mobile</button>\n",
+    "<button id=3>Help</button>\n",
+    "<button id=4 alt=\"Language Picker\">EN</button>\n",
+    "<link id=5>OpenTable logo</link>\n",
+    "<button id=6 alt =\"search\">Search</button>\n",
+    "<text id=7>Find your table for any occasion</text>\n",
+    "<button id=8>(Date selector)</button>\n",
+    "<text id=9>Sep 28, 2022</text>\n",
+    "<text id=10>7:00 PM</text>\n",
+    "<text id=11>2 people</text>\n",
+    "<input id=12 alt=\"Location, Restaurant, or Cuisine\"></input>\n",
+    "<button id=13>Let’s go</button>\n",
+    "<text id=14>It looks like you're in Peninsula. Not correct?</text>\n",
+    "<button id=15>Get current location</button>\n",
+    "<button id=16>Next</button>\"\"\"\n",
+    "examples = [\n",
+    "    {\n",
+    "        \"i\": 1,\n",
+    "        \"content\": content_1,\n",
+    "        \"objective\": \"Find a 2 bedroom house for sale in Anchorage AK for under $750k\",\n",
+    "        \"current_url\": \"https://www.google.com/\",\n",
+    "        \"command\": 'TYPESUBMIT 8 \"anchorage redfin\"'\n",
+    "    },\n",
+    "    {\n",
+    "        \"i\": 2,\n",
+    "        \"content\": content_2,\n",
+    "        \"objective\": \"Make a reservation for 4 at Dorsia at 8pm\",\n",
+    "        \"current_url\": \"https://www.google.com/\",\n",
+    "        \"command\": 'TYPESUBMIT 8 \"dorsia nyc opentable\"'\n",
+    "    },\n",
+    "    {\n",
+    "        \"i\": 3,\n",
+    "        \"content\": content_3,\n",
+    "        \"objective\": \"Make a reservation for 4 for dinner at Dorsia in New York City at 8pm\",\n",
+    "        \"current_url\": \"https://www.opentable.com/\",\n",
+    "        \"command\": 'TYPESUBMIT 12 \"dorsia new york city\"'\n",
+    "    },\n",
+    "]\n",
+    "example_prompt_template=\"\"\"EXAMPLE {i}:\n",
+    "==================================================\n",
+    "CURRENT BROWSER CONTENT:\n",
+    "------------------\n",
+    "{content}\n",
+    "------------------\n",
+    "OBJECTIVE: {objective}\n",
+    "CURRENT URL: {current_url}\n",
+    "YOUR COMMAND:\n",
+    "{command}\"\"\"\n",
+    "example_prompt = PromptTemplate(input_variables=[\"i\", \"content\", \"objective\", \"current_url\", \"command\"], template=example_prompt_template)\n",
+    "\n",
+    "\n",
+    "prefix = \"\"\"\n",
+    "You are an agent controlling a browser. You are given:\n",
+    "\t(1) an objective that you are trying to achieve\n",
+    "\t(2) the URL of your current web page\n",
+    "\t(3) a simplified text description of what's visible in the browser window (more on that below)\n",
+    "You can issue these commands:\n",
+    "\tSCROLL UP - scroll up one page\n",
+    "\tSCROLL DOWN - scroll down one page\n",
+    "\tCLICK X - click on a given element. You can only click on links, buttons, and inputs!\n",
+    "\tTYPE X \"TEXT\" - type the specified text into the input with id X\n",
+    "\tTYPESUBMIT X \"TEXT\" - same as TYPE above, except then it presses ENTER to submit the form\n",
+    "The format of the browser content is highly simplified; all formatting elements are stripped.\n",
+    "Interactive elements such as links, inputs, buttons are represented like this:\n",
+    "\t\t<link id=1>text</link>\n",
+    "\t\t<button id=2>text</button>\n",
+    "\t\t<input id=3>text</input>\n",
+    "Images are rendered as their alt text like this:\n",
+    "\t\t<img id=4 alt=\"\"/>\n",
+    "Based on your given objective, issue whatever command you believe will get you closest to achieving your goal.\n",
+    "You always start on Google; you should submit a search query to Google that will take you to the best page for\n",
+    "achieving your objective. And then interact with that page to achieve your objective.\n",
+    "If you find yourself on Google and there are no search results displayed yet, you should probably issue a command\n",
+    "like \"TYPESUBMIT 7 \"search query\"\" to get to a more useful page.\n",
+    "Then, if you find yourself on a Google search results page, you might issue the command \"CLICK 24\" to click\n",
+    "on the first link in the search results. (If your previous command was a TYPESUBMIT your next command should\n",
+    "probably be a CLICK.)\n",
+    "Don't try to interact with elements that you can't see.\n",
+    "Here are some examples:\n",
+    "\"\"\"\n",
+    "suffix=\"\"\"\n",
+    "The current browser content, objective, and current URL follow. Reply with your next command to the browser.\n",
+    "CURRENT BROWSER CONTENT:\n",
+    "------------------\n",
+    "{browser_content}\n",
+    "------------------\n",
+    "OBJECTIVE: {objective}\n",
+    "CURRENT URL: {url}\n",
+    "PREVIOUS COMMAND: {previous_command}\n",
+    "YOUR COMMAND:\n",
+    "\"\"\"\n",
+    "PROMPT = FewShotPromptTemplate(\n",
+    "    examples = examples,\n",
+    "    example_prompt=example_prompt,\n",
+    "    example_separator=example_seperator,\n",
+    "    input_variables=[\"browser_content\", \"url\", \"previous_command\", \"objective\"],\n",
+    "    prefix=prefix,\n",
+    "    suffix=suffix,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ce5927c6",
+   "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": "3.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/examples/prompts/generate_examples.ipynb

@@ -100,14 +100,23 @@
       "text/plain": [
        "['',\n",
        " '',\n",
-       " 'Question: What is the difference between the Illinois and Missouri orogeny?',\n",
-       " 'Thought 1: I need to search Illinois and Missouri orogeny, and find the difference between them.',\n",
-       " 'Action 1: Search[Illinois orogeny]',\n",
-       " 'Observation 1: The Illinois orogeny is a hypothesized orogenic event that occurred in the Late Paleozoic either in the Pennsylvanian or Permian period.',\n",
-       " 'Thought 2: The Illinois orogeny is a hypothesized orogenic event. I need to search Missouri orogeny next and find its details.',\n",
-       " 'Action 2: Search[Missouri orogeny]',\n",
-       " 'Observation 2: The Missouri orogeny was a major tectonic event that occurred in the late Pennsylvanian and early Permian period (about 300 million years ago).',\n",
-       " 'Thought 3: The Illinois orogeny is hypothesized and occurred in the Late Paleozoic and the Missouri orogeny was a major tectonic event that occurred in the late Pennsylvanian and early Permian period. So the difference between the Illinois and Missouri orogeny is that the Illinois orogeny is hypothesized and occurred in the Late Paleozoic while the Missouri orogeny was a major']"
+       " 'Question: What is the highest mountain peak in North America?',\n",
+       " '',\n",
+       " 'Thought 1: I need to search North America and find the highest mountain peak.',\n",
+       " '',\n",
+       " 'Action 1: Search[North America]',\n",
+       " '',\n",
+       " 'Observation 1: North America is a continent entirely within the Northern Hemisphere and almost all within the Western Hemisphere.',\n",
+       " '',\n",
+       " 'Thought 2: I need to look up \"highest mountain peak\".',\n",
+       " '',\n",
+       " 'Action 2: Lookup[highest mountain peak]',\n",
+       " '',\n",
+       " 'Observation 2: (Result 1 / 1) Denali, formerly Mount McKinley, is the highest mountain peak in North America, with a summit elevation of 20,310 feet (6,190 m) above sea level.',\n",
+       " '',\n",
+       " 'Thought 3: Denali is the highest mountain peak in North America, with a summit elevation of 20,310 feet.',\n",
+       " '',\n",
+       " 'Action 3: Finish[20,310 feet]']"
       ]
      },
      "execution_count": 4,
@@ -144,12 +153,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
-  },
-  "vscode": {
-   "interpreter": {
-    "hash": "b1677b440931f40d89ef8be7bf03acb108ce003de0ac9b18e8d43753ea2e7103"
-   }
+   "version": "3.7.6"
   }
  },
  "nbformat": 4,

docs/examples/prompts/prompt_management.ipynb

@@ -5,7 +5,7 @@
    "id": "43fb16cb",
    "metadata": {},
    "source": [
-    "# Getting Started\n",
+    "# Prompt Management\n",
     "\n",
     "Managing your prompts is annoying and tedious, with everyone writing their own slightly different variants of the same ideas. But it shouldn't be this way. \n",
     "\n",
@@ -50,7 +50,7 @@
     "The only two things that define a prompt are:\n",
     "\n",
     "1. `input_variables`: The user inputted variables that are needed to format the prompt.\n",
-    "2. `format`: A method which takes in keyword arguments and returns a formatted prompt. The keys are expected to be the input variables\n",
+    "2. `format`: A method which takes in keyword arguments are returns a formatted prompt. The keys are expected to be the input variables\n",
     "    \n",
     "The rest of the logic of how the prompt is constructed is left up to different implementations. Let's take a look at some below."
    ]
@@ -71,7 +71,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 1,
    "id": "094229f4",
    "metadata": {},
    "outputs": [],
@@ -81,7 +81,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 2,
    "id": "ab46bd2a",
    "metadata": {},
    "outputs": [
@@ -91,7 +91,7 @@
        "'Tell me a joke.'"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -104,7 +104,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 3,
    "id": "c3ad0fa8",
    "metadata": {},
    "outputs": [
@@ -114,7 +114,7 @@
        "'Tell me a funny joke.'"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -127,7 +127,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 4,
    "id": "ba577dcf",
    "metadata": {},
    "outputs": [
@@ -137,7 +137,7 @@
        "'Tell me a funny joke about chickens.'"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -151,100 +151,6 @@
     "multiple_input_prompt.format(adjective=\"funny\", content=\"chickens\")"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "cc991ad2",
-   "metadata": {},
-   "source": [
-    "## From Template\n",
-    "You can also easily load a prompt template by just specifying the template, and not worrying about the input variables."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "d0a0756c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "template = \"Tell me a {adjective} joke about {content}.\"\n",
-    "multiple_input_prompt = PromptTemplate.from_template(template)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "59046640",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "PromptTemplate(input_variables=['adjective', 'content'], output_parser=None, template='Tell me a {adjective} joke about {content}.', template_format='f-string', validate_template=True)"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "multiple_input_prompt"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "b2dd6154",
-   "metadata": {},
-   "source": [
-    "## Alternative formats\n",
-    "\n",
-    "This section shows how to use alternative formats besides \"f-string\" to format prompts."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "53b41b6a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Jinja2\n",
-    "template = \"\"\"\n",
-    "{% for item in items %}\n",
-    "Question: {{ item.question }}\n",
-    "Answer: {{ item.answer }}\n",
-    "{% endfor %}\n",
-    "\"\"\"\n",
-    "items=[{\"question\": \"foo\", \"answer\": \"bar\"},{\"question\": \"1\", \"answer\": \"2\"}]\n",
-    "jinja2_prompt = PromptTemplate(\n",
-    "    input_variables=[\"items\"], \n",
-    "    template=template,\n",
-    "    template_format=\"jinja2\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "ba8aabd3",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'\\n\\nQuestion: foo\\nAnswer: bar\\n\\nQuestion: 1\\nAnswer: 2\\n'"
-      ]
-     },
-     "execution_count": 10,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "jinja2_prompt.format(items=items)"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "1492b49d",
@@ -261,7 +167,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 5,
    "id": "3eb36972",
    "metadata": {},
    "outputs": [],
@@ -280,7 +186,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 6,
    "id": "80a91d96",
    "metadata": {},
    "outputs": [],
@@ -290,7 +196,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 7,
    "id": "7931e5f2",
    "metadata": {},
    "outputs": [
@@ -332,69 +238,6 @@
     "print(prompt_from_string_examples.format(adjective=\"big\"))"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "874b7575",
-   "metadata": {},
-   "source": [
-    "## Few Shot Prompts with Templates\n",
-    "We can also construct few shot prompt templates where the prefix and suffix themselves are prompt templates"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "e710115f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.prompts import FewShotPromptWithTemplates"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "5bf23a65",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "prefix = PromptTemplate(input_variables=[\"content\"], template=\"This is a test about {content}.\")\n",
-    "suffix = PromptTemplate(input_variables=[\"new_content\"], template=\"Now you try to talk about {new_content}.\")\n",
-    "\n",
-    "prompt = FewShotPromptWithTemplates(\n",
-    "    suffix=suffix,\n",
-    "    prefix=prefix,\n",
-    "    input_variables=[\"content\", \"new_content\"],\n",
-    "    examples=examples,\n",
-    "    example_prompt=example_prompt,\n",
-    "    example_separator=\"\\n\",\n",
-    ")\n",
-    "output = prompt.format(content=\"animals\", new_content=\"party\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "d4036351",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "This is a test about animals.\n",
-      "Input: happy\n",
-      "Output: sad\n",
-      "Input: tall\n",
-      "Output: short\n",
-      "Now you try to talk about party.\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(output)"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "bf038596",
@@ -428,7 +271,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 8,
    "id": "7c469c95",
    "metadata": {},
    "outputs": [],
@@ -438,7 +281,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 9,
    "id": "0ec6d950",
    "metadata": {},
    "outputs": [],
@@ -455,7 +298,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 10,
    "id": "207e55f7",
    "metadata": {},
    "outputs": [],
@@ -467,7 +310,7 @@
     "    example_prompt=example_prompt, \n",
     "    # This is the maximum length that the formatted examples should be.\n",
     "    # Length is measured by the get_text_length function below.\n",
-    "    max_length=25,\n",
+    "    max_length=18,\n",
     "    # This is the function used to get the length of a string, which is used\n",
     "    # to determine which examples to include. It is commented out because\n",
     "    # it is provided as a default value if none is specified.\n",
@@ -485,7 +328,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 11,
    "id": "d00b4385",
    "metadata": {},
    "outputs": [
@@ -522,7 +365,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 12,
    "id": "878bcde9",
    "metadata": {},
    "outputs": [
@@ -535,59 +378,17 @@
       "Input: happy\n",
       "Output: sad\n",
       "\n",
-      "Input: big and huge and massive and large and gigantic and tall and much much much much much bigger than everything else\n",
+      "Input: big and huge and massive and large and gigantic and tall and bigger than everything else\n",
       "Output:\n"
      ]
     }
    ],
    "source": [
     "# An example with long input, so it selects only one example.\n",
-    "long_string = \"big and huge and massive and large and gigantic and tall and much much much much much bigger than everything else\"\n",
+    "long_string = \"big and huge and massive and large and gigantic and tall and bigger than everything else\"\n",
     "print(dynamic_prompt.format(adjective=long_string))"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "id": "e4bebcd9",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Give the antonym of every input\n",
-      "\n",
-      "Input: happy\n",
-      "Output: sad\n",
-      "\n",
-      "Input: tall\n",
-      "Output: short\n",
-      "\n",
-      "Input: energetic\n",
-      "Output: lethargic\n",
-      "\n",
-      "Input: sunny\n",
-      "Output: gloomy\n",
-      "\n",
-      "Input: windy\n",
-      "Output: calm\n",
-      "\n",
-      "Input: big\n",
-      "Output: small\n",
-      "\n",
-      "Input: enthusiastic\n",
-      "Output:\n"
-     ]
-    }
-   ],
-   "source": [
-    "# You can add an example to an example selector as well.\n",
-    "new_example = {\"input\": \"big\", \"output\": \"small\"}\n",
-    "dynamic_prompt.example_selector.add_example(new_example)\n",
-    "print(dynamic_prompt.format(adjective=\"enthusiastic\"))"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "2d007b0a",
@@ -600,31 +401,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 13,
    "id": "241bfe80",
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain.prompts.example_selector import SemanticSimilarityExampleSelector\n",
-    "from langchain.vectorstores import Chroma\n",
+    "from langchain.vectorstores import FAISS\n",
     "from langchain.embeddings import OpenAIEmbeddings"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 14,
    "id": "50d0a701",
    "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"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "example_selector = SemanticSimilarityExampleSelector.from_examples(\n",
     "    # This is the list of examples available to select from.\n",
@@ -632,7 +424,7 @@
     "    # This is the embedding class used to produce embeddings which are used to measure semantic similarity.\n",
     "    OpenAIEmbeddings(), \n",
     "    # This is the VectorStore class that is used to store the embeddings and do a similarity search over.\n",
-    "    Chroma, \n",
+    "    FAISS, \n",
     "    # This is the number of examples to produce.\n",
     "    k=1\n",
     ")\n",
@@ -648,7 +440,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 15,
    "id": "4c8fdf45",
    "metadata": {},
    "outputs": [
@@ -673,11 +465,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 16,
    "id": "829af21a",
-   "metadata": {
-    "scrolled": true
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -685,8 +475,8 @@
      "text": [
       "Give the antonym of every input\n",
       "\n",
-      "Input: happy\n",
-      "Output: sad\n",
+      "Input: tall\n",
+      "Output: short\n",
       "\n",
       "Input: fat\n",
       "Output:\n"
@@ -694,141 +484,10 @@
     }
    ],
    "source": [
-    "# Input is a measurement, so should select the tall/short example\n",
+    "# Input is a measurment, so should select the tall/short example\n",
     "print(similar_prompt.format(adjective=\"fat\"))"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 20,
-   "id": "3c16fe23",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Give the antonym of every input\n",
-      "\n",
-      "Input: happy\n",
-      "Output: sad\n",
-      "\n",
-      "Input: joyful\n",
-      "Output:\n"
-     ]
-    }
-   ],
-   "source": [
-    "# You can add new examples to the SemanticSimilarityExampleSelector as well\n",
-    "similar_prompt.example_selector.add_example({\"input\": \"enthusiastic\", \"output\": \"apathetic\"})\n",
-    "print(similar_prompt.format(adjective=\"joyful\"))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "bc35afd0",
-   "metadata": {},
-   "source": [
-    "### Maximal Marginal Relevance ExampleSelector\n",
-    "\n",
-    "The MaxMarginalRelevanceExampleSelector selects examples based on a combination of which examples are most similar to the inputs, while also optimizing for diversity. It does this by finding the examples with the embeddings that have the greatest cosine similarity with the inputs, and then iteratively adding them while penalizing them for closeness to already selected examples.\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 21,
-   "id": "ac95c968",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.prompts.example_selector import MaxMarginalRelevanceExampleSelector\n",
-    "from langchain.vectorstores import FAISS"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "id": "db579bea",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "example_selector = MaxMarginalRelevanceExampleSelector.from_examples(\n",
-    "    # This is the list of examples available to select from.\n",
-    "    examples, \n",
-    "    # This is the embedding class used to produce embeddings which are used to measure semantic similarity.\n",
-    "    OpenAIEmbeddings(), \n",
-    "    # This is the VectorStore class that is used to store the embeddings and do a similarity search over.\n",
-    "    FAISS, \n",
-    "    # This is the number of examples to produce.\n",
-    "    k=2\n",
-    ")\n",
-    "mmr_prompt = FewShotPromptTemplate(\n",
-    "    # We provide an ExampleSelector instead of examples.\n",
-    "    example_selector=example_selector,\n",
-    "    example_prompt=example_prompt,\n",
-    "    prefix=\"Give the antonym of every input\",\n",
-    "    suffix=\"Input: {adjective}\\nOutput:\", \n",
-    "    input_variables=[\"adjective\"],\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 23,
-   "id": "cd76e344",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Give the antonym of every input\n",
-      "\n",
-      "Input: happy\n",
-      "Output: sad\n",
-      "\n",
-      "Input: windy\n",
-      "Output: calm\n",
-      "\n",
-      "Input: worried\n",
-      "Output:\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Input is a feeling, so should select the happy/sad example as the first one\n",
-    "print(mmr_prompt.format(adjective=\"worried\"))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 24,
-   "id": "cf82956b",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Give the antonym of every input\n",
-      "\n",
-      "Input: happy\n",
-      "Output: sad\n",
-      "\n",
-      "Input: enthusiastic\n",
-      "Output: apathetic\n",
-      "\n",
-      "Input: worried\n",
-      "Output:\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Let's compare this to what we would just get if we went solely off of similarity\n",
-    "similar_prompt.example_selector.k = 2\n",
-    "print(similar_prompt.format(adjective=\"worried\"))"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "dbc32551",
@@ -873,12 +532,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
-  },
-  "vscode": {
-   "interpreter": {
-    "hash": "b1677b440931f40d89ef8be7bf03acb108ce003de0ac9b18e8d43753ea2e7103"
-   }
+   "version": "3.7.6"
   }
  },
  "nbformat": 4,

docs/examples/prompts/prompt_serialization.ipynb

@@ -11,7 +11,7 @@
     "\n",
     "At a high level, the following design principles are applied to serialization:\n",
     "\n",
-    "1. Both JSON and YAML are supported. We want to support serialization methods that are human readable on disk, and YAML and JSON are two of the most popular methods for that. Note that this rule applies to prompts. For other assets, like Examples, different serialization methods may be supported.\n",
+    "1. Both JSON and YAML are supported. We want to support serialization methods are human readable on disk, and YAML and JSON are two of the most popular methods for that. Note that this rule applies to prompts. For other assets, like Examples, different serialization methods may be supported.\n",
     "\n",
     "2. We support specifying everything in one file, or storing different components (templates, examples, etc) in different files and referencing them. For some cases, storing everything in file makes the most sense, but for others it is preferrable to split up some of the assets (long templates, large examples, reusable components). LangChain supports both.\n",
     "\n",
@@ -225,35 +225,6 @@
     "!cat examples.json"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "d3052850",
-   "metadata": {},
-   "source": [
-    "And here is what the same examples stored as yaml might look like."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "901385d1",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "- input: happy\r\n",
-      "  output: sad\r\n",
-      "- input: tall\r\n",
-      "  output: short\r\n"
-     ]
-    }
-   ],
-   "source": [
-    "!cat examples.yaml"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "8e300335",
@@ -265,7 +236,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 9,
    "id": "e2bec0fc",
    "metadata": {},
    "outputs": [
@@ -296,7 +267,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 10,
    "id": "98c8f356",
    "metadata": {},
    "outputs": [
@@ -322,73 +293,6 @@
     "print(prompt.format(adjective=\"funny\"))"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "13620324",
-   "metadata": {},
-   "source": [
-    "The same would work if you loaded examples from the yaml file."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "831e5e4a",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "_type: few_shot\r\n",
-      "input_variables:\r\n",
-      "    [\"adjective\"]\r\n",
-      "prefix: \r\n",
-      "    Write antonyms for the following words.\r\n",
-      "example_prompt:\r\n",
-      "    input_variables:\r\n",
-      "        [\"input\", \"output\"]\r\n",
-      "    template:\r\n",
-      "        \"Input: {input}\\nOutput: {output}\"\r\n",
-      "examples:\r\n",
-      "    examples.yaml\r\n",
-      "suffix:\r\n",
-      "    \"Input: {adjective}\\nOutput:\"\r\n"
-     ]
-    }
-   ],
-   "source": [
-    "!cat few_shot_prompt_yaml_examples.yaml"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "6f0a7eaa",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Write antonyms for the following words.\n",
-      "\n",
-      "Input: happy\n",
-      "Output: sad\n",
-      "\n",
-      "Input: tall\n",
-      "Output: short\n",
-      "\n",
-      "Input: funny\n",
-      "Output:\n"
-     ]
-    }
-   ],
-   "source": [
-    "prompt = load_prompt(\"few_shot_prompt_yaml_examples.yaml\")\n",
-    "print(prompt.format(adjective=\"funny\"))"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "4870aa9d",
@@ -400,7 +304,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 11,
    "id": "9d996a86",
    "metadata": {},
    "outputs": [
@@ -428,7 +332,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 12,
    "id": "dd2c10bb",
    "metadata": {},
    "outputs": [
@@ -465,7 +369,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 13,
    "id": "6cd781ef",
    "metadata": {},
    "outputs": [
@@ -496,7 +400,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 14,
    "id": "533ab8a7",
    "metadata": {},
    "outputs": [
@@ -533,7 +437,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 15,
    "id": "0b6dd7b8",
    "metadata": {},
    "outputs": [
@@ -554,7 +458,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 16,
    "id": "76a1065d",
    "metadata": {},
    "outputs": [
@@ -579,7 +483,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 17,
    "id": "744d275d",
    "metadata": {},
    "outputs": [
@@ -604,6 +508,14 @@
     "prompt = load_prompt(\"few_shot_prompt_example_prompt.json\")\n",
     "print(prompt.format(adjective=\"funny\"))"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "dcfc7176",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -622,12 +534,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
-  },
-  "vscode": {
-   "interpreter": {
-    "hash": "8eb71adebe840dca1185e9603533462bc47eb1b1a73bf7dab2d0a8a4c932882e"
-   }
+   "version": "3.7.6"
   }
  },
  "nbformat": 4,

docs/explanation/core_concepts.md

@@ -0,0 +1,27 @@
+# Core Concepts
+
+This section goes over the core concepts of LangChain.
+Understanding these will go a long way in helping you understand the codebase and how to construct chains.
+
+## PromptTemplates
+PromptTemplates generically have a `format` method that takes in variables and returns a formatted string.
+The most simple implementation of this is to have a template string with some variables in it, and then format it with the incoming variables.
+More complex iterations dynamically construct the template string from few shot examples, etc.
+
+For a more detailed explanation of how LangChain approaches prompts and prompt templates, see [here](/examples/prompts/prompt_management).
+
+## LLMs
+Wrappers around Large Language Models (in particular, the `generate` ability of large language models) are some of the core functionality of LangChain.
+These wrappers are classes that are callable: they take in an input string, and return the generated output string.
+
+## Embeddings
+These classes are very similar to the LLM classes in that they are wrappers around models, 
+but rather than return a string they return an embedding (list of floats). This are particularly useful when 
+implementing semantic search functionality. They expose separate methods for embedding queries versus embedding documents.
+
+## Vectorstores
+These are datastores that store documents. They expose a method for passing in a string and finding similar documents.
+
+## Chains
+These are pipelines that combine multiple of the above ideas. 
+They vary greatly in complexity and are combination of generic, highly configurable pipelines and more narrow (but usually more complex) pipelines.

docs/explanation/glossary.md

@@ -4,87 +4,71 @@ This is a collection of terminology commonly used when developing LLM applicatio
 It contains reference to external papers or sources where the concept was first introduced, 
 as well as to places in LangChain where the concept is used.
 
-## Chain of Thought Prompting
+### Chain of Thought Prompting
 
 A prompting technique used to encourage the model to generate a series of intermediate reasoning steps. 
 A less formal way to induce this behavior is to include “Let’s think step-by-step” in the prompt.
 
 Resources:
-
 - [Chain-of-Thought Paper](https://arxiv.org/pdf/2201.11903.pdf)
 - [Step-by-Step Paper](https://arxiv.org/abs/2112.00114)
 
-## Action Plan Generation
+### Action Plan Generation
 
 A prompt usage that uses a language model to generate actions to take. 
 The results of these actions can then be fed back into the language model to generate a subsequent action.
 
 Resources:
-
 - [WebGPT Paper](https://arxiv.org/pdf/2112.09332.pdf)
 - [SayCan Paper](https://say-can.github.io/assets/palm_saycan.pdf)
 
-## ReAct Prompting
+### ReAct Prompting
 
 A prompting technique that combines Chain-of-Thought prompting with action plan generation. 
 This induces the to model to think about what action to take, then take it. 
 
 Resources:
-
 - [Paper](https://arxiv.org/pdf/2210.03629.pdf)
-- [LangChain Example](./modules/agents/implementations/react.ipynb)
+- [LangChain Example](https://github.com/hwchase17/langchain/blob/master/examples/react.ipynb)
 
-## Self-ask
+### Self-ask
 
 A prompting method that builds on top of chain-of-thought prompting. 
 In this method, the model explicitly asks itself follow-up questions, which are then answered by an external search engine. 
 
 Resources:
-
 - [Paper](https://ofir.io/self-ask.pdf)
-- [LangChain Example](./modules/agents/implementations/self_ask_with_search.ipynb)
+- [LangChain Example](https://github.com/hwchase17/langchain/blob/master/examples/self_ask_with_search.ipynb)
 
-## Prompt Chaining
+### Prompt Chaining
 
-Combining multiple LLM calls together, with the output of one-step being the input to the next.
+Combining multiple LLM calls together, with the output of one step being the input to the next. 
 
 Resources: 
-
 - [PromptChainer Paper](https://arxiv.org/pdf/2203.06566.pdf)
 - [Language Model Cascades](https://arxiv.org/abs/2207.10342)
 - [ICE Primer Book](https://primer.ought.org/)
 - [Socratic Models](https://socraticmodels.github.io/)
 
-## Memetic Proxy
+### Memetic Proxy
 
 Encouraging the LLM to respond in a certain way framing the discussion in a context that the model knows of and that will result in that type of response. For example, as a conversation between a student and a teacher. 
 
 Resources:
-
 - [Paper](https://arxiv.org/pdf/2102.07350.pdf)
 
-## Self Consistency
+### Self Consistency
 
 A decoding strategy that samples a diverse set of reasoning paths and then selects the most consistent answer. 
 Is most effective when combined with Chain-of-thought prompting. 
 
 Resources:
-
 - [Paper](https://arxiv.org/pdf/2203.11171.pdf)
 
-## Inception
+### Inception
 
 Also called “First Person Instruction”. 
 Encouraging the model to think a certain way by including the start of the model’s response in the prompt. 
 
 Resources:
-
 - [Example](https://twitter.com/goodside/status/1583262455207460865?s=20&t=8Hz7XBnK1OF8siQrxxCIGQ)
-
-## MemPrompt
-
-MemPrompt maintains a memory of errors and user feedback, and uses them to prevent repetition of mistakes.
-
-Resources:
-
-- [Paper](https://memprompt.com/)

docs/gallery.rst

@@ -1,326 +0,0 @@
-LangChain Gallery
-=============
-
-Lots of people have built some pretty awesome stuff with LangChain.
-This is a collection of our favorites.
-If you see any other demos that you think we should highlight, be sure to let us know!
-
-
-Open Source
------------
-
-.. panels::
-    :body: text-center
-
-    ---
-
-    .. link-button:: https://github.com/bborn/howdoi.ai
-        :type: url
-        :text: HowDoI.ai
-        :classes: stretched-link btn-lg
-
-    +++
-
-    This is an experiment in building a large-language-model-backed chatbot. It can hold a conversation, remember previous comments/questions, 
-    and answer all types of queries (history, web search, movie data, weather, news, and more).
-
-    ---
-
-    .. link-button:: https://colab.research.google.com/drive/1sKSTjt9cPstl_WMZ86JsgEqFG-aSAwkn?usp=sharing
-        :type: url
-        :text: YouTube Transcription QA with Sources
-        :classes: stretched-link btn-lg
-
-    +++
-
-    An end-to-end example of doing question answering on YouTube transcripts, returning the timestamps as sources to legitimize the answer.
-
-    ---
-
-    .. link-button:: https://github.com/normandmickey/MrsStax
-        :type: url
-        :text: QA Slack Bot
-        :classes: stretched-link btn-lg
-
-    +++
-
-    This application is a Slack Bot that uses Langchain and OpenAI's GPT3 language model to provide domain specific answers. You provide the documents.
-
-    ---
-
-    .. link-button:: https://github.com/OpenBioLink/ThoughtSource
-        :type: url
-        :text: ThoughtSource
-        :classes: stretched-link btn-lg
-
-    +++
-
-    A central, open resource and community around data and tools related to chain-of-thought reasoning in large language models.
-
-    ---
-
-    .. link-button:: https://github.com/blackhc/llm-strategy
-        :type: url
-        :text: LLM Strategy
-        :classes: stretched-link btn-lg
-    
-    +++
-
-    This Python package adds a decorator llm_strategy that connects to an LLM (such as OpenAI’s GPT-3) and uses the LLM to "implement" abstract methods in interface classes. It does this by forwarding requests to the LLM and converting the responses back to Python data using Python's @dataclasses.
-
-    ---
-
-    .. link-button:: https://github.com/JohnNay/llm-lobbyist
-        :type: url
-        :text: Zero-Shot Corporate Lobbyist
-        :classes: stretched-link btn-lg
-
-    +++
-
-    A notebook showing how to use GPT to help with the work of a corporate lobbyist.
-
-    ---
-
-    .. link-button:: https://dagster.io/blog/chatgpt-langchain
-        :type: url
-        :text: Dagster Documentation ChatBot
-        :classes: stretched-link btn-lg
-
-    +++
-
-    A jupyter notebook demonstrating how you could create a semantic search engine on documents in one of your Google Folders
-
-    ---
-
-    .. link-button:: https://github.com/venuv/langchain_semantic_search
-        :type: url
-        :text: Google Folder Semantic Search
-        :classes: stretched-link btn-lg
-
-    +++
-
-    Build a GitHub support bot with GPT3, LangChain, and Python.
-
-    ---
-
-    .. link-button:: https://huggingface.co/spaces/team7/talk_with_wind
-        :type: url
-        :text: Talk With Wind
-        :classes: stretched-link btn-lg
-
-    +++
-
-    Record sounds of anything (birds, wind, fire, train station) and chat with it.
-
-    ---
-
-    .. link-button:: https://huggingface.co/spaces/JavaFXpert/Chat-GPT-LangChain
-        :type: url
-        :text: ChatGPT LangChain
-        :classes: stretched-link btn-lg
-
-    +++
-
-    This simple application demonstrates a conversational agent implemented with OpenAI GPT-3.5 and LangChain. When necessary, it leverages tools for complex math, searching the internet, and accessing news and weather.
-
-    ---
-
-    .. link-button:: https://huggingface.co/spaces/JavaFXpert/gpt-math-techniques
-        :type: url
-        :text: GPT Math Techniques
-        :classes: stretched-link btn-lg
-
-    +++
-
-    A Hugging Face spaces project showing off the benefits of using PAL for math problems.
-
-    ---
-
-    .. link-button:: https://colab.research.google.com/drive/1xt2IsFPGYMEQdoJFNgWNAjWGxa60VXdV
-        :type: url
-        :text: GPT Political Compass
-        :classes: stretched-link btn-lg
-
-    +++
-
-    Measure the political compass of GPT.
-
-    ---
-
-    .. link-button:: https://github.com/hwchase17/notion-qa
-        :type: url
-        :text: Notion Database Question-Answering Bot
-        :classes: stretched-link btn-lg
-    
-    +++
-
-    Open source GitHub project shows how to use LangChain to create a chatbot that can answer questions about an arbitrary Notion database.
-
-    ---
-
-    .. link-button:: https://github.com/jerryjliu/gpt_index
-        :type: url
-        :text: GPT Index
-        :classes: stretched-link btn-lg
-    
-    +++
-
-    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.
-
-    ---
-
-    .. link-button:: https://github.com/JavaFXpert/llm-grovers-search-party
-        :type: url
-        :text: Grover's Algorithm
-        :classes: stretched-link btn-lg
-
-    +++
-
-    Leveraging Qiskit, OpenAI and LangChain to demonstrate Grover's algorithm
-
-    ---
-
-    .. link-button:: https://huggingface.co/spaces/rituthombre/QNim
-        :type: url
-        :text: QNimGPT
-        :classes: stretched-link btn-lg
-
-    +++
-
-    A chat UI to play Nim, where a player can select an opponent, either a quantum computer or an AI
-
-    ---
-
-    .. link-button:: https://colab.research.google.com/drive/19WTIWC3prw5LDMHmRMvqNV2loD9FHls6?usp=sharing
-        :type: url
-        :text: ReAct TextWorld
-        :classes: stretched-link btn-lg
-
-    +++
-
-    Leveraging the ReActTextWorldAgent to play TextWorld with an LLM!
-
-    ---
-
-    .. link-button:: https://github.com/jagilley/fact-checker
-        :type: url
-        :text: Fact Checker
-        :classes: stretched-link btn-lg
-    
-    +++
-
-    This repo is a simple demonstration of using LangChain to do fact-checking with prompt chaining.
-    
-    ---
-
-    .. link-button:: https://github.com/arc53/docsgpt
-        :type: url
-        :text: DocsGPT
-        :classes: stretched-link btn-lg
-    
-    +++
-
-    Answer questions about the documentation of any project    
-
-Misc. Colab Notebooks
-~~~~~~~~~~~~~~~
-
-.. panels::
-    :body: text-center
-
-    ---
-
-    .. link-button:: https://colab.research.google.com/drive/1AAyEdTz-Z6ShKvewbt1ZHUICqak0MiwR?usp=sharing
-        :type: url
-        :text: Wolfram Alpha in Conversational Agent
-        :classes: stretched-link btn-lg
-    
-    +++
-
-    Give ChatGPT a WolframAlpha neural implant
-    
-    ---
-
-    .. link-button:: https://colab.research.google.com/drive/1UsCLcPy8q5PMNQ5ytgrAAAHa124dzLJg?usp=sharing
-        :type: url
-        :text: Tool Updates in Agents
-        :classes: stretched-link btn-lg
-    
-    +++
-
-    Agent improvements (6th Jan 2023)
-    
-    ---
-
-    .. link-button:: https://colab.research.google.com/drive/1UsCLcPy8q5PMNQ5ytgrAAAHa124dzLJg?usp=sharing
-        :type: url
-        :text: Conversational Agent with Tools (Langchain AGI)
-        :classes: stretched-link btn-lg
-    
-    +++
-
-    Langchain AGI (23rd Dec 2022)    
-
-Proprietary
------------
-
-.. panels::
-    :body: text-center
-
-    ---
-
-    .. link-button:: https://twitter.com/sjwhitmore/status/1580593217153531908?s=20&t=neQvtZZTlp623U3LZwz3bQ
-        :type: url
-        :text: Daimon
-        :classes: stretched-link btn-lg
-
-    +++
-
-    A chat-based AI personal assistant with long-term memory about you.
-
-    ---
-
-    .. link-button:: https://twitter.com/dory111111/status/1608406234646052870?s=20&t=XYlrbKM0ornJsrtGa0br-g
-        :type: url
-        :text: AI Assisted SQL Query Generator
-        :classes: stretched-link btn-lg
-
-    +++
-
-    An app to write SQL using natural language, and execute against real DB.
-
-    ---
-
-    .. link-button:: https://twitter.com/krrish_dh/status/1581028925618106368?s=20&t=neQvtZZTlp623U3LZwz3bQ
-        :type: url
-        :text: Clerkie
-        :classes: stretched-link btn-lg
-
-    +++
-
-    Stack Tracing QA Bot to help debug complex stack tracing (especially the ones that go multi-function/file deep).
-
-    ---
-
-    .. link-button:: https://twitter.com/Raza_Habib496/status/1596880140490838017?s=20&t=6MqEQYWfSqmJwsKahjCVOA
-        :type: url
-        :text: Sales Email Writer
-        :classes: stretched-link btn-lg
-
-    +++
-
-    By Raza Habib, this demo utilizes LangChain + SerpAPI + HumanLoop to write sales emails. Give it a company name and a person, this application will use Google Search (via SerpAPI) to get more information on the company and the person, and then write them a sales message.
-
-    ---
-
-    .. link-button:: https://twitter.com/chillzaza_/status/1592961099384905730?s=20&t=EhU8jl0KyCPJ7vE9Rnz-cQ
-        :type: url
-        :text: Question-Answering on a Web Browser
-        :classes: stretched-link btn-lg
-
-    +++
-
-    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>`_.
-
-
-

docs/getting_started/chains.md

@@ -0,0 +1,39 @@
+# Using Chains
+
+Calling an LLM is a great first step, but it's just the beginning.
+Normally when you use an LLM in an application, you are not sending user input directly to the LLM.
+Instead, you are probably taking user input and constructing a prompt, and then sending that to the LLM.
+
+For example, in the previous example, the text we passed in was hardcoded to ask for a name for a company that made colorful socks.
+In this imaginary service, what we would want to do is take only the user input describing what the company does, and then format the prompt with that information.
+
+This is easy to do with LangChain!
+
+First lets define the prompt:
+
+```python
+from langchain.prompts import PromptTemplate
+
+prompt = PromptTemplate(
+    input_variables=["product"],
+    template="What is a good name for a company that makes {product}?",
+)
+```
+
+We can now create a very simple chain that will take user input, format the prompt with it, and then send it to the LLM:
+
+```python
+from langchain.chains import LLMChain
+chain = LLMChain(llm=llm, prompt=prompt)
+```
+
+Now we can run that can only specifying the product!
+
+```python
+chain.run("colorful socks")
+```
+
+There we go! There's the first chain.
+
+That is it for the Getting Started example. 
+As a next step, we would suggest checking out the more complex chains in the [Demos section](/examples/demos)

docs/getting_started/environment.md

@@ -0,0 +1,37 @@
+# Setting up your environment
+
+Using LangChain will usually require integrations with one or more model providers, data stores, apis, etc.
+There are two components to setting this up, installing the correct python packages and setting the right environment variables.
+
+## Python packages
+The python package needed varies based on the integration. See the list of integrations for details.
+There should also be helpful error messages raised if you try to run an integration and are missing any required python packages.
+
+## Environment Variables
+The environment variable needed varies based on the integration. See the list of integrations for details.
+There should also be helpful error messages raised if you try to run an integration and are missing any required environment variables.
+
+You can set the environment variable in a few ways. 
+If you are trying to set the environment variable `FOO` to value `bar`, here are the ways you could do so:
+- From the command line:
+```
+export FOO=bar
+```
+- From the python notebook/script:
+```python
+import os
+os.environ["FOO"] = "bar"
+```
+
+For the Getting Started example, we will be using OpenAI's APIs, so we will first need to install their SDK:
+
+```
+pip install openai
+```
+
+We will then need to set the environment variable. Let's do this from inside the Jupyter notebook (or Python script).
+
+```python
+import os
+os.environ["OPENAI_API_KEY"] = "..."
+```

docs/getting_started/getting_started.md

@@ -1,290 +0,0 @@
-# Quickstart Guide
-
-
-This tutorial gives you a quick walkthrough about building an end-to-end language model application with LangChain.
-
-## Installation
-
-To get started, install LangChain with the following command:
-
-```bash
-pip install langchain
-```
-
-
-## Environment Setup
-
-Using LangChain will usually require integrations with one or more model providers, data stores, apis, etc.
-
-For this example, we will be using OpenAI's APIs, so we will first need to install their SDK:
-
-```bash
-pip install openai
-```
-
-We will then need to set the environment variable in the terminal.
-
-```bash
-export OPENAI_API_KEY="..."
-```
-
-Alternatively, you could do this from inside the Jupyter notebook (or Python script):
-
-```python
-import os
-os.environ["OPENAI_API_KEY"] = "..."
-```
-
-
-## Building a Language Model Application
-
-Now that we have installed LangChain and set up our environment, we can start building our language model application.
-
-LangChain provides many modules that can be used to build language model applications. Modules can be combined to create more complex applications, or be used individually for simple applications.
-
-
-
-`````{dropdown} LLMs: Get predictions from a language model
-
-The most basic building block of LangChain is calling an LLM on some input.
-Let's walk through a simple example of how to do this. 
-For this purpose, let's pretend we are building a service that generates a company name based on what the company makes.
-
-In order to do this, we first need to import the LLM wrapper.
-
-```python
-from langchain.llms import OpenAI
-```
-
-We can then initialize the wrapper with any arguments.
-In this example, we probably want the outputs to be MORE random, so we'll initialize it with a HIGH temperature.
-
-```python
-llm = OpenAI(temperature=0.9)
-```
-
-We can now call it on some input!
-
-```python
-text = "What would be a good company name a company that makes colorful socks?"
-print(llm(text))
-```
-
-```pycon
-Feetful of Fun
-```
-
-For more details on how to use LLMs within LangChain, see the [LLM getting started guide](../modules/llms/getting_started.ipynb).
-`````
-
-
-`````{dropdown} Prompt Templates: Manage prompts for LLMs
-
-Calling an LLM is a great first step, but it's just the beginning.
-Normally when you use an LLM in an application, you are not sending user input directly to the LLM.
-Instead, you are probably taking user input and constructing a prompt, and then sending that to the LLM.
-
-For example, in the previous example, the text we passed in was hardcoded to ask for a name for a company that made colorful socks.
-In this imaginary service, what we would want to do is take only the user input describing what the company does, and then format the prompt with that information.
-
-This is easy to do with LangChain!
-
-First lets define the prompt template:
-
-```python
-from langchain.prompts import PromptTemplate
-
-prompt = PromptTemplate(
-    input_variables=["product"],
-    template="What is a good name for a company that makes {product}?",
-)
-```
-
-Let's now see how this works! We can call the `.format` method to format it.
-
-```python
-print(prompt.format(product="colorful socks"))
-```
-
-```pycon
-What is a good name for a company that makes colorful socks?
-```
-
-
-[For more details, check out the getting started guide for prompts.](../modules/prompts/getting_started.ipynb)
-
-`````
-
-
-
-`````{dropdown} Chains: Combine LLMs and prompts in multi-step workflows
-
-Up until now, we've worked with the PromptTemplate and LLM primitives by themselves. But of course, a real application is not just one primitive, but rather a combination of them.
-
-A chain in LangChain is made up of links, which can be either primitives like LLMs or other chains.
-
-The most core type of chain is an LLMChain, which consists of a PromptTemplate and an LLM.
-
-Extending the previous example, we can construct an LLMChain which takes user input, formats it with a PromptTemplate, and then passes the formatted response to an LLM.
-
-```python
-from langchain.prompts import PromptTemplate
-from langchain.llms import OpenAI
-
-llm = OpenAI(temperature=0.9)
-prompt = PromptTemplate(
-    input_variables=["product"],
-    template="What is a good name for a company that makes {product}?",
-)
-```
-
-We can now create a very simple chain that will take user input, format the prompt with it, and then send it to the LLM:
-
-```python
-from langchain.chains import LLMChain
-chain = LLMChain(llm=llm, prompt=prompt)
-```
-
-Now we can run that chain only specifying the product!
-
-```python
-chain.run("colorful socks")
-# -> '\n\nSocktastic!'
-```
-
-There we go! There's the first chain - an LLM Chain.
-This is one of the simpler types of chains, but understanding how it works will set you up well for working with more complex chains.
-
-[For more details, check out the getting started guide for chains.](../modules/chains/getting_started.ipynb)
-
-`````
-
-
-`````{dropdown} Agents: Dynamically call chains based on user input
-
-So far the chains we've looked at run in a predetermined order.
-
-Agents no longer do: they use an LLM to determine which actions to take and in what order. An action can either be using a tool and observing its output, or returning to the user.
-
-When used correctly agents can be extremely powerful. In this tutorial, we show you how to easily use agents through the simplest, highest level API.
-
-
-In order to load agents, you should understand the following concepts:
-
-- Tool: A function that performs a specific duty. This can be things like: Google Search, Database lookup, Python REPL, other chains. The interface for a tool is currently a function that is expected to have a string as an input, with a string as an output.
-- LLM: The language model powering the agent.
-- Agent: The agent to use. This should be a string that references a support agent class. Because this notebook focuses on the simplest, highest level API, this only covers using the standard supported agents. If you want to implement a custom agent, see the documentation for custom agents (coming soon).
-
-**Agents**: For a list of supported agents and their specifications, see [here](../modules/agents/agents.md).
-
-**Tools**: For a list of predefined tools and their specifications, see [here](../modules/agents/tools.md).
-
-For this example, you will also need to install the SerpAPI Python package.
-
-```bash
-pip install google-search-results
-```
-
-And set the appropriate environment variables.
-
-```python
-import os
-os.environ["SERPAPI_API_KEY"] = "..."
-```
-
-Now we can get started!
-
-```python
-from langchain.agents import load_tools
-from langchain.agents import initialize_agent
-from langchain.llms import OpenAI
-
-# First, let's load the language model we're going to use to control the agent.
-llm = OpenAI(temperature=0)
-
-# Next, let's load some tools to use. Note that the `llm-math` tool uses an LLM, so we need to pass that in.
-tools = load_tools(["serpapi", "llm-math"], llm=llm)
-
-
-# Finally, let's initialize an agent with the tools, the language model, and the type of agent we want to use.
-agent = initialize_agent(tools, llm, agent="zero-shot-react-description", verbose=True)
-
-# Now let's test it out!
-agent.run("Who is Olivia Wilde's boyfriend? What is his current age raised to the 0.23 power?")
-```
-
-```pycon
-Entering new AgentExecutor chain...
- I need to find out who Olivia Wilde's boyfriend is and then calculate his age raised to the 0.23 power.
-Action: Search
-Action Input: "Olivia Wilde boyfriend"
-Observation: Jason Sudeikis
-Thought: I need to find out Jason Sudeikis' age
-Action: Search
-Action Input: "Jason Sudeikis age"
-Observation: 47 years
-Thought: I need to calculate 47 raised to the 0.23 power
-Action: Calculator
-Action Input: 47^0.23
-Observation: Answer: 2.4242784855673896
-
-Thought: I now know the final answer
-Final Answer: Jason Sudeikis, Olivia Wilde's boyfriend, is 47 years old and his age raised to the 0.23 power is 2.4242784855673896.
-> Finished AgentExecutor chain.
-"Jason Sudeikis, Olivia Wilde's boyfriend, is 47 years old and his age raised to the 0.23 power is 2.4242784855673896."
-```
-
-
-`````
-
-
-`````{dropdown} Memory: Add state to chains and agents
-
-So far, all the chains and agents we've gone through have been stateless. But often, you may want a chain or agent to have some concept of "memory" so that it may remember information about its previous interactions. The clearest and simple example of this is when designing a chatbot - you want it to remember previous messages so it can use context from that to have a better conversation. This would be a type of "short-term memory". On the more complex side, you could imagine a chain/agent remembering key pieces of information over time - this would be a form of "long-term memory". For more concrete ideas on the latter, see this [awesome paper](https://memprompt.com/).
-
-LangChain provides several specially created chains just for this purpose. This notebook walks through using one of those chains (the `ConversationChain`) with two different types of memory.
-
-By default, the `ConversationChain` has a simple type of memory that remembers all previous inputs/outputs and adds them to the context that is passed. Let's take a look at using this chain (setting `verbose=True` so we can see the prompt).
-
-```python
-from langchain import OpenAI, ConversationChain
-
-llm = OpenAI(temperature=0)
-conversation = ConversationChain(llm=llm, verbose=True)
-
-conversation.predict(input="Hi there!")
-```
-
-```pycon
-> Entering new chain...
-Prompt after formatting:
-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.
-
-Current conversation:
-
-Human: Hi there!
-AI:
-
-> Finished chain.
-' Hello! How are you today?'
-```
-
-```python
-conversation.predict(input="I'm doing well! Just having a conversation with an AI.")
-```
-
-```pycon
-> Entering new chain...
-Prompt after formatting:
-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.
-
-Current conversation:
-
-Human: Hi there!
-AI:  Hello! How are you today?
-Human: I'm doing well! Just having a conversation with an AI.
-AI:
-
-> Finished chain.
-" That's great! What would you like to talk about?"
-```

docs/getting_started/installation.md

@@ -0,0 +1,11 @@
+# Installation
+
+LangChain is available on PyPi, so to it is easily installable with: 
+
+```
+pip install langchain
+```
+
+For more involved installation options, see the [Installation Reference](/installation.md) section.
+
+That's it! LangChain is now installed. You can now use LangChain from a python script or Jupyter notebook.

docs/getting_started/llm.md

@@ -0,0 +1,25 @@
+# Calling a LLM
+
+The most basic building block of LangChain is calling an LLM on some input.
+Let's walk through a simple example of how to do this. 
+For this purpose, let's pretend we are building a service that generates a company name based on what the company makes.
+
+In order to do this, we first need to import the LLM wrapper.
+
+```python
+from langchain.llms import OpenAI
+```
+
+We can then initialize the wrapper with any arguments.
+In this example, we probably want the outputs to be MORE random, so we'll initialize it with a HIGH temperature.
+
+```python
+llm = OpenAI(temperature=0.9)
+```
+
+We can now call it on some input!
+
+```python
+text = "What would be a good company name a company that makes colorful socks?"
+print(llm(text))
+```

docs/index.rst

@@ -7,182 +7,113 @@ But using these LLMs in isolation is often not enough to
 create a truly powerful app - the real power comes when you are able to
 combine them with other sources of computation or knowledge.
 
-This library is aimed at assisting in the development of those types of applications. Common examples of these types of applications include:
+This library is aimed at assisting in the development of those types of applications.
 
-**❓ Question Answering over specific documents**
+There are three main areas (with a forth coming soon) that LangChain is designed to help with.
+These are, in increasing order of complexity:
+1. LLM and Prompt usage
+2. Chaining LLMs with other tools in a deterministic manner
+3. Having a router LLM which uses other tools as needed
+4. (Coming Soon) Memory
 
-- `Documentation <./use_cases/question_answering.html>`_
-- End-to-end Example: `Question Answering over Notion Database <https://github.com/hwchase17/notion-qa>`_
+**LLMs and Prompts**
 
-**💬 Chatbots**
+Calling out to an LLM once is pretty easy, with most of them being behind well documented APIs.
+However, there are still some challenges going from that to an application running in production that LangChain attempts to address:
+- Easy switching costs: by exposing a standard interface for all the top LLM providers, LangChain makes it easy to switch from one provider to another, whether it be for production use cases or just for testing stuff out.
+- Prompt management: managing your prompts is easy when you only have one simple one, but can get tricky when you have a bunch or when they start to get more complex. LangChain provides a standard way for storing, constructing, and referencing prompts.
+- Prompt optimization: despite the underlying models getting better and better, there is still currently a need for carefully constructing prompts.
+- More coming soon
 
-- `Documentation <./use_cases/chatbots.html>`_
-- End-to-end Example: `Chat-LangChain <https://github.com/hwchase17/chat-langchain>`_
+**Chains**
 
-**🤖 Agents**
+Using an LLM in isolation is fine for some simple applications, but many more complex ones require chaining LLMs - either with eachother or with other tools.
+LangChain provides several parts to help with that:
+- Standard interface for working with Chains
+- Easy way to construct chains of LLMs
+- Lots of integrations with other tools that you may want to use in conjunction with LLMs (search, databases, Python REPL, etc)
+- End-to-end chains for common workflows (database question/answer, recursive summarization, etc)
 
-- `Documentation <./use_cases/agents.html>`_
-- End-to-end Example: `GPT+WolframAlpha <https://huggingface.co/spaces/JavaFXpert/Chat-GPT-LangChain>`_
+**Routing Chains**
 
-Getting Started
-----------------
+Some applications will require not just a predetermined chain of calls to LLMs/other tools, but potentially an unknown chain that depends on the user input.
+In these types of chains, there is a "router" LLM chain which has access to a suite of tools.
+Depending on the user input, the router can then decide which, if any, of these tools to call.
+To help develop applications like these, LangChain provides:
+- Standard router and router chain interfaces
+- Common router LLM chains from literature
+- Common chains that can be used as tools
 
-Checkout the below guide for a walkthrough of how to get started using LangChain to create an Language Model application.
+**Memory**
+Coming soon.
+
+Documentation Structure
+=======================
+The documentation is structured into the following sections:
 
-- `Getting Started Documentation <./getting_started/getting_started.html>`_
 
 .. toctree::
    :maxdepth: 1
    :caption: Getting Started
    :name: getting_started
-   :hidden:
 
-   getting_started/getting_started.md
+   getting_started/installation.md
+   getting_started/environment.md
+   getting_started/llm.md
+   getting_started/chains.md
 
-Modules
------------
-
-There are several main modules that LangChain provides support for.
-For each module we provide some examples to get started, how-to guides, reference docs, and conceptual guides.
-These modules are, in increasing order of complexity:
-
-
-- `Prompts <./modules/prompts.html>`_: This includes prompt management, prompt optimization, and prompt serialization.
-
-- `LLMs <./modules/llms.html>`_: This includes a generic interface for all LLMs, and common utilities for working with LLMs.
-
-- `Document Loaders <./modules/document_loaders.html>`_: This includes a standard interface for loading documents, as well as specific integrations to all types of text data sources.
-
-- `Utils <./modules/utils.html>`_: Language models are often more powerful when interacting with other sources of knowledge or computation. This can include Python REPLs, embeddings, search engines, and more. LangChain provides a large collection of common utils to use in your application.
-
-- `Chains <./modules/chains.html>`_: Chains 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.
-
-- `Indexes <./modules/indexes.html>`_: Language models are often more powerful when combined with your own text data - this module covers best practices for doing exactly that.
-
-- `Agents <./modules/agents.html>`_: Agents 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.
-
-- `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.
+Goes over a simple walk through and tutorial for getting started setting up a simple chain that generates a company name based on what the company makes.
+Covers installation, environment set up, calling LLMs, and using prompts.
+Start here if you haven't used LangChain before.
 
 
 .. toctree::
    :maxdepth: 1
-   :caption: Modules
-   :name: modules
-   :hidden:
+   :caption: How-To Examples
+   :name: examples
 
-   ./modules/prompts.md
-   ./modules/llms.md
-   ./modules/document_loaders.md
-   ./modules/utils.md
-   ./modules/indexes.md
-   ./modules/chains.md
-   ./modules/agents.md
-   ./modules/memory.md
+   examples/demos.rst
+   examples/integrations.rst
+   examples/prompts.rst
+   examples/model_laboratory.ipynb
 
-Use Cases
-----------
-
-The above modules can be used in a variety of ways. LangChain also provides guidance and assistance in this. Below are some of the common use cases LangChain supports.
-
-- `Agents <./use_cases/agents.html>`_: Agents are systems that use a language model to interact with other tools. These can be used to do more grounded question/answering, interact with APIs, or even take actions.
-
-- `Chatbots <./use_cases/chatbots.html>`_: Since language models are good at producing text, that makes them ideal for creating chatbots.
-
-- `Data Augmented Generation <./use_cases/combine_docs.html>`_: Data 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.
-
-- `Question Answering <./use_cases/question_answering.html>`_: Answering questions over specific documents, only utilizing the information in those documents to construct an answer. A type of Data Augmented Generation.
-
-- `Summarization <./use_cases/summarization.html>`_: Summarizing longer documents into shorter, more condensed chunks of information. A type of Data Augmented Generation.
-
-- `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.
-
-- `Compare models <./use_cases/model_laboratory.html>`_: Experimenting with different prompts, models, and chains is a big part of developing the best possible application. The ModelLaboratory makes it easy to do so.
+More elaborate examples and walk-throughs of particular
+integrations and use cases. This is the place to look if you have questions
+about how to integrate certain pieces, or if you want to find examples of
+common tasks or cool demos.
 
 
-
-.. toctree::
-   :maxdepth: 1
-   :caption: Use Cases
-   :name: use_cases
-   :hidden:
-
-   ./use_cases/agents.md
-   ./use_cases/chatbots.md
-   ./use_cases/generate_examples.ipynb
-   ./use_cases/combine_docs.md
-   ./use_cases/question_answering.md
-   ./use_cases/summarization.md
-   ./use_cases/evaluation.rst
-   ./use_cases/model_laboratory.ipynb
-
-
-Reference Docs
----------------
-
-All of LangChain's reference documentation, in one place. Full documentation on all methods, classes, installation methods, and integration setups for LangChain.
-
-
-- `Reference Documentation <./reference.html>`_
 .. toctree::
    :maxdepth: 1
    :caption: Reference
    :name: reference
-   :hidden:
 
-   ./reference/installation.md
-   ./reference/integrations.md
-   ./reference.rst
+   installation.md
+   integrations.md
+   modules/prompt
+   modules/example_selector
+   modules/llms
+   modules/embeddings
+   modules/text_splitter
+   modules/vectorstore
+   modules/chains
+   modules/routing_chains
 
 
-LangChain Ecosystem
--------------------
-
-Guides for how other companies/products can be used with LangChain
-
-- `LangChain Ecosystem <./ecosystem.html>`_
-
-.. toctree::
-   :maxdepth: 1
-   :glob:
-   :caption: Ecosystem
-   :name: ecosystem
-   :hidden:
-
-   ./ecosystem.rst
-
-
-Additional Resources
----------------------
-
-Additional collection of resources we think may be useful as you develop your application!
-
-- `LangChainHub <https://github.com/hwchase17/langchain-hub>`_: The LangChainHub is a place to share and explore other prompts, chains, and agents.
-
-- `Glossary <./glossary.html>`_: A glossary of all related terms, papers, methods, etc. Whether implemented in LangChain or not!
-
-- `Gallery <./gallery.html>`_: A collection of our favorite projects that use LangChain. Useful for finding inspiration or seeing how things were done in other applications.
-
-- `Deployments <./deployments.html>`_: A collection of instructions, code snippets, and template repositories for deploying LangChain apps.
-
-- `Discord <https://discord.gg/6adMQxSpJS>`_: Join us on our Discord to discuss all things LangChain!
-
-- `Tracing <./tracing.html>`_: A guide on using tracing in LangChain to visualize the execution of chains and agents.
-
-- `Production Support <https://forms.gle/57d8AmXBYp8PP8tZA>`_: As you move your LangChains into production, we'd love to offer more comprehensive support. Please fill out this form and we'll set up a dedicated support Slack channel.
+Full API documentation. This is the place to look if you want to
+see detailed information about the various classes, methods, and APIs.
 
 
 .. toctree::
    :maxdepth: 1
-   :caption: Additional Resources
+   :caption: Resources
    :name: resources
-   :hidden:
 
-   LangChainHub <https://github.com/hwchase17/langchain-hub>
-   ./glossary.md
-   ./gallery.rst
-   ./deployments.md
-   ./tracing.md
+   explanation/core_concepts.md
+   explanation/glossary.md
    Discord <https://discord.gg/6adMQxSpJS>
-   Production Support <https://forms.gle/57d8AmXBYp8PP8tZA>
+
+Higher level, conceptual explanations of the LangChain components.
+This is the place to go if you want to increase your high level understanding
+of the problems LangChain is solving, and how we decided to go about do so.
+