forked from Archives/langchain
Compare commits
244 Commits
Author | SHA1 | Date |
---|---|---|
blob42 | 897cad58dc | 1 year ago |
blob42 | e367ee71e7 | 1 year ago |
Harrison Chase | b83e826510 | 1 year ago |
Mario Kostelac | e7d6de6b1c | 1 year ago |
Harrison Chase | 6e0d3880df | 1 year ago |
Harrison Chase | 6ec5780547 | 1 year ago |
Harrison Chase | 47d37db2d2 | 1 year ago |
Enwei Jiao | 4f364db9a9 | 1 year ago |
Tim Asp | 030ce9f506 | 1 year ago |
Harrison Chase | 8990122d5d | 1 year ago |
Harrison Chase | 52d6bf04d0 | 1 year ago |
Harrison Chase | 910da8518f | 1 year ago |
Naoki Ainoya | 2f27ef92fe | 1 year ago |
Harrison Chase | 75149d6d38 | 1 year ago |
Harrison Chase | fab7994b74 | 1 year ago |
Harrison Chase | eb80d6e0e4 | 1 year ago |
Harrison Chase | b5667bed9e | 1 year ago |
Eric Zhu | b3be83c750 | 1 year ago |
Harrison Chase | 50626a10ee | 1 year ago |
Harrison Chase | 6e1b5b8f7e | 1 year ago |
Harrison Chase | eec9b1b306 | 1 year ago |
Xin Qiu | ea142f6a32 | 1 year ago |
Eli | 12f868b292 | 1 year ago |
Memento Mori | 31f9ecfc19 | 1 year ago |
Eric Zhu | 273e9bf296 | 1 year ago |
Maurício Maia | f155d9d3ec | 1 year ago |
Klein Tahiraj | d3d4503ce2 | 1 year ago |
Harrison Chase | 1f93c5cf69 | 1 year ago |
Sean Zheng | 15b5a08f4b | 1 year ago |
Kushal Chordiya | ff4a25b841 | 1 year ago |
Maurício Maia | 2212520a6c | 1 year ago |
Harrison Chase | d08f940336 | 1 year ago |
Harrison Chase | 2280a2cb2f | 1 year ago |
Harrison Chase | ce5d97bcb3 | 1 year ago |
DeadBranch | 8fa1764c60 | 1 year ago |
Harrison Chase | f299bd1416 | 1 year ago |
Philipp Schmid | 064be93edf | 1 year ago |
anupam-tiwari | 86822d1cc2 | 1 year ago |
Harrison Chase | a581bce379 | 1 year ago |
Harrison Chase | 2ffc643086 | 1 year ago |
Harrison Chase | 2136dc94bb | 1 year ago |
Matt Tucker | a92344f476 | 1 year ago |
Tomoko Uchida | b706966ebc | 1 year ago |
Harrison Chase | 1c22657256 | 1 year ago |
Harrison Chase | 6f02286805 | 1 year ago |
Simon Zhou | 3674074eb0 | 1 year ago |
Wenbin Fang | a7e09d46c5 | 1 year ago |
Matt Tucker | fa2e546b76 | 1 year ago |
Daniel Dror (Dubovski) | c592b12043 | 1 year ago |
Ikko Eltociear Ashimine | 9555bbd5bb | 1 year ago |
Harrison Chase | 0ca1641b14 | 1 year ago |
Harrison Chase | d5b4393bb2 | 1 year ago |
Bryan Helmig | 7b6ff7fe00 | 1 year ago |
Harrison Chase | 76c7b1f677 | 1 year ago |
Paul | 5aa8ece211 | 1 year ago |
Harrison Chase | f6d24d5740 | 1 year ago |
Harrison Chase | b1c4480d7c | 1 year ago |
Daniel Chalef | b6ba989f2f | 1 year ago |
Ankush Gola | 04acda55ec | 1 year ago |
Harrison Chase | 8e5c4ac867 | 1 year ago |
Aratako | df8702fead | 1 year ago |
Harrison Chase | d5d50c39e6 | 1 year ago |
Harrison Chase | 1f18698b2a | 1 year ago |
Harrison Chase | ef4945af6b | 1 year ago |
Harrison Chase | 7de2ada3ea | 1 year ago |
Bernat Felip i Díaz | 262d4cb9a8 | 1 year ago |
Harrison Chase | 951c158106 | 1 year ago |
Bao Nguyen | 85e4dd7fc3 | 1 year ago |
Harrison Chase | b1b4a4065a | 1 year ago |
Huang Chongdi | 08f23c95d9 | 1 year ago |
hitoshi44 | 3cf493b089 | 1 year ago |
hitoshi44 | e635c86145 | 1 year ago |
Harrison Chase | 779790167e | 1 year ago |
Nils Durner | 3161ced4bc | 1 year ago |
hung_ng__ | 3d6fcb85dc | 1 year ago |
LeoGrin | 3701b2901e | 1 year ago |
Ben Gahtan | 280cb4160d | 1 year ago |
Kevin | 80d8db5f60 | 1 year ago |
Piyush Jain | 1a8790d808 | 1 year ago |
Eric Zhu | 34840f3aee | 1 year ago |
Harrison Chase | 8685d53adc | 1 year ago |
Harrison Chase | 2f6833d433 | 1 year ago |
Harrison Chase | dd90fd02d5 | 1 year ago |
Harrison Chase | 07766a69f3 | 1 year ago |
Harrison Chase | aa854988bf | 1 year ago |
Harrison Chase | 96ebe98dc2 | 1 year ago |
Harrison Chase | 45f05fc939 | 1 year ago |
Vincent Liao | cf9c3f54f7 | 1 year ago |
Merbin J Anselm | fbc0c85b90 | 1 year ago |
Harrison Chase | 276940fd9b | 1 year ago |
Piyush Jain | cdff6c8181 | 1 year ago |
alekhyablue | cd45adbea2 | 1 year ago |
Mario Kostelac | aff44d0a98 | 1 year ago |
libra | 8a95fdaee1 | 1 year ago |
Alexandros Mavrogiannis | 5d8dc83ede | 1 year ago |
Daniel Chalef | b157e0c1c3 | 1 year ago |
Harrison Chase | 40e9488055 | 1 year ago |
jerwelborn | 55efbb8a7e | 1 year ago |
Alex Strick van Linschoten | d6bbf395af | 1 year ago |
Jonathan Pedoeem | 606605925d | 1 year ago |
Jeff Huber | f93c011456 | 1 year ago |
Harrison Chase | 3c24684522 | 1 year ago |
Harrison Chase | b84d190fd0 | 1 year ago |
Harrison Chase | aad4bff098 | 1 year ago |
Harrison Chase | 3ea6d9c4d2 | 1 year ago |
Pandazki | ced412e1c1 | 1 year ago |
Piyush Jain | 1279c8de39 | 1 year ago |
at-b612 | c7779c800a | 1 year ago |
Jithin James | 6f4f771897 | 1 year ago |
Kacper Łukawski | 4a327dd1d6 | 1 year ago |
Ankush Gola | d4edd3c312 | 1 year ago |
Harrison Chase | e72074f78a | 1 year ago |
Harrison Chase | 0b29e68c17 | 1 year ago |
Harrison Chase | 4d7fdb8957 | 1 year ago |
Harrison Chase | 656efe6ef3 | 1 year ago |
Harrison Chase | 362586fe8b | 1 year ago |
Matt Robinson | 63aa28e2a6 | 1 year ago |
Matthias Kern | c3dfbdf0da | 1 year ago |
Bilel MEDIMEGH | a2280f321f | 1 year ago |
Xin Qiu | 4e13cef05a | 1 year ago |
Harrison Chase | e5c1659864 | 1 year ago |
Harrison Chase | 2d098e8869 | 1 year ago |
Harrison Chase | 8965a2f0af | 1 year ago |
Harrison Chase | e222ea4ee8 | 1 year ago |
Harrison Chase | e326939759 | 1 year ago |
Harrison Chase | 7cf46b3fee | 1 year ago |
Abhinav Upadhyay | 84cd825a0e | 1 year ago |
Jon Luo | 0a1b1806e9 | 1 year ago |
Brian Thorne | 9ee2713272 | 1 year ago |
Tim Asp | b3234bf3b0 | 1 year ago |
Luis | 562d9891ea | 1 year ago |
Harrison Chase | 56aff797c0 | 1 year ago |
Harrison Chase | d53ff270e0 | 1 year ago |
Harrison Chase | df6c33d4b3 | 1 year ago |
Dennis Aumiller | 039d05c808 | 1 year ago |
Harrison Chase | aed9f9febe | 1 year ago |
Harrison Chase | 72b461e257 | 1 year ago |
Peng Qu | cb646082ba | 1 year ago |
Eugene Yurtsev | bd4a2a670b | 1 year ago |
Ikko Eltociear Ashimine | 6e98ab01e1 | 1 year ago |
Harrison Chase | c0ad5d13b8 | 1 year ago |
yakigac | acd86d33bc | 1 year ago |
Abhinav Upadhyay | 9707eda83c | 1 year ago |
Kayvane Shakerifar | 7e550df6d4 | 1 year ago |
Harrison Chase | c9b5a30b37 | 1 year ago |
Harrison Chase | cb04ba0136 | 1 year ago |
Harrison Chase | 5903a93f3d | 1 year ago |
Harrison Chase | 15de3e8137 | 1 year ago |
Harrison Chase | f95d551f7a | 1 year ago |
Harrison Chase | c6bfa00178 | 1 year ago |
Tim Asp | 01a57198b8 | 1 year ago |
Harrison Chase | 8dba30f31e | 1 year ago |
Harrison Chase | 9f78717b3c | 1 year ago |
Harrison Chase | 90846dcc28 | 1 year ago |
Claus Thomasen | 6ed16e13b1 | 1 year ago |
Harrison Chase | c1dc784a3d | 1 year ago |
fabi.s | 5b0e747f9a | 1 year ago |
Zach Schillaci | 624c72c266 | 1 year ago |
Ryan Dao | a950287206 | 1 year ago |
Tim Asp | 30383abb12 | 1 year ago |
Zach Schillaci | cdb97f3dfb | 1 year ago |
Felix Altenberger | b44c8bd969 | 1 year ago |
Andriy Mulyar | c9189d354a | 1 year ago |
blob42 | 622578a022 | 1 year ago |
Matt Robinson | 7018806a92 | 1 year ago |
Harrison Chase | bd335ffd64 | 1 year ago |
Harrison Chase | a094c49153 | 1 year ago |
Brenton Wheeler | 99fe023496 | 1 year ago |
Harrison Chase | 3ee32a01ea | 1 year ago |
Harrison Chase | c844d1fd46 | 1 year ago |
Harrison Chase | 9405af6919 | 1 year ago |
Harrison Chase | 357d808484 | 1 year ago |
Harrison Chase | cc423f40f1 | 1 year ago |
Harrison Chase | b053f831cd | 1 year ago |
Harrison Chase | 523ad8d2e2 | 1 year ago |
Graham Neubig | 31303d0b11 | 1 year ago |
gidler | 494c9d341a | 1 year ago |
Harrison Chase | 519f0187b6 | 1 year ago |
Florian Leuerer | 64c6435545 | 1 year ago |
Harrison Chase | 7eba828e1b | 1 year ago |
Harrison Chase | 2a7215bc3b | 1 year ago |
Alpri Else | 784d24a1d5 | 1 year ago |
Harrison Chase | aba58e9e2e | 1 year ago |
Harrison Chase | c4a557bdd4 | 1 year ago |
Ivan | 97e3666e0d | 1 year ago |
Harrison Chase | 7ade419a0e | 1 year ago |
Harrison Chase | a4a2d79087 | 1 year ago |
Harrison Chase | 8f21605d71 | 1 year ago |
Harrison Chase | 064741db58 | 1 year ago |
Tom Dyson | e3354404ad | 1 year ago |
Harrison Chase | 3610ef2830 | 1 year ago |
Ankush Gola | 27104d4921 | 1 year ago |
Harrison Chase | 4f41e20f09 | 1 year ago |
Harrison Chase | d0062c7a9a | 1 year ago |
Harrison Chase | 8e6f599822 | 1 year ago |
Harrison Chase | f276bfad8e | 1 year ago |
Harrison Chase | 7bec461782 | 1 year ago |
kahkeng | df6865cd52 | 1 year ago |
Harrison Chase | 312c319d8b | 1 year ago |
Harrison Chase | 0e21463f07 | 1 year ago |
Juanky Soriano | dec3750875 | 1 year ago |
Tim Asp | 763f879536 | 1 year ago |
Harrison Chase | 56b850648f | 1 year ago |
Harrison Chase | 63a5614d23 | 1 year ago |
Harrison Chase | a1b9dfc099 | 1 year ago |
Peng Qu | 68ce68f290 | 1 year ago |
Ikko Eltociear Ashimine | b8a7828d1f | 1 year ago |
Kentaro Tanaka | 6a4ee07e4f | 1 year ago |
Tim Asp | 23231d65a9 | 1 year ago |
blob42 | 3d54b05863 | 1 year ago |
Tim Asp | bca0935d90 | 1 year ago |
Jon Luo | 882f7964fb | 1 year ago |
JonLuca De Caro | 443992c4d5 | 1 year ago |
Eugene Yurtsev | a83a371069 | 1 year ago |
Nuno Campos | 499e76b199 | 1 year ago |
Kacper Łukawski | 8947797250 | 1 year ago |
Jason Gill | 1989e7d4c2 | 1 year ago |
Harrison Chase | dda5259f68 | 1 year ago |
Kacper Łukawski | f032609f8d | 1 year ago |
Kacper Łukawski | 9ac442624c | 1 year ago |
Francisco Ingham | 34abcd31b9 | 1 year ago |
Ankush Gola | fe30be6fba | 1 year ago |
Lakshya Agarwal | cfed0497ac | 1 year ago |
Ryan Dao | 59157b6891 | 1 year ago |
Harrison Chase | e178008b75 | 1 year ago |
Harrison Chase | 1cd8996074 | 1 year ago |
yakigac | cfae03042d | 1 year ago |
Harrison Chase | 4b5e850361 | 1 year ago |
Harrison Chase | 4d4b43cf5a | 1 year ago |
Harrison Chase | c01f9100e4 | 1 year ago |
Christie Jacob | edb3915ee7 | 1 year ago |
Harrison Chase | fe7dbecfe6 | 1 year ago |
Harrison Chase | 02ec72df87 | 1 year ago |
Jon Luo | 92ab27e4b8 | 1 year ago |
Ankush Gola | 82baecc892 | 1 year ago |
Jon Luo | 35f1e8f569 | 1 year ago |
kurehajime | 6c629b54e6 | 1 year ago |
James Brotchie | 3574418a40 | 1 year ago |
Jon Luo | 5bf8772f26 | 1 year ago |
Harrison Chase | 924bba5ce9 | 1 year ago |
Harrison Chase | 786852e9e6 | 1 year ago |
Tim Asp | 72ef69d1ba | 1 year ago |
Matt Robinson | 1aa41b5741 | 1 year ago |
Eugene Yurtsev | c14cff60d0 | 1 year ago |
@ -0,0 +1,20 @@
|
|||||||
|
# Milvus
|
||||||
|
|
||||||
|
This page covers how to use the Milvus ecosystem within LangChain.
|
||||||
|
It is broken into two parts: installation and setup, and then references to specific Milvus wrappers.
|
||||||
|
|
||||||
|
## Installation and Setup
|
||||||
|
- Install the Python SDK with `pip install pymilvus`
|
||||||
|
## Wrappers
|
||||||
|
|
||||||
|
### VectorStore
|
||||||
|
|
||||||
|
There exists a wrapper around Milvus indexes, allowing you to use it as a vectorstore,
|
||||||
|
whether for semantic search or example selection.
|
||||||
|
|
||||||
|
To import this vectorstore:
|
||||||
|
```python
|
||||||
|
from langchain.vectorstores import Milvus
|
||||||
|
```
|
||||||
|
|
||||||
|
For a more detailed walkthrough of the Miluvs wrapper, see [this notebook](../modules/indexes/vectorstore_examples/milvus.ipynb)
|
@ -0,0 +1,29 @@
|
|||||||
|
# PGVector
|
||||||
|
|
||||||
|
This page covers how to use the Postgres [PGVector](https://github.com/pgvector/pgvector) ecosystem within LangChain
|
||||||
|
It is broken into two parts: installation and setup, and then references to specific PGVector wrappers.
|
||||||
|
|
||||||
|
## Installation
|
||||||
|
- Install the Python package with `pip install pgvector`
|
||||||
|
|
||||||
|
|
||||||
|
## Setup
|
||||||
|
1. The first step is to create a database with the `pgvector` extension installed.
|
||||||
|
|
||||||
|
Follow the steps at [PGVector Installation Steps](https://github.com/pgvector/pgvector#installation) to install the database and the extension. The docker image is the easiest way to get started.
|
||||||
|
|
||||||
|
## Wrappers
|
||||||
|
|
||||||
|
### VectorStore
|
||||||
|
|
||||||
|
There exists a wrapper around Postgres vector databases, allowing you to use it as a vectorstore,
|
||||||
|
whether for semantic search or example selection.
|
||||||
|
|
||||||
|
To import this vectorstore:
|
||||||
|
```python
|
||||||
|
from langchain.vectorstores.pgvector import PGVector
|
||||||
|
```
|
||||||
|
|
||||||
|
### Usage
|
||||||
|
|
||||||
|
For a more detailed walkthrough of the PGVector Wrapper, see [this notebook](../modules/indexes/vectorstore_examples/pgvector.ipynb)
|
@ -0,0 +1,20 @@
|
|||||||
|
# Qdrant
|
||||||
|
|
||||||
|
This page covers how to use the Qdrant ecosystem within LangChain.
|
||||||
|
It is broken into two parts: installation and setup, and then references to specific Qdrant wrappers.
|
||||||
|
|
||||||
|
## Installation and Setup
|
||||||
|
- Install the Python SDK with `pip install qdrant-client`
|
||||||
|
## Wrappers
|
||||||
|
|
||||||
|
### VectorStore
|
||||||
|
|
||||||
|
There exists a wrapper around Qdrant indexes, allowing you to use it as a vectorstore,
|
||||||
|
whether for semantic search or example selection.
|
||||||
|
|
||||||
|
To import this vectorstore:
|
||||||
|
```python
|
||||||
|
from langchain.vectorstores import Qdrant
|
||||||
|
```
|
||||||
|
|
||||||
|
For a more detailed walkthrough of the Qdrant wrapper, see [this notebook](../modules/indexes/vectorstore_examples/qdrant.ipynb)
|
@ -0,0 +1,625 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# Weights & Biases\n",
|
||||||
|
"\n",
|
||||||
|
"This notebook goes over how to track your LangChain experiments into one centralized Weights and Biases dashboard. To learn more about prompt engineering and the callback please refer to this Report which explains both alongside the resultant dashboards you can expect to see.\n",
|
||||||
|
"\n",
|
||||||
|
"Run in Colab: https://colab.research.google.com/drive/1DXH4beT4HFaRKy_Vm4PoxhXVDRf7Ym8L?usp=sharing\n",
|
||||||
|
"\n",
|
||||||
|
"View Report: https://wandb.ai/a-sh0ts/langchain_callback_demo/reports/Prompt-Engineering-LLMs-with-LangChain-and-W-B--VmlldzozNjk1NTUw#👋-how-to-build-a-callback-in-langchain-for-better-prompt-engineering"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"!pip install wandb\n",
|
||||||
|
"!pip install pandas\n",
|
||||||
|
"!pip install textstat\n",
|
||||||
|
"!pip install spacy\n",
|
||||||
|
"!python -m spacy download en_core_web_sm"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 1,
|
||||||
|
"metadata": {
|
||||||
|
"id": "T1bSmKd6V2If"
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"import os\n",
|
||||||
|
"os.environ[\"WANDB_API_KEY\"] = \"\"\n",
|
||||||
|
"# os.environ[\"OPENAI_API_KEY\"] = \"\"\n",
|
||||||
|
"# os.environ[\"SERPAPI_API_KEY\"] = \"\""
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 2,
|
||||||
|
"metadata": {
|
||||||
|
"id": "8WAGnTWpUUnD"
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from datetime import datetime\n",
|
||||||
|
"from langchain.callbacks import WandbCallbackHandler, StdOutCallbackHandler\n",
|
||||||
|
"from langchain.callbacks.base import CallbackManager\n",
|
||||||
|
"from langchain.llms import OpenAI"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"```\n",
|
||||||
|
"Callback Handler that logs to Weights and Biases.\n",
|
||||||
|
"\n",
|
||||||
|
"Parameters:\n",
|
||||||
|
" job_type (str): The type of job.\n",
|
||||||
|
" project (str): The project to log to.\n",
|
||||||
|
" entity (str): The entity to log to.\n",
|
||||||
|
" tags (list): The tags to log.\n",
|
||||||
|
" group (str): The group to log to.\n",
|
||||||
|
" name (str): The name of the run.\n",
|
||||||
|
" notes (str): The notes to log.\n",
|
||||||
|
" visualize (bool): Whether to visualize the run.\n",
|
||||||
|
" complexity_metrics (bool): Whether to log complexity metrics.\n",
|
||||||
|
" stream_logs (bool): Whether to stream callback actions to W&B\n",
|
||||||
|
"```"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {
|
||||||
|
"id": "cxBFfZR8d9FC"
|
||||||
|
},
|
||||||
|
"source": [
|
||||||
|
"```\n",
|
||||||
|
"Default values for WandbCallbackHandler(...)\n",
|
||||||
|
"\n",
|
||||||
|
"visualize: bool = False,\n",
|
||||||
|
"complexity_metrics: bool = False,\n",
|
||||||
|
"stream_logs: bool = False,\n",
|
||||||
|
"```\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"NOTE: For beta workflows we have made the default analysis based on textstat and the visualizations based on spacy"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 3,
|
||||||
|
"metadata": {
|
||||||
|
"id": "KAz8weWuUeXF"
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stderr",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\u001b[34m\u001b[1mwandb\u001b[0m: Currently logged in as: \u001b[33mharrison-chase\u001b[0m. Use \u001b[1m`wandb login --relogin`\u001b[0m to force relogin\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/html": [
|
||||||
|
"Tracking run with wandb version 0.14.0"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
"<IPython.core.display.HTML object>"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/html": [
|
||||||
|
"Run data is saved locally in <code>/Users/harrisonchase/workplace/langchain/docs/ecosystem/wandb/run-20230318_150408-e47j1914</code>"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
"<IPython.core.display.HTML object>"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/html": [
|
||||||
|
"Syncing run <strong><a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/e47j1914' target=\"_blank\">llm</a></strong> to <a href='https://wandb.ai/harrison-chase/langchain_callback_demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/run' target=\"_blank\">docs</a>)<br/>"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
"<IPython.core.display.HTML object>"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/html": [
|
||||||
|
" View project at <a href='https://wandb.ai/harrison-chase/langchain_callback_demo' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo</a>"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
"<IPython.core.display.HTML object>"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/html": [
|
||||||
|
" View run at <a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/e47j1914' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo/runs/e47j1914</a>"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
"<IPython.core.display.HTML object>"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "stderr",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m The wandb callback is currently in beta and is subject to change based on updates to `langchain`. Please report any issues to https://github.com/wandb/wandb/issues with the tag `langchain`.\n"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"\"\"\"Main function.\n",
|
||||||
|
"\n",
|
||||||
|
"This function is used to try the callback handler.\n",
|
||||||
|
"Scenarios:\n",
|
||||||
|
"1. OpenAI LLM\n",
|
||||||
|
"2. Chain with multiple SubChains on multiple generations\n",
|
||||||
|
"3. Agent with Tools\n",
|
||||||
|
"\"\"\"\n",
|
||||||
|
"session_group = datetime.now().strftime(\"%m.%d.%Y_%H.%M.%S\")\n",
|
||||||
|
"wandb_callback = WandbCallbackHandler(\n",
|
||||||
|
" job_type=\"inference\",\n",
|
||||||
|
" project=\"langchain_callback_demo\",\n",
|
||||||
|
" group=f\"minimal_{session_group}\",\n",
|
||||||
|
" name=\"llm\",\n",
|
||||||
|
" tags=[\"test\"],\n",
|
||||||
|
")\n",
|
||||||
|
"manager = CallbackManager([StdOutCallbackHandler(), wandb_callback])\n",
|
||||||
|
"llm = OpenAI(temperature=0, callback_manager=manager, verbose=True)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {
|
||||||
|
"id": "Q-65jwrDeK6w"
|
||||||
|
},
|
||||||
|
"source": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"```\n",
|
||||||
|
"# Defaults for WandbCallbackHandler.flush_tracker(...)\n",
|
||||||
|
"\n",
|
||||||
|
"reset: bool = True,\n",
|
||||||
|
"finish: bool = False,\n",
|
||||||
|
"```\n",
|
||||||
|
"\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"The `flush_tracker` function is used to log LangChain sessions to Weights & Biases. It takes in the LangChain module or agent, and logs at minimum the prompts and generations alongside the serialized form of the LangChain module to the specified Weights & Biases project. By default we reset the session as opposed to concluding the session outright."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 4,
|
||||||
|
"metadata": {
|
||||||
|
"id": "o_VmneyIUyx8"
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/html": [
|
||||||
|
"Waiting for W&B process to finish... <strong style=\"color:green\">(success).</strong>"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
"<IPython.core.display.HTML object>"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/html": [
|
||||||
|
" View run <strong style=\"color:#cdcd00\">llm</strong> at: <a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/e47j1914' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo/runs/e47j1914</a><br/>Synced 5 W&B file(s), 2 media file(s), 5 artifact file(s) and 0 other file(s)"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
"<IPython.core.display.HTML object>"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/html": [
|
||||||
|
"Find logs at: <code>./wandb/run-20230318_150408-e47j1914/logs</code>"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
"<IPython.core.display.HTML object>"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"application/vnd.jupyter.widget-view+json": {
|
||||||
|
"model_id": "0d7b4307ccdb450ea631497174fca2d1",
|
||||||
|
"version_major": 2,
|
||||||
|
"version_minor": 0
|
||||||
|
},
|
||||||
|
"text/plain": [
|
||||||
|
"VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.016745895149999985, max=1.0…"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/html": [
|
||||||
|
"Tracking run with wandb version 0.14.0"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
"<IPython.core.display.HTML object>"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/html": [
|
||||||
|
"Run data is saved locally in <code>/Users/harrisonchase/workplace/langchain/docs/ecosystem/wandb/run-20230318_150534-jyxma7hu</code>"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
"<IPython.core.display.HTML object>"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/html": [
|
||||||
|
"Syncing run <strong><a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/jyxma7hu' target=\"_blank\">simple_sequential</a></strong> to <a href='https://wandb.ai/harrison-chase/langchain_callback_demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/run' target=\"_blank\">docs</a>)<br/>"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
"<IPython.core.display.HTML object>"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/html": [
|
||||||
|
" View project at <a href='https://wandb.ai/harrison-chase/langchain_callback_demo' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo</a>"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
"<IPython.core.display.HTML object>"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/html": [
|
||||||
|
" View run at <a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/jyxma7hu' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo/runs/jyxma7hu</a>"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
"<IPython.core.display.HTML object>"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"# SCENARIO 1 - LLM\n",
|
||||||
|
"llm_result = llm.generate([\"Tell me a joke\", \"Tell me a poem\"] * 3)\n",
|
||||||
|
"wandb_callback.flush_tracker(llm, name=\"simple_sequential\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 5,
|
||||||
|
"metadata": {
|
||||||
|
"id": "trxslyb1U28Y"
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.prompts import PromptTemplate\n",
|
||||||
|
"from langchain.chains import LLMChain"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 6,
|
||||||
|
"metadata": {
|
||||||
|
"id": "uauQk10SUzF6"
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/html": [
|
||||||
|
"Waiting for W&B process to finish... <strong style=\"color:green\">(success).</strong>"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
"<IPython.core.display.HTML object>"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/html": [
|
||||||
|
" View run <strong style=\"color:#cdcd00\">simple_sequential</strong> at: <a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/jyxma7hu' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo/runs/jyxma7hu</a><br/>Synced 4 W&B file(s), 2 media file(s), 6 artifact file(s) and 0 other file(s)"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
"<IPython.core.display.HTML object>"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/html": [
|
||||||
|
"Find logs at: <code>./wandb/run-20230318_150534-jyxma7hu/logs</code>"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
"<IPython.core.display.HTML object>"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"application/vnd.jupyter.widget-view+json": {
|
||||||
|
"model_id": "dbdbf28fb8ed40a3a60218d2e6d1a987",
|
||||||
|
"version_major": 2,
|
||||||
|
"version_minor": 0
|
||||||
|
},
|
||||||
|
"text/plain": [
|
||||||
|
"VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.016736786816666675, max=1.0…"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/html": [
|
||||||
|
"Tracking run with wandb version 0.14.0"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
"<IPython.core.display.HTML object>"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/html": [
|
||||||
|
"Run data is saved locally in <code>/Users/harrisonchase/workplace/langchain/docs/ecosystem/wandb/run-20230318_150550-wzy59zjq</code>"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
"<IPython.core.display.HTML object>"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/html": [
|
||||||
|
"Syncing run <strong><a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/wzy59zjq' target=\"_blank\">agent</a></strong> to <a href='https://wandb.ai/harrison-chase/langchain_callback_demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/run' target=\"_blank\">docs</a>)<br/>"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
"<IPython.core.display.HTML object>"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/html": [
|
||||||
|
" View project at <a href='https://wandb.ai/harrison-chase/langchain_callback_demo' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo</a>"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
"<IPython.core.display.HTML object>"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/html": [
|
||||||
|
" View run at <a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/wzy59zjq' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo/runs/wzy59zjq</a>"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
"<IPython.core.display.HTML object>"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"# SCENARIO 2 - Chain\n",
|
||||||
|
"template = \"\"\"You are a playwright. Given the title of play, it is your job to write a synopsis for that title.\n",
|
||||||
|
"Title: {title}\n",
|
||||||
|
"Playwright: This is a synopsis for the above play:\"\"\"\n",
|
||||||
|
"prompt_template = PromptTemplate(input_variables=[\"title\"], template=template)\n",
|
||||||
|
"synopsis_chain = LLMChain(llm=llm, prompt=prompt_template, callback_manager=manager)\n",
|
||||||
|
"\n",
|
||||||
|
"test_prompts = [\n",
|
||||||
|
" {\n",
|
||||||
|
" \"title\": \"documentary about good video games that push the boundary of game design\"\n",
|
||||||
|
" },\n",
|
||||||
|
" {\"title\": \"cocaine bear vs heroin wolf\"},\n",
|
||||||
|
" {\"title\": \"the best in class mlops tooling\"},\n",
|
||||||
|
"]\n",
|
||||||
|
"synopsis_chain.apply(test_prompts)\n",
|
||||||
|
"wandb_callback.flush_tracker(synopsis_chain, name=\"agent\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 7,
|
||||||
|
"metadata": {
|
||||||
|
"id": "_jN73xcPVEpI"
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.agents import initialize_agent, load_tools"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 8,
|
||||||
|
"metadata": {
|
||||||
|
"id": "Gpq4rk6VT9cu"
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3m I need to find out who Leo DiCaprio's girlfriend is and then calculate her age raised to the 0.43 power.\n",
|
||||||
|
"Action: Search\n",
|
||||||
|
"Action Input: \"Leo DiCaprio girlfriend\"\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3mDiCaprio had a steady girlfriend in Camila Morrone. He had been with the model turned actress for nearly five years, as they were first said to be dating at the end of 2017. And the now 26-year-old Morrone is no stranger to Hollywood.\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate her age raised to the 0.43 power.\n",
|
||||||
|
"Action: Calculator\n",
|
||||||
|
"Action Input: 26^0.43\u001b[0m\n",
|
||||||
|
"Observation: \u001b[33;1m\u001b[1;3mAnswer: 4.059182145592686\n",
|
||||||
|
"\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
|
||||||
|
"Final Answer: Leo DiCaprio's girlfriend is Camila Morrone and her current age raised to the 0.43 power is 4.059182145592686.\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/html": [
|
||||||
|
"Waiting for W&B process to finish... <strong style=\"color:green\">(success).</strong>"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
"<IPython.core.display.HTML object>"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/html": [
|
||||||
|
" View run <strong style=\"color:#cdcd00\">agent</strong> at: <a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/wzy59zjq' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo/runs/wzy59zjq</a><br/>Synced 5 W&B file(s), 2 media file(s), 7 artifact file(s) and 0 other file(s)"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
"<IPython.core.display.HTML object>"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/html": [
|
||||||
|
"Find logs at: <code>./wandb/run-20230318_150550-wzy59zjq/logs</code>"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
"<IPython.core.display.HTML object>"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"# SCENARIO 3 - Agent with Tools\n",
|
||||||
|
"tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm, callback_manager=manager)\n",
|
||||||
|
"agent = initialize_agent(\n",
|
||||||
|
" tools,\n",
|
||||||
|
" llm,\n",
|
||||||
|
" agent=\"zero-shot-react-description\",\n",
|
||||||
|
" callback_manager=manager,\n",
|
||||||
|
" verbose=True,\n",
|
||||||
|
")\n",
|
||||||
|
"agent.run(\n",
|
||||||
|
" \"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\"\n",
|
||||||
|
")\n",
|
||||||
|
"wandb_callback.flush_tracker(agent, reset=False, finish=True)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": []
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"colab": {
|
||||||
|
"provenance": []
|
||||||
|
},
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "Python 3 (ipykernel)",
|
||||||
|
"language": "python",
|
||||||
|
"name": "python3"
|
||||||
|
},
|
||||||
|
"language_info": {
|
||||||
|
"codemirror_mode": {
|
||||||
|
"name": "ipython",
|
||||||
|
"version": 3
|
||||||
|
},
|
||||||
|
"file_extension": ".py",
|
||||||
|
"mimetype": "text/x-python",
|
||||||
|
"name": "python",
|
||||||
|
"nbconvert_exporter": "python",
|
||||||
|
"pygments_lexer": "ipython3",
|
||||||
|
"version": "3.9.1"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 1
|
||||||
|
}
|
@ -0,0 +1,202 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "7094e328",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# CSV Agent\n",
|
||||||
|
"\n",
|
||||||
|
"This notebook shows how to use agents to interact with a csv. It is mostly optimized for question answering.\n",
|
||||||
|
"\n",
|
||||||
|
"**NOTE: this agent calls the Pandas DataFrame agent under the hood, which in turn calls the Python agent, which executes LLM generated Python code - this can be bad if the LLM generated Python code is harmful. Use cautiously.**\n",
|
||||||
|
"\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 1,
|
||||||
|
"id": "827982c7",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.agents import create_csv_agent"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 2,
|
||||||
|
"id": "caae0bec",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.llms import OpenAI"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 11,
|
||||||
|
"id": "16c4dc59",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"agent = create_csv_agent(OpenAI(temperature=0), 'titanic.csv', verbose=True)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 12,
|
||||||
|
"id": "46b9489d",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3mThought: I need to count the number of rows\n",
|
||||||
|
"Action: python_repl_ast\n",
|
||||||
|
"Action Input: len(df)\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m891\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||||
|
"Final Answer: There are 891 rows in the dataframe.\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"'There are 891 rows in the dataframe.'"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 12,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"agent.run(\"how many rows are there?\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 6,
|
||||||
|
"id": "a96309be",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3mThought: I need to count the number of people with more than 3 siblings\n",
|
||||||
|
"Action: python_repl_ast\n",
|
||||||
|
"Action Input: df[df['SibSp'] > 3].shape[0]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m30\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||||
|
"Final Answer: 30 people have more than 3 siblings.\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"'30 people have more than 3 siblings.'"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 6,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"agent.run(\"how many people have more than 3 sibligngs\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 7,
|
||||||
|
"id": "964a09f7",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3mThought: I need to calculate the average age first\n",
|
||||||
|
"Action: python_repl_ast\n",
|
||||||
|
"Action Input: df['Age'].mean()\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m29.69911764705882\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I can now calculate the square root\n",
|
||||||
|
"Action: python_repl_ast\n",
|
||||||
|
"Action Input: math.sqrt(df['Age'].mean())\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3mname 'math' is not defined\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I need to import the math library\n",
|
||||||
|
"Action: python_repl_ast\n",
|
||||||
|
"Action Input: import math\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3mNone\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I can now calculate the square root\n",
|
||||||
|
"Action: python_repl_ast\n",
|
||||||
|
"Action Input: math.sqrt(df['Age'].mean())\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m5.449689683556195\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||||
|
"Final Answer: 5.449689683556195\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"'5.449689683556195'"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 7,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"agent.run(\"whats the square root of the average age?\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "551de2be",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": []
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "Python 3 (ipykernel)",
|
||||||
|
"language": "python",
|
||||||
|
"name": "python3"
|
||||||
|
},
|
||||||
|
"language_info": {
|
||||||
|
"codemirror_mode": {
|
||||||
|
"name": "ipython",
|
||||||
|
"version": 3
|
||||||
|
},
|
||||||
|
"file_extension": ".py",
|
||||||
|
"mimetype": "text/x-python",
|
||||||
|
"name": "python",
|
||||||
|
"nbconvert_exporter": "python",
|
||||||
|
"pygments_lexer": "ipython3",
|
||||||
|
"version": "3.9.1"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 5
|
||||||
|
}
|
@ -0,0 +1,190 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "85fb2c03-ab88-4c8c-97e3-a7f2954555ab",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# JSON Agent\n",
|
||||||
|
"\n",
|
||||||
|
"This notebook showcases an agent designed to interact with large JSON/dict objects. This is useful when you want to answer questions about a JSON blob that's too large to fit in the context window of an LLM. The agent is able to iteratively explore the blob to find what it needs to answer the user's question.\n",
|
||||||
|
"\n",
|
||||||
|
"In the below example, we are using the OpenAPI spec for the OpenAI API, which you can find [here](https://github.com/openai/openai-openapi/blob/master/openapi.yaml).\n",
|
||||||
|
"\n",
|
||||||
|
"We will use the JSON agent to answer some questions about the API spec."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "893f90fd-f8f6-470a-a76d-1f200ba02e2f",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Initialization"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 1,
|
||||||
|
"id": "ff988466-c389-4ec6-b6ac-14364a537fd5",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"import os\n",
|
||||||
|
"import yaml\n",
|
||||||
|
"\n",
|
||||||
|
"from langchain.agents import (\n",
|
||||||
|
" create_json_agent,\n",
|
||||||
|
" AgentExecutor\n",
|
||||||
|
")\n",
|
||||||
|
"from langchain.agents.agent_toolkits import JsonToolkit\n",
|
||||||
|
"from langchain.chains import LLMChain\n",
|
||||||
|
"from langchain.llms.openai import OpenAI\n",
|
||||||
|
"from langchain.requests import RequestsWrapper\n",
|
||||||
|
"from langchain.tools.json.tool import JsonSpec"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 2,
|
||||||
|
"id": "9ecd1ba0-3937-4359-a41e-68605f0596a1",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"with open(\"openai_openapi.yml\") as f:\n",
|
||||||
|
" data = yaml.load(f, Loader=yaml.FullLoader)\n",
|
||||||
|
"json_spec = JsonSpec(dict_=data, max_value_length=4000)\n",
|
||||||
|
"json_toolkit = JsonToolkit(spec=json_spec)\n",
|
||||||
|
"\n",
|
||||||
|
"json_agent_executor = create_json_agent(\n",
|
||||||
|
" llm=OpenAI(temperature=0),\n",
|
||||||
|
" toolkit=json_toolkit,\n",
|
||||||
|
" verbose=True\n",
|
||||||
|
")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "05cfcb24-4389-4b8f-ad9e-466e3fca8db0",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Example: getting the required POST parameters for a request"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 5,
|
||||||
|
"id": "faf13702-50f0-4d1b-b91f-48c750ccfd98",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3mAction: json_spec_list_keys\n",
|
||||||
|
"Action Input: data\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta']\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should look at the paths key to see what endpoints exist\n",
|
||||||
|
"Action: json_spec_list_keys\n",
|
||||||
|
"Action Input: data[\"paths\"]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m['/engines', '/engines/{engine_id}', '/completions', '/edits', '/images/generations', '/images/edits', '/images/variations', '/embeddings', '/engines/{engine_id}/search', '/files', '/files/{file_id}', '/files/{file_id}/content', '/answers', '/classifications', '/fine-tunes', '/fine-tunes/{fine_tune_id}', '/fine-tunes/{fine_tune_id}/cancel', '/fine-tunes/{fine_tune_id}/events', '/models', '/models/{model}', '/moderations']\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should look at the /completions endpoint to see what parameters are required\n",
|
||||||
|
"Action: json_spec_list_keys\n",
|
||||||
|
"Action Input: data[\"paths\"][\"/completions\"]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m['post']\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should look at the post key to see what parameters are required\n",
|
||||||
|
"Action: json_spec_list_keys\n",
|
||||||
|
"Action Input: data[\"paths\"][\"/completions\"][\"post\"]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m['operationId', 'tags', 'summary', 'requestBody', 'responses', 'x-oaiMeta']\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should look at the requestBody key to see what parameters are required\n",
|
||||||
|
"Action: json_spec_list_keys\n",
|
||||||
|
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m['required', 'content']\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should look at the required key to see what parameters are required\n",
|
||||||
|
"Action: json_spec_get_value\n",
|
||||||
|
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"required\"]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[33;1m\u001b[1;3mTrue\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should look at the content key to see what parameters are required\n",
|
||||||
|
"Action: json_spec_list_keys\n",
|
||||||
|
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m['application/json']\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should look at the application/json key to see what parameters are required\n",
|
||||||
|
"Action: json_spec_list_keys\n",
|
||||||
|
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m['schema']\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should look at the schema key to see what parameters are required\n",
|
||||||
|
"Action: json_spec_list_keys\n",
|
||||||
|
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m['$ref']\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should look at the $ref key to see what parameters are required\n",
|
||||||
|
"Action: json_spec_get_value\n",
|
||||||
|
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"][\"$ref\"]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[33;1m\u001b[1;3m#/components/schemas/CreateCompletionRequest\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should look at the CreateCompletionRequest schema to see what parameters are required\n",
|
||||||
|
"Action: json_spec_list_keys\n",
|
||||||
|
"Action Input: data[\"components\"][\"schemas\"][\"CreateCompletionRequest\"]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m['type', 'properties', 'required']\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should look at the required key to see what parameters are required\n",
|
||||||
|
"Action: json_spec_get_value\n",
|
||||||
|
"Action Input: data[\"components\"][\"schemas\"][\"CreateCompletionRequest\"][\"required\"]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[33;1m\u001b[1;3m['model']\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||||
|
"Final Answer: The required parameters in the request body to the /completions endpoint are 'model'.\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"\"The required parameters in the request body to the /completions endpoint are 'model'.\""
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 5,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"json_agent_executor.run(\"What are the required parameters in the request body to the /completions endpoint?\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "ba9c9d30",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": []
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "Python 3 (ipykernel)",
|
||||||
|
"language": "python",
|
||||||
|
"name": "python3"
|
||||||
|
},
|
||||||
|
"language_info": {
|
||||||
|
"codemirror_mode": {
|
||||||
|
"name": "ipython",
|
||||||
|
"version": 3
|
||||||
|
},
|
||||||
|
"file_extension": ".py",
|
||||||
|
"mimetype": "text/x-python",
|
||||||
|
"name": "python",
|
||||||
|
"nbconvert_exporter": "python",
|
||||||
|
"pygments_lexer": "ipython3",
|
||||||
|
"version": "3.10.9"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 5
|
||||||
|
}
|
File diff suppressed because it is too large
Load Diff
@ -0,0 +1,242 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "85fb2c03-ab88-4c8c-97e3-a7f2954555ab",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# OpenAPI Agent\n",
|
||||||
|
"\n",
|
||||||
|
"This notebook showcases an agent designed to interact with an OpenAPI spec and make a correct API request based on the information it has gathered from the spec.\n",
|
||||||
|
"\n",
|
||||||
|
"In the below example, we are using the OpenAPI spec for the OpenAI API, which you can find [here](https://github.com/openai/openai-openapi/blob/master/openapi.yaml)."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "893f90fd-f8f6-470a-a76d-1f200ba02e2f",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Initialization"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 1,
|
||||||
|
"id": "ff988466-c389-4ec6-b6ac-14364a537fd5",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"import os\n",
|
||||||
|
"import yaml\n",
|
||||||
|
"\n",
|
||||||
|
"from langchain.agents import create_openapi_agent\n",
|
||||||
|
"from langchain.agents.agent_toolkits import OpenAPIToolkit\n",
|
||||||
|
"from langchain.llms.openai import OpenAI\n",
|
||||||
|
"from langchain.requests import RequestsWrapper\n",
|
||||||
|
"from langchain.tools.json.tool import JsonSpec"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 2,
|
||||||
|
"id": "9ecd1ba0-3937-4359-a41e-68605f0596a1",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"with open(\"openai_openapi.yml\") as f:\n",
|
||||||
|
" data = yaml.load(f, Loader=yaml.FullLoader)\n",
|
||||||
|
"json_spec=JsonSpec(dict_=data, max_value_length=4000)\n",
|
||||||
|
"headers = {\n",
|
||||||
|
" \"Authorization\": f\"Bearer {os.getenv('OPENAI_API_KEY')}\"\n",
|
||||||
|
"}\n",
|
||||||
|
"requests_wrapper=RequestsWrapper(headers=headers)\n",
|
||||||
|
"openapi_toolkit = OpenAPIToolkit.from_llm(OpenAI(temperature=0), json_spec, requests_wrapper, verbose=True)\n",
|
||||||
|
"openapi_agent_executor = create_openapi_agent(\n",
|
||||||
|
" llm=OpenAI(temperature=0),\n",
|
||||||
|
" toolkit=openapi_toolkit,\n",
|
||||||
|
" verbose=True\n",
|
||||||
|
")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "f111879d-ae84-41f9-ad82-d3e6b72c41ba",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Example: agent capable of analyzing OpenAPI spec and making requests"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 3,
|
||||||
|
"id": "548db7f7-337b-4ba8-905c-e7fd58c01799",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3mAction: json_explorer\n",
|
||||||
|
"Action Input: What is the base url for the API?\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3mAction: json_spec_list_keys\n",
|
||||||
|
"Action Input: data\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta']\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should look at the servers key to see what the base url is\n",
|
||||||
|
"Action: json_spec_list_keys\n",
|
||||||
|
"Action Input: data[\"servers\"][0]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3mValueError('Value at path `data[\"servers\"][0]` is not a dict, get the value directly.')\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should get the value of the servers key\n",
|
||||||
|
"Action: json_spec_get_value\n",
|
||||||
|
"Action Input: data[\"servers\"][0]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[33;1m\u001b[1;3m{'url': 'https://api.openai.com/v1'}\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I now know the base url for the API\n",
|
||||||
|
"Final Answer: The base url for the API is https://api.openai.com/v1\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"Observation: \u001b[33;1m\u001b[1;3mThe base url for the API is https://api.openai.com/v1\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should find the path for the /completions endpoint.\n",
|
||||||
|
"Action: json_explorer\n",
|
||||||
|
"Action Input: What is the path for the /completions endpoint?\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3mAction: json_spec_list_keys\n",
|
||||||
|
"Action Input: data\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta']\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should look at the paths key to see what endpoints exist\n",
|
||||||
|
"Action: json_spec_list_keys\n",
|
||||||
|
"Action Input: data[\"paths\"]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m['/engines', '/engines/{engine_id}', '/completions', '/edits', '/images/generations', '/images/edits', '/images/variations', '/embeddings', '/engines/{engine_id}/search', '/files', '/files/{file_id}', '/files/{file_id}/content', '/answers', '/classifications', '/fine-tunes', '/fine-tunes/{fine_tune_id}', '/fine-tunes/{fine_tune_id}/cancel', '/fine-tunes/{fine_tune_id}/events', '/models', '/models/{model}', '/moderations']\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I now know the path for the /completions endpoint\n",
|
||||||
|
"Final Answer: data[\"paths\"][2]\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"Observation: \u001b[33;1m\u001b[1;3mdata[\"paths\"][2]\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should find the required parameters for the POST request.\n",
|
||||||
|
"Action: json_explorer\n",
|
||||||
|
"Action Input: What are the required parameters for a POST request to the /completions endpoint?\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3mAction: json_spec_list_keys\n",
|
||||||
|
"Action Input: data\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta']\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should look at the paths key to see what endpoints exist\n",
|
||||||
|
"Action: json_spec_list_keys\n",
|
||||||
|
"Action Input: data[\"paths\"]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m['/engines', '/engines/{engine_id}', '/completions', '/edits', '/images/generations', '/images/edits', '/images/variations', '/embeddings', '/engines/{engine_id}/search', '/files', '/files/{file_id}', '/files/{file_id}/content', '/answers', '/classifications', '/fine-tunes', '/fine-tunes/{fine_tune_id}', '/fine-tunes/{fine_tune_id}/cancel', '/fine-tunes/{fine_tune_id}/events', '/models', '/models/{model}', '/moderations']\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should look at the /completions endpoint to see what parameters are required\n",
|
||||||
|
"Action: json_spec_list_keys\n",
|
||||||
|
"Action Input: data[\"paths\"][\"/completions\"]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m['post']\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should look at the post key to see what parameters are required\n",
|
||||||
|
"Action: json_spec_list_keys\n",
|
||||||
|
"Action Input: data[\"paths\"][\"/completions\"][\"post\"]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m['operationId', 'tags', 'summary', 'requestBody', 'responses', 'x-oaiMeta']\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should look at the requestBody key to see what parameters are required\n",
|
||||||
|
"Action: json_spec_list_keys\n",
|
||||||
|
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m['required', 'content']\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should look at the content key to see what parameters are required\n",
|
||||||
|
"Action: json_spec_list_keys\n",
|
||||||
|
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m['application/json']\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should look at the application/json key to see what parameters are required\n",
|
||||||
|
"Action: json_spec_list_keys\n",
|
||||||
|
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m['schema']\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should look at the schema key to see what parameters are required\n",
|
||||||
|
"Action: json_spec_list_keys\n",
|
||||||
|
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m['$ref']\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should look at the $ref key to see what parameters are required\n",
|
||||||
|
"Action: json_spec_list_keys\n",
|
||||||
|
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"][\"$ref\"]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3mValueError('Value at path `data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"][\"$ref\"]` is not a dict, get the value directly.')\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should look at the $ref key to get the value directly\n",
|
||||||
|
"Action: json_spec_get_value\n",
|
||||||
|
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"][\"$ref\"]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[33;1m\u001b[1;3m#/components/schemas/CreateCompletionRequest\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should look at the CreateCompletionRequest schema to see what parameters are required\n",
|
||||||
|
"Action: json_spec_list_keys\n",
|
||||||
|
"Action Input: data[\"components\"][\"schemas\"][\"CreateCompletionRequest\"]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m['type', 'properties', 'required']\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I should look at the required key to see what parameters are required\n",
|
||||||
|
"Action: json_spec_get_value\n",
|
||||||
|
"Action Input: data[\"components\"][\"schemas\"][\"CreateCompletionRequest\"][\"required\"]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[33;1m\u001b[1;3m['model']\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||||
|
"Final Answer: The required parameters for a POST request to the /completions endpoint are 'model'.\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"Observation: \u001b[33;1m\u001b[1;3mThe required parameters for a POST request to the /completions endpoint are 'model'.\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I now know the parameters needed to make the request.\n",
|
||||||
|
"Action: requests_post\n",
|
||||||
|
"Action Input: { \"url\": \"https://api.openai.com/v1/completions\", \"data\": { \"model\": \"davinci\", \"prompt\": \"tell me a joke\" } }\u001b[0m\n",
|
||||||
|
"Observation: \u001b[33;1m\u001b[1;3m{\"id\":\"cmpl-6oeEcNETfq8TOuIUQvAct6NrBXihs\",\"object\":\"text_completion\",\"created\":1677529082,\"model\":\"davinci\",\"choices\":[{\"text\":\"\\n\\n\\n\\nLove is a battlefield\\n\\n\\n\\nIt's me...And some\",\"index\":0,\"logprobs\":null,\"finish_reason\":\"length\"}],\"usage\":{\"prompt_tokens\":4,\"completion_tokens\":16,\"total_tokens\":20}}\n",
|
||||||
|
"\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
|
||||||
|
"Final Answer: Love is a battlefield. It's me...And some.\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"\"Love is a battlefield. It's me...And some.\""
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 3,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"openapi_agent_executor.run(\"Make a post request to openai /completions. The prompt should be 'tell me a joke.'\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "6ec9582b",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": []
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "Python 3 (ipykernel)",
|
||||||
|
"language": "python",
|
||||||
|
"name": "python3"
|
||||||
|
},
|
||||||
|
"language_info": {
|
||||||
|
"codemirror_mode": {
|
||||||
|
"name": "ipython",
|
||||||
|
"version": 3
|
||||||
|
},
|
||||||
|
"file_extension": ".py",
|
||||||
|
"mimetype": "text/x-python",
|
||||||
|
"name": "python",
|
||||||
|
"nbconvert_exporter": "python",
|
||||||
|
"pygments_lexer": "ipython3",
|
||||||
|
"version": "3.10.9"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 5
|
||||||
|
}
|
@ -0,0 +1,204 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "c81da886",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# Pandas Dataframe Agent\n",
|
||||||
|
"\n",
|
||||||
|
"This notebook shows how to use agents to interact with a pandas dataframe. It is mostly optimized for question answering.\n",
|
||||||
|
"\n",
|
||||||
|
"**NOTE: this agent calls the Python agent under the hood, which executes LLM generated Python code - this can be bad if the LLM generated Python code is harmful. Use cautiously.**"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 7,
|
||||||
|
"id": "0cdd9bf5",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.agents import create_pandas_dataframe_agent"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 2,
|
||||||
|
"id": "051ebe84",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.llms import OpenAI\n",
|
||||||
|
"import pandas as pd\n",
|
||||||
|
"\n",
|
||||||
|
"df = pd.read_csv('titanic.csv')"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 3,
|
||||||
|
"id": "4185ff46",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"agent = create_pandas_dataframe_agent(OpenAI(temperature=0), df, verbose=True)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 4,
|
||||||
|
"id": "a9207a2e",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3mThought: I need to count the number of rows\n",
|
||||||
|
"Action: python_repl_ast\n",
|
||||||
|
"Action Input: len(df)\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m891\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||||
|
"Final Answer: There are 891 rows in the dataframe.\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"'There are 891 rows in the dataframe.'"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 4,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"agent.run(\"how many rows are there?\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 5,
|
||||||
|
"id": "bd43617c",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3mThought: I need to count the number of people with more than 3 siblings\n",
|
||||||
|
"Action: python_repl_ast\n",
|
||||||
|
"Action Input: df[df['SibSp'] > 3].shape[0]\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m30\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||||
|
"Final Answer: 30 people have more than 3 siblings.\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"'30 people have more than 3 siblings.'"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 5,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"agent.run(\"how many people have more than 3 sibligngs\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 6,
|
||||||
|
"id": "94e64b58",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3mThought: I need to calculate the average age first\n",
|
||||||
|
"Action: python_repl_ast\n",
|
||||||
|
"Action Input: df['Age'].mean()\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m29.69911764705882\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I can now calculate the square root\n",
|
||||||
|
"Action: python_repl_ast\n",
|
||||||
|
"Action Input: math.sqrt(df['Age'].mean())\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3mname 'math' is not defined\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I need to import the math library\n",
|
||||||
|
"Action: python_repl_ast\n",
|
||||||
|
"Action Input: import math\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3mNone\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I can now calculate the square root\n",
|
||||||
|
"Action: python_repl_ast\n",
|
||||||
|
"Action Input: math.sqrt(df['Age'].mean())\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m5.449689683556195\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||||
|
"Final Answer: 5.449689683556195\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"'5.449689683556195'"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 6,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"agent.run(\"whats the square root of the average age?\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "eba13b4d",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": []
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "Python 3 (ipykernel)",
|
||||||
|
"language": "python",
|
||||||
|
"name": "python3"
|
||||||
|
},
|
||||||
|
"language_info": {
|
||||||
|
"codemirror_mode": {
|
||||||
|
"name": "ipython",
|
||||||
|
"version": 3
|
||||||
|
},
|
||||||
|
"file_extension": ".py",
|
||||||
|
"mimetype": "text/x-python",
|
||||||
|
"name": "python",
|
||||||
|
"nbconvert_exporter": "python",
|
||||||
|
"pygments_lexer": "ipython3",
|
||||||
|
"version": "3.9.1"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 5
|
||||||
|
}
|
@ -0,0 +1,228 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "82a4c2cc-20ea-4b20-a565-63e905dee8ff",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Python Agent\n",
|
||||||
|
"\n",
|
||||||
|
"This notebook showcases an agent designed to write and execute python code to answer a question."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 1,
|
||||||
|
"id": "f98e9c90-5c37-4fb9-af3e-d09693af8543",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.agents.agent_toolkits import create_python_agent\n",
|
||||||
|
"from langchain.tools.python.tool import PythonREPLTool\n",
|
||||||
|
"from langchain.python import PythonREPL\n",
|
||||||
|
"from langchain.llms.openai import OpenAI"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 2,
|
||||||
|
"id": "cc422f53-c51c-4694-a834-72ecd1e68363",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"agent_executor = create_python_agent(\n",
|
||||||
|
" llm=OpenAI(temperature=0, max_tokens=1000),\n",
|
||||||
|
" tool=PythonREPLTool(),\n",
|
||||||
|
" verbose=True\n",
|
||||||
|
")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "c16161de",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Fibonacci Example\n",
|
||||||
|
"This example was created by [John Wiseman](https://twitter.com/lemonodor/status/1628270074074398720?s=20)."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 3,
|
||||||
|
"id": "25cd4f92-ea9b-4fe6-9838-a4f85f81eebe",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3m I need to calculate the 10th fibonacci number\n",
|
||||||
|
"Action: Python REPL\n",
|
||||||
|
"Action Input: def fibonacci(n):\n",
|
||||||
|
" if n == 0:\n",
|
||||||
|
" return 0\n",
|
||||||
|
" elif n == 1:\n",
|
||||||
|
" return 1\n",
|
||||||
|
" else:\n",
|
||||||
|
" return fibonacci(n-1) + fibonacci(n-2)\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I need to call the function with 10 as the argument\n",
|
||||||
|
"Action: Python REPL\n",
|
||||||
|
"Action Input: fibonacci(10)\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||||
|
"Final Answer: 55\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"'55'"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 3,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"agent_executor.run(\"What is the 10th fibonacci number?\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "7caa30de",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Training neural net\n",
|
||||||
|
"This example was created by [Samee Ur Rehman](https://twitter.com/sameeurehman/status/1630130518133207046?s=20)."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 4,
|
||||||
|
"id": "4b9f60e7-eb6a-4f14-8604-498d863d4482",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3m I need to write a neural network in PyTorch and train it on the given data.\n",
|
||||||
|
"Action: Python REPL\n",
|
||||||
|
"Action Input: \n",
|
||||||
|
"import torch\n",
|
||||||
|
"\n",
|
||||||
|
"# Define the model\n",
|
||||||
|
"model = torch.nn.Sequential(\n",
|
||||||
|
" torch.nn.Linear(1, 1)\n",
|
||||||
|
")\n",
|
||||||
|
"\n",
|
||||||
|
"# Define the loss\n",
|
||||||
|
"loss_fn = torch.nn.MSELoss()\n",
|
||||||
|
"\n",
|
||||||
|
"# Define the optimizer\n",
|
||||||
|
"optimizer = torch.optim.SGD(model.parameters(), lr=0.01)\n",
|
||||||
|
"\n",
|
||||||
|
"# Define the data\n",
|
||||||
|
"x_data = torch.tensor([[1.0], [2.0], [3.0], [4.0]])\n",
|
||||||
|
"y_data = torch.tensor([[2.0], [4.0], [6.0], [8.0]])\n",
|
||||||
|
"\n",
|
||||||
|
"# Train the model\n",
|
||||||
|
"for epoch in range(1000):\n",
|
||||||
|
" # Forward pass\n",
|
||||||
|
" y_pred = model(x_data)\n",
|
||||||
|
"\n",
|
||||||
|
" # Compute and print loss\n",
|
||||||
|
" loss = loss_fn(y_pred, y_data)\n",
|
||||||
|
" if (epoch+1) % 100 == 0:\n",
|
||||||
|
" print(f'Epoch {epoch+1}: loss = {loss.item():.4f}')\n",
|
||||||
|
"\n",
|
||||||
|
" # Zero the gradients\n",
|
||||||
|
" optimizer.zero_grad()\n",
|
||||||
|
"\n",
|
||||||
|
" # Backward pass\n",
|
||||||
|
" loss.backward()\n",
|
||||||
|
"\n",
|
||||||
|
" # Update the weights\n",
|
||||||
|
" optimizer.step()\n",
|
||||||
|
"\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3mEpoch 100: loss = 0.0013\n",
|
||||||
|
"Epoch 200: loss = 0.0007\n",
|
||||||
|
"Epoch 300: loss = 0.0004\n",
|
||||||
|
"Epoch 400: loss = 0.0002\n",
|
||||||
|
"Epoch 500: loss = 0.0001\n",
|
||||||
|
"Epoch 600: loss = 0.0001\n",
|
||||||
|
"Epoch 700: loss = 0.0000\n",
|
||||||
|
"Epoch 800: loss = 0.0000\n",
|
||||||
|
"Epoch 900: loss = 0.0000\n",
|
||||||
|
"Epoch 1000: loss = 0.0000\n",
|
||||||
|
"\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||||
|
"Final Answer: The prediction for x = 5 is 10.0.\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"'The prediction for x = 5 is 10.0.'"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 4,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"agent_executor.run(\"\"\"Understand, write a single neuron neural network in PyTorch.\n",
|
||||||
|
"Take synthetic data for y=2x. Train for 1000 epochs and print every 100 epochs.\n",
|
||||||
|
"Return prediction for x = 5\"\"\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "eb654671",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": []
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "Python 3 (ipykernel)",
|
||||||
|
"language": "python",
|
||||||
|
"name": "python3"
|
||||||
|
},
|
||||||
|
"language_info": {
|
||||||
|
"codemirror_mode": {
|
||||||
|
"name": "ipython",
|
||||||
|
"version": 3
|
||||||
|
},
|
||||||
|
"file_extension": ".py",
|
||||||
|
"mimetype": "text/x-python",
|
||||||
|
"name": "python",
|
||||||
|
"nbconvert_exporter": "python",
|
||||||
|
"pygments_lexer": "ipython3",
|
||||||
|
"version": "3.9.1"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 5
|
||||||
|
}
|
@ -0,0 +1,892 @@
|
|||||||
|
PassengerId,Survived,Pclass,Name,Sex,Age,SibSp,Parch,Ticket,Fare,Cabin,Embarked
|
||||||
|
1,0,3,"Braund, Mr. Owen Harris",male,22,1,0,A/5 21171,7.25,,S
|
||||||
|
2,1,1,"Cumings, Mrs. John Bradley (Florence Briggs Thayer)",female,38,1,0,PC 17599,71.2833,C85,C
|
||||||
|
3,1,3,"Heikkinen, Miss. Laina",female,26,0,0,STON/O2. 3101282,7.925,,S
|
||||||
|
4,1,1,"Futrelle, Mrs. Jacques Heath (Lily May Peel)",female,35,1,0,113803,53.1,C123,S
|
||||||
|
5,0,3,"Allen, Mr. William Henry",male,35,0,0,373450,8.05,,S
|
||||||
|
6,0,3,"Moran, Mr. James",male,,0,0,330877,8.4583,,Q
|
||||||
|
7,0,1,"McCarthy, Mr. Timothy J",male,54,0,0,17463,51.8625,E46,S
|
||||||
|
8,0,3,"Palsson, Master. Gosta Leonard",male,2,3,1,349909,21.075,,S
|
||||||
|
9,1,3,"Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)",female,27,0,2,347742,11.1333,,S
|
||||||
|
10,1,2,"Nasser, Mrs. Nicholas (Adele Achem)",female,14,1,0,237736,30.0708,,C
|
||||||
|
11,1,3,"Sandstrom, Miss. Marguerite Rut",female,4,1,1,PP 9549,16.7,G6,S
|
||||||
|
12,1,1,"Bonnell, Miss. Elizabeth",female,58,0,0,113783,26.55,C103,S
|
||||||
|
13,0,3,"Saundercock, Mr. William Henry",male,20,0,0,A/5. 2151,8.05,,S
|
||||||
|
14,0,3,"Andersson, Mr. Anders Johan",male,39,1,5,347082,31.275,,S
|
||||||
|
15,0,3,"Vestrom, Miss. Hulda Amanda Adolfina",female,14,0,0,350406,7.8542,,S
|
||||||
|
16,1,2,"Hewlett, Mrs. (Mary D Kingcome) ",female,55,0,0,248706,16,,S
|
||||||
|
17,0,3,"Rice, Master. Eugene",male,2,4,1,382652,29.125,,Q
|
||||||
|
18,1,2,"Williams, Mr. Charles Eugene",male,,0,0,244373,13,,S
|
||||||
|
19,0,3,"Vander Planke, Mrs. Julius (Emelia Maria Vandemoortele)",female,31,1,0,345763,18,,S
|
||||||
|
20,1,3,"Masselmani, Mrs. Fatima",female,,0,0,2649,7.225,,C
|
||||||
|
21,0,2,"Fynney, Mr. Joseph J",male,35,0,0,239865,26,,S
|
||||||
|
22,1,2,"Beesley, Mr. Lawrence",male,34,0,0,248698,13,D56,S
|
||||||
|
23,1,3,"McGowan, Miss. Anna ""Annie""",female,15,0,0,330923,8.0292,,Q
|
||||||
|
24,1,1,"Sloper, Mr. William Thompson",male,28,0,0,113788,35.5,A6,S
|
||||||
|
25,0,3,"Palsson, Miss. Torborg Danira",female,8,3,1,349909,21.075,,S
|
||||||
|
26,1,3,"Asplund, Mrs. Carl Oscar (Selma Augusta Emilia Johansson)",female,38,1,5,347077,31.3875,,S
|
||||||
|
27,0,3,"Emir, Mr. Farred Chehab",male,,0,0,2631,7.225,,C
|
||||||
|
28,0,1,"Fortune, Mr. Charles Alexander",male,19,3,2,19950,263,C23 C25 C27,S
|
||||||
|
29,1,3,"O'Dwyer, Miss. Ellen ""Nellie""",female,,0,0,330959,7.8792,,Q
|
||||||
|
30,0,3,"Todoroff, Mr. Lalio",male,,0,0,349216,7.8958,,S
|
||||||
|
31,0,1,"Uruchurtu, Don. Manuel E",male,40,0,0,PC 17601,27.7208,,C
|
||||||
|
32,1,1,"Spencer, Mrs. William Augustus (Marie Eugenie)",female,,1,0,PC 17569,146.5208,B78,C
|
||||||
|
33,1,3,"Glynn, Miss. Mary Agatha",female,,0,0,335677,7.75,,Q
|
||||||
|
34,0,2,"Wheadon, Mr. Edward H",male,66,0,0,C.A. 24579,10.5,,S
|
||||||
|
35,0,1,"Meyer, Mr. Edgar Joseph",male,28,1,0,PC 17604,82.1708,,C
|
||||||
|
36,0,1,"Holverson, Mr. Alexander Oskar",male,42,1,0,113789,52,,S
|
||||||
|
37,1,3,"Mamee, Mr. Hanna",male,,0,0,2677,7.2292,,C
|
||||||
|
38,0,3,"Cann, Mr. Ernest Charles",male,21,0,0,A./5. 2152,8.05,,S
|
||||||
|
39,0,3,"Vander Planke, Miss. Augusta Maria",female,18,2,0,345764,18,,S
|
||||||
|
40,1,3,"Nicola-Yarred, Miss. Jamila",female,14,1,0,2651,11.2417,,C
|
||||||
|
41,0,3,"Ahlin, Mrs. Johan (Johanna Persdotter Larsson)",female,40,1,0,7546,9.475,,S
|
||||||
|
42,0,2,"Turpin, Mrs. William John Robert (Dorothy Ann Wonnacott)",female,27,1,0,11668,21,,S
|
||||||
|
43,0,3,"Kraeff, Mr. Theodor",male,,0,0,349253,7.8958,,C
|
||||||
|
44,1,2,"Laroche, Miss. Simonne Marie Anne Andree",female,3,1,2,SC/Paris 2123,41.5792,,C
|
||||||
|
45,1,3,"Devaney, Miss. Margaret Delia",female,19,0,0,330958,7.8792,,Q
|
||||||
|
46,0,3,"Rogers, Mr. William John",male,,0,0,S.C./A.4. 23567,8.05,,S
|
||||||
|
47,0,3,"Lennon, Mr. Denis",male,,1,0,370371,15.5,,Q
|
||||||
|
48,1,3,"O'Driscoll, Miss. Bridget",female,,0,0,14311,7.75,,Q
|
||||||
|
49,0,3,"Samaan, Mr. Youssef",male,,2,0,2662,21.6792,,C
|
||||||
|
50,0,3,"Arnold-Franchi, Mrs. Josef (Josefine Franchi)",female,18,1,0,349237,17.8,,S
|
||||||
|
51,0,3,"Panula, Master. Juha Niilo",male,7,4,1,3101295,39.6875,,S
|
||||||
|
52,0,3,"Nosworthy, Mr. Richard Cater",male,21,0,0,A/4. 39886,7.8,,S
|
||||||
|
53,1,1,"Harper, Mrs. Henry Sleeper (Myna Haxtun)",female,49,1,0,PC 17572,76.7292,D33,C
|
||||||
|
54,1,2,"Faunthorpe, Mrs. Lizzie (Elizabeth Anne Wilkinson)",female,29,1,0,2926,26,,S
|
||||||
|
55,0,1,"Ostby, Mr. Engelhart Cornelius",male,65,0,1,113509,61.9792,B30,C
|
||||||
|
56,1,1,"Woolner, Mr. Hugh",male,,0,0,19947,35.5,C52,S
|
||||||
|
57,1,2,"Rugg, Miss. Emily",female,21,0,0,C.A. 31026,10.5,,S
|
||||||
|
58,0,3,"Novel, Mr. Mansouer",male,28.5,0,0,2697,7.2292,,C
|
||||||
|
59,1,2,"West, Miss. Constance Mirium",female,5,1,2,C.A. 34651,27.75,,S
|
||||||
|
60,0,3,"Goodwin, Master. William Frederick",male,11,5,2,CA 2144,46.9,,S
|
||||||
|
61,0,3,"Sirayanian, Mr. Orsen",male,22,0,0,2669,7.2292,,C
|
||||||
|
62,1,1,"Icard, Miss. Amelie",female,38,0,0,113572,80,B28,
|
||||||
|
63,0,1,"Harris, Mr. Henry Birkhardt",male,45,1,0,36973,83.475,C83,S
|
||||||
|
64,0,3,"Skoog, Master. Harald",male,4,3,2,347088,27.9,,S
|
||||||
|
65,0,1,"Stewart, Mr. Albert A",male,,0,0,PC 17605,27.7208,,C
|
||||||
|
66,1,3,"Moubarek, Master. Gerios",male,,1,1,2661,15.2458,,C
|
||||||
|
67,1,2,"Nye, Mrs. (Elizabeth Ramell)",female,29,0,0,C.A. 29395,10.5,F33,S
|
||||||
|
68,0,3,"Crease, Mr. Ernest James",male,19,0,0,S.P. 3464,8.1583,,S
|
||||||
|
69,1,3,"Andersson, Miss. Erna Alexandra",female,17,4,2,3101281,7.925,,S
|
||||||
|
70,0,3,"Kink, Mr. Vincenz",male,26,2,0,315151,8.6625,,S
|
||||||
|
71,0,2,"Jenkin, Mr. Stephen Curnow",male,32,0,0,C.A. 33111,10.5,,S
|
||||||
|
72,0,3,"Goodwin, Miss. Lillian Amy",female,16,5,2,CA 2144,46.9,,S
|
||||||
|
73,0,2,"Hood, Mr. Ambrose Jr",male,21,0,0,S.O.C. 14879,73.5,,S
|
||||||
|
74,0,3,"Chronopoulos, Mr. Apostolos",male,26,1,0,2680,14.4542,,C
|
||||||
|
75,1,3,"Bing, Mr. Lee",male,32,0,0,1601,56.4958,,S
|
||||||
|
76,0,3,"Moen, Mr. Sigurd Hansen",male,25,0,0,348123,7.65,F G73,S
|
||||||
|
77,0,3,"Staneff, Mr. Ivan",male,,0,0,349208,7.8958,,S
|
||||||
|
78,0,3,"Moutal, Mr. Rahamin Haim",male,,0,0,374746,8.05,,S
|
||||||
|
79,1,2,"Caldwell, Master. Alden Gates",male,0.83,0,2,248738,29,,S
|
||||||
|
80,1,3,"Dowdell, Miss. Elizabeth",female,30,0,0,364516,12.475,,S
|
||||||
|
81,0,3,"Waelens, Mr. Achille",male,22,0,0,345767,9,,S
|
||||||
|
82,1,3,"Sheerlinck, Mr. Jan Baptist",male,29,0,0,345779,9.5,,S
|
||||||
|
83,1,3,"McDermott, Miss. Brigdet Delia",female,,0,0,330932,7.7875,,Q
|
||||||
|
84,0,1,"Carrau, Mr. Francisco M",male,28,0,0,113059,47.1,,S
|
||||||
|
85,1,2,"Ilett, Miss. Bertha",female,17,0,0,SO/C 14885,10.5,,S
|
||||||
|
86,1,3,"Backstrom, Mrs. Karl Alfred (Maria Mathilda Gustafsson)",female,33,3,0,3101278,15.85,,S
|
||||||
|
87,0,3,"Ford, Mr. William Neal",male,16,1,3,W./C. 6608,34.375,,S
|
||||||
|
88,0,3,"Slocovski, Mr. Selman Francis",male,,0,0,SOTON/OQ 392086,8.05,,S
|
||||||
|
89,1,1,"Fortune, Miss. Mabel Helen",female,23,3,2,19950,263,C23 C25 C27,S
|
||||||
|
90,0,3,"Celotti, Mr. Francesco",male,24,0,0,343275,8.05,,S
|
||||||
|
91,0,3,"Christmann, Mr. Emil",male,29,0,0,343276,8.05,,S
|
||||||
|
92,0,3,"Andreasson, Mr. Paul Edvin",male,20,0,0,347466,7.8542,,S
|
||||||
|
93,0,1,"Chaffee, Mr. Herbert Fuller",male,46,1,0,W.E.P. 5734,61.175,E31,S
|
||||||
|
94,0,3,"Dean, Mr. Bertram Frank",male,26,1,2,C.A. 2315,20.575,,S
|
||||||
|
95,0,3,"Coxon, Mr. Daniel",male,59,0,0,364500,7.25,,S
|
||||||
|
96,0,3,"Shorney, Mr. Charles Joseph",male,,0,0,374910,8.05,,S
|
||||||
|
97,0,1,"Goldschmidt, Mr. George B",male,71,0,0,PC 17754,34.6542,A5,C
|
||||||
|
98,1,1,"Greenfield, Mr. William Bertram",male,23,0,1,PC 17759,63.3583,D10 D12,C
|
||||||
|
99,1,2,"Doling, Mrs. John T (Ada Julia Bone)",female,34,0,1,231919,23,,S
|
||||||
|
100,0,2,"Kantor, Mr. Sinai",male,34,1,0,244367,26,,S
|
||||||
|
101,0,3,"Petranec, Miss. Matilda",female,28,0,0,349245,7.8958,,S
|
||||||
|
102,0,3,"Petroff, Mr. Pastcho (""Pentcho"")",male,,0,0,349215,7.8958,,S
|
||||||
|
103,0,1,"White, Mr. Richard Frasar",male,21,0,1,35281,77.2875,D26,S
|
||||||
|
104,0,3,"Johansson, Mr. Gustaf Joel",male,33,0,0,7540,8.6542,,S
|
||||||
|
105,0,3,"Gustafsson, Mr. Anders Vilhelm",male,37,2,0,3101276,7.925,,S
|
||||||
|
106,0,3,"Mionoff, Mr. Stoytcho",male,28,0,0,349207,7.8958,,S
|
||||||
|
107,1,3,"Salkjelsvik, Miss. Anna Kristine",female,21,0,0,343120,7.65,,S
|
||||||
|
108,1,3,"Moss, Mr. Albert Johan",male,,0,0,312991,7.775,,S
|
||||||
|
109,0,3,"Rekic, Mr. Tido",male,38,0,0,349249,7.8958,,S
|
||||||
|
110,1,3,"Moran, Miss. Bertha",female,,1,0,371110,24.15,,Q
|
||||||
|
111,0,1,"Porter, Mr. Walter Chamberlain",male,47,0,0,110465,52,C110,S
|
||||||
|
112,0,3,"Zabour, Miss. Hileni",female,14.5,1,0,2665,14.4542,,C
|
||||||
|
113,0,3,"Barton, Mr. David John",male,22,0,0,324669,8.05,,S
|
||||||
|
114,0,3,"Jussila, Miss. Katriina",female,20,1,0,4136,9.825,,S
|
||||||
|
115,0,3,"Attalah, Miss. Malake",female,17,0,0,2627,14.4583,,C
|
||||||
|
116,0,3,"Pekoniemi, Mr. Edvard",male,21,0,0,STON/O 2. 3101294,7.925,,S
|
||||||
|
117,0,3,"Connors, Mr. Patrick",male,70.5,0,0,370369,7.75,,Q
|
||||||
|
118,0,2,"Turpin, Mr. William John Robert",male,29,1,0,11668,21,,S
|
||||||
|
119,0,1,"Baxter, Mr. Quigg Edmond",male,24,0,1,PC 17558,247.5208,B58 B60,C
|
||||||
|
120,0,3,"Andersson, Miss. Ellis Anna Maria",female,2,4,2,347082,31.275,,S
|
||||||
|
121,0,2,"Hickman, Mr. Stanley George",male,21,2,0,S.O.C. 14879,73.5,,S
|
||||||
|
122,0,3,"Moore, Mr. Leonard Charles",male,,0,0,A4. 54510,8.05,,S
|
||||||
|
123,0,2,"Nasser, Mr. Nicholas",male,32.5,1,0,237736,30.0708,,C
|
||||||
|
124,1,2,"Webber, Miss. Susan",female,32.5,0,0,27267,13,E101,S
|
||||||
|
125,0,1,"White, Mr. Percival Wayland",male,54,0,1,35281,77.2875,D26,S
|
||||||
|
126,1,3,"Nicola-Yarred, Master. Elias",male,12,1,0,2651,11.2417,,C
|
||||||
|
127,0,3,"McMahon, Mr. Martin",male,,0,0,370372,7.75,,Q
|
||||||
|
128,1,3,"Madsen, Mr. Fridtjof Arne",male,24,0,0,C 17369,7.1417,,S
|
||||||
|
129,1,3,"Peter, Miss. Anna",female,,1,1,2668,22.3583,F E69,C
|
||||||
|
130,0,3,"Ekstrom, Mr. Johan",male,45,0,0,347061,6.975,,S
|
||||||
|
131,0,3,"Drazenoic, Mr. Jozef",male,33,0,0,349241,7.8958,,C
|
||||||
|
132,0,3,"Coelho, Mr. Domingos Fernandeo",male,20,0,0,SOTON/O.Q. 3101307,7.05,,S
|
||||||
|
133,0,3,"Robins, Mrs. Alexander A (Grace Charity Laury)",female,47,1,0,A/5. 3337,14.5,,S
|
||||||
|
134,1,2,"Weisz, Mrs. Leopold (Mathilde Francoise Pede)",female,29,1,0,228414,26,,S
|
||||||
|
135,0,2,"Sobey, Mr. Samuel James Hayden",male,25,0,0,C.A. 29178,13,,S
|
||||||
|
136,0,2,"Richard, Mr. Emile",male,23,0,0,SC/PARIS 2133,15.0458,,C
|
||||||
|
137,1,1,"Newsom, Miss. Helen Monypeny",female,19,0,2,11752,26.2833,D47,S
|
||||||
|
138,0,1,"Futrelle, Mr. Jacques Heath",male,37,1,0,113803,53.1,C123,S
|
||||||
|
139,0,3,"Osen, Mr. Olaf Elon",male,16,0,0,7534,9.2167,,S
|
||||||
|
140,0,1,"Giglio, Mr. Victor",male,24,0,0,PC 17593,79.2,B86,C
|
||||||
|
141,0,3,"Boulos, Mrs. Joseph (Sultana)",female,,0,2,2678,15.2458,,C
|
||||||
|
142,1,3,"Nysten, Miss. Anna Sofia",female,22,0,0,347081,7.75,,S
|
||||||
|
143,1,3,"Hakkarainen, Mrs. Pekka Pietari (Elin Matilda Dolck)",female,24,1,0,STON/O2. 3101279,15.85,,S
|
||||||
|
144,0,3,"Burke, Mr. Jeremiah",male,19,0,0,365222,6.75,,Q
|
||||||
|
145,0,2,"Andrew, Mr. Edgardo Samuel",male,18,0,0,231945,11.5,,S
|
||||||
|
146,0,2,"Nicholls, Mr. Joseph Charles",male,19,1,1,C.A. 33112,36.75,,S
|
||||||
|
147,1,3,"Andersson, Mr. August Edvard (""Wennerstrom"")",male,27,0,0,350043,7.7958,,S
|
||||||
|
148,0,3,"Ford, Miss. Robina Maggie ""Ruby""",female,9,2,2,W./C. 6608,34.375,,S
|
||||||
|
149,0,2,"Navratil, Mr. Michel (""Louis M Hoffman"")",male,36.5,0,2,230080,26,F2,S
|
||||||
|
150,0,2,"Byles, Rev. Thomas Roussel Davids",male,42,0,0,244310,13,,S
|
||||||
|
151,0,2,"Bateman, Rev. Robert James",male,51,0,0,S.O.P. 1166,12.525,,S
|
||||||
|
152,1,1,"Pears, Mrs. Thomas (Edith Wearne)",female,22,1,0,113776,66.6,C2,S
|
||||||
|
153,0,3,"Meo, Mr. Alfonzo",male,55.5,0,0,A.5. 11206,8.05,,S
|
||||||
|
154,0,3,"van Billiard, Mr. Austin Blyler",male,40.5,0,2,A/5. 851,14.5,,S
|
||||||
|
155,0,3,"Olsen, Mr. Ole Martin",male,,0,0,Fa 265302,7.3125,,S
|
||||||
|
156,0,1,"Williams, Mr. Charles Duane",male,51,0,1,PC 17597,61.3792,,C
|
||||||
|
157,1,3,"Gilnagh, Miss. Katherine ""Katie""",female,16,0,0,35851,7.7333,,Q
|
||||||
|
158,0,3,"Corn, Mr. Harry",male,30,0,0,SOTON/OQ 392090,8.05,,S
|
||||||
|
159,0,3,"Smiljanic, Mr. Mile",male,,0,0,315037,8.6625,,S
|
||||||
|
160,0,3,"Sage, Master. Thomas Henry",male,,8,2,CA. 2343,69.55,,S
|
||||||
|
161,0,3,"Cribb, Mr. John Hatfield",male,44,0,1,371362,16.1,,S
|
||||||
|
162,1,2,"Watt, Mrs. James (Elizabeth ""Bessie"" Inglis Milne)",female,40,0,0,C.A. 33595,15.75,,S
|
||||||
|
163,0,3,"Bengtsson, Mr. John Viktor",male,26,0,0,347068,7.775,,S
|
||||||
|
164,0,3,"Calic, Mr. Jovo",male,17,0,0,315093,8.6625,,S
|
||||||
|
165,0,3,"Panula, Master. Eino Viljami",male,1,4,1,3101295,39.6875,,S
|
||||||
|
166,1,3,"Goldsmith, Master. Frank John William ""Frankie""",male,9,0,2,363291,20.525,,S
|
||||||
|
167,1,1,"Chibnall, Mrs. (Edith Martha Bowerman)",female,,0,1,113505,55,E33,S
|
||||||
|
168,0,3,"Skoog, Mrs. William (Anna Bernhardina Karlsson)",female,45,1,4,347088,27.9,,S
|
||||||
|
169,0,1,"Baumann, Mr. John D",male,,0,0,PC 17318,25.925,,S
|
||||||
|
170,0,3,"Ling, Mr. Lee",male,28,0,0,1601,56.4958,,S
|
||||||
|
171,0,1,"Van der hoef, Mr. Wyckoff",male,61,0,0,111240,33.5,B19,S
|
||||||
|
172,0,3,"Rice, Master. Arthur",male,4,4,1,382652,29.125,,Q
|
||||||
|
173,1,3,"Johnson, Miss. Eleanor Ileen",female,1,1,1,347742,11.1333,,S
|
||||||
|
174,0,3,"Sivola, Mr. Antti Wilhelm",male,21,0,0,STON/O 2. 3101280,7.925,,S
|
||||||
|
175,0,1,"Smith, Mr. James Clinch",male,56,0,0,17764,30.6958,A7,C
|
||||||
|
176,0,3,"Klasen, Mr. Klas Albin",male,18,1,1,350404,7.8542,,S
|
||||||
|
177,0,3,"Lefebre, Master. Henry Forbes",male,,3,1,4133,25.4667,,S
|
||||||
|
178,0,1,"Isham, Miss. Ann Elizabeth",female,50,0,0,PC 17595,28.7125,C49,C
|
||||||
|
179,0,2,"Hale, Mr. Reginald",male,30,0,0,250653,13,,S
|
||||||
|
180,0,3,"Leonard, Mr. Lionel",male,36,0,0,LINE,0,,S
|
||||||
|
181,0,3,"Sage, Miss. Constance Gladys",female,,8,2,CA. 2343,69.55,,S
|
||||||
|
182,0,2,"Pernot, Mr. Rene",male,,0,0,SC/PARIS 2131,15.05,,C
|
||||||
|
183,0,3,"Asplund, Master. Clarence Gustaf Hugo",male,9,4,2,347077,31.3875,,S
|
||||||
|
184,1,2,"Becker, Master. Richard F",male,1,2,1,230136,39,F4,S
|
||||||
|
185,1,3,"Kink-Heilmann, Miss. Luise Gretchen",female,4,0,2,315153,22.025,,S
|
||||||
|
186,0,1,"Rood, Mr. Hugh Roscoe",male,,0,0,113767,50,A32,S
|
||||||
|
187,1,3,"O'Brien, Mrs. Thomas (Johanna ""Hannah"" Godfrey)",female,,1,0,370365,15.5,,Q
|
||||||
|
188,1,1,"Romaine, Mr. Charles Hallace (""Mr C Rolmane"")",male,45,0,0,111428,26.55,,S
|
||||||
|
189,0,3,"Bourke, Mr. John",male,40,1,1,364849,15.5,,Q
|
||||||
|
190,0,3,"Turcin, Mr. Stjepan",male,36,0,0,349247,7.8958,,S
|
||||||
|
191,1,2,"Pinsky, Mrs. (Rosa)",female,32,0,0,234604,13,,S
|
||||||
|
192,0,2,"Carbines, Mr. William",male,19,0,0,28424,13,,S
|
||||||
|
193,1,3,"Andersen-Jensen, Miss. Carla Christine Nielsine",female,19,1,0,350046,7.8542,,S
|
||||||
|
194,1,2,"Navratil, Master. Michel M",male,3,1,1,230080,26,F2,S
|
||||||
|
195,1,1,"Brown, Mrs. James Joseph (Margaret Tobin)",female,44,0,0,PC 17610,27.7208,B4,C
|
||||||
|
196,1,1,"Lurette, Miss. Elise",female,58,0,0,PC 17569,146.5208,B80,C
|
||||||
|
197,0,3,"Mernagh, Mr. Robert",male,,0,0,368703,7.75,,Q
|
||||||
|
198,0,3,"Olsen, Mr. Karl Siegwart Andreas",male,42,0,1,4579,8.4042,,S
|
||||||
|
199,1,3,"Madigan, Miss. Margaret ""Maggie""",female,,0,0,370370,7.75,,Q
|
||||||
|
200,0,2,"Yrois, Miss. Henriette (""Mrs Harbeck"")",female,24,0,0,248747,13,,S
|
||||||
|
201,0,3,"Vande Walle, Mr. Nestor Cyriel",male,28,0,0,345770,9.5,,S
|
||||||
|
202,0,3,"Sage, Mr. Frederick",male,,8,2,CA. 2343,69.55,,S
|
||||||
|
203,0,3,"Johanson, Mr. Jakob Alfred",male,34,0,0,3101264,6.4958,,S
|
||||||
|
204,0,3,"Youseff, Mr. Gerious",male,45.5,0,0,2628,7.225,,C
|
||||||
|
205,1,3,"Cohen, Mr. Gurshon ""Gus""",male,18,0,0,A/5 3540,8.05,,S
|
||||||
|
206,0,3,"Strom, Miss. Telma Matilda",female,2,0,1,347054,10.4625,G6,S
|
||||||
|
207,0,3,"Backstrom, Mr. Karl Alfred",male,32,1,0,3101278,15.85,,S
|
||||||
|
208,1,3,"Albimona, Mr. Nassef Cassem",male,26,0,0,2699,18.7875,,C
|
||||||
|
209,1,3,"Carr, Miss. Helen ""Ellen""",female,16,0,0,367231,7.75,,Q
|
||||||
|
210,1,1,"Blank, Mr. Henry",male,40,0,0,112277,31,A31,C
|
||||||
|
211,0,3,"Ali, Mr. Ahmed",male,24,0,0,SOTON/O.Q. 3101311,7.05,,S
|
||||||
|
212,1,2,"Cameron, Miss. Clear Annie",female,35,0,0,F.C.C. 13528,21,,S
|
||||||
|
213,0,3,"Perkin, Mr. John Henry",male,22,0,0,A/5 21174,7.25,,S
|
||||||
|
214,0,2,"Givard, Mr. Hans Kristensen",male,30,0,0,250646,13,,S
|
||||||
|
215,0,3,"Kiernan, Mr. Philip",male,,1,0,367229,7.75,,Q
|
||||||
|
216,1,1,"Newell, Miss. Madeleine",female,31,1,0,35273,113.275,D36,C
|
||||||
|
217,1,3,"Honkanen, Miss. Eliina",female,27,0,0,STON/O2. 3101283,7.925,,S
|
||||||
|
218,0,2,"Jacobsohn, Mr. Sidney Samuel",male,42,1,0,243847,27,,S
|
||||||
|
219,1,1,"Bazzani, Miss. Albina",female,32,0,0,11813,76.2917,D15,C
|
||||||
|
220,0,2,"Harris, Mr. Walter",male,30,0,0,W/C 14208,10.5,,S
|
||||||
|
221,1,3,"Sunderland, Mr. Victor Francis",male,16,0,0,SOTON/OQ 392089,8.05,,S
|
||||||
|
222,0,2,"Bracken, Mr. James H",male,27,0,0,220367,13,,S
|
||||||
|
223,0,3,"Green, Mr. George Henry",male,51,0,0,21440,8.05,,S
|
||||||
|
224,0,3,"Nenkoff, Mr. Christo",male,,0,0,349234,7.8958,,S
|
||||||
|
225,1,1,"Hoyt, Mr. Frederick Maxfield",male,38,1,0,19943,90,C93,S
|
||||||
|
226,0,3,"Berglund, Mr. Karl Ivar Sven",male,22,0,0,PP 4348,9.35,,S
|
||||||
|
227,1,2,"Mellors, Mr. William John",male,19,0,0,SW/PP 751,10.5,,S
|
||||||
|
228,0,3,"Lovell, Mr. John Hall (""Henry"")",male,20.5,0,0,A/5 21173,7.25,,S
|
||||||
|
229,0,2,"Fahlstrom, Mr. Arne Jonas",male,18,0,0,236171,13,,S
|
||||||
|
230,0,3,"Lefebre, Miss. Mathilde",female,,3,1,4133,25.4667,,S
|
||||||
|
231,1,1,"Harris, Mrs. Henry Birkhardt (Irene Wallach)",female,35,1,0,36973,83.475,C83,S
|
||||||
|
232,0,3,"Larsson, Mr. Bengt Edvin",male,29,0,0,347067,7.775,,S
|
||||||
|
233,0,2,"Sjostedt, Mr. Ernst Adolf",male,59,0,0,237442,13.5,,S
|
||||||
|
234,1,3,"Asplund, Miss. Lillian Gertrud",female,5,4,2,347077,31.3875,,S
|
||||||
|
235,0,2,"Leyson, Mr. Robert William Norman",male,24,0,0,C.A. 29566,10.5,,S
|
||||||
|
236,0,3,"Harknett, Miss. Alice Phoebe",female,,0,0,W./C. 6609,7.55,,S
|
||||||
|
237,0,2,"Hold, Mr. Stephen",male,44,1,0,26707,26,,S
|
||||||
|
238,1,2,"Collyer, Miss. Marjorie ""Lottie""",female,8,0,2,C.A. 31921,26.25,,S
|
||||||
|
239,0,2,"Pengelly, Mr. Frederick William",male,19,0,0,28665,10.5,,S
|
||||||
|
240,0,2,"Hunt, Mr. George Henry",male,33,0,0,SCO/W 1585,12.275,,S
|
||||||
|
241,0,3,"Zabour, Miss. Thamine",female,,1,0,2665,14.4542,,C
|
||||||
|
242,1,3,"Murphy, Miss. Katherine ""Kate""",female,,1,0,367230,15.5,,Q
|
||||||
|
243,0,2,"Coleridge, Mr. Reginald Charles",male,29,0,0,W./C. 14263,10.5,,S
|
||||||
|
244,0,3,"Maenpaa, Mr. Matti Alexanteri",male,22,0,0,STON/O 2. 3101275,7.125,,S
|
||||||
|
245,0,3,"Attalah, Mr. Sleiman",male,30,0,0,2694,7.225,,C
|
||||||
|
246,0,1,"Minahan, Dr. William Edward",male,44,2,0,19928,90,C78,Q
|
||||||
|
247,0,3,"Lindahl, Miss. Agda Thorilda Viktoria",female,25,0,0,347071,7.775,,S
|
||||||
|
248,1,2,"Hamalainen, Mrs. William (Anna)",female,24,0,2,250649,14.5,,S
|
||||||
|
249,1,1,"Beckwith, Mr. Richard Leonard",male,37,1,1,11751,52.5542,D35,S
|
||||||
|
250,0,2,"Carter, Rev. Ernest Courtenay",male,54,1,0,244252,26,,S
|
||||||
|
251,0,3,"Reed, Mr. James George",male,,0,0,362316,7.25,,S
|
||||||
|
252,0,3,"Strom, Mrs. Wilhelm (Elna Matilda Persson)",female,29,1,1,347054,10.4625,G6,S
|
||||||
|
253,0,1,"Stead, Mr. William Thomas",male,62,0,0,113514,26.55,C87,S
|
||||||
|
254,0,3,"Lobb, Mr. William Arthur",male,30,1,0,A/5. 3336,16.1,,S
|
||||||
|
255,0,3,"Rosblom, Mrs. Viktor (Helena Wilhelmina)",female,41,0,2,370129,20.2125,,S
|
||||||
|
256,1,3,"Touma, Mrs. Darwis (Hanne Youssef Razi)",female,29,0,2,2650,15.2458,,C
|
||||||
|
257,1,1,"Thorne, Mrs. Gertrude Maybelle",female,,0,0,PC 17585,79.2,,C
|
||||||
|
258,1,1,"Cherry, Miss. Gladys",female,30,0,0,110152,86.5,B77,S
|
||||||
|
259,1,1,"Ward, Miss. Anna",female,35,0,0,PC 17755,512.3292,,C
|
||||||
|
260,1,2,"Parrish, Mrs. (Lutie Davis)",female,50,0,1,230433,26,,S
|
||||||
|
261,0,3,"Smith, Mr. Thomas",male,,0,0,384461,7.75,,Q
|
||||||
|
262,1,3,"Asplund, Master. Edvin Rojj Felix",male,3,4,2,347077,31.3875,,S
|
||||||
|
263,0,1,"Taussig, Mr. Emil",male,52,1,1,110413,79.65,E67,S
|
||||||
|
264,0,1,"Harrison, Mr. William",male,40,0,0,112059,0,B94,S
|
||||||
|
265,0,3,"Henry, Miss. Delia",female,,0,0,382649,7.75,,Q
|
||||||
|
266,0,2,"Reeves, Mr. David",male,36,0,0,C.A. 17248,10.5,,S
|
||||||
|
267,0,3,"Panula, Mr. Ernesti Arvid",male,16,4,1,3101295,39.6875,,S
|
||||||
|
268,1,3,"Persson, Mr. Ernst Ulrik",male,25,1,0,347083,7.775,,S
|
||||||
|
269,1,1,"Graham, Mrs. William Thompson (Edith Junkins)",female,58,0,1,PC 17582,153.4625,C125,S
|
||||||
|
270,1,1,"Bissette, Miss. Amelia",female,35,0,0,PC 17760,135.6333,C99,S
|
||||||
|
271,0,1,"Cairns, Mr. Alexander",male,,0,0,113798,31,,S
|
||||||
|
272,1,3,"Tornquist, Mr. William Henry",male,25,0,0,LINE,0,,S
|
||||||
|
273,1,2,"Mellinger, Mrs. (Elizabeth Anne Maidment)",female,41,0,1,250644,19.5,,S
|
||||||
|
274,0,1,"Natsch, Mr. Charles H",male,37,0,1,PC 17596,29.7,C118,C
|
||||||
|
275,1,3,"Healy, Miss. Hanora ""Nora""",female,,0,0,370375,7.75,,Q
|
||||||
|
276,1,1,"Andrews, Miss. Kornelia Theodosia",female,63,1,0,13502,77.9583,D7,S
|
||||||
|
277,0,3,"Lindblom, Miss. Augusta Charlotta",female,45,0,0,347073,7.75,,S
|
||||||
|
278,0,2,"Parkes, Mr. Francis ""Frank""",male,,0,0,239853,0,,S
|
||||||
|
279,0,3,"Rice, Master. Eric",male,7,4,1,382652,29.125,,Q
|
||||||
|
280,1,3,"Abbott, Mrs. Stanton (Rosa Hunt)",female,35,1,1,C.A. 2673,20.25,,S
|
||||||
|
281,0,3,"Duane, Mr. Frank",male,65,0,0,336439,7.75,,Q
|
||||||
|
282,0,3,"Olsson, Mr. Nils Johan Goransson",male,28,0,0,347464,7.8542,,S
|
||||||
|
283,0,3,"de Pelsmaeker, Mr. Alfons",male,16,0,0,345778,9.5,,S
|
||||||
|
284,1,3,"Dorking, Mr. Edward Arthur",male,19,0,0,A/5. 10482,8.05,,S
|
||||||
|
285,0,1,"Smith, Mr. Richard William",male,,0,0,113056,26,A19,S
|
||||||
|
286,0,3,"Stankovic, Mr. Ivan",male,33,0,0,349239,8.6625,,C
|
||||||
|
287,1,3,"de Mulder, Mr. Theodore",male,30,0,0,345774,9.5,,S
|
||||||
|
288,0,3,"Naidenoff, Mr. Penko",male,22,0,0,349206,7.8958,,S
|
||||||
|
289,1,2,"Hosono, Mr. Masabumi",male,42,0,0,237798,13,,S
|
||||||
|
290,1,3,"Connolly, Miss. Kate",female,22,0,0,370373,7.75,,Q
|
||||||
|
291,1,1,"Barber, Miss. Ellen ""Nellie""",female,26,0,0,19877,78.85,,S
|
||||||
|
292,1,1,"Bishop, Mrs. Dickinson H (Helen Walton)",female,19,1,0,11967,91.0792,B49,C
|
||||||
|
293,0,2,"Levy, Mr. Rene Jacques",male,36,0,0,SC/Paris 2163,12.875,D,C
|
||||||
|
294,0,3,"Haas, Miss. Aloisia",female,24,0,0,349236,8.85,,S
|
||||||
|
295,0,3,"Mineff, Mr. Ivan",male,24,0,0,349233,7.8958,,S
|
||||||
|
296,0,1,"Lewy, Mr. Ervin G",male,,0,0,PC 17612,27.7208,,C
|
||||||
|
297,0,3,"Hanna, Mr. Mansour",male,23.5,0,0,2693,7.2292,,C
|
||||||
|
298,0,1,"Allison, Miss. Helen Loraine",female,2,1,2,113781,151.55,C22 C26,S
|
||||||
|
299,1,1,"Saalfeld, Mr. Adolphe",male,,0,0,19988,30.5,C106,S
|
||||||
|
300,1,1,"Baxter, Mrs. James (Helene DeLaudeniere Chaput)",female,50,0,1,PC 17558,247.5208,B58 B60,C
|
||||||
|
301,1,3,"Kelly, Miss. Anna Katherine ""Annie Kate""",female,,0,0,9234,7.75,,Q
|
||||||
|
302,1,3,"McCoy, Mr. Bernard",male,,2,0,367226,23.25,,Q
|
||||||
|
303,0,3,"Johnson, Mr. William Cahoone Jr",male,19,0,0,LINE,0,,S
|
||||||
|
304,1,2,"Keane, Miss. Nora A",female,,0,0,226593,12.35,E101,Q
|
||||||
|
305,0,3,"Williams, Mr. Howard Hugh ""Harry""",male,,0,0,A/5 2466,8.05,,S
|
||||||
|
306,1,1,"Allison, Master. Hudson Trevor",male,0.92,1,2,113781,151.55,C22 C26,S
|
||||||
|
307,1,1,"Fleming, Miss. Margaret",female,,0,0,17421,110.8833,,C
|
||||||
|
308,1,1,"Penasco y Castellana, Mrs. Victor de Satode (Maria Josefa Perez de Soto y Vallejo)",female,17,1,0,PC 17758,108.9,C65,C
|
||||||
|
309,0,2,"Abelson, Mr. Samuel",male,30,1,0,P/PP 3381,24,,C
|
||||||
|
310,1,1,"Francatelli, Miss. Laura Mabel",female,30,0,0,PC 17485,56.9292,E36,C
|
||||||
|
311,1,1,"Hays, Miss. Margaret Bechstein",female,24,0,0,11767,83.1583,C54,C
|
||||||
|
312,1,1,"Ryerson, Miss. Emily Borie",female,18,2,2,PC 17608,262.375,B57 B59 B63 B66,C
|
||||||
|
313,0,2,"Lahtinen, Mrs. William (Anna Sylfven)",female,26,1,1,250651,26,,S
|
||||||
|
314,0,3,"Hendekovic, Mr. Ignjac",male,28,0,0,349243,7.8958,,S
|
||||||
|
315,0,2,"Hart, Mr. Benjamin",male,43,1,1,F.C.C. 13529,26.25,,S
|
||||||
|
316,1,3,"Nilsson, Miss. Helmina Josefina",female,26,0,0,347470,7.8542,,S
|
||||||
|
317,1,2,"Kantor, Mrs. Sinai (Miriam Sternin)",female,24,1,0,244367,26,,S
|
||||||
|
318,0,2,"Moraweck, Dr. Ernest",male,54,0,0,29011,14,,S
|
||||||
|
319,1,1,"Wick, Miss. Mary Natalie",female,31,0,2,36928,164.8667,C7,S
|
||||||
|
320,1,1,"Spedden, Mrs. Frederic Oakley (Margaretta Corning Stone)",female,40,1,1,16966,134.5,E34,C
|
||||||
|
321,0,3,"Dennis, Mr. Samuel",male,22,0,0,A/5 21172,7.25,,S
|
||||||
|
322,0,3,"Danoff, Mr. Yoto",male,27,0,0,349219,7.8958,,S
|
||||||
|
323,1,2,"Slayter, Miss. Hilda Mary",female,30,0,0,234818,12.35,,Q
|
||||||
|
324,1,2,"Caldwell, Mrs. Albert Francis (Sylvia Mae Harbaugh)",female,22,1,1,248738,29,,S
|
||||||
|
325,0,3,"Sage, Mr. George John Jr",male,,8,2,CA. 2343,69.55,,S
|
||||||
|
326,1,1,"Young, Miss. Marie Grice",female,36,0,0,PC 17760,135.6333,C32,C
|
||||||
|
327,0,3,"Nysveen, Mr. Johan Hansen",male,61,0,0,345364,6.2375,,S
|
||||||
|
328,1,2,"Ball, Mrs. (Ada E Hall)",female,36,0,0,28551,13,D,S
|
||||||
|
329,1,3,"Goldsmith, Mrs. Frank John (Emily Alice Brown)",female,31,1,1,363291,20.525,,S
|
||||||
|
330,1,1,"Hippach, Miss. Jean Gertrude",female,16,0,1,111361,57.9792,B18,C
|
||||||
|
331,1,3,"McCoy, Miss. Agnes",female,,2,0,367226,23.25,,Q
|
||||||
|
332,0,1,"Partner, Mr. Austen",male,45.5,0,0,113043,28.5,C124,S
|
||||||
|
333,0,1,"Graham, Mr. George Edward",male,38,0,1,PC 17582,153.4625,C91,S
|
||||||
|
334,0,3,"Vander Planke, Mr. Leo Edmondus",male,16,2,0,345764,18,,S
|
||||||
|
335,1,1,"Frauenthal, Mrs. Henry William (Clara Heinsheimer)",female,,1,0,PC 17611,133.65,,S
|
||||||
|
336,0,3,"Denkoff, Mr. Mitto",male,,0,0,349225,7.8958,,S
|
||||||
|
337,0,1,"Pears, Mr. Thomas Clinton",male,29,1,0,113776,66.6,C2,S
|
||||||
|
338,1,1,"Burns, Miss. Elizabeth Margaret",female,41,0,0,16966,134.5,E40,C
|
||||||
|
339,1,3,"Dahl, Mr. Karl Edwart",male,45,0,0,7598,8.05,,S
|
||||||
|
340,0,1,"Blackwell, Mr. Stephen Weart",male,45,0,0,113784,35.5,T,S
|
||||||
|
341,1,2,"Navratil, Master. Edmond Roger",male,2,1,1,230080,26,F2,S
|
||||||
|
342,1,1,"Fortune, Miss. Alice Elizabeth",female,24,3,2,19950,263,C23 C25 C27,S
|
||||||
|
343,0,2,"Collander, Mr. Erik Gustaf",male,28,0,0,248740,13,,S
|
||||||
|
344,0,2,"Sedgwick, Mr. Charles Frederick Waddington",male,25,0,0,244361,13,,S
|
||||||
|
345,0,2,"Fox, Mr. Stanley Hubert",male,36,0,0,229236,13,,S
|
||||||
|
346,1,2,"Brown, Miss. Amelia ""Mildred""",female,24,0,0,248733,13,F33,S
|
||||||
|
347,1,2,"Smith, Miss. Marion Elsie",female,40,0,0,31418,13,,S
|
||||||
|
348,1,3,"Davison, Mrs. Thomas Henry (Mary E Finck)",female,,1,0,386525,16.1,,S
|
||||||
|
349,1,3,"Coutts, Master. William Loch ""William""",male,3,1,1,C.A. 37671,15.9,,S
|
||||||
|
350,0,3,"Dimic, Mr. Jovan",male,42,0,0,315088,8.6625,,S
|
||||||
|
351,0,3,"Odahl, Mr. Nils Martin",male,23,0,0,7267,9.225,,S
|
||||||
|
352,0,1,"Williams-Lambert, Mr. Fletcher Fellows",male,,0,0,113510,35,C128,S
|
||||||
|
353,0,3,"Elias, Mr. Tannous",male,15,1,1,2695,7.2292,,C
|
||||||
|
354,0,3,"Arnold-Franchi, Mr. Josef",male,25,1,0,349237,17.8,,S
|
||||||
|
355,0,3,"Yousif, Mr. Wazli",male,,0,0,2647,7.225,,C
|
||||||
|
356,0,3,"Vanden Steen, Mr. Leo Peter",male,28,0,0,345783,9.5,,S
|
||||||
|
357,1,1,"Bowerman, Miss. Elsie Edith",female,22,0,1,113505,55,E33,S
|
||||||
|
358,0,2,"Funk, Miss. Annie Clemmer",female,38,0,0,237671,13,,S
|
||||||
|
359,1,3,"McGovern, Miss. Mary",female,,0,0,330931,7.8792,,Q
|
||||||
|
360,1,3,"Mockler, Miss. Helen Mary ""Ellie""",female,,0,0,330980,7.8792,,Q
|
||||||
|
361,0,3,"Skoog, Mr. Wilhelm",male,40,1,4,347088,27.9,,S
|
||||||
|
362,0,2,"del Carlo, Mr. Sebastiano",male,29,1,0,SC/PARIS 2167,27.7208,,C
|
||||||
|
363,0,3,"Barbara, Mrs. (Catherine David)",female,45,0,1,2691,14.4542,,C
|
||||||
|
364,0,3,"Asim, Mr. Adola",male,35,0,0,SOTON/O.Q. 3101310,7.05,,S
|
||||||
|
365,0,3,"O'Brien, Mr. Thomas",male,,1,0,370365,15.5,,Q
|
||||||
|
366,0,3,"Adahl, Mr. Mauritz Nils Martin",male,30,0,0,C 7076,7.25,,S
|
||||||
|
367,1,1,"Warren, Mrs. Frank Manley (Anna Sophia Atkinson)",female,60,1,0,110813,75.25,D37,C
|
||||||
|
368,1,3,"Moussa, Mrs. (Mantoura Boulos)",female,,0,0,2626,7.2292,,C
|
||||||
|
369,1,3,"Jermyn, Miss. Annie",female,,0,0,14313,7.75,,Q
|
||||||
|
370,1,1,"Aubart, Mme. Leontine Pauline",female,24,0,0,PC 17477,69.3,B35,C
|
||||||
|
371,1,1,"Harder, Mr. George Achilles",male,25,1,0,11765,55.4417,E50,C
|
||||||
|
372,0,3,"Wiklund, Mr. Jakob Alfred",male,18,1,0,3101267,6.4958,,S
|
||||||
|
373,0,3,"Beavan, Mr. William Thomas",male,19,0,0,323951,8.05,,S
|
||||||
|
374,0,1,"Ringhini, Mr. Sante",male,22,0,0,PC 17760,135.6333,,C
|
||||||
|
375,0,3,"Palsson, Miss. Stina Viola",female,3,3,1,349909,21.075,,S
|
||||||
|
376,1,1,"Meyer, Mrs. Edgar Joseph (Leila Saks)",female,,1,0,PC 17604,82.1708,,C
|
||||||
|
377,1,3,"Landergren, Miss. Aurora Adelia",female,22,0,0,C 7077,7.25,,S
|
||||||
|
378,0,1,"Widener, Mr. Harry Elkins",male,27,0,2,113503,211.5,C82,C
|
||||||
|
379,0,3,"Betros, Mr. Tannous",male,20,0,0,2648,4.0125,,C
|
||||||
|
380,0,3,"Gustafsson, Mr. Karl Gideon",male,19,0,0,347069,7.775,,S
|
||||||
|
381,1,1,"Bidois, Miss. Rosalie",female,42,0,0,PC 17757,227.525,,C
|
||||||
|
382,1,3,"Nakid, Miss. Maria (""Mary"")",female,1,0,2,2653,15.7417,,C
|
||||||
|
383,0,3,"Tikkanen, Mr. Juho",male,32,0,0,STON/O 2. 3101293,7.925,,S
|
||||||
|
384,1,1,"Holverson, Mrs. Alexander Oskar (Mary Aline Towner)",female,35,1,0,113789,52,,S
|
||||||
|
385,0,3,"Plotcharsky, Mr. Vasil",male,,0,0,349227,7.8958,,S
|
||||||
|
386,0,2,"Davies, Mr. Charles Henry",male,18,0,0,S.O.C. 14879,73.5,,S
|
||||||
|
387,0,3,"Goodwin, Master. Sidney Leonard",male,1,5,2,CA 2144,46.9,,S
|
||||||
|
388,1,2,"Buss, Miss. Kate",female,36,0,0,27849,13,,S
|
||||||
|
389,0,3,"Sadlier, Mr. Matthew",male,,0,0,367655,7.7292,,Q
|
||||||
|
390,1,2,"Lehmann, Miss. Bertha",female,17,0,0,SC 1748,12,,C
|
||||||
|
391,1,1,"Carter, Mr. William Ernest",male,36,1,2,113760,120,B96 B98,S
|
||||||
|
392,1,3,"Jansson, Mr. Carl Olof",male,21,0,0,350034,7.7958,,S
|
||||||
|
393,0,3,"Gustafsson, Mr. Johan Birger",male,28,2,0,3101277,7.925,,S
|
||||||
|
394,1,1,"Newell, Miss. Marjorie",female,23,1,0,35273,113.275,D36,C
|
||||||
|
395,1,3,"Sandstrom, Mrs. Hjalmar (Agnes Charlotta Bengtsson)",female,24,0,2,PP 9549,16.7,G6,S
|
||||||
|
396,0,3,"Johansson, Mr. Erik",male,22,0,0,350052,7.7958,,S
|
||||||
|
397,0,3,"Olsson, Miss. Elina",female,31,0,0,350407,7.8542,,S
|
||||||
|
398,0,2,"McKane, Mr. Peter David",male,46,0,0,28403,26,,S
|
||||||
|
399,0,2,"Pain, Dr. Alfred",male,23,0,0,244278,10.5,,S
|
||||||
|
400,1,2,"Trout, Mrs. William H (Jessie L)",female,28,0,0,240929,12.65,,S
|
||||||
|
401,1,3,"Niskanen, Mr. Juha",male,39,0,0,STON/O 2. 3101289,7.925,,S
|
||||||
|
402,0,3,"Adams, Mr. John",male,26,0,0,341826,8.05,,S
|
||||||
|
403,0,3,"Jussila, Miss. Mari Aina",female,21,1,0,4137,9.825,,S
|
||||||
|
404,0,3,"Hakkarainen, Mr. Pekka Pietari",male,28,1,0,STON/O2. 3101279,15.85,,S
|
||||||
|
405,0,3,"Oreskovic, Miss. Marija",female,20,0,0,315096,8.6625,,S
|
||||||
|
406,0,2,"Gale, Mr. Shadrach",male,34,1,0,28664,21,,S
|
||||||
|
407,0,3,"Widegren, Mr. Carl/Charles Peter",male,51,0,0,347064,7.75,,S
|
||||||
|
408,1,2,"Richards, Master. William Rowe",male,3,1,1,29106,18.75,,S
|
||||||
|
409,0,3,"Birkeland, Mr. Hans Martin Monsen",male,21,0,0,312992,7.775,,S
|
||||||
|
410,0,3,"Lefebre, Miss. Ida",female,,3,1,4133,25.4667,,S
|
||||||
|
411,0,3,"Sdycoff, Mr. Todor",male,,0,0,349222,7.8958,,S
|
||||||
|
412,0,3,"Hart, Mr. Henry",male,,0,0,394140,6.8583,,Q
|
||||||
|
413,1,1,"Minahan, Miss. Daisy E",female,33,1,0,19928,90,C78,Q
|
||||||
|
414,0,2,"Cunningham, Mr. Alfred Fleming",male,,0,0,239853,0,,S
|
||||||
|
415,1,3,"Sundman, Mr. Johan Julian",male,44,0,0,STON/O 2. 3101269,7.925,,S
|
||||||
|
416,0,3,"Meek, Mrs. Thomas (Annie Louise Rowley)",female,,0,0,343095,8.05,,S
|
||||||
|
417,1,2,"Drew, Mrs. James Vivian (Lulu Thorne Christian)",female,34,1,1,28220,32.5,,S
|
||||||
|
418,1,2,"Silven, Miss. Lyyli Karoliina",female,18,0,2,250652,13,,S
|
||||||
|
419,0,2,"Matthews, Mr. William John",male,30,0,0,28228,13,,S
|
||||||
|
420,0,3,"Van Impe, Miss. Catharina",female,10,0,2,345773,24.15,,S
|
||||||
|
421,0,3,"Gheorgheff, Mr. Stanio",male,,0,0,349254,7.8958,,C
|
||||||
|
422,0,3,"Charters, Mr. David",male,21,0,0,A/5. 13032,7.7333,,Q
|
||||||
|
423,0,3,"Zimmerman, Mr. Leo",male,29,0,0,315082,7.875,,S
|
||||||
|
424,0,3,"Danbom, Mrs. Ernst Gilbert (Anna Sigrid Maria Brogren)",female,28,1,1,347080,14.4,,S
|
||||||
|
425,0,3,"Rosblom, Mr. Viktor Richard",male,18,1,1,370129,20.2125,,S
|
||||||
|
426,0,3,"Wiseman, Mr. Phillippe",male,,0,0,A/4. 34244,7.25,,S
|
||||||
|
427,1,2,"Clarke, Mrs. Charles V (Ada Maria Winfield)",female,28,1,0,2003,26,,S
|
||||||
|
428,1,2,"Phillips, Miss. Kate Florence (""Mrs Kate Louise Phillips Marshall"")",female,19,0,0,250655,26,,S
|
||||||
|
429,0,3,"Flynn, Mr. James",male,,0,0,364851,7.75,,Q
|
||||||
|
430,1,3,"Pickard, Mr. Berk (Berk Trembisky)",male,32,0,0,SOTON/O.Q. 392078,8.05,E10,S
|
||||||
|
431,1,1,"Bjornstrom-Steffansson, Mr. Mauritz Hakan",male,28,0,0,110564,26.55,C52,S
|
||||||
|
432,1,3,"Thorneycroft, Mrs. Percival (Florence Kate White)",female,,1,0,376564,16.1,,S
|
||||||
|
433,1,2,"Louch, Mrs. Charles Alexander (Alice Adelaide Slow)",female,42,1,0,SC/AH 3085,26,,S
|
||||||
|
434,0,3,"Kallio, Mr. Nikolai Erland",male,17,0,0,STON/O 2. 3101274,7.125,,S
|
||||||
|
435,0,1,"Silvey, Mr. William Baird",male,50,1,0,13507,55.9,E44,S
|
||||||
|
436,1,1,"Carter, Miss. Lucile Polk",female,14,1,2,113760,120,B96 B98,S
|
||||||
|
437,0,3,"Ford, Miss. Doolina Margaret ""Daisy""",female,21,2,2,W./C. 6608,34.375,,S
|
||||||
|
438,1,2,"Richards, Mrs. Sidney (Emily Hocking)",female,24,2,3,29106,18.75,,S
|
||||||
|
439,0,1,"Fortune, Mr. Mark",male,64,1,4,19950,263,C23 C25 C27,S
|
||||||
|
440,0,2,"Kvillner, Mr. Johan Henrik Johannesson",male,31,0,0,C.A. 18723,10.5,,S
|
||||||
|
441,1,2,"Hart, Mrs. Benjamin (Esther Ada Bloomfield)",female,45,1,1,F.C.C. 13529,26.25,,S
|
||||||
|
442,0,3,"Hampe, Mr. Leon",male,20,0,0,345769,9.5,,S
|
||||||
|
443,0,3,"Petterson, Mr. Johan Emil",male,25,1,0,347076,7.775,,S
|
||||||
|
444,1,2,"Reynaldo, Ms. Encarnacion",female,28,0,0,230434,13,,S
|
||||||
|
445,1,3,"Johannesen-Bratthammer, Mr. Bernt",male,,0,0,65306,8.1125,,S
|
||||||
|
446,1,1,"Dodge, Master. Washington",male,4,0,2,33638,81.8583,A34,S
|
||||||
|
447,1,2,"Mellinger, Miss. Madeleine Violet",female,13,0,1,250644,19.5,,S
|
||||||
|
448,1,1,"Seward, Mr. Frederic Kimber",male,34,0,0,113794,26.55,,S
|
||||||
|
449,1,3,"Baclini, Miss. Marie Catherine",female,5,2,1,2666,19.2583,,C
|
||||||
|
450,1,1,"Peuchen, Major. Arthur Godfrey",male,52,0,0,113786,30.5,C104,S
|
||||||
|
451,0,2,"West, Mr. Edwy Arthur",male,36,1,2,C.A. 34651,27.75,,S
|
||||||
|
452,0,3,"Hagland, Mr. Ingvald Olai Olsen",male,,1,0,65303,19.9667,,S
|
||||||
|
453,0,1,"Foreman, Mr. Benjamin Laventall",male,30,0,0,113051,27.75,C111,C
|
||||||
|
454,1,1,"Goldenberg, Mr. Samuel L",male,49,1,0,17453,89.1042,C92,C
|
||||||
|
455,0,3,"Peduzzi, Mr. Joseph",male,,0,0,A/5 2817,8.05,,S
|
||||||
|
456,1,3,"Jalsevac, Mr. Ivan",male,29,0,0,349240,7.8958,,C
|
||||||
|
457,0,1,"Millet, Mr. Francis Davis",male,65,0,0,13509,26.55,E38,S
|
||||||
|
458,1,1,"Kenyon, Mrs. Frederick R (Marion)",female,,1,0,17464,51.8625,D21,S
|
||||||
|
459,1,2,"Toomey, Miss. Ellen",female,50,0,0,F.C.C. 13531,10.5,,S
|
||||||
|
460,0,3,"O'Connor, Mr. Maurice",male,,0,0,371060,7.75,,Q
|
||||||
|
461,1,1,"Anderson, Mr. Harry",male,48,0,0,19952,26.55,E12,S
|
||||||
|
462,0,3,"Morley, Mr. William",male,34,0,0,364506,8.05,,S
|
||||||
|
463,0,1,"Gee, Mr. Arthur H",male,47,0,0,111320,38.5,E63,S
|
||||||
|
464,0,2,"Milling, Mr. Jacob Christian",male,48,0,0,234360,13,,S
|
||||||
|
465,0,3,"Maisner, Mr. Simon",male,,0,0,A/S 2816,8.05,,S
|
||||||
|
466,0,3,"Goncalves, Mr. Manuel Estanslas",male,38,0,0,SOTON/O.Q. 3101306,7.05,,S
|
||||||
|
467,0,2,"Campbell, Mr. William",male,,0,0,239853,0,,S
|
||||||
|
468,0,1,"Smart, Mr. John Montgomery",male,56,0,0,113792,26.55,,S
|
||||||
|
469,0,3,"Scanlan, Mr. James",male,,0,0,36209,7.725,,Q
|
||||||
|
470,1,3,"Baclini, Miss. Helene Barbara",female,0.75,2,1,2666,19.2583,,C
|
||||||
|
471,0,3,"Keefe, Mr. Arthur",male,,0,0,323592,7.25,,S
|
||||||
|
472,0,3,"Cacic, Mr. Luka",male,38,0,0,315089,8.6625,,S
|
||||||
|
473,1,2,"West, Mrs. Edwy Arthur (Ada Mary Worth)",female,33,1,2,C.A. 34651,27.75,,S
|
||||||
|
474,1,2,"Jerwan, Mrs. Amin S (Marie Marthe Thuillard)",female,23,0,0,SC/AH Basle 541,13.7917,D,C
|
||||||
|
475,0,3,"Strandberg, Miss. Ida Sofia",female,22,0,0,7553,9.8375,,S
|
||||||
|
476,0,1,"Clifford, Mr. George Quincy",male,,0,0,110465,52,A14,S
|
||||||
|
477,0,2,"Renouf, Mr. Peter Henry",male,34,1,0,31027,21,,S
|
||||||
|
478,0,3,"Braund, Mr. Lewis Richard",male,29,1,0,3460,7.0458,,S
|
||||||
|
479,0,3,"Karlsson, Mr. Nils August",male,22,0,0,350060,7.5208,,S
|
||||||
|
480,1,3,"Hirvonen, Miss. Hildur E",female,2,0,1,3101298,12.2875,,S
|
||||||
|
481,0,3,"Goodwin, Master. Harold Victor",male,9,5,2,CA 2144,46.9,,S
|
||||||
|
482,0,2,"Frost, Mr. Anthony Wood ""Archie""",male,,0,0,239854,0,,S
|
||||||
|
483,0,3,"Rouse, Mr. Richard Henry",male,50,0,0,A/5 3594,8.05,,S
|
||||||
|
484,1,3,"Turkula, Mrs. (Hedwig)",female,63,0,0,4134,9.5875,,S
|
||||||
|
485,1,1,"Bishop, Mr. Dickinson H",male,25,1,0,11967,91.0792,B49,C
|
||||||
|
486,0,3,"Lefebre, Miss. Jeannie",female,,3,1,4133,25.4667,,S
|
||||||
|
487,1,1,"Hoyt, Mrs. Frederick Maxfield (Jane Anne Forby)",female,35,1,0,19943,90,C93,S
|
||||||
|
488,0,1,"Kent, Mr. Edward Austin",male,58,0,0,11771,29.7,B37,C
|
||||||
|
489,0,3,"Somerton, Mr. Francis William",male,30,0,0,A.5. 18509,8.05,,S
|
||||||
|
490,1,3,"Coutts, Master. Eden Leslie ""Neville""",male,9,1,1,C.A. 37671,15.9,,S
|
||||||
|
491,0,3,"Hagland, Mr. Konrad Mathias Reiersen",male,,1,0,65304,19.9667,,S
|
||||||
|
492,0,3,"Windelov, Mr. Einar",male,21,0,0,SOTON/OQ 3101317,7.25,,S
|
||||||
|
493,0,1,"Molson, Mr. Harry Markland",male,55,0,0,113787,30.5,C30,S
|
||||||
|
494,0,1,"Artagaveytia, Mr. Ramon",male,71,0,0,PC 17609,49.5042,,C
|
||||||
|
495,0,3,"Stanley, Mr. Edward Roland",male,21,0,0,A/4 45380,8.05,,S
|
||||||
|
496,0,3,"Yousseff, Mr. Gerious",male,,0,0,2627,14.4583,,C
|
||||||
|
497,1,1,"Eustis, Miss. Elizabeth Mussey",female,54,1,0,36947,78.2667,D20,C
|
||||||
|
498,0,3,"Shellard, Mr. Frederick William",male,,0,0,C.A. 6212,15.1,,S
|
||||||
|
499,0,1,"Allison, Mrs. Hudson J C (Bessie Waldo Daniels)",female,25,1,2,113781,151.55,C22 C26,S
|
||||||
|
500,0,3,"Svensson, Mr. Olof",male,24,0,0,350035,7.7958,,S
|
||||||
|
501,0,3,"Calic, Mr. Petar",male,17,0,0,315086,8.6625,,S
|
||||||
|
502,0,3,"Canavan, Miss. Mary",female,21,0,0,364846,7.75,,Q
|
||||||
|
503,0,3,"O'Sullivan, Miss. Bridget Mary",female,,0,0,330909,7.6292,,Q
|
||||||
|
504,0,3,"Laitinen, Miss. Kristina Sofia",female,37,0,0,4135,9.5875,,S
|
||||||
|
505,1,1,"Maioni, Miss. Roberta",female,16,0,0,110152,86.5,B79,S
|
||||||
|
506,0,1,"Penasco y Castellana, Mr. Victor de Satode",male,18,1,0,PC 17758,108.9,C65,C
|
||||||
|
507,1,2,"Quick, Mrs. Frederick Charles (Jane Richards)",female,33,0,2,26360,26,,S
|
||||||
|
508,1,1,"Bradley, Mr. George (""George Arthur Brayton"")",male,,0,0,111427,26.55,,S
|
||||||
|
509,0,3,"Olsen, Mr. Henry Margido",male,28,0,0,C 4001,22.525,,S
|
||||||
|
510,1,3,"Lang, Mr. Fang",male,26,0,0,1601,56.4958,,S
|
||||||
|
511,1,3,"Daly, Mr. Eugene Patrick",male,29,0,0,382651,7.75,,Q
|
||||||
|
512,0,3,"Webber, Mr. James",male,,0,0,SOTON/OQ 3101316,8.05,,S
|
||||||
|
513,1,1,"McGough, Mr. James Robert",male,36,0,0,PC 17473,26.2875,E25,S
|
||||||
|
514,1,1,"Rothschild, Mrs. Martin (Elizabeth L. Barrett)",female,54,1,0,PC 17603,59.4,,C
|
||||||
|
515,0,3,"Coleff, Mr. Satio",male,24,0,0,349209,7.4958,,S
|
||||||
|
516,0,1,"Walker, Mr. William Anderson",male,47,0,0,36967,34.0208,D46,S
|
||||||
|
517,1,2,"Lemore, Mrs. (Amelia Milley)",female,34,0,0,C.A. 34260,10.5,F33,S
|
||||||
|
518,0,3,"Ryan, Mr. Patrick",male,,0,0,371110,24.15,,Q
|
||||||
|
519,1,2,"Angle, Mrs. William A (Florence ""Mary"" Agnes Hughes)",female,36,1,0,226875,26,,S
|
||||||
|
520,0,3,"Pavlovic, Mr. Stefo",male,32,0,0,349242,7.8958,,S
|
||||||
|
521,1,1,"Perreault, Miss. Anne",female,30,0,0,12749,93.5,B73,S
|
||||||
|
522,0,3,"Vovk, Mr. Janko",male,22,0,0,349252,7.8958,,S
|
||||||
|
523,0,3,"Lahoud, Mr. Sarkis",male,,0,0,2624,7.225,,C
|
||||||
|
524,1,1,"Hippach, Mrs. Louis Albert (Ida Sophia Fischer)",female,44,0,1,111361,57.9792,B18,C
|
||||||
|
525,0,3,"Kassem, Mr. Fared",male,,0,0,2700,7.2292,,C
|
||||||
|
526,0,3,"Farrell, Mr. James",male,40.5,0,0,367232,7.75,,Q
|
||||||
|
527,1,2,"Ridsdale, Miss. Lucy",female,50,0,0,W./C. 14258,10.5,,S
|
||||||
|
528,0,1,"Farthing, Mr. John",male,,0,0,PC 17483,221.7792,C95,S
|
||||||
|
529,0,3,"Salonen, Mr. Johan Werner",male,39,0,0,3101296,7.925,,S
|
||||||
|
530,0,2,"Hocking, Mr. Richard George",male,23,2,1,29104,11.5,,S
|
||||||
|
531,1,2,"Quick, Miss. Phyllis May",female,2,1,1,26360,26,,S
|
||||||
|
532,0,3,"Toufik, Mr. Nakli",male,,0,0,2641,7.2292,,C
|
||||||
|
533,0,3,"Elias, Mr. Joseph Jr",male,17,1,1,2690,7.2292,,C
|
||||||
|
534,1,3,"Peter, Mrs. Catherine (Catherine Rizk)",female,,0,2,2668,22.3583,,C
|
||||||
|
535,0,3,"Cacic, Miss. Marija",female,30,0,0,315084,8.6625,,S
|
||||||
|
536,1,2,"Hart, Miss. Eva Miriam",female,7,0,2,F.C.C. 13529,26.25,,S
|
||||||
|
537,0,1,"Butt, Major. Archibald Willingham",male,45,0,0,113050,26.55,B38,S
|
||||||
|
538,1,1,"LeRoy, Miss. Bertha",female,30,0,0,PC 17761,106.425,,C
|
||||||
|
539,0,3,"Risien, Mr. Samuel Beard",male,,0,0,364498,14.5,,S
|
||||||
|
540,1,1,"Frolicher, Miss. Hedwig Margaritha",female,22,0,2,13568,49.5,B39,C
|
||||||
|
541,1,1,"Crosby, Miss. Harriet R",female,36,0,2,WE/P 5735,71,B22,S
|
||||||
|
542,0,3,"Andersson, Miss. Ingeborg Constanzia",female,9,4,2,347082,31.275,,S
|
||||||
|
543,0,3,"Andersson, Miss. Sigrid Elisabeth",female,11,4,2,347082,31.275,,S
|
||||||
|
544,1,2,"Beane, Mr. Edward",male,32,1,0,2908,26,,S
|
||||||
|
545,0,1,"Douglas, Mr. Walter Donald",male,50,1,0,PC 17761,106.425,C86,C
|
||||||
|
546,0,1,"Nicholson, Mr. Arthur Ernest",male,64,0,0,693,26,,S
|
||||||
|
547,1,2,"Beane, Mrs. Edward (Ethel Clarke)",female,19,1,0,2908,26,,S
|
||||||
|
548,1,2,"Padro y Manent, Mr. Julian",male,,0,0,SC/PARIS 2146,13.8625,,C
|
||||||
|
549,0,3,"Goldsmith, Mr. Frank John",male,33,1,1,363291,20.525,,S
|
||||||
|
550,1,2,"Davies, Master. John Morgan Jr",male,8,1,1,C.A. 33112,36.75,,S
|
||||||
|
551,1,1,"Thayer, Mr. John Borland Jr",male,17,0,2,17421,110.8833,C70,C
|
||||||
|
552,0,2,"Sharp, Mr. Percival James R",male,27,0,0,244358,26,,S
|
||||||
|
553,0,3,"O'Brien, Mr. Timothy",male,,0,0,330979,7.8292,,Q
|
||||||
|
554,1,3,"Leeni, Mr. Fahim (""Philip Zenni"")",male,22,0,0,2620,7.225,,C
|
||||||
|
555,1,3,"Ohman, Miss. Velin",female,22,0,0,347085,7.775,,S
|
||||||
|
556,0,1,"Wright, Mr. George",male,62,0,0,113807,26.55,,S
|
||||||
|
557,1,1,"Duff Gordon, Lady. (Lucille Christiana Sutherland) (""Mrs Morgan"")",female,48,1,0,11755,39.6,A16,C
|
||||||
|
558,0,1,"Robbins, Mr. Victor",male,,0,0,PC 17757,227.525,,C
|
||||||
|
559,1,1,"Taussig, Mrs. Emil (Tillie Mandelbaum)",female,39,1,1,110413,79.65,E67,S
|
||||||
|
560,1,3,"de Messemaeker, Mrs. Guillaume Joseph (Emma)",female,36,1,0,345572,17.4,,S
|
||||||
|
561,0,3,"Morrow, Mr. Thomas Rowan",male,,0,0,372622,7.75,,Q
|
||||||
|
562,0,3,"Sivic, Mr. Husein",male,40,0,0,349251,7.8958,,S
|
||||||
|
563,0,2,"Norman, Mr. Robert Douglas",male,28,0,0,218629,13.5,,S
|
||||||
|
564,0,3,"Simmons, Mr. John",male,,0,0,SOTON/OQ 392082,8.05,,S
|
||||||
|
565,0,3,"Meanwell, Miss. (Marion Ogden)",female,,0,0,SOTON/O.Q. 392087,8.05,,S
|
||||||
|
566,0,3,"Davies, Mr. Alfred J",male,24,2,0,A/4 48871,24.15,,S
|
||||||
|
567,0,3,"Stoytcheff, Mr. Ilia",male,19,0,0,349205,7.8958,,S
|
||||||
|
568,0,3,"Palsson, Mrs. Nils (Alma Cornelia Berglund)",female,29,0,4,349909,21.075,,S
|
||||||
|
569,0,3,"Doharr, Mr. Tannous",male,,0,0,2686,7.2292,,C
|
||||||
|
570,1,3,"Jonsson, Mr. Carl",male,32,0,0,350417,7.8542,,S
|
||||||
|
571,1,2,"Harris, Mr. George",male,62,0,0,S.W./PP 752,10.5,,S
|
||||||
|
572,1,1,"Appleton, Mrs. Edward Dale (Charlotte Lamson)",female,53,2,0,11769,51.4792,C101,S
|
||||||
|
573,1,1,"Flynn, Mr. John Irwin (""Irving"")",male,36,0,0,PC 17474,26.3875,E25,S
|
||||||
|
574,1,3,"Kelly, Miss. Mary",female,,0,0,14312,7.75,,Q
|
||||||
|
575,0,3,"Rush, Mr. Alfred George John",male,16,0,0,A/4. 20589,8.05,,S
|
||||||
|
576,0,3,"Patchett, Mr. George",male,19,0,0,358585,14.5,,S
|
||||||
|
577,1,2,"Garside, Miss. Ethel",female,34,0,0,243880,13,,S
|
||||||
|
578,1,1,"Silvey, Mrs. William Baird (Alice Munger)",female,39,1,0,13507,55.9,E44,S
|
||||||
|
579,0,3,"Caram, Mrs. Joseph (Maria Elias)",female,,1,0,2689,14.4583,,C
|
||||||
|
580,1,3,"Jussila, Mr. Eiriik",male,32,0,0,STON/O 2. 3101286,7.925,,S
|
||||||
|
581,1,2,"Christy, Miss. Julie Rachel",female,25,1,1,237789,30,,S
|
||||||
|
582,1,1,"Thayer, Mrs. John Borland (Marian Longstreth Morris)",female,39,1,1,17421,110.8833,C68,C
|
||||||
|
583,0,2,"Downton, Mr. William James",male,54,0,0,28403,26,,S
|
||||||
|
584,0,1,"Ross, Mr. John Hugo",male,36,0,0,13049,40.125,A10,C
|
||||||
|
585,0,3,"Paulner, Mr. Uscher",male,,0,0,3411,8.7125,,C
|
||||||
|
586,1,1,"Taussig, Miss. Ruth",female,18,0,2,110413,79.65,E68,S
|
||||||
|
587,0,2,"Jarvis, Mr. John Denzil",male,47,0,0,237565,15,,S
|
||||||
|
588,1,1,"Frolicher-Stehli, Mr. Maxmillian",male,60,1,1,13567,79.2,B41,C
|
||||||
|
589,0,3,"Gilinski, Mr. Eliezer",male,22,0,0,14973,8.05,,S
|
||||||
|
590,0,3,"Murdlin, Mr. Joseph",male,,0,0,A./5. 3235,8.05,,S
|
||||||
|
591,0,3,"Rintamaki, Mr. Matti",male,35,0,0,STON/O 2. 3101273,7.125,,S
|
||||||
|
592,1,1,"Stephenson, Mrs. Walter Bertram (Martha Eustis)",female,52,1,0,36947,78.2667,D20,C
|
||||||
|
593,0,3,"Elsbury, Mr. William James",male,47,0,0,A/5 3902,7.25,,S
|
||||||
|
594,0,3,"Bourke, Miss. Mary",female,,0,2,364848,7.75,,Q
|
||||||
|
595,0,2,"Chapman, Mr. John Henry",male,37,1,0,SC/AH 29037,26,,S
|
||||||
|
596,0,3,"Van Impe, Mr. Jean Baptiste",male,36,1,1,345773,24.15,,S
|
||||||
|
597,1,2,"Leitch, Miss. Jessie Wills",female,,0,0,248727,33,,S
|
||||||
|
598,0,3,"Johnson, Mr. Alfred",male,49,0,0,LINE,0,,S
|
||||||
|
599,0,3,"Boulos, Mr. Hanna",male,,0,0,2664,7.225,,C
|
||||||
|
600,1,1,"Duff Gordon, Sir. Cosmo Edmund (""Mr Morgan"")",male,49,1,0,PC 17485,56.9292,A20,C
|
||||||
|
601,1,2,"Jacobsohn, Mrs. Sidney Samuel (Amy Frances Christy)",female,24,2,1,243847,27,,S
|
||||||
|
602,0,3,"Slabenoff, Mr. Petco",male,,0,0,349214,7.8958,,S
|
||||||
|
603,0,1,"Harrington, Mr. Charles H",male,,0,0,113796,42.4,,S
|
||||||
|
604,0,3,"Torber, Mr. Ernst William",male,44,0,0,364511,8.05,,S
|
||||||
|
605,1,1,"Homer, Mr. Harry (""Mr E Haven"")",male,35,0,0,111426,26.55,,C
|
||||||
|
606,0,3,"Lindell, Mr. Edvard Bengtsson",male,36,1,0,349910,15.55,,S
|
||||||
|
607,0,3,"Karaic, Mr. Milan",male,30,0,0,349246,7.8958,,S
|
||||||
|
608,1,1,"Daniel, Mr. Robert Williams",male,27,0,0,113804,30.5,,S
|
||||||
|
609,1,2,"Laroche, Mrs. Joseph (Juliette Marie Louise Lafargue)",female,22,1,2,SC/Paris 2123,41.5792,,C
|
||||||
|
610,1,1,"Shutes, Miss. Elizabeth W",female,40,0,0,PC 17582,153.4625,C125,S
|
||||||
|
611,0,3,"Andersson, Mrs. Anders Johan (Alfrida Konstantia Brogren)",female,39,1,5,347082,31.275,,S
|
||||||
|
612,0,3,"Jardin, Mr. Jose Neto",male,,0,0,SOTON/O.Q. 3101305,7.05,,S
|
||||||
|
613,1,3,"Murphy, Miss. Margaret Jane",female,,1,0,367230,15.5,,Q
|
||||||
|
614,0,3,"Horgan, Mr. John",male,,0,0,370377,7.75,,Q
|
||||||
|
615,0,3,"Brocklebank, Mr. William Alfred",male,35,0,0,364512,8.05,,S
|
||||||
|
616,1,2,"Herman, Miss. Alice",female,24,1,2,220845,65,,S
|
||||||
|
617,0,3,"Danbom, Mr. Ernst Gilbert",male,34,1,1,347080,14.4,,S
|
||||||
|
618,0,3,"Lobb, Mrs. William Arthur (Cordelia K Stanlick)",female,26,1,0,A/5. 3336,16.1,,S
|
||||||
|
619,1,2,"Becker, Miss. Marion Louise",female,4,2,1,230136,39,F4,S
|
||||||
|
620,0,2,"Gavey, Mr. Lawrence",male,26,0,0,31028,10.5,,S
|
||||||
|
621,0,3,"Yasbeck, Mr. Antoni",male,27,1,0,2659,14.4542,,C
|
||||||
|
622,1,1,"Kimball, Mr. Edwin Nelson Jr",male,42,1,0,11753,52.5542,D19,S
|
||||||
|
623,1,3,"Nakid, Mr. Sahid",male,20,1,1,2653,15.7417,,C
|
||||||
|
624,0,3,"Hansen, Mr. Henry Damsgaard",male,21,0,0,350029,7.8542,,S
|
||||||
|
625,0,3,"Bowen, Mr. David John ""Dai""",male,21,0,0,54636,16.1,,S
|
||||||
|
626,0,1,"Sutton, Mr. Frederick",male,61,0,0,36963,32.3208,D50,S
|
||||||
|
627,0,2,"Kirkland, Rev. Charles Leonard",male,57,0,0,219533,12.35,,Q
|
||||||
|
628,1,1,"Longley, Miss. Gretchen Fiske",female,21,0,0,13502,77.9583,D9,S
|
||||||
|
629,0,3,"Bostandyeff, Mr. Guentcho",male,26,0,0,349224,7.8958,,S
|
||||||
|
630,0,3,"O'Connell, Mr. Patrick D",male,,0,0,334912,7.7333,,Q
|
||||||
|
631,1,1,"Barkworth, Mr. Algernon Henry Wilson",male,80,0,0,27042,30,A23,S
|
||||||
|
632,0,3,"Lundahl, Mr. Johan Svensson",male,51,0,0,347743,7.0542,,S
|
||||||
|
633,1,1,"Stahelin-Maeglin, Dr. Max",male,32,0,0,13214,30.5,B50,C
|
||||||
|
634,0,1,"Parr, Mr. William Henry Marsh",male,,0,0,112052,0,,S
|
||||||
|
635,0,3,"Skoog, Miss. Mabel",female,9,3,2,347088,27.9,,S
|
||||||
|
636,1,2,"Davis, Miss. Mary",female,28,0,0,237668,13,,S
|
||||||
|
637,0,3,"Leinonen, Mr. Antti Gustaf",male,32,0,0,STON/O 2. 3101292,7.925,,S
|
||||||
|
638,0,2,"Collyer, Mr. Harvey",male,31,1,1,C.A. 31921,26.25,,S
|
||||||
|
639,0,3,"Panula, Mrs. Juha (Maria Emilia Ojala)",female,41,0,5,3101295,39.6875,,S
|
||||||
|
640,0,3,"Thorneycroft, Mr. Percival",male,,1,0,376564,16.1,,S
|
||||||
|
641,0,3,"Jensen, Mr. Hans Peder",male,20,0,0,350050,7.8542,,S
|
||||||
|
642,1,1,"Sagesser, Mlle. Emma",female,24,0,0,PC 17477,69.3,B35,C
|
||||||
|
643,0,3,"Skoog, Miss. Margit Elizabeth",female,2,3,2,347088,27.9,,S
|
||||||
|
644,1,3,"Foo, Mr. Choong",male,,0,0,1601,56.4958,,S
|
||||||
|
645,1,3,"Baclini, Miss. Eugenie",female,0.75,2,1,2666,19.2583,,C
|
||||||
|
646,1,1,"Harper, Mr. Henry Sleeper",male,48,1,0,PC 17572,76.7292,D33,C
|
||||||
|
647,0,3,"Cor, Mr. Liudevit",male,19,0,0,349231,7.8958,,S
|
||||||
|
648,1,1,"Simonius-Blumer, Col. Oberst Alfons",male,56,0,0,13213,35.5,A26,C
|
||||||
|
649,0,3,"Willey, Mr. Edward",male,,0,0,S.O./P.P. 751,7.55,,S
|
||||||
|
650,1,3,"Stanley, Miss. Amy Zillah Elsie",female,23,0,0,CA. 2314,7.55,,S
|
||||||
|
651,0,3,"Mitkoff, Mr. Mito",male,,0,0,349221,7.8958,,S
|
||||||
|
652,1,2,"Doling, Miss. Elsie",female,18,0,1,231919,23,,S
|
||||||
|
653,0,3,"Kalvik, Mr. Johannes Halvorsen",male,21,0,0,8475,8.4333,,S
|
||||||
|
654,1,3,"O'Leary, Miss. Hanora ""Norah""",female,,0,0,330919,7.8292,,Q
|
||||||
|
655,0,3,"Hegarty, Miss. Hanora ""Nora""",female,18,0,0,365226,6.75,,Q
|
||||||
|
656,0,2,"Hickman, Mr. Leonard Mark",male,24,2,0,S.O.C. 14879,73.5,,S
|
||||||
|
657,0,3,"Radeff, Mr. Alexander",male,,0,0,349223,7.8958,,S
|
||||||
|
658,0,3,"Bourke, Mrs. John (Catherine)",female,32,1,1,364849,15.5,,Q
|
||||||
|
659,0,2,"Eitemiller, Mr. George Floyd",male,23,0,0,29751,13,,S
|
||||||
|
660,0,1,"Newell, Mr. Arthur Webster",male,58,0,2,35273,113.275,D48,C
|
||||||
|
661,1,1,"Frauenthal, Dr. Henry William",male,50,2,0,PC 17611,133.65,,S
|
||||||
|
662,0,3,"Badt, Mr. Mohamed",male,40,0,0,2623,7.225,,C
|
||||||
|
663,0,1,"Colley, Mr. Edward Pomeroy",male,47,0,0,5727,25.5875,E58,S
|
||||||
|
664,0,3,"Coleff, Mr. Peju",male,36,0,0,349210,7.4958,,S
|
||||||
|
665,1,3,"Lindqvist, Mr. Eino William",male,20,1,0,STON/O 2. 3101285,7.925,,S
|
||||||
|
666,0,2,"Hickman, Mr. Lewis",male,32,2,0,S.O.C. 14879,73.5,,S
|
||||||
|
667,0,2,"Butler, Mr. Reginald Fenton",male,25,0,0,234686,13,,S
|
||||||
|
668,0,3,"Rommetvedt, Mr. Knud Paust",male,,0,0,312993,7.775,,S
|
||||||
|
669,0,3,"Cook, Mr. Jacob",male,43,0,0,A/5 3536,8.05,,S
|
||||||
|
670,1,1,"Taylor, Mrs. Elmer Zebley (Juliet Cummins Wright)",female,,1,0,19996,52,C126,S
|
||||||
|
671,1,2,"Brown, Mrs. Thomas William Solomon (Elizabeth Catherine Ford)",female,40,1,1,29750,39,,S
|
||||||
|
672,0,1,"Davidson, Mr. Thornton",male,31,1,0,F.C. 12750,52,B71,S
|
||||||
|
673,0,2,"Mitchell, Mr. Henry Michael",male,70,0,0,C.A. 24580,10.5,,S
|
||||||
|
674,1,2,"Wilhelms, Mr. Charles",male,31,0,0,244270,13,,S
|
||||||
|
675,0,2,"Watson, Mr. Ennis Hastings",male,,0,0,239856,0,,S
|
||||||
|
676,0,3,"Edvardsson, Mr. Gustaf Hjalmar",male,18,0,0,349912,7.775,,S
|
||||||
|
677,0,3,"Sawyer, Mr. Frederick Charles",male,24.5,0,0,342826,8.05,,S
|
||||||
|
678,1,3,"Turja, Miss. Anna Sofia",female,18,0,0,4138,9.8417,,S
|
||||||
|
679,0,3,"Goodwin, Mrs. Frederick (Augusta Tyler)",female,43,1,6,CA 2144,46.9,,S
|
||||||
|
680,1,1,"Cardeza, Mr. Thomas Drake Martinez",male,36,0,1,PC 17755,512.3292,B51 B53 B55,C
|
||||||
|
681,0,3,"Peters, Miss. Katie",female,,0,0,330935,8.1375,,Q
|
||||||
|
682,1,1,"Hassab, Mr. Hammad",male,27,0,0,PC 17572,76.7292,D49,C
|
||||||
|
683,0,3,"Olsvigen, Mr. Thor Anderson",male,20,0,0,6563,9.225,,S
|
||||||
|
684,0,3,"Goodwin, Mr. Charles Edward",male,14,5,2,CA 2144,46.9,,S
|
||||||
|
685,0,2,"Brown, Mr. Thomas William Solomon",male,60,1,1,29750,39,,S
|
||||||
|
686,0,2,"Laroche, Mr. Joseph Philippe Lemercier",male,25,1,2,SC/Paris 2123,41.5792,,C
|
||||||
|
687,0,3,"Panula, Mr. Jaako Arnold",male,14,4,1,3101295,39.6875,,S
|
||||||
|
688,0,3,"Dakic, Mr. Branko",male,19,0,0,349228,10.1708,,S
|
||||||
|
689,0,3,"Fischer, Mr. Eberhard Thelander",male,18,0,0,350036,7.7958,,S
|
||||||
|
690,1,1,"Madill, Miss. Georgette Alexandra",female,15,0,1,24160,211.3375,B5,S
|
||||||
|
691,1,1,"Dick, Mr. Albert Adrian",male,31,1,0,17474,57,B20,S
|
||||||
|
692,1,3,"Karun, Miss. Manca",female,4,0,1,349256,13.4167,,C
|
||||||
|
693,1,3,"Lam, Mr. Ali",male,,0,0,1601,56.4958,,S
|
||||||
|
694,0,3,"Saad, Mr. Khalil",male,25,0,0,2672,7.225,,C
|
||||||
|
695,0,1,"Weir, Col. John",male,60,0,0,113800,26.55,,S
|
||||||
|
696,0,2,"Chapman, Mr. Charles Henry",male,52,0,0,248731,13.5,,S
|
||||||
|
697,0,3,"Kelly, Mr. James",male,44,0,0,363592,8.05,,S
|
||||||
|
698,1,3,"Mullens, Miss. Katherine ""Katie""",female,,0,0,35852,7.7333,,Q
|
||||||
|
699,0,1,"Thayer, Mr. John Borland",male,49,1,1,17421,110.8833,C68,C
|
||||||
|
700,0,3,"Humblen, Mr. Adolf Mathias Nicolai Olsen",male,42,0,0,348121,7.65,F G63,S
|
||||||
|
701,1,1,"Astor, Mrs. John Jacob (Madeleine Talmadge Force)",female,18,1,0,PC 17757,227.525,C62 C64,C
|
||||||
|
702,1,1,"Silverthorne, Mr. Spencer Victor",male,35,0,0,PC 17475,26.2875,E24,S
|
||||||
|
703,0,3,"Barbara, Miss. Saiide",female,18,0,1,2691,14.4542,,C
|
||||||
|
704,0,3,"Gallagher, Mr. Martin",male,25,0,0,36864,7.7417,,Q
|
||||||
|
705,0,3,"Hansen, Mr. Henrik Juul",male,26,1,0,350025,7.8542,,S
|
||||||
|
706,0,2,"Morley, Mr. Henry Samuel (""Mr Henry Marshall"")",male,39,0,0,250655,26,,S
|
||||||
|
707,1,2,"Kelly, Mrs. Florence ""Fannie""",female,45,0,0,223596,13.5,,S
|
||||||
|
708,1,1,"Calderhead, Mr. Edward Pennington",male,42,0,0,PC 17476,26.2875,E24,S
|
||||||
|
709,1,1,"Cleaver, Miss. Alice",female,22,0,0,113781,151.55,,S
|
||||||
|
710,1,3,"Moubarek, Master. Halim Gonios (""William George"")",male,,1,1,2661,15.2458,,C
|
||||||
|
711,1,1,"Mayne, Mlle. Berthe Antonine (""Mrs de Villiers"")",female,24,0,0,PC 17482,49.5042,C90,C
|
||||||
|
712,0,1,"Klaber, Mr. Herman",male,,0,0,113028,26.55,C124,S
|
||||||
|
713,1,1,"Taylor, Mr. Elmer Zebley",male,48,1,0,19996,52,C126,S
|
||||||
|
714,0,3,"Larsson, Mr. August Viktor",male,29,0,0,7545,9.4833,,S
|
||||||
|
715,0,2,"Greenberg, Mr. Samuel",male,52,0,0,250647,13,,S
|
||||||
|
716,0,3,"Soholt, Mr. Peter Andreas Lauritz Andersen",male,19,0,0,348124,7.65,F G73,S
|
||||||
|
717,1,1,"Endres, Miss. Caroline Louise",female,38,0,0,PC 17757,227.525,C45,C
|
||||||
|
718,1,2,"Troutt, Miss. Edwina Celia ""Winnie""",female,27,0,0,34218,10.5,E101,S
|
||||||
|
719,0,3,"McEvoy, Mr. Michael",male,,0,0,36568,15.5,,Q
|
||||||
|
720,0,3,"Johnson, Mr. Malkolm Joackim",male,33,0,0,347062,7.775,,S
|
||||||
|
721,1,2,"Harper, Miss. Annie Jessie ""Nina""",female,6,0,1,248727,33,,S
|
||||||
|
722,0,3,"Jensen, Mr. Svend Lauritz",male,17,1,0,350048,7.0542,,S
|
||||||
|
723,0,2,"Gillespie, Mr. William Henry",male,34,0,0,12233,13,,S
|
||||||
|
724,0,2,"Hodges, Mr. Henry Price",male,50,0,0,250643,13,,S
|
||||||
|
725,1,1,"Chambers, Mr. Norman Campbell",male,27,1,0,113806,53.1,E8,S
|
||||||
|
726,0,3,"Oreskovic, Mr. Luka",male,20,0,0,315094,8.6625,,S
|
||||||
|
727,1,2,"Renouf, Mrs. Peter Henry (Lillian Jefferys)",female,30,3,0,31027,21,,S
|
||||||
|
728,1,3,"Mannion, Miss. Margareth",female,,0,0,36866,7.7375,,Q
|
||||||
|
729,0,2,"Bryhl, Mr. Kurt Arnold Gottfrid",male,25,1,0,236853,26,,S
|
||||||
|
730,0,3,"Ilmakangas, Miss. Pieta Sofia",female,25,1,0,STON/O2. 3101271,7.925,,S
|
||||||
|
731,1,1,"Allen, Miss. Elisabeth Walton",female,29,0,0,24160,211.3375,B5,S
|
||||||
|
732,0,3,"Hassan, Mr. Houssein G N",male,11,0,0,2699,18.7875,,C
|
||||||
|
733,0,2,"Knight, Mr. Robert J",male,,0,0,239855,0,,S
|
||||||
|
734,0,2,"Berriman, Mr. William John",male,23,0,0,28425,13,,S
|
||||||
|
735,0,2,"Troupiansky, Mr. Moses Aaron",male,23,0,0,233639,13,,S
|
||||||
|
736,0,3,"Williams, Mr. Leslie",male,28.5,0,0,54636,16.1,,S
|
||||||
|
737,0,3,"Ford, Mrs. Edward (Margaret Ann Watson)",female,48,1,3,W./C. 6608,34.375,,S
|
||||||
|
738,1,1,"Lesurer, Mr. Gustave J",male,35,0,0,PC 17755,512.3292,B101,C
|
||||||
|
739,0,3,"Ivanoff, Mr. Kanio",male,,0,0,349201,7.8958,,S
|
||||||
|
740,0,3,"Nankoff, Mr. Minko",male,,0,0,349218,7.8958,,S
|
||||||
|
741,1,1,"Hawksford, Mr. Walter James",male,,0,0,16988,30,D45,S
|
||||||
|
742,0,1,"Cavendish, Mr. Tyrell William",male,36,1,0,19877,78.85,C46,S
|
||||||
|
743,1,1,"Ryerson, Miss. Susan Parker ""Suzette""",female,21,2,2,PC 17608,262.375,B57 B59 B63 B66,C
|
||||||
|
744,0,3,"McNamee, Mr. Neal",male,24,1,0,376566,16.1,,S
|
||||||
|
745,1,3,"Stranden, Mr. Juho",male,31,0,0,STON/O 2. 3101288,7.925,,S
|
||||||
|
746,0,1,"Crosby, Capt. Edward Gifford",male,70,1,1,WE/P 5735,71,B22,S
|
||||||
|
747,0,3,"Abbott, Mr. Rossmore Edward",male,16,1,1,C.A. 2673,20.25,,S
|
||||||
|
748,1,2,"Sinkkonen, Miss. Anna",female,30,0,0,250648,13,,S
|
||||||
|
749,0,1,"Marvin, Mr. Daniel Warner",male,19,1,0,113773,53.1,D30,S
|
||||||
|
750,0,3,"Connaghton, Mr. Michael",male,31,0,0,335097,7.75,,Q
|
||||||
|
751,1,2,"Wells, Miss. Joan",female,4,1,1,29103,23,,S
|
||||||
|
752,1,3,"Moor, Master. Meier",male,6,0,1,392096,12.475,E121,S
|
||||||
|
753,0,3,"Vande Velde, Mr. Johannes Joseph",male,33,0,0,345780,9.5,,S
|
||||||
|
754,0,3,"Jonkoff, Mr. Lalio",male,23,0,0,349204,7.8958,,S
|
||||||
|
755,1,2,"Herman, Mrs. Samuel (Jane Laver)",female,48,1,2,220845,65,,S
|
||||||
|
756,1,2,"Hamalainen, Master. Viljo",male,0.67,1,1,250649,14.5,,S
|
||||||
|
757,0,3,"Carlsson, Mr. August Sigfrid",male,28,0,0,350042,7.7958,,S
|
||||||
|
758,0,2,"Bailey, Mr. Percy Andrew",male,18,0,0,29108,11.5,,S
|
||||||
|
759,0,3,"Theobald, Mr. Thomas Leonard",male,34,0,0,363294,8.05,,S
|
||||||
|
760,1,1,"Rothes, the Countess. of (Lucy Noel Martha Dyer-Edwards)",female,33,0,0,110152,86.5,B77,S
|
||||||
|
761,0,3,"Garfirth, Mr. John",male,,0,0,358585,14.5,,S
|
||||||
|
762,0,3,"Nirva, Mr. Iisakki Antino Aijo",male,41,0,0,SOTON/O2 3101272,7.125,,S
|
||||||
|
763,1,3,"Barah, Mr. Hanna Assi",male,20,0,0,2663,7.2292,,C
|
||||||
|
764,1,1,"Carter, Mrs. William Ernest (Lucile Polk)",female,36,1,2,113760,120,B96 B98,S
|
||||||
|
765,0,3,"Eklund, Mr. Hans Linus",male,16,0,0,347074,7.775,,S
|
||||||
|
766,1,1,"Hogeboom, Mrs. John C (Anna Andrews)",female,51,1,0,13502,77.9583,D11,S
|
||||||
|
767,0,1,"Brewe, Dr. Arthur Jackson",male,,0,0,112379,39.6,,C
|
||||||
|
768,0,3,"Mangan, Miss. Mary",female,30.5,0,0,364850,7.75,,Q
|
||||||
|
769,0,3,"Moran, Mr. Daniel J",male,,1,0,371110,24.15,,Q
|
||||||
|
770,0,3,"Gronnestad, Mr. Daniel Danielsen",male,32,0,0,8471,8.3625,,S
|
||||||
|
771,0,3,"Lievens, Mr. Rene Aime",male,24,0,0,345781,9.5,,S
|
||||||
|
772,0,3,"Jensen, Mr. Niels Peder",male,48,0,0,350047,7.8542,,S
|
||||||
|
773,0,2,"Mack, Mrs. (Mary)",female,57,0,0,S.O./P.P. 3,10.5,E77,S
|
||||||
|
774,0,3,"Elias, Mr. Dibo",male,,0,0,2674,7.225,,C
|
||||||
|
775,1,2,"Hocking, Mrs. Elizabeth (Eliza Needs)",female,54,1,3,29105,23,,S
|
||||||
|
776,0,3,"Myhrman, Mr. Pehr Fabian Oliver Malkolm",male,18,0,0,347078,7.75,,S
|
||||||
|
777,0,3,"Tobin, Mr. Roger",male,,0,0,383121,7.75,F38,Q
|
||||||
|
778,1,3,"Emanuel, Miss. Virginia Ethel",female,5,0,0,364516,12.475,,S
|
||||||
|
779,0,3,"Kilgannon, Mr. Thomas J",male,,0,0,36865,7.7375,,Q
|
||||||
|
780,1,1,"Robert, Mrs. Edward Scott (Elisabeth Walton McMillan)",female,43,0,1,24160,211.3375,B3,S
|
||||||
|
781,1,3,"Ayoub, Miss. Banoura",female,13,0,0,2687,7.2292,,C
|
||||||
|
782,1,1,"Dick, Mrs. Albert Adrian (Vera Gillespie)",female,17,1,0,17474,57,B20,S
|
||||||
|
783,0,1,"Long, Mr. Milton Clyde",male,29,0,0,113501,30,D6,S
|
||||||
|
784,0,3,"Johnston, Mr. Andrew G",male,,1,2,W./C. 6607,23.45,,S
|
||||||
|
785,0,3,"Ali, Mr. William",male,25,0,0,SOTON/O.Q. 3101312,7.05,,S
|
||||||
|
786,0,3,"Harmer, Mr. Abraham (David Lishin)",male,25,0,0,374887,7.25,,S
|
||||||
|
787,1,3,"Sjoblom, Miss. Anna Sofia",female,18,0,0,3101265,7.4958,,S
|
||||||
|
788,0,3,"Rice, Master. George Hugh",male,8,4,1,382652,29.125,,Q
|
||||||
|
789,1,3,"Dean, Master. Bertram Vere",male,1,1,2,C.A. 2315,20.575,,S
|
||||||
|
790,0,1,"Guggenheim, Mr. Benjamin",male,46,0,0,PC 17593,79.2,B82 B84,C
|
||||||
|
791,0,3,"Keane, Mr. Andrew ""Andy""",male,,0,0,12460,7.75,,Q
|
||||||
|
792,0,2,"Gaskell, Mr. Alfred",male,16,0,0,239865,26,,S
|
||||||
|
793,0,3,"Sage, Miss. Stella Anna",female,,8,2,CA. 2343,69.55,,S
|
||||||
|
794,0,1,"Hoyt, Mr. William Fisher",male,,0,0,PC 17600,30.6958,,C
|
||||||
|
795,0,3,"Dantcheff, Mr. Ristiu",male,25,0,0,349203,7.8958,,S
|
||||||
|
796,0,2,"Otter, Mr. Richard",male,39,0,0,28213,13,,S
|
||||||
|
797,1,1,"Leader, Dr. Alice (Farnham)",female,49,0,0,17465,25.9292,D17,S
|
||||||
|
798,1,3,"Osman, Mrs. Mara",female,31,0,0,349244,8.6833,,S
|
||||||
|
799,0,3,"Ibrahim Shawah, Mr. Yousseff",male,30,0,0,2685,7.2292,,C
|
||||||
|
800,0,3,"Van Impe, Mrs. Jean Baptiste (Rosalie Paula Govaert)",female,30,1,1,345773,24.15,,S
|
||||||
|
801,0,2,"Ponesell, Mr. Martin",male,34,0,0,250647,13,,S
|
||||||
|
802,1,2,"Collyer, Mrs. Harvey (Charlotte Annie Tate)",female,31,1,1,C.A. 31921,26.25,,S
|
||||||
|
803,1,1,"Carter, Master. William Thornton II",male,11,1,2,113760,120,B96 B98,S
|
||||||
|
804,1,3,"Thomas, Master. Assad Alexander",male,0.42,0,1,2625,8.5167,,C
|
||||||
|
805,1,3,"Hedman, Mr. Oskar Arvid",male,27,0,0,347089,6.975,,S
|
||||||
|
806,0,3,"Johansson, Mr. Karl Johan",male,31,0,0,347063,7.775,,S
|
||||||
|
807,0,1,"Andrews, Mr. Thomas Jr",male,39,0,0,112050,0,A36,S
|
||||||
|
808,0,3,"Pettersson, Miss. Ellen Natalia",female,18,0,0,347087,7.775,,S
|
||||||
|
809,0,2,"Meyer, Mr. August",male,39,0,0,248723,13,,S
|
||||||
|
810,1,1,"Chambers, Mrs. Norman Campbell (Bertha Griggs)",female,33,1,0,113806,53.1,E8,S
|
||||||
|
811,0,3,"Alexander, Mr. William",male,26,0,0,3474,7.8875,,S
|
||||||
|
812,0,3,"Lester, Mr. James",male,39,0,0,A/4 48871,24.15,,S
|
||||||
|
813,0,2,"Slemen, Mr. Richard James",male,35,0,0,28206,10.5,,S
|
||||||
|
814,0,3,"Andersson, Miss. Ebba Iris Alfrida",female,6,4,2,347082,31.275,,S
|
||||||
|
815,0,3,"Tomlin, Mr. Ernest Portage",male,30.5,0,0,364499,8.05,,S
|
||||||
|
816,0,1,"Fry, Mr. Richard",male,,0,0,112058,0,B102,S
|
||||||
|
817,0,3,"Heininen, Miss. Wendla Maria",female,23,0,0,STON/O2. 3101290,7.925,,S
|
||||||
|
818,0,2,"Mallet, Mr. Albert",male,31,1,1,S.C./PARIS 2079,37.0042,,C
|
||||||
|
819,0,3,"Holm, Mr. John Fredrik Alexander",male,43,0,0,C 7075,6.45,,S
|
||||||
|
820,0,3,"Skoog, Master. Karl Thorsten",male,10,3,2,347088,27.9,,S
|
||||||
|
821,1,1,"Hays, Mrs. Charles Melville (Clara Jennings Gregg)",female,52,1,1,12749,93.5,B69,S
|
||||||
|
822,1,3,"Lulic, Mr. Nikola",male,27,0,0,315098,8.6625,,S
|
||||||
|
823,0,1,"Reuchlin, Jonkheer. John George",male,38,0,0,19972,0,,S
|
||||||
|
824,1,3,"Moor, Mrs. (Beila)",female,27,0,1,392096,12.475,E121,S
|
||||||
|
825,0,3,"Panula, Master. Urho Abraham",male,2,4,1,3101295,39.6875,,S
|
||||||
|
826,0,3,"Flynn, Mr. John",male,,0,0,368323,6.95,,Q
|
||||||
|
827,0,3,"Lam, Mr. Len",male,,0,0,1601,56.4958,,S
|
||||||
|
828,1,2,"Mallet, Master. Andre",male,1,0,2,S.C./PARIS 2079,37.0042,,C
|
||||||
|
829,1,3,"McCormack, Mr. Thomas Joseph",male,,0,0,367228,7.75,,Q
|
||||||
|
830,1,1,"Stone, Mrs. George Nelson (Martha Evelyn)",female,62,0,0,113572,80,B28,
|
||||||
|
831,1,3,"Yasbeck, Mrs. Antoni (Selini Alexander)",female,15,1,0,2659,14.4542,,C
|
||||||
|
832,1,2,"Richards, Master. George Sibley",male,0.83,1,1,29106,18.75,,S
|
||||||
|
833,0,3,"Saad, Mr. Amin",male,,0,0,2671,7.2292,,C
|
||||||
|
834,0,3,"Augustsson, Mr. Albert",male,23,0,0,347468,7.8542,,S
|
||||||
|
835,0,3,"Allum, Mr. Owen George",male,18,0,0,2223,8.3,,S
|
||||||
|
836,1,1,"Compton, Miss. Sara Rebecca",female,39,1,1,PC 17756,83.1583,E49,C
|
||||||
|
837,0,3,"Pasic, Mr. Jakob",male,21,0,0,315097,8.6625,,S
|
||||||
|
838,0,3,"Sirota, Mr. Maurice",male,,0,0,392092,8.05,,S
|
||||||
|
839,1,3,"Chip, Mr. Chang",male,32,0,0,1601,56.4958,,S
|
||||||
|
840,1,1,"Marechal, Mr. Pierre",male,,0,0,11774,29.7,C47,C
|
||||||
|
841,0,3,"Alhomaki, Mr. Ilmari Rudolf",male,20,0,0,SOTON/O2 3101287,7.925,,S
|
||||||
|
842,0,2,"Mudd, Mr. Thomas Charles",male,16,0,0,S.O./P.P. 3,10.5,,S
|
||||||
|
843,1,1,"Serepeca, Miss. Augusta",female,30,0,0,113798,31,,C
|
||||||
|
844,0,3,"Lemberopolous, Mr. Peter L",male,34.5,0,0,2683,6.4375,,C
|
||||||
|
845,0,3,"Culumovic, Mr. Jeso",male,17,0,0,315090,8.6625,,S
|
||||||
|
846,0,3,"Abbing, Mr. Anthony",male,42,0,0,C.A. 5547,7.55,,S
|
||||||
|
847,0,3,"Sage, Mr. Douglas Bullen",male,,8,2,CA. 2343,69.55,,S
|
||||||
|
848,0,3,"Markoff, Mr. Marin",male,35,0,0,349213,7.8958,,C
|
||||||
|
849,0,2,"Harper, Rev. John",male,28,0,1,248727,33,,S
|
||||||
|
850,1,1,"Goldenberg, Mrs. Samuel L (Edwiga Grabowska)",female,,1,0,17453,89.1042,C92,C
|
||||||
|
851,0,3,"Andersson, Master. Sigvard Harald Elias",male,4,4,2,347082,31.275,,S
|
||||||
|
852,0,3,"Svensson, Mr. Johan",male,74,0,0,347060,7.775,,S
|
||||||
|
853,0,3,"Boulos, Miss. Nourelain",female,9,1,1,2678,15.2458,,C
|
||||||
|
854,1,1,"Lines, Miss. Mary Conover",female,16,0,1,PC 17592,39.4,D28,S
|
||||||
|
855,0,2,"Carter, Mrs. Ernest Courtenay (Lilian Hughes)",female,44,1,0,244252,26,,S
|
||||||
|
856,1,3,"Aks, Mrs. Sam (Leah Rosen)",female,18,0,1,392091,9.35,,S
|
||||||
|
857,1,1,"Wick, Mrs. George Dennick (Mary Hitchcock)",female,45,1,1,36928,164.8667,,S
|
||||||
|
858,1,1,"Daly, Mr. Peter Denis ",male,51,0,0,113055,26.55,E17,S
|
||||||
|
859,1,3,"Baclini, Mrs. Solomon (Latifa Qurban)",female,24,0,3,2666,19.2583,,C
|
||||||
|
860,0,3,"Razi, Mr. Raihed",male,,0,0,2629,7.2292,,C
|
||||||
|
861,0,3,"Hansen, Mr. Claus Peter",male,41,2,0,350026,14.1083,,S
|
||||||
|
862,0,2,"Giles, Mr. Frederick Edward",male,21,1,0,28134,11.5,,S
|
||||||
|
863,1,1,"Swift, Mrs. Frederick Joel (Margaret Welles Barron)",female,48,0,0,17466,25.9292,D17,S
|
||||||
|
864,0,3,"Sage, Miss. Dorothy Edith ""Dolly""",female,,8,2,CA. 2343,69.55,,S
|
||||||
|
865,0,2,"Gill, Mr. John William",male,24,0,0,233866,13,,S
|
||||||
|
866,1,2,"Bystrom, Mrs. (Karolina)",female,42,0,0,236852,13,,S
|
||||||
|
867,1,2,"Duran y More, Miss. Asuncion",female,27,1,0,SC/PARIS 2149,13.8583,,C
|
||||||
|
868,0,1,"Roebling, Mr. Washington Augustus II",male,31,0,0,PC 17590,50.4958,A24,S
|
||||||
|
869,0,3,"van Melkebeke, Mr. Philemon",male,,0,0,345777,9.5,,S
|
||||||
|
870,1,3,"Johnson, Master. Harold Theodor",male,4,1,1,347742,11.1333,,S
|
||||||
|
871,0,3,"Balkic, Mr. Cerin",male,26,0,0,349248,7.8958,,S
|
||||||
|
872,1,1,"Beckwith, Mrs. Richard Leonard (Sallie Monypeny)",female,47,1,1,11751,52.5542,D35,S
|
||||||
|
873,0,1,"Carlsson, Mr. Frans Olof",male,33,0,0,695,5,B51 B53 B55,S
|
||||||
|
874,0,3,"Vander Cruyssen, Mr. Victor",male,47,0,0,345765,9,,S
|
||||||
|
875,1,2,"Abelson, Mrs. Samuel (Hannah Wizosky)",female,28,1,0,P/PP 3381,24,,C
|
||||||
|
876,1,3,"Najib, Miss. Adele Kiamie ""Jane""",female,15,0,0,2667,7.225,,C
|
||||||
|
877,0,3,"Gustafsson, Mr. Alfred Ossian",male,20,0,0,7534,9.8458,,S
|
||||||
|
878,0,3,"Petroff, Mr. Nedelio",male,19,0,0,349212,7.8958,,S
|
||||||
|
879,0,3,"Laleff, Mr. Kristo",male,,0,0,349217,7.8958,,S
|
||||||
|
880,1,1,"Potter, Mrs. Thomas Jr (Lily Alexenia Wilson)",female,56,0,1,11767,83.1583,C50,C
|
||||||
|
881,1,2,"Shelley, Mrs. William (Imanita Parrish Hall)",female,25,0,1,230433,26,,S
|
||||||
|
882,0,3,"Markun, Mr. Johann",male,33,0,0,349257,7.8958,,S
|
||||||
|
883,0,3,"Dahlberg, Miss. Gerda Ulrika",female,22,0,0,7552,10.5167,,S
|
||||||
|
884,0,2,"Banfield, Mr. Frederick James",male,28,0,0,C.A./SOTON 34068,10.5,,S
|
||||||
|
885,0,3,"Sutehall, Mr. Henry Jr",male,25,0,0,SOTON/OQ 392076,7.05,,S
|
||||||
|
886,0,3,"Rice, Mrs. William (Margaret Norton)",female,39,0,5,382652,29.125,,Q
|
||||||
|
887,0,2,"Montvila, Rev. Juozas",male,27,0,0,211536,13,,S
|
||||||
|
888,1,1,"Graham, Miss. Margaret Edith",female,19,0,0,112053,30,B42,S
|
||||||
|
889,0,3,"Johnston, Miss. Catherine Helen ""Carrie""",female,,1,2,W./C. 6607,23.45,,S
|
||||||
|
890,1,1,"Behr, Mr. Karl Howell",male,26,0,0,111369,30,C148,C
|
||||||
|
891,0,3,"Dooley, Mr. Patrick",male,32,0,0,370376,7.75,,Q
|
|
@ -0,0 +1,417 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "18ada398-dce6-4049-9b56-fc0ede63da9c",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# Vectorstore Agent\n",
|
||||||
|
"\n",
|
||||||
|
"This notebook showcases an agent designed to retrieve information from one or more vectorstores, either with or without sources."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "eecb683b-3a46-4b9d-81a3-7caefbfec1a1",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Create the Vectorstores"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 1,
|
||||||
|
"id": "9bfd0ed8-a5eb-443e-8e92-90be8cabb0a7",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
|
||||||
|
"from langchain.vectorstores import Chroma\n",
|
||||||
|
"from langchain.text_splitter import CharacterTextSplitter\n",
|
||||||
|
"from langchain import OpenAI, VectorDBQA\n",
|
||||||
|
"llm = OpenAI(temperature=0)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 2,
|
||||||
|
"id": "345bb078-4ec1-4e3a-827b-cd238c49054d",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"Running Chroma using direct local API.\n",
|
||||||
|
"Using DuckDB in-memory for database. Data will be transient.\n"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"from langchain.document_loaders import TextLoader\n",
|
||||||
|
"loader = TextLoader('../../state_of_the_union.txt')\n",
|
||||||
|
"documents = loader.load()\n",
|
||||||
|
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
|
||||||
|
"texts = text_splitter.split_documents(documents)\n",
|
||||||
|
"\n",
|
||||||
|
"embeddings = OpenAIEmbeddings()\n",
|
||||||
|
"state_of_union_store = Chroma.from_documents(texts, embeddings, collection_name=\"state-of-union\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 3,
|
||||||
|
"id": "5f50eb82-e1a5-4252-8306-8ec1b478d9b4",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"Running Chroma using direct local API.\n",
|
||||||
|
"Using DuckDB in-memory for database. Data will be transient.\n"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"from langchain.document_loaders import WebBaseLoader\n",
|
||||||
|
"loader = WebBaseLoader(\"https://beta.ruff.rs/docs/faq/\")\n",
|
||||||
|
"docs = loader.load()\n",
|
||||||
|
"ruff_texts = text_splitter.split_documents(docs)\n",
|
||||||
|
"ruff_store = Chroma.from_documents(ruff_texts, embeddings, collection_name=\"ruff\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "f4814175-964d-42f1-aa9d-22801ce1e912",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Initialize Toolkit and Agent\n",
|
||||||
|
"\n",
|
||||||
|
"First, we'll create an agent with a single vectorstore."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 4,
|
||||||
|
"id": "5b3b3206",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.agents.agent_toolkits import (\n",
|
||||||
|
" create_vectorstore_agent,\n",
|
||||||
|
" VectorStoreToolkit,\n",
|
||||||
|
" VectorStoreInfo,\n",
|
||||||
|
")\n",
|
||||||
|
"vectorstore_info = VectorStoreInfo(\n",
|
||||||
|
" name=\"state_of_union_address\",\n",
|
||||||
|
" description=\"the most recent state of the Union adress\",\n",
|
||||||
|
" vectorstore=state_of_union_store\n",
|
||||||
|
")\n",
|
||||||
|
"toolkit = VectorStoreToolkit(vectorstore_info=vectorstore_info)\n",
|
||||||
|
"agent_executor = create_vectorstore_agent(\n",
|
||||||
|
" llm=llm,\n",
|
||||||
|
" toolkit=toolkit,\n",
|
||||||
|
" verbose=True\n",
|
||||||
|
")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "8a38ad10",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Examples"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 5,
|
||||||
|
"id": "3f2f455c",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3m I need to find the answer in the state of the union address\n",
|
||||||
|
"Action: state_of_union_address\n",
|
||||||
|
"Action Input: What did biden say about ketanji brown jackson\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||||
|
"Final Answer: Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"\"Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\""
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 5,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"agent_executor.run(\"What did biden say about ketanji brown jackson is the state of the union address?\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 6,
|
||||||
|
"id": "d61e1e63",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3m I need to use the state_of_union_address_with_sources tool to answer this question.\n",
|
||||||
|
"Action: state_of_union_address_with_sources\n",
|
||||||
|
"Action Input: What did biden say about ketanji brown jackson\u001b[0m\n",
|
||||||
|
"Observation: \u001b[33;1m\u001b[1;3m{\"answer\": \" Biden said that he nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to the United States Supreme Court, and that she is one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\\n\", \"sources\": \"../../state_of_the_union.txt\"}\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||||
|
"Final Answer: Biden said that he nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to the United States Supreme Court, and that she is one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence. Sources: ../../state_of_the_union.txt\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"\"Biden said that he nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to the United States Supreme Court, and that she is one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence. Sources: ../../state_of_the_union.txt\""
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 6,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"agent_executor.run(\"What did biden say about ketanji brown jackson is the state of the union address? List the source.\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "7ca07707",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Multiple Vectorstores\n",
|
||||||
|
"We can also easily use this initialize an agent with multiple vectorstores and use the agent to route between them. To do this. This agent is optimized for routing, so it is a different toolkit and initializer."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 7,
|
||||||
|
"id": "c3209fd3",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.agents.agent_toolkits import (\n",
|
||||||
|
" create_vectorstore_router_agent,\n",
|
||||||
|
" VectorStoreRouterToolkit,\n",
|
||||||
|
" VectorStoreInfo,\n",
|
||||||
|
")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 8,
|
||||||
|
"id": "815c4f39-308d-4949-b992-1361036e6e09",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"ruff_vectorstore_info = VectorStoreInfo(\n",
|
||||||
|
" name=\"ruff\",\n",
|
||||||
|
" description=\"Information about the Ruff python linting library\",\n",
|
||||||
|
" vectorstore=ruff_store\n",
|
||||||
|
")\n",
|
||||||
|
"router_toolkit = VectorStoreRouterToolkit(\n",
|
||||||
|
" vectorstores=[vectorstore_info, ruff_vectorstore_info],\n",
|
||||||
|
" llm=llm\n",
|
||||||
|
")\n",
|
||||||
|
"agent_executor = create_vectorstore_agent(\n",
|
||||||
|
" llm=llm,\n",
|
||||||
|
" toolkit=router_toolkit,\n",
|
||||||
|
" verbose=True\n",
|
||||||
|
")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "71680984-edaf-4a63-90f5-94edbd263550",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Examples"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 9,
|
||||||
|
"id": "3cd1bf3e-e3df-4e69-bbe1-71c64b1af947",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3m I need to use the state_of_union_address tool to answer this question.\n",
|
||||||
|
"Action: state_of_union_address\n",
|
||||||
|
"Action Input: What did biden say about ketanji brown jackson\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||||
|
"Final Answer: Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"\"Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\""
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 9,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"agent_executor.run(\"What did biden say about ketanji brown jackson is the state of the union address?\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 10,
|
||||||
|
"id": "c5998b8d",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3m I need to find out what tool ruff uses to run over Jupyter Notebooks\n",
|
||||||
|
"Action: ruff\n",
|
||||||
|
"Action Input: What tool does ruff use to run over Jupyter Notebooks?\u001b[0m\n",
|
||||||
|
"Observation: \u001b[33;1m\u001b[1;3m Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.ipynb\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||||
|
"Final Answer: Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.ipynb\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"'Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.ipynb'"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 10,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"agent_executor.run(\"What tool does ruff use to run over Jupyter Notebooks?\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 11,
|
||||||
|
"id": "744e9b51-fbd9-4778-b594-ea957d0f3467",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3m I need to find out what tool ruff uses and if the president mentioned it in the state of the union.\n",
|
||||||
|
"Action: ruff\n",
|
||||||
|
"Action Input: What tool does ruff use to run over Jupyter Notebooks?\u001b[0m\n",
|
||||||
|
"Observation: \u001b[33;1m\u001b[1;3m Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.ipynb\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I need to find out if the president mentioned nbQA in the state of the union.\n",
|
||||||
|
"Action: state_of_union_address\n",
|
||||||
|
"Action Input: Did the president mention nbQA in the state of the union?\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m No, the president did not mention nbQA in the state of the union.\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
|
||||||
|
"Final Answer: No, the president did not mention nbQA in the state of the union.\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"'No, the president did not mention nbQA in the state of the union.'"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 11,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"agent_executor.run(\"What tool does ruff use to run over Jupyter Notebooks? Did the president mention that tool in the state of the union?\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "92203aa9-f63a-4ce1-b562-fadf4474ad9d",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": []
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "Python 3 (ipykernel)",
|
||||||
|
"language": "python",
|
||||||
|
"name": "python3"
|
||||||
|
},
|
||||||
|
"language_info": {
|
||||||
|
"codemirror_mode": {
|
||||||
|
"name": "ipython",
|
||||||
|
"version": 3
|
||||||
|
},
|
||||||
|
"file_extension": ".py",
|
||||||
|
"mimetype": "text/x-python",
|
||||||
|
"name": "python",
|
||||||
|
"nbconvert_exporter": "python",
|
||||||
|
"pygments_lexer": "ipython3",
|
||||||
|
"version": "3.10.9"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 5
|
||||||
|
}
|
@ -0,0 +1,309 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "4658d71a",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# Conversation Agent (for Chat Models)\n",
|
||||||
|
"\n",
|
||||||
|
"This notebook walks through using an agent optimized for conversation, using ChatModels. Other agents are often optimized for using tools to figure out the best response, which is not ideal in a conversational setting where you may want the agent to be able to chat with the user as well.\n",
|
||||||
|
"\n",
|
||||||
|
"This is accomplished with a specific type of agent (`chat-conversational-react-description`) which expects to be used with a memory component."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 1,
|
||||||
|
"id": "f4f5d1a8",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"import os\n",
|
||||||
|
"os.environ[\"LANGCHAIN_HANDLER\"] = \"langchain\""
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 2,
|
||||||
|
"id": "f65308ab",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.agents import Tool\n",
|
||||||
|
"from langchain.memory import ConversationBufferMemory\n",
|
||||||
|
"from langchain.chat_models import ChatOpenAI\n",
|
||||||
|
"from langchain.utilities import SerpAPIWrapper\n",
|
||||||
|
"from langchain.agents import initialize_agent"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 3,
|
||||||
|
"id": "5fb14d6d",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"search = SerpAPIWrapper()\n",
|
||||||
|
"tools = [\n",
|
||||||
|
" Tool(\n",
|
||||||
|
" name = \"Current Search\",\n",
|
||||||
|
" func=search.run,\n",
|
||||||
|
" description=\"useful for when you need to answer questions about current events or the current state of the world. the input to this should be a single search term.\"\n",
|
||||||
|
" ),\n",
|
||||||
|
"]"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 4,
|
||||||
|
"id": "dddc34c4",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"memory = ConversationBufferMemory(memory_key=\"chat_history\", return_messages=True)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 5,
|
||||||
|
"id": "cafe9bc1",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"llm=ChatOpenAI(temperature=0)\n",
|
||||||
|
"agent_chain = initialize_agent(tools, llm, agent=\"chat-conversational-react-description\", verbose=True, memory=memory)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 6,
|
||||||
|
"id": "dc70b454",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3m{\n",
|
||||||
|
" \"action\": \"Final Answer\",\n",
|
||||||
|
" \"action_input\": \"Hello Bob! How can I assist you today?\"\n",
|
||||||
|
"}\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"'Hello Bob! How can I assist you today?'"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 6,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"agent_chain.run(input=\"hi, i am bob\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 7,
|
||||||
|
"id": "3dcf7953",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3m{\n",
|
||||||
|
" \"action\": \"Final Answer\",\n",
|
||||||
|
" \"action_input\": \"Your name is Bob.\"\n",
|
||||||
|
"}\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"'Your name is Bob.'"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 7,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"agent_chain.run(input=\"what's my name?\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 8,
|
||||||
|
"id": "aa05f566",
|
||||||
|
"metadata": {
|
||||||
|
"scrolled": false
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3m{\n",
|
||||||
|
" \"action\": \"Current Search\",\n",
|
||||||
|
" \"action_input\": \"Thai food dinner recipes\"\n",
|
||||||
|
"}\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m59 easy Thai recipes for any night of the week · Marion Grasby's Thai spicy chilli and basil fried rice · Thai curry noodle soup · Marion Grasby's ...\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m{\n",
|
||||||
|
" \"action\": \"Final Answer\",\n",
|
||||||
|
" \"action_input\": \"Here are some Thai food dinner recipes you can make this week: Thai spicy chilli and basil fried rice, Thai curry noodle soup, and many more. You can find 59 easy Thai recipes for any night of the week on Marion Grasby's website.\"\n",
|
||||||
|
"}\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"\"Here are some Thai food dinner recipes you can make this week: Thai spicy chilli and basil fried rice, Thai curry noodle soup, and many more. You can find 59 easy Thai recipes for any night of the week on Marion Grasby's website.\""
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 8,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"agent_chain.run(\"what are some good dinners to make this week, if i like thai food?\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 9,
|
||||||
|
"id": "c5d8b7ea",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3m```json\n",
|
||||||
|
"{\n",
|
||||||
|
" \"action\": \"Current Search\",\n",
|
||||||
|
" \"action_input\": \"who won the world cup in 1978\"\n",
|
||||||
|
"}\n",
|
||||||
|
"```\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3mThe Argentina national football team represents Argentina in men's international football and is administered by the Argentine Football Association, the governing body for football in Argentina. Nicknamed La Albiceleste, they are the reigning world champions, having won the most recent World Cup in 2022.\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m```json\n",
|
||||||
|
"{\n",
|
||||||
|
" \"action\": \"Final Answer\",\n",
|
||||||
|
" \"action_input\": \"The last letter in your name is 'b'. The Argentina national football team won the World Cup in 1978.\"\n",
|
||||||
|
"}\n",
|
||||||
|
"```\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"\"The last letter in your name is 'b'. The Argentina national football team won the World Cup in 1978.\""
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 9,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"agent_chain.run(input=\"tell me the last letter in my name, and also tell me who won the world cup in 1978?\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 10,
|
||||||
|
"id": "f608889b",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3m{\n",
|
||||||
|
" \"action\": \"Current Search\",\n",
|
||||||
|
" \"action_input\": \"weather in pomfret\"\n",
|
||||||
|
"}\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3mMostly cloudy with gusty winds developing during the afternoon. A few flurries or snow showers possible. High near 40F. Winds NNW at 20 to 30 mph.\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3m{\n",
|
||||||
|
" \"action\": \"Final Answer\",\n",
|
||||||
|
" \"action_input\": \"The weather in Pomfret is mostly cloudy with gusty winds developing during the afternoon. A few flurries or snow showers are possible. High near 40F. Winds NNW at 20 to 30 mph.\"\n",
|
||||||
|
"}\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"'The weather in Pomfret is mostly cloudy with gusty winds developing during the afternoon. A few flurries or snow showers are possible. High near 40F. Winds NNW at 20 to 30 mph.'"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 10,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"agent_chain.run(input=\"whats the weather like in pomfret?\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "0084efd6",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": []
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "Python 3 (ipykernel)",
|
||||||
|
"language": "python",
|
||||||
|
"name": "python3"
|
||||||
|
},
|
||||||
|
"language_info": {
|
||||||
|
"codemirror_mode": {
|
||||||
|
"name": "ipython",
|
||||||
|
"version": 3
|
||||||
|
},
|
||||||
|
"file_extension": ".py",
|
||||||
|
"mimetype": "text/x-python",
|
||||||
|
"name": "python",
|
||||||
|
"nbconvert_exporter": "python",
|
||||||
|
"pygments_lexer": "ipython3",
|
||||||
|
"version": "3.9.1"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 5
|
||||||
|
}
|
@ -0,0 +1,119 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "3f34700b",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# ChatGPT Plugins\n",
|
||||||
|
"\n",
|
||||||
|
"This example shows how to use ChatGPT Plugins within LangChain abstractions.\n",
|
||||||
|
"\n",
|
||||||
|
"Note 1: This currently only works for plugins with no auth.\n",
|
||||||
|
"\n",
|
||||||
|
"Note 2: There are almost certainly other ways to do this, this is just a first pass. If you have better ideas, please open a PR!"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 2,
|
||||||
|
"id": "d41405b5",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.chat_models import ChatOpenAI\n",
|
||||||
|
"from langchain.agents import load_tools, initialize_agent\n",
|
||||||
|
"from langchain.tools import AIPluginTool"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 4,
|
||||||
|
"id": "d9e61df5",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"tool = AIPluginTool.from_plugin_url(\"https://www.klarna.com/.well-known/ai-plugin.json\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 5,
|
||||||
|
"id": "edc0ea0e",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3mI need to check the Klarna Shopping API to see if it has information on available t shirts.\n",
|
||||||
|
"Action: KlarnaProducts\n",
|
||||||
|
"Action Input: None\u001b[0m\n",
|
||||||
|
"Observation: \u001b[33;1m\u001b[1;3mUsage Guide: Use the Klarna plugin to get relevant product suggestions for any shopping or researching purpose. The query to be sent should not include stopwords like articles, prepositions and determinants. The api works best when searching for words that are related to products, like their name, brand, model or category. Links will always be returned and should be shown to the user.\n",
|
||||||
|
"\n",
|
||||||
|
"OpenAPI Spec: {'openapi': '3.0.1', 'info': {'version': 'v0', 'title': 'Open AI Klarna product Api'}, 'servers': [{'url': 'https://www.klarna.com/us/shopping'}], 'tags': [{'name': 'open-ai-product-endpoint', 'description': 'Open AI Product Endpoint. Query for products.'}], 'paths': {'/public/openai/v0/products': {'get': {'tags': ['open-ai-product-endpoint'], 'summary': 'API for fetching Klarna product information', 'operationId': 'productsUsingGET', 'parameters': [{'name': 'q', 'in': 'query', 'description': 'query, must be between 2 and 100 characters', 'required': True, 'schema': {'type': 'string'}}, {'name': 'size', 'in': 'query', 'description': 'number of products returned', 'required': False, 'schema': {'type': 'integer'}}, {'name': 'budget', 'in': 'query', 'description': 'maximum price of the matching product in local currency, filters results', 'required': False, 'schema': {'type': 'integer'}}], 'responses': {'200': {'description': 'Products found', 'content': {'application/json': {'schema': {'$ref': '#/components/schemas/ProductResponse'}}}}, '503': {'description': 'one or more services are unavailable'}}, 'deprecated': False}}}, 'components': {'schemas': {'Product': {'type': 'object', 'properties': {'attributes': {'type': 'array', 'items': {'type': 'string'}}, 'name': {'type': 'string'}, 'price': {'type': 'string'}, 'url': {'type': 'string'}}, 'title': 'Product'}, 'ProductResponse': {'type': 'object', 'properties': {'products': {'type': 'array', 'items': {'$ref': '#/components/schemas/Product'}}}, 'title': 'ProductResponse'}}}}\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3mI need to use the Klarna Shopping API to search for t shirts.\n",
|
||||||
|
"Action: requests_get\n",
|
||||||
|
"Action Input: https://www.klarna.com/us/shopping/public/openai/v0/products?q=t%20shirts\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3m{\"products\":[{\"name\":\"Lacoste Men's Pack of Plain T-Shirts\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3202043025/Clothing/Lacoste-Men-s-Pack-of-Plain-T-Shirts/?source=openai\",\"price\":\"$28.99\",\"attributes\":[\"Material:Cotton\",\"Target Group:Man\",\"Color:White,Black\"]},{\"name\":\"Hanes Men's Ultimate 6pk. Crewneck T-Shirts\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3201808270/Clothing/Hanes-Men-s-Ultimate-6pk.-Crewneck-T-Shirts/?source=openai\",\"price\":\"$13.40\",\"attributes\":[\"Material:Cotton\",\"Target Group:Man\",\"Color:White\"]},{\"name\":\"Nike Boy's Jordan Stretch T-shirts\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl359/3201863202/Children-s-Clothing/Nike-Boy-s-Jordan-Stretch-T-shirts/?source=openai\",\"price\":\"$14.99\",\"attributes\":[\"Color:White,Green\",\"Model:Boy\",\"Pattern:Solid Color\",\"Size (Small-Large):S,XL,L,M\"]},{\"name\":\"Polo Classic Fit Cotton V-Neck T-Shirts 3-Pack\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3203028500/Clothing/Polo-Classic-Fit-Cotton-V-Neck-T-Shirts-3-Pack/?source=openai\",\"price\":\"$29.95\",\"attributes\":[\"Material:Cotton\",\"Target Group:Man\",\"Color:White,Blue,Black\"]},{\"name\":\"adidas Comfort T-shirts Men's 3-pack\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3202640533/Clothing/adidas-Comfort-T-shirts-Men-s-3-pack/?source=openai\",\"price\":\"$14.99\",\"attributes\":[\"Material:Cotton\",\"Target Group:Man\",\"Color:White,Black\",\"Pattern:Solid Color\"]}]}\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3mThe available t shirts on Klarna are Lacoste Men's Pack of Plain T-Shirts, Hanes Men's Ultimate 6pk. Crewneck T-Shirts, Nike Boy's Jordan Stretch T-shirts, Polo Classic Fit Cotton V-Neck T-Shirts 3-Pack, and adidas Comfort T-shirts Men's 3-pack.\n",
|
||||||
|
"Final Answer: The available t shirts on Klarna are Lacoste Men's Pack of Plain T-Shirts, Hanes Men's Ultimate 6pk. Crewneck T-Shirts, Nike Boy's Jordan Stretch T-shirts, Polo Classic Fit Cotton V-Neck T-Shirts 3-Pack, and adidas Comfort T-shirts Men's 3-pack.\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"\"The available t shirts on Klarna are Lacoste Men's Pack of Plain T-Shirts, Hanes Men's Ultimate 6pk. Crewneck T-Shirts, Nike Boy's Jordan Stretch T-shirts, Polo Classic Fit Cotton V-Neck T-Shirts 3-Pack, and adidas Comfort T-shirts Men's 3-pack.\""
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 5,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"llm = ChatOpenAI(temperature=0)\n",
|
||||||
|
"tools = load_tools([\"requests\"] )\n",
|
||||||
|
"tools += [tool]\n",
|
||||||
|
"\n",
|
||||||
|
"agent_chain = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)\n",
|
||||||
|
"\n",
|
||||||
|
"agent_chain.run(\"what t shirts are available in klarna?\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "e49318a4",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": []
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "Python 3 (ipykernel)",
|
||||||
|
"language": "python",
|
||||||
|
"name": "python3"
|
||||||
|
},
|
||||||
|
"language_info": {
|
||||||
|
"codemirror_mode": {
|
||||||
|
"name": "ipython",
|
||||||
|
"version": 3
|
||||||
|
},
|
||||||
|
"file_extension": ".py",
|
||||||
|
"mimetype": "text/x-python",
|
||||||
|
"name": "python",
|
||||||
|
"nbconvert_exporter": "python",
|
||||||
|
"pygments_lexer": "ipython3",
|
||||||
|
"version": "3.9.1"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 5
|
||||||
|
}
|
@ -0,0 +1,132 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# Human as a tool\n",
|
||||||
|
"\n",
|
||||||
|
"Human are AGI so they can certainly be used as a tool to help out AI agent \n",
|
||||||
|
"when it is confused."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 1,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"import sys\n",
|
||||||
|
"from langchain.chat_models import ChatOpenAI\n",
|
||||||
|
"from langchain.llms import OpenAI\n",
|
||||||
|
"from langchain.agents import load_tools, initialize_agent\n",
|
||||||
|
"\n",
|
||||||
|
"llm = ChatOpenAI(temperature=0.0)\n",
|
||||||
|
"math_llm = OpenAI(temperature=0.0)\n",
|
||||||
|
"tools = load_tools(\n",
|
||||||
|
" [\"human\", \"llm-math\"], \n",
|
||||||
|
" llm=math_llm,\n",
|
||||||
|
")\n",
|
||||||
|
"\n",
|
||||||
|
"agent_chain = initialize_agent(\n",
|
||||||
|
" tools,\n",
|
||||||
|
" llm,\n",
|
||||||
|
" agent=\"zero-shot-react-description\",\n",
|
||||||
|
" verbose=True,\n",
|
||||||
|
")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"In the above code you can see the tool takes input directly from command line.\n",
|
||||||
|
"You can customize `prompt_func` and `input_func` according to your need."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 3,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3mI don't know Eric Zhu, so I should ask a human for guidance.\n",
|
||||||
|
"Action: Human\n",
|
||||||
|
"Action Input: \"Do you know when Eric Zhu's birthday is?\"\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"Do you know when Eric Zhu's birthday is?\n",
|
||||||
|
"last week\n",
|
||||||
|
"\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3mlast week\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3mThat's not very helpful. I should ask for more information.\n",
|
||||||
|
"Action: Human\n",
|
||||||
|
"Action Input: \"Do you know the specific date of Eric Zhu's birthday?\"\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"Do you know the specific date of Eric Zhu's birthday?\n",
|
||||||
|
"august 1st\n",
|
||||||
|
"\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3maugust 1st\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3mNow that I have the date, I can check if it's a leap year or not.\n",
|
||||||
|
"Action: Calculator\n",
|
||||||
|
"Action Input: \"Is 2021 a leap year?\"\u001b[0m\n",
|
||||||
|
"Observation: \u001b[33;1m\u001b[1;3mAnswer: False\n",
|
||||||
|
"\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3mI have all the information I need to answer the original question.\n",
|
||||||
|
"Final Answer: Eric Zhu's birthday is on August 1st and it is not a leap year in 2021.\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"\"Eric Zhu's birthday is on August 1st and it is not a leap year in 2021.\""
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 3,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"\n",
|
||||||
|
"agent_chain.run(\"What is Eric Zhu's birthday?\")\n",
|
||||||
|
"# Answer with \"last week\""
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": []
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "Python 3 (ipykernel)",
|
||||||
|
"language": "python",
|
||||||
|
"name": "python3"
|
||||||
|
},
|
||||||
|
"language_info": {
|
||||||
|
"codemirror_mode": {
|
||||||
|
"name": "ipython",
|
||||||
|
"version": 3
|
||||||
|
},
|
||||||
|
"file_extension": ".py",
|
||||||
|
"mimetype": "text/x-python",
|
||||||
|
"name": "python",
|
||||||
|
"nbconvert_exporter": "python",
|
||||||
|
"pygments_lexer": "ipython3",
|
||||||
|
"version": "3.9.1"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 2
|
||||||
|
}
|
@ -0,0 +1,253 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "f1390152",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# MRKL Chat\n",
|
||||||
|
"\n",
|
||||||
|
"This notebook showcases using an agent to replicate the MRKL chain using an agent optimized for chat models."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "39ea3638",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"This uses the example Chinook database.\n",
|
||||||
|
"To set it up follow the instructions on https://database.guide/2-sample-databases-sqlite/, placing the `.db` file in a notebooks folder at the root of this repository."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 1,
|
||||||
|
"id": "ac561cc4",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain import OpenAI, LLMMathChain, SerpAPIWrapper, SQLDatabase, SQLDatabaseChain\n",
|
||||||
|
"from langchain.agents import initialize_agent, Tool\n",
|
||||||
|
"from langchain.chat_models import ChatOpenAI"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 2,
|
||||||
|
"id": "07e96d99",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"llm = ChatOpenAI(temperature=0)\n",
|
||||||
|
"llm1 = OpenAI(temperature=0)\n",
|
||||||
|
"search = SerpAPIWrapper()\n",
|
||||||
|
"llm_math_chain = LLMMathChain(llm=llm1, verbose=True)\n",
|
||||||
|
"db = SQLDatabase.from_uri(\"sqlite:///../../../../notebooks/Chinook.db\")\n",
|
||||||
|
"db_chain = SQLDatabaseChain(llm=llm1, database=db, verbose=True)\n",
|
||||||
|
"tools = [\n",
|
||||||
|
" Tool(\n",
|
||||||
|
" name = \"Search\",\n",
|
||||||
|
" func=search.run,\n",
|
||||||
|
" description=\"useful for when you need to answer questions about current events. You should ask targeted questions\"\n",
|
||||||
|
" ),\n",
|
||||||
|
" Tool(\n",
|
||||||
|
" name=\"Calculator\",\n",
|
||||||
|
" func=llm_math_chain.run,\n",
|
||||||
|
" description=\"useful for when you need to answer questions about math\"\n",
|
||||||
|
" ),\n",
|
||||||
|
" Tool(\n",
|
||||||
|
" name=\"FooBar DB\",\n",
|
||||||
|
" func=db_chain.run,\n",
|
||||||
|
" description=\"useful for when you need to answer questions about FooBar. Input should be in the form of a question containing full context\"\n",
|
||||||
|
" )\n",
|
||||||
|
"]"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 3,
|
||||||
|
"id": "a069c4b6",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"mrkl = initialize_agent(tools, llm, agent=\"chat-zero-shot-react-description\", verbose=True)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 4,
|
||||||
|
"id": "e603cd7d",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3mThought: The first question requires a search, while the second question requires a calculator.\n",
|
||||||
|
"Action:\n",
|
||||||
|
"```\n",
|
||||||
|
"{\n",
|
||||||
|
" \"action\": \"Search\",\n",
|
||||||
|
" \"action_input\": \"Who is Leo DiCaprio's girlfriend?\"\n",
|
||||||
|
"}\n",
|
||||||
|
"```\n",
|
||||||
|
"\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3mCamila Morrone\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3mFor the second question, I need to use the calculator tool to raise her current age to the 0.43 power.\n",
|
||||||
|
"Action:\n",
|
||||||
|
"```\n",
|
||||||
|
"{\n",
|
||||||
|
" \"action\": \"Calculator\",\n",
|
||||||
|
" \"action_input\": \"22.0^(0.43)\"\n",
|
||||||
|
"}\n",
|
||||||
|
"```\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
|
||||||
|
"22.0^(0.43)\u001b[32;1m\u001b[1;3m\n",
|
||||||
|
"```python\n",
|
||||||
|
"import math\n",
|
||||||
|
"print(math.pow(22.0, 0.43))\n",
|
||||||
|
"```\n",
|
||||||
|
"\u001b[0m\n",
|
||||||
|
"Answer: \u001b[33;1m\u001b[1;3m3.777824273683966\n",
|
||||||
|
"\u001b[0m\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"Observation: \u001b[33;1m\u001b[1;3mAnswer: 3.777824273683966\n",
|
||||||
|
"\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3mI now know the final answer.\n",
|
||||||
|
"Final Answer: Camila Morrone, 3.777824273683966.\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"'Camila Morrone, 3.777824273683966.'"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 4,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"mrkl.run(\"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 5,
|
||||||
|
"id": "a5c07010",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3mQuestion: What is the full name of the artist who recently released an album called 'The Storm Before the Calm' and are they in the FooBar database? If so, what albums of theirs are in the FooBar database?\n",
|
||||||
|
"Thought: I should use the Search tool to find the answer to the first part of the question and then use the FooBar DB tool to find the answer to the second part of the question.\n",
|
||||||
|
"Action:\n",
|
||||||
|
"```\n",
|
||||||
|
"{\n",
|
||||||
|
" \"action\": \"Search\",\n",
|
||||||
|
" \"action_input\": \"Who recently released an album called 'The Storm Before the Calm'\"\n",
|
||||||
|
"}\n",
|
||||||
|
"```\n",
|
||||||
|
"\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3mAlanis Morissette\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3mNow that I have the name of the artist, I can use the FooBar DB tool to find their albums in the database.\n",
|
||||||
|
"Action:\n",
|
||||||
|
"```\n",
|
||||||
|
"{\n",
|
||||||
|
" \"action\": \"FooBar DB\",\n",
|
||||||
|
" \"action_input\": \"What albums does Alanis Morissette have in the database?\"\n",
|
||||||
|
"}\n",
|
||||||
|
"```\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new SQLDatabaseChain chain...\u001b[0m\n",
|
||||||
|
"What albums does Alanis Morissette have in the database? \n",
|
||||||
|
"SQLQuery:"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "stderr",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"/Users/harrisonchase/workplace/langchain/langchain/sql_database.py:141: SAWarning: Dialect sqlite+pysqlite does *not* support Decimal objects natively, and SQLAlchemy must convert from floating point - rounding errors and other issues may occur. Please consider storing Decimal numbers as strings or integers on this platform for lossless storage.\n",
|
||||||
|
" sample_rows = connection.execute(command)\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\u001b[32;1m\u001b[1;3m SELECT Title FROM Album WHERE ArtistId IN (SELECT ArtistId FROM Artist WHERE Name = 'Alanis Morissette') LIMIT 5;\u001b[0m\n",
|
||||||
|
"SQLResult: \u001b[33;1m\u001b[1;3m[('Jagged Little Pill',)]\u001b[0m\n",
|
||||||
|
"Answer:\u001b[32;1m\u001b[1;3m Alanis Morissette has the album 'Jagged Little Pill' in the database.\u001b[0m\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"Observation: \u001b[38;5;200m\u001b[1;3m Alanis Morissette has the album 'Jagged Little Pill' in the database.\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3mI have found the answer to both parts of the question.\n",
|
||||||
|
"Final Answer: The artist who recently released an album called 'The Storm Before the Calm' is Alanis Morissette. The album 'Jagged Little Pill' is in the FooBar database.\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"\"The artist who recently released an album called 'The Storm Before the Calm' is Alanis Morissette. The album 'Jagged Little Pill' is in the FooBar database.\""
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 5,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"mrkl.run(\"What is the full name of the artist who recently released an album called 'The Storm Before the Calm' and are they in the FooBar database? If so, what albums of theirs are in the FooBar database?\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "af016a70",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": []
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "Python 3 (ipykernel)",
|
||||||
|
"language": "python",
|
||||||
|
"name": "python3"
|
||||||
|
},
|
||||||
|
"language_info": {
|
||||||
|
"codemirror_mode": {
|
||||||
|
"name": "ipython",
|
||||||
|
"version": 3
|
||||||
|
},
|
||||||
|
"file_extension": ".py",
|
||||||
|
"mimetype": "text/x-python",
|
||||||
|
"name": "python",
|
||||||
|
"nbconvert_exporter": "python",
|
||||||
|
"pygments_lexer": "ipython3",
|
||||||
|
"version": "3.9.1"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 5
|
||||||
|
}
|
File diff suppressed because it is too large
Load Diff
@ -0,0 +1,26 @@
|
|||||||
|
Chat
|
||||||
|
==========================
|
||||||
|
|
||||||
|
Chat models are a variation on language models.
|
||||||
|
While chat models use language models under the hood, the interface they expose is a bit different.
|
||||||
|
Rather than expose a "text in, text out" API, they expose an interface where "chat messages" are the inputs and outputs.
|
||||||
|
|
||||||
|
Chat model APIs are fairly new, so we are still figuring out the correct abstractions.
|
||||||
|
|
||||||
|
The following sections of documentation are provided:
|
||||||
|
|
||||||
|
- `Getting Started <./chat/getting_started.html>`_: An overview of the basics of chat models.
|
||||||
|
|
||||||
|
- `Key Concepts <./chat/key_concepts.html>`_: A conceptual guide going over the various concepts related to chat models.
|
||||||
|
|
||||||
|
- `How-To Guides <./chat/how_to_guides.html>`_: A collection of how-to guides. These highlight how to accomplish various objectives with our chat model class, as well as how to integrate with various chat model providers.
|
||||||
|
|
||||||
|
|
||||||
|
.. toctree::
|
||||||
|
:maxdepth: 1
|
||||||
|
:name: LLMs
|
||||||
|
:hidden:
|
||||||
|
|
||||||
|
./chat/getting_started.ipynb
|
||||||
|
./chat/key_concepts.md
|
||||||
|
./chat/how_to_guides.rst
|
@ -0,0 +1,208 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "e58f4d5a",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# Agent\n",
|
||||||
|
"This notebook covers how to create a custom agent for a chat model. It will utilize chat specific prompts."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 3,
|
||||||
|
"id": "5268c7fa",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.agents import ZeroShotAgent, Tool, AgentExecutor\n",
|
||||||
|
"from langchain.chains import LLMChain\n",
|
||||||
|
"from langchain.utilities import SerpAPIWrapper"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 4,
|
||||||
|
"id": "fbaa4dbe",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"search = SerpAPIWrapper()\n",
|
||||||
|
"tools = [\n",
|
||||||
|
" Tool(\n",
|
||||||
|
" name = \"Search\",\n",
|
||||||
|
" func=search.run,\n",
|
||||||
|
" description=\"useful for when you need to answer questions about current events\"\n",
|
||||||
|
" )\n",
|
||||||
|
"]"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 6,
|
||||||
|
"id": "f3ba6f08",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"prefix = \"\"\"Answer the following questions as best you can, but speaking as a pirate might speak. You have access to the following tools:\"\"\"\n",
|
||||||
|
"suffix = \"\"\"Begin! Remember to speak as a pirate when giving your final answer. Use lots of \"Args\"\"\"\n",
|
||||||
|
"\n",
|
||||||
|
"prompt = ZeroShotAgent.create_prompt(\n",
|
||||||
|
" tools, \n",
|
||||||
|
" prefix=prefix, \n",
|
||||||
|
" suffix=suffix, \n",
|
||||||
|
" input_variables=[]\n",
|
||||||
|
")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 7,
|
||||||
|
"id": "3547a37d",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.chat_models import ChatOpenAI\n",
|
||||||
|
"from langchain.prompts.chat import (\n",
|
||||||
|
" ChatPromptTemplate,\n",
|
||||||
|
" SystemMessagePromptTemplate,\n",
|
||||||
|
" AIMessagePromptTemplate,\n",
|
||||||
|
" HumanMessagePromptTemplate,\n",
|
||||||
|
")\n",
|
||||||
|
"from langchain.schema import (\n",
|
||||||
|
" AIMessage,\n",
|
||||||
|
" HumanMessage,\n",
|
||||||
|
" SystemMessage\n",
|
||||||
|
")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 8,
|
||||||
|
"id": "a78f886f",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"messages = [\n",
|
||||||
|
" SystemMessagePromptTemplate(prompt=prompt),\n",
|
||||||
|
" HumanMessagePromptTemplate.from_template(\"{input}\\n\\nThis was your previous work \"\n",
|
||||||
|
" f\"(but I haven't seen any of it! I only see what \"\n",
|
||||||
|
" \"you return as final answer):\\n{agent_scratchpad}\")\n",
|
||||||
|
"]"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 9,
|
||||||
|
"id": "dadadd70",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"prompt = ChatPromptTemplate.from_messages(messages)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 10,
|
||||||
|
"id": "b7180182",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"llm_chain = LLMChain(llm=ChatOpenAI(temperature=0), prompt=prompt)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 11,
|
||||||
|
"id": "ddddb07b",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"tool_names = [tool.name for tool in tools]\n",
|
||||||
|
"agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 12,
|
||||||
|
"id": "36aef054",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"agent_executor = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 13,
|
||||||
|
"id": "33a4d6cc",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||||
|
"\u001b[32;1m\u001b[1;3mArrr, ye be in luck, matey! I'll find ye the answer to yer question.\n",
|
||||||
|
"\n",
|
||||||
|
"Thought: I need to search for the current population of Canada.\n",
|
||||||
|
"Action: Search\n",
|
||||||
|
"Action Input: \"current population of Canada 2023\"\n",
|
||||||
|
"\u001b[0m\n",
|
||||||
|
"Observation: \u001b[36;1m\u001b[1;3mThe current population of Canada is 38,623,091 as of Saturday, March 4, 2023, based on Worldometer elaboration of the latest United Nations data.\u001b[0m\n",
|
||||||
|
"Thought:\u001b[32;1m\u001b[1;3mAhoy, me hearties! I've found the answer to yer question.\n",
|
||||||
|
"\n",
|
||||||
|
"Final Answer: As of March 4, 2023, the population of Canada be 38,623,091. Arrr!\u001b[0m\n",
|
||||||
|
"\n",
|
||||||
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"'As of March 4, 2023, the population of Canada be 38,623,091. Arrr!'"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 13,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"agent_executor.run(\"How many people live in canada as of 2023?\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "6aefe978",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": []
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "Python 3 (ipykernel)",
|
||||||
|
"language": "python",
|
||||||
|
"name": "python3"
|
||||||
|
},
|
||||||
|
"language_info": {
|
||||||
|
"codemirror_mode": {
|
||||||
|
"name": "ipython",
|
||||||
|
"version": 3
|
||||||
|
},
|
||||||
|
"file_extension": ".py",
|
||||||
|
"mimetype": "text/x-python",
|
||||||
|
"name": "python",
|
||||||
|
"nbconvert_exporter": "python",
|
||||||
|
"pygments_lexer": "ipython3",
|
||||||
|
"version": "3.9.1"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 5
|
||||||
|
}
|
@ -0,0 +1,376 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "134a0785",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# Chat Vector DB\n",
|
||||||
|
"\n",
|
||||||
|
"This notebook goes over how to set up a chat model to chat with a vector database.\n",
|
||||||
|
"\n",
|
||||||
|
"This notebook is very similar to the example of using an LLM in the ConversationalRetrievalChain. The only differences here are (1) using a ChatModel, and (2) passing in a ChatPromptTemplate (optimized for chat models)."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 1,
|
||||||
|
"id": "70c4e529",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
|
||||||
|
"from langchain.vectorstores import Chroma\n",
|
||||||
|
"from langchain.text_splitter import CharacterTextSplitter\n",
|
||||||
|
"from langchain.chains import ConversationalRetrievalChain"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "cdff94be",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"Load in documents. You can replace this with a loader for whatever type of data you want"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 2,
|
||||||
|
"id": "01c46e92",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.document_loaders import TextLoader\n",
|
||||||
|
"loader = TextLoader('../../state_of_the_union.txt')\n",
|
||||||
|
"documents = loader.load()"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "e9be4779",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"If you had multiple loaders that you wanted to combine, you do something like:"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 3,
|
||||||
|
"id": "433363a5",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"# loaders = [....]\n",
|
||||||
|
"# docs = []\n",
|
||||||
|
"# for loader in loaders:\n",
|
||||||
|
"# docs.extend(loader.load())"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "239475d2",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"We now split the documents, create embeddings for them, and put them in a vectorstore. This allows us to do semantic search over them."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 4,
|
||||||
|
"id": "a8930cf7",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"Running Chroma using direct local API.\n",
|
||||||
|
"Using DuckDB in-memory for database. Data will be transient.\n"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
|
||||||
|
"documents = text_splitter.split_documents(documents)\n",
|
||||||
|
"\n",
|
||||||
|
"embeddings = OpenAIEmbeddings()\n",
|
||||||
|
"vectorstore = Chroma.from_documents(documents, embeddings)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "18415aca",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"We are now going to construct a prompt specifically designed for chat models."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 5,
|
||||||
|
"id": "c8805230",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.chat_models import ChatOpenAI\n",
|
||||||
|
"from langchain.prompts.chat import (\n",
|
||||||
|
" ChatPromptTemplate,\n",
|
||||||
|
" SystemMessagePromptTemplate,\n",
|
||||||
|
" AIMessagePromptTemplate,\n",
|
||||||
|
" HumanMessagePromptTemplate,\n",
|
||||||
|
")\n",
|
||||||
|
"from langchain.schema import (\n",
|
||||||
|
" AIMessage,\n",
|
||||||
|
" HumanMessage,\n",
|
||||||
|
" SystemMessage\n",
|
||||||
|
")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 6,
|
||||||
|
"id": "cc86c30e",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"system_template=\"\"\"Use the following pieces of context to answer the users question. \n",
|
||||||
|
"If you don't know the answer, just say that you don't know, don't try to make up an answer.\n",
|
||||||
|
"----------------\n",
|
||||||
|
"{context}\"\"\"\n",
|
||||||
|
"messages = [\n",
|
||||||
|
" SystemMessagePromptTemplate.from_template(system_template),\n",
|
||||||
|
" HumanMessagePromptTemplate.from_template(\"{question}\")\n",
|
||||||
|
"]\n",
|
||||||
|
"prompt = ChatPromptTemplate.from_messages(messages)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "3c96b118",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"We now initialize the ConversationalRetrievalChain"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 7,
|
||||||
|
"id": "7b4110f3",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"qa = ConversationalRetrievalChain.from_llm(ChatOpenAI(temperature=0), vectorstore,qa_prompt=prompt)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "3872432d",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"Here's an example of asking a question with no chat history"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 8,
|
||||||
|
"id": "7fe3e730",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"chat_history = []\n",
|
||||||
|
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
|
||||||
|
"result = qa({\"question\": query, \"chat_history\": chat_history})"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 9,
|
||||||
|
"id": "bfff9cc8",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"\"The President nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to serve on the United States Supreme Court. He described her as one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, and a consensus builder. She has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 9,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"result[\"answer\"]"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "9e46edf7",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"Here's an example of asking a question with some chat history"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 10,
|
||||||
|
"id": "00b4cf00",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"chat_history = [(query, result[\"answer\"])]\n",
|
||||||
|
"query = \"Did he mention who came before her\"\n",
|
||||||
|
"result = qa({\"question\": query, \"chat_history\": chat_history})"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 11,
|
||||||
|
"id": "f01828d1",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"\"The President mentioned Circuit Court of Appeals Judge Ketanji Brown Jackson as the nominee for the United States Supreme Court. He described her as one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence. The President did not mention any specific sources of support for Judge Jackson, but he did note that advancing immigration reform is supported by everyone from labor unions to religious leaders to the U.S. Chamber of Commerce.\""
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 11,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"result['answer']"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "2324cdc6-98bf-4708-b8cd-02a98b1e5b67",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## ConversationalRetrievalChain with streaming to `stdout`\n",
|
||||||
|
"\n",
|
||||||
|
"Output from the chain will be streamed to `stdout` token by token in this example."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 12,
|
||||||
|
"id": "2efacec3-2690-4b05-8de3-a32fd2ac3911",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.chains.llm import LLMChain\n",
|
||||||
|
"from langchain.llms import OpenAI\n",
|
||||||
|
"from langchain.callbacks.base import CallbackManager\n",
|
||||||
|
"from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
|
||||||
|
"from langchain.chains.chat_index.prompts import CONDENSE_QUESTION_PROMPT\n",
|
||||||
|
"from langchain.chains.question_answering import load_qa_chain\n",
|
||||||
|
"\n",
|
||||||
|
"# Construct a ChatVectorDBChain with a streaming llm for combine docs\n",
|
||||||
|
"# and a separate, non-streaming llm for question generation\n",
|
||||||
|
"llm = OpenAI(temperature=0)\n",
|
||||||
|
"streaming_llm = ChatOpenAI(streaming=True, callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), verbose=True, temperature=0)\n",
|
||||||
|
"\n",
|
||||||
|
"question_generator = LLMChain(llm=llm, prompt=CONDENSE_QUESTION_PROMPT)\n",
|
||||||
|
"doc_chain = load_qa_chain(streaming_llm, chain_type=\"stuff\", prompt=prompt)\n",
|
||||||
|
"\n",
|
||||||
|
"qa = ConversationalRetrievalChain(retriever=vectorstore.as_retriever(), combine_docs_chain=doc_chain, question_generator=question_generator)\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 13,
|
||||||
|
"id": "fd6d43f4-7428-44a4-81bc-26fe88a98762",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"The President nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to serve on the United States Supreme Court. He described her as one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, and a consensus builder. He also mentioned that she has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans."
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"chat_history = []\n",
|
||||||
|
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
|
||||||
|
"result = qa({\"question\": query, \"chat_history\": chat_history})"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 14,
|
||||||
|
"id": "5ab38978-f3e8-4fa7-808c-c79dec48379a",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"The context does not provide information on who Ketanji Brown Jackson succeeded on the United States Supreme Court."
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"chat_history = [(query, result[\"answer\"])]\n",
|
||||||
|
"query = \"Did he mention who she suceeded\"\n",
|
||||||
|
"result = qa({\"question\": query, \"chat_history\": chat_history})\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "8e8d0055",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": []
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "Python 3 (ipykernel)",
|
||||||
|
"language": "python",
|
||||||
|
"name": "python3"
|
||||||
|
},
|
||||||
|
"language_info": {
|
||||||
|
"codemirror_mode": {
|
||||||
|
"name": "ipython",
|
||||||
|
"version": 3
|
||||||
|
},
|
||||||
|
"file_extension": ".py",
|
||||||
|
"mimetype": "text/x-python",
|
||||||
|
"name": "python",
|
||||||
|
"nbconvert_exporter": "python",
|
||||||
|
"pygments_lexer": "ipython3",
|
||||||
|
"version": "3.9.1"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 5
|
||||||
|
}
|
@ -0,0 +1,166 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "bb0735c0",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# Few Shot Examples\n",
|
||||||
|
"\n",
|
||||||
|
"This notebook covers how to use few shot examples in chat models.\n",
|
||||||
|
"\n",
|
||||||
|
"There does not appear to be solid consensus on how best to do few shot prompting. As a result, we are not solidifying any abstractions around this yet but rather using existing abstractions."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "c6e9664c",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Alternating Human/AI messages\n",
|
||||||
|
"The first way of doing few shot prompting relies on using alternating human/ai messages. See an example of this below."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 1,
|
||||||
|
"id": "62156fe4",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.chat_models import ChatOpenAI\n",
|
||||||
|
"from langchain import PromptTemplate, LLMChain\n",
|
||||||
|
"from langchain.prompts.chat import (\n",
|
||||||
|
" ChatPromptTemplate,\n",
|
||||||
|
" SystemMessagePromptTemplate,\n",
|
||||||
|
" AIMessagePromptTemplate,\n",
|
||||||
|
" HumanMessagePromptTemplate,\n",
|
||||||
|
")\n",
|
||||||
|
"from langchain.schema import (\n",
|
||||||
|
" AIMessage,\n",
|
||||||
|
" HumanMessage,\n",
|
||||||
|
" SystemMessage\n",
|
||||||
|
")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 2,
|
||||||
|
"id": "ed7ac3c6",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"chat = ChatOpenAI(temperature=0)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 3,
|
||||||
|
"id": "98791aa9",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"template=\"You are a helpful assistant that translates english to pirate.\"\n",
|
||||||
|
"system_message_prompt = SystemMessagePromptTemplate.from_template(template)\n",
|
||||||
|
"example_human = HumanMessagePromptTemplate.from_template(\"Hi\")\n",
|
||||||
|
"example_ai = AIMessagePromptTemplate.from_template(\"Argh me mateys\")\n",
|
||||||
|
"human_template=\"{text}\"\n",
|
||||||
|
"human_message_prompt = HumanMessagePromptTemplate.from_template(human_template)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 4,
|
||||||
|
"id": "4eebdcd7",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"\"I be lovin' programmin', me hearty!\""
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 4,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"chat_prompt = ChatPromptTemplate.from_messages([system_message_prompt, example_human, example_ai, human_message_prompt])\n",
|
||||||
|
"chain = LLMChain(llm=chat, prompt=chat_prompt)\n",
|
||||||
|
"# get a chat completion from the formatted messages\n",
|
||||||
|
"chain.run(\"I love programming.\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "5c4135d7",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## System Messages\n",
|
||||||
|
"\n",
|
||||||
|
"OpenAI provides an optional `name` parameter that they also recommend using in conjunction with system messages to do few shot prompting. Here is an example of how to do that below."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 5,
|
||||||
|
"id": "1ba92d59",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"template=\"You are a helpful assistant that translates english to pirate.\"\n",
|
||||||
|
"system_message_prompt = SystemMessagePromptTemplate.from_template(template)\n",
|
||||||
|
"example_human = SystemMessagePromptTemplate.from_template(\"Hi\", additional_kwargs={\"name\": \"example_user\"})\n",
|
||||||
|
"example_ai = SystemMessagePromptTemplate.from_template(\"Argh me mateys\", additional_kwargs={\"name\": \"example_assistant\"})\n",
|
||||||
|
"human_template=\"{text}\"\n",
|
||||||
|
"human_message_prompt = HumanMessagePromptTemplate.from_template(human_template)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 6,
|
||||||
|
"id": "56e488a7",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"\"I be lovin' programmin', me hearty.\""
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 6,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"chat_prompt = ChatPromptTemplate.from_messages([system_message_prompt, example_human, example_ai, human_message_prompt])\n",
|
||||||
|
"chain = LLMChain(llm=chat, prompt=chat_prompt)\n",
|
||||||
|
"# get a chat completion from the formatted messages\n",
|
||||||
|
"chain.run(\"I love programming.\")"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "Python 3 (ipykernel)",
|
||||||
|
"language": "python",
|
||||||
|
"name": "python3"
|
||||||
|
},
|
||||||
|
"language_info": {
|
||||||
|
"codemirror_mode": {
|
||||||
|
"name": "ipython",
|
||||||
|
"version": 3
|
||||||
|
},
|
||||||
|
"file_extension": ".py",
|
||||||
|
"mimetype": "text/x-python",
|
||||||
|
"name": "python",
|
||||||
|
"nbconvert_exporter": "python",
|
||||||
|
"pygments_lexer": "ipython3",
|
||||||
|
"version": "3.9.1"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 5
|
||||||
|
}
|
@ -0,0 +1,192 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "9a9350a6",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# Memory\n",
|
||||||
|
"This notebook goes over how to use Memory with chat models. The main difference between this and Memory for LLMs is that rather than trying to condense all previous messages into a string, we can keep them as their own unique memory object."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 1,
|
||||||
|
"id": "110935ae",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.prompts import (\n",
|
||||||
|
" ChatPromptTemplate, \n",
|
||||||
|
" MessagesPlaceholder, \n",
|
||||||
|
" SystemMessagePromptTemplate, \n",
|
||||||
|
" HumanMessagePromptTemplate\n",
|
||||||
|
")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 2,
|
||||||
|
"id": "161b6629",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"prompt = ChatPromptTemplate.from_messages([\n",
|
||||||
|
" SystemMessagePromptTemplate.from_template(\"The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\"),\n",
|
||||||
|
" MessagesPlaceholder(variable_name=\"history\"),\n",
|
||||||
|
" HumanMessagePromptTemplate.from_template(\"{input}\")\n",
|
||||||
|
"])"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 4,
|
||||||
|
"id": "4976fbda",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.chains import ConversationChain\n",
|
||||||
|
"from langchain.chat_models import ChatOpenAI\n",
|
||||||
|
"from langchain.memory import ConversationBufferMemory"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 5,
|
||||||
|
"id": "12a0bea6",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"llm = ChatOpenAI(temperature=0)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "f6edcd6a",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"We can now initialize the memory. Note that we set `return_messages=True` To denote that this should return a list of messages when appropriate"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 6,
|
||||||
|
"id": "f55bea38",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"memory = ConversationBufferMemory(return_messages=True)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "737e8c78",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"We can now use this in the rest of the chain."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 8,
|
||||||
|
"id": "80152db7",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"conversation = ConversationChain(memory=memory, prompt=prompt, llm=llm)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 9,
|
||||||
|
"id": "ac68e766",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"'Hello! How can I assist you today?'"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 9,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"conversation.predict(input=\"Hi there!\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 10,
|
||||||
|
"id": "babb33d0",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"\"That sounds like fun! I'm happy to chat with you. Is there anything specific you'd like to talk about?\""
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 10,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"conversation.predict(input=\"I'm doing well! Just having a conversation with an AI.\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 11,
|
||||||
|
"id": "36f8a1dc",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"\"Sure! I am an AI language model created by OpenAI. I was trained on a large dataset of text from the internet, which allows me to understand and generate human-like language. I can answer questions, provide information, and even have conversations like this one. Is there anything else you'd like to know about me?\""
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 11,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"conversation.predict(input=\"Tell me about yourself.\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "79fb460b",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": []
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "Python 3 (ipykernel)",
|
||||||
|
"language": "python",
|
||||||
|
"name": "python3"
|
||||||
|
},
|
||||||
|
"language_info": {
|
||||||
|
"codemirror_mode": {
|
||||||
|
"name": "ipython",
|
||||||
|
"version": 3
|
||||||
|
},
|
||||||
|
"file_extension": ".py",
|
||||||
|
"mimetype": "text/x-python",
|
||||||
|
"name": "python",
|
||||||
|
"nbconvert_exporter": "python",
|
||||||
|
"pygments_lexer": "ipython3",
|
||||||
|
"version": "3.9.1"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 5
|
||||||
|
}
|
@ -0,0 +1,188 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"attachments": {},
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "959300d4",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# PromptLayer ChatOpenAI\n",
|
||||||
|
"\n",
|
||||||
|
"This example showcases how to connect to [PromptLayer](https://www.promptlayer.com) to start recording your ChatOpenAI requests."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"attachments": {},
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "6a45943e",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Install PromptLayer\n",
|
||||||
|
"The `promptlayer` package is required to use PromptLayer with OpenAI. Install `promptlayer` using pip."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "dbe09bd8",
|
||||||
|
"metadata": {
|
||||||
|
"vscode": {
|
||||||
|
"languageId": "powershell"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"pip install promptlayer"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "536c1dfa",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Imports"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 2,
|
||||||
|
"id": "c16da3b5",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"import os\n",
|
||||||
|
"from langchain.chat_models import PromptLayerChatOpenAI\n",
|
||||||
|
"from langchain.schema import HumanMessage"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"attachments": {},
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "8564ce7d",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Set the Environment API Key\n",
|
||||||
|
"You can create a PromptLayer API Key at [wwww.promptlayer.com](https://ww.promptlayer.com) by clicking the settings cog in the navbar.\n",
|
||||||
|
"\n",
|
||||||
|
"Set it as an environment variable called `PROMPTLAYER_API_KEY`."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 5,
|
||||||
|
"id": "46ba25dc",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"os.environ[\"PROMPTLAYER_API_KEY\"] = \"**********\""
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"attachments": {},
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "bf0294de",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Use the PromptLayerOpenAI LLM like normal\n",
|
||||||
|
"*You can optionally pass in `pl_tags` to track your requests with PromptLayer's tagging feature.*"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 4,
|
||||||
|
"id": "3acf0069",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"AIMessage(content='to take a nap in a cozy spot. I search around for a suitable place and finally settle on a soft cushion on the window sill. I curl up into a ball and close my eyes, relishing the warmth of the sun on my fur. As I drift off to sleep, I can hear the birds chirping outside and feel the gentle breeze blowing through the window. This is the life of a contented cat.', additional_kwargs={})"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 4,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"chat = PromptLayerChatOpenAI(pl_tags=[\"langchain\"])\n",
|
||||||
|
"chat([HumanMessage(content=\"I am a cat and I want\")])"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"attachments": {},
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "a2d76826",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"**The above request should now appear on your [PromptLayer dashboard](https://ww.promptlayer.com).**"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "05e9e2fe",
|
||||||
|
"metadata": {},
|
||||||
|
"source": []
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"attachments": {},
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "c43803d1",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Using PromptLayer Track\n",
|
||||||
|
"If you would like to use any of the [PromptLayer tracking features](https://magniv.notion.site/Track-4deee1b1f7a34c1680d085f82567dab9), you need to pass the argument `return_pl_id` when instantializing the PromptLayer LLM to get the request id. "
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "b7d4db01",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"chat = PromptLayerChatOpenAI(return_pl_id=True)\n",
|
||||||
|
"chat_results = chat.generate([[HumanMessage(content=\"I am a cat and I want\")]])\n",
|
||||||
|
"\n",
|
||||||
|
"for res in chat_results.generations:\n",
|
||||||
|
" pl_request_id = res[0].generation_info[\"pl_request_id\"]\n",
|
||||||
|
" promptlayer.track.score(request_id=pl_request_id, score=100)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "13e56507",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"Using this allows you to track the performance of your model in the PromptLayer dashboard. If you are using a prompt template, you can attach a template to a request as well.\n",
|
||||||
|
"Overall, this gives you the opportunity to track the performance of different templates and models in the PromptLayer dashboard."
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "base",
|
||||||
|
"language": "python",
|
||||||
|
"name": "python3"
|
||||||
|
},
|
||||||
|
"language_info": {
|
||||||
|
"codemirror_mode": {
|
||||||
|
"name": "ipython",
|
||||||
|
"version": 3
|
||||||
|
},
|
||||||
|
"file_extension": ".py",
|
||||||
|
"mimetype": "text/x-python",
|
||||||
|
"name": "python",
|
||||||
|
"nbconvert_exporter": "python",
|
||||||
|
"pygments_lexer": "ipython3",
|
||||||
|
"version": "3.8.8 (default, Apr 13 2021, 12:59:45) \n[Clang 10.0.0 ]"
|
||||||
|
},
|
||||||
|
"vscode": {
|
||||||
|
"interpreter": {
|
||||||
|
"hash": "8a5edab282632443219e051e4ade2d1d5bbc671c781051bf1437897cbdfea0f1"
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 5
|
||||||
|
}
|
@ -0,0 +1,119 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "fe4e96b5",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# Streaming\n",
|
||||||
|
"\n",
|
||||||
|
"This notebook goes over how to use streaming with a chat model."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 4,
|
||||||
|
"id": "e0244f2a",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.chat_models import ChatOpenAI\n",
|
||||||
|
"from langchain.schema import (\n",
|
||||||
|
" HumanMessage,\n",
|
||||||
|
")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 5,
|
||||||
|
"id": "ad342bfa",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"Verse 1:\n",
|
||||||
|
"Bubbles rising to the top\n",
|
||||||
|
"A refreshing drink that never stops\n",
|
||||||
|
"Clear and crisp, it's pure delight\n",
|
||||||
|
"A taste that's sure to excite\n",
|
||||||
|
"\n",
|
||||||
|
"Chorus:\n",
|
||||||
|
"Sparkling water, oh so fine\n",
|
||||||
|
"A drink that's always on my mind\n",
|
||||||
|
"With every sip, I feel alive\n",
|
||||||
|
"Sparkling water, you're my vibe\n",
|
||||||
|
"\n",
|
||||||
|
"Verse 2:\n",
|
||||||
|
"No sugar, no calories, just pure bliss\n",
|
||||||
|
"A drink that's hard to resist\n",
|
||||||
|
"It's the perfect way to quench my thirst\n",
|
||||||
|
"A drink that always comes first\n",
|
||||||
|
"\n",
|
||||||
|
"Chorus:\n",
|
||||||
|
"Sparkling water, oh so fine\n",
|
||||||
|
"A drink that's always on my mind\n",
|
||||||
|
"With every sip, I feel alive\n",
|
||||||
|
"Sparkling water, you're my vibe\n",
|
||||||
|
"\n",
|
||||||
|
"Bridge:\n",
|
||||||
|
"From the mountains to the sea\n",
|
||||||
|
"Sparkling water, you're the key\n",
|
||||||
|
"To a healthy life, a happy soul\n",
|
||||||
|
"A drink that makes me feel whole\n",
|
||||||
|
"\n",
|
||||||
|
"Chorus:\n",
|
||||||
|
"Sparkling water, oh so fine\n",
|
||||||
|
"A drink that's always on my mind\n",
|
||||||
|
"With every sip, I feel alive\n",
|
||||||
|
"Sparkling water, you're my vibe\n",
|
||||||
|
"\n",
|
||||||
|
"Outro:\n",
|
||||||
|
"Sparkling water, you're the one\n",
|
||||||
|
"A drink that's always so much fun\n",
|
||||||
|
"I'll never let you go, my friend\n",
|
||||||
|
"Sparkling"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"from langchain.callbacks.base import CallbackManager\n",
|
||||||
|
"from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
|
||||||
|
"chat = ChatOpenAI(streaming=True, callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), verbose=True, temperature=0)\n",
|
||||||
|
"resp = chat([HumanMessage(content=\"Write me a song about sparkling water.\")])"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "67c44deb",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": []
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "Python 3 (ipykernel)",
|
||||||
|
"language": "python",
|
||||||
|
"name": "python3"
|
||||||
|
},
|
||||||
|
"language_info": {
|
||||||
|
"codemirror_mode": {
|
||||||
|
"name": "ipython",
|
||||||
|
"version": 3
|
||||||
|
},
|
||||||
|
"file_extension": ".py",
|
||||||
|
"mimetype": "text/x-python",
|
||||||
|
"name": "python",
|
||||||
|
"nbconvert_exporter": "python",
|
||||||
|
"pygments_lexer": "ipython3",
|
||||||
|
"version": "3.9.1"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 5
|
||||||
|
}
|
@ -0,0 +1,169 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "07c1e3b9",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# Retrieval Question/Answering\n",
|
||||||
|
"\n",
|
||||||
|
"This example showcases using a chat model to do question answering over a vector database.\n",
|
||||||
|
"\n",
|
||||||
|
"This notebook is very similar to the example of using an LLM in the RetrievalQA. The only differences here are (1) using a ChatModel, and (2) passing in a ChatPromptTemplate (optimized for chat models)."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 7,
|
||||||
|
"id": "82525493",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
|
||||||
|
"from langchain.vectorstores import Chroma\n",
|
||||||
|
"from langchain.text_splitter import CharacterTextSplitter\n",
|
||||||
|
"from langchain.chains import RetrievalQA"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 2,
|
||||||
|
"id": "5c7049db",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"Running Chroma using direct local API.\n",
|
||||||
|
"Using DuckDB in-memory for database. Data will be transient.\n"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"from langchain.document_loaders import TextLoader\n",
|
||||||
|
"loader = TextLoader('../../state_of_the_union.txt')\n",
|
||||||
|
"documents = loader.load()\n",
|
||||||
|
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
|
||||||
|
"texts = text_splitter.split_documents(documents)\n",
|
||||||
|
"\n",
|
||||||
|
"embeddings = OpenAIEmbeddings()\n",
|
||||||
|
"docsearch = Chroma.from_documents(texts, embeddings)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "35f99145",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"We can now set up the chat model and chat model specific prompt"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 3,
|
||||||
|
"id": "32a49412",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.chat_models import ChatOpenAI\n",
|
||||||
|
"from langchain.prompts.chat import (\n",
|
||||||
|
" ChatPromptTemplate,\n",
|
||||||
|
" SystemMessagePromptTemplate,\n",
|
||||||
|
" AIMessagePromptTemplate,\n",
|
||||||
|
" HumanMessagePromptTemplate,\n",
|
||||||
|
")\n",
|
||||||
|
"from langchain.schema import (\n",
|
||||||
|
" AIMessage,\n",
|
||||||
|
" HumanMessage,\n",
|
||||||
|
" SystemMessage\n",
|
||||||
|
")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 4,
|
||||||
|
"id": "f231fb9b",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"system_template=\"\"\"Use the following pieces of context to answer the users question. \n",
|
||||||
|
"If you don't know the answer, just say that you don't know, don't try to make up an answer.\n",
|
||||||
|
"----------------\n",
|
||||||
|
"{context}\"\"\"\n",
|
||||||
|
"messages = [\n",
|
||||||
|
" SystemMessagePromptTemplate.from_template(system_template),\n",
|
||||||
|
" HumanMessagePromptTemplate.from_template(\"{question}\")\n",
|
||||||
|
"]\n",
|
||||||
|
"prompt = ChatPromptTemplate.from_messages(messages)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 8,
|
||||||
|
"id": "3018f865",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"chain_type_kwargs = {\"prompt\": prompt}\n",
|
||||||
|
"qa = RetrievalQA.from_chain_type(llm=ChatOpenAI(), chain_type=\"stuff\", retriever=docsearch.as_retriever(), chain_type_kwargs=chain_type_kwargs)\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 9,
|
||||||
|
"id": "032a47f8",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"\"The president nominated Ketanji Brown Jackson to serve on the United States Supreme Court. He referred to her as one of our nation's top legal minds, a former federal public defender, a consensus builder, and from a family of public school educators and police officers. Since she's been nominated, she has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 9,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
|
||||||
|
"qa.run(query)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "8b403637",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": []
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "Python 3 (ipykernel)",
|
||||||
|
"language": "python",
|
||||||
|
"name": "python3"
|
||||||
|
},
|
||||||
|
"language_info": {
|
||||||
|
"codemirror_mode": {
|
||||||
|
"name": "ipython",
|
||||||
|
"version": 3
|
||||||
|
},
|
||||||
|
"file_extension": ".py",
|
||||||
|
"mimetype": "text/x-python",
|
||||||
|
"name": "python",
|
||||||
|
"nbconvert_exporter": "python",
|
||||||
|
"pygments_lexer": "ipython3",
|
||||||
|
"version": "3.9.1"
|
||||||
|
},
|
||||||
|
"vscode": {
|
||||||
|
"interpreter": {
|
||||||
|
"hash": "b1677b440931f40d89ef8be7bf03acb108ce003de0ac9b18e8d43753ea2e7103"
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 5
|
||||||
|
}
|
@ -0,0 +1,206 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "efc5be67",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# Retrieval Question Answering with Sources\n",
|
||||||
|
"\n",
|
||||||
|
"This notebook goes over how to do question-answering with sources with a chat model over a vector database. It does this by using the `RetrievalQAWithSourcesChain`, which does the lookup of the documents from a vector database. \n",
|
||||||
|
"\n",
|
||||||
|
"This notebook is very similar to the example of using an LLM in the RetrievalQAWithSources. The only differences here are (1) using a ChatModel, and (2) passing in a ChatPromptTemplate (optimized for chat models)."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 1,
|
||||||
|
"id": "1c613960",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
|
||||||
|
"from langchain.embeddings.cohere import CohereEmbeddings\n",
|
||||||
|
"from langchain.text_splitter import CharacterTextSplitter\n",
|
||||||
|
"from langchain.vectorstores.elastic_vector_search import ElasticVectorSearch\n",
|
||||||
|
"from langchain.vectorstores import Chroma"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 2,
|
||||||
|
"id": "17d1306e",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"with open('../../state_of_the_union.txt') as f:\n",
|
||||||
|
" state_of_the_union = f.read()\n",
|
||||||
|
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
|
||||||
|
"texts = text_splitter.split_text(state_of_the_union)\n",
|
||||||
|
"\n",
|
||||||
|
"embeddings = OpenAIEmbeddings()"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 3,
|
||||||
|
"id": "0e745d99",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"Running Chroma using direct local API.\n",
|
||||||
|
"Using DuckDB in-memory for database. Data will be transient.\n",
|
||||||
|
"Running Chroma using direct local API.\n",
|
||||||
|
"Using DuckDB in-memory for database. Data will be transient.\n"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"docsearch = Chroma.from_texts(texts, embeddings, metadatas=[{\"source\": f\"{i}-pl\"} for i in range(len(texts))])"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 9,
|
||||||
|
"id": "8aa571ae",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.chains import RetrievalQAWithSourcesChain"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "1f73b14a",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"We can now set up the chat model and chat model specific prompt"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 5,
|
||||||
|
"id": "9643c775",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.chat_models import ChatOpenAI\n",
|
||||||
|
"from langchain.prompts.chat import (\n",
|
||||||
|
" ChatPromptTemplate,\n",
|
||||||
|
" SystemMessagePromptTemplate,\n",
|
||||||
|
" AIMessagePromptTemplate,\n",
|
||||||
|
" HumanMessagePromptTemplate,\n",
|
||||||
|
")\n",
|
||||||
|
"from langchain.schema import (\n",
|
||||||
|
" AIMessage,\n",
|
||||||
|
" HumanMessage,\n",
|
||||||
|
" SystemMessage\n",
|
||||||
|
")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 6,
|
||||||
|
"id": "ed00e906",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"system_template=\"\"\"Use the following pieces of context to answer the users question. \n",
|
||||||
|
"If you don't know the answer, just say that you don't know, don't try to make up an answer.\n",
|
||||||
|
"ALWAYS return a \"SOURCES\" part in your answer.\n",
|
||||||
|
"The \"SOURCES\" part should be a reference to the source of the document from which you got your answer.\n",
|
||||||
|
"\n",
|
||||||
|
"Example of your response should be:\n",
|
||||||
|
"\n",
|
||||||
|
"```\n",
|
||||||
|
"The answer is foo\n",
|
||||||
|
"SOURCES: xyz\n",
|
||||||
|
"```\n",
|
||||||
|
"\n",
|
||||||
|
"Begin!\n",
|
||||||
|
"----------------\n",
|
||||||
|
"{summaries}\"\"\"\n",
|
||||||
|
"messages = [\n",
|
||||||
|
" SystemMessagePromptTemplate.from_template(system_template),\n",
|
||||||
|
" HumanMessagePromptTemplate.from_template(\"{question}\")\n",
|
||||||
|
"]\n",
|
||||||
|
"prompt = ChatPromptTemplate.from_messages(messages)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 10,
|
||||||
|
"id": "aa859d4c",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"chain_type_kwargs = {\"prompt\": prompt}\n",
|
||||||
|
"chain = RetrievalQAWithSourcesChain.from_chain_type(\n",
|
||||||
|
" ChatOpenAI(temperature=0), \n",
|
||||||
|
" chain_type=\"stuff\", \n",
|
||||||
|
" retriever=docsearch.as_retriever(),\n",
|
||||||
|
" chain_type_kwargs=chain_type_kwargs\n",
|
||||||
|
")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 11,
|
||||||
|
"id": "8ba36fa7",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"{'answer': 'The President honored Justice Stephen Breyer, an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court, for his dedicated service to the country. \\n',\n",
|
||||||
|
" 'sources': '31-pl'}"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 11,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"chain({\"question\": \"What did the president say about Justice Breyer\"}, return_only_outputs=True)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "8308fbf7",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": []
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "Python 3 (ipykernel)",
|
||||||
|
"language": "python",
|
||||||
|
"name": "python3"
|
||||||
|
},
|
||||||
|
"language_info": {
|
||||||
|
"codemirror_mode": {
|
||||||
|
"name": "ipython",
|
||||||
|
"version": 3
|
||||||
|
},
|
||||||
|
"file_extension": ".py",
|
||||||
|
"mimetype": "text/x-python",
|
||||||
|
"name": "python",
|
||||||
|
"nbconvert_exporter": "python",
|
||||||
|
"pygments_lexer": "ipython3",
|
||||||
|
"version": "3.9.1"
|
||||||
|
},
|
||||||
|
"vscode": {
|
||||||
|
"interpreter": {
|
||||||
|
"hash": "b1677b440931f40d89ef8be7bf03acb108ce003de0ac9b18e8d43753ea2e7103"
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 5
|
||||||
|
}
|
@ -0,0 +1,412 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "e49f1e0d",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# Getting Started\n",
|
||||||
|
"\n",
|
||||||
|
"This notebook covers how to get started with chat models. The interface is based around messages rather than raw text."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 1,
|
||||||
|
"id": "522686de",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.chat_models import ChatOpenAI\n",
|
||||||
|
"from langchain import PromptTemplate, LLMChain\n",
|
||||||
|
"from langchain.prompts.chat import (\n",
|
||||||
|
" ChatPromptTemplate,\n",
|
||||||
|
" SystemMessagePromptTemplate,\n",
|
||||||
|
" AIMessagePromptTemplate,\n",
|
||||||
|
" HumanMessagePromptTemplate,\n",
|
||||||
|
")\n",
|
||||||
|
"from langchain.schema import (\n",
|
||||||
|
" AIMessage,\n",
|
||||||
|
" HumanMessage,\n",
|
||||||
|
" SystemMessage\n",
|
||||||
|
")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 2,
|
||||||
|
"id": "62e0dbc3",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"chat = ChatOpenAI(temperature=0)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "bbaec18e-3684-4eef-955f-c1cec8bf765d",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"You can get chat completions by passing one or more messages to the chat model. The response will be a message. The types of messages currently supported in LangChain are `AIMessage`, `HumanMessage`, `SystemMessage`, and `ChatMessage` -- `ChatMessage` takes in an arbitrary role parameter. Most of the time, you'll just be dealing with `HumanMessage`, `AIMessage`, and `SystemMessage`"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 3,
|
||||||
|
"id": "76a6e7b0-e927-4bfb-a414-1332a4149106",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"AIMessage(content=\"J'aime programmer.\", additional_kwargs={})"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 3,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"chat([HumanMessage(content=\"Translate this sentence from English to French. I love programming.\")])"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "a62153d4-1211-411b-a493-3febfe446ae0",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"OpenAI's chat model supports multiple messages as input. See [here](https://platform.openai.com/docs/guides/chat/chat-vs-completions) for more information. Here is an example of sending a system and user message to the chat model:"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 4,
|
||||||
|
"id": "ce16ad78-8e6f-48cd-954e-98be75eb5836",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"AIMessage(content=\"J'aime programmer.\", additional_kwargs={})"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 4,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"messages = [\n",
|
||||||
|
" SystemMessage(content=\"You are a helpful assistant that translates English to French.\"),\n",
|
||||||
|
" HumanMessage(content=\"Translate this sentence from English to French. I love programming.\")\n",
|
||||||
|
"]\n",
|
||||||
|
"chat(messages)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "36dc8d7e-bd25-47ac-8c1b-60e3422603d3",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"You can go one step further and generate completions for multiple sets of messages using `generate`. This returns an `LLMResult` with an additional `message` parameter."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 5,
|
||||||
|
"id": "2b21fc52-74b6-4950-ab78-45d12c68fb4d",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"LLMResult(generations=[[ChatGeneration(text=\"J'aime programmer.\", generation_info=None, message=AIMessage(content=\"J'aime programmer.\", additional_kwargs={}))], [ChatGeneration(text=\"J'aime l'intelligence artificielle.\", generation_info=None, message=AIMessage(content=\"J'aime l'intelligence artificielle.\", additional_kwargs={}))]], llm_output={'token_usage': {'prompt_tokens': 71, 'completion_tokens': 18, 'total_tokens': 89}})"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 5,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"batch_messages = [\n",
|
||||||
|
" [\n",
|
||||||
|
" SystemMessage(content=\"You are a helpful assistant that translates English to French.\"),\n",
|
||||||
|
" HumanMessage(content=\"Translate this sentence from English to French. I love programming.\")\n",
|
||||||
|
" ],\n",
|
||||||
|
" [\n",
|
||||||
|
" SystemMessage(content=\"You are a helpful assistant that translates English to French.\"),\n",
|
||||||
|
" HumanMessage(content=\"Translate this sentence from English to French. I love artificial intelligence.\")\n",
|
||||||
|
" ],\n",
|
||||||
|
"]\n",
|
||||||
|
"result = chat.generate(batch_messages)\n",
|
||||||
|
"result"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "2960f50f",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"You can recover things like token usage from this LLMResult"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 6,
|
||||||
|
"id": "a6186bee",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"{'token_usage': {'prompt_tokens': 71,\n",
|
||||||
|
" 'completion_tokens': 18,\n",
|
||||||
|
" 'total_tokens': 89}}"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 6,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"result.llm_output"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "b10b00ef-f373-4bc3-8302-2dfc28033734",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## PromptTemplates"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "778f912a-66ea-4a5d-b3de-6c7db4baba26",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"You can make use of templating by using a `MessagePromptTemplate`. You can build a `ChatPromptTemplate` from one or more `MessagePromptTemplates`. You can use `ChatPromptTemplate`'s `format_prompt` -- this returns a `PromptValue`, which you can convert to a string or Message object, depending on whether you want to use the formatted value as input to an llm or chat model.\n",
|
||||||
|
"\n",
|
||||||
|
"For convience, there is a `from_template` method exposed on the template. If you were to use this template, this is what it would look like:"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 7,
|
||||||
|
"id": "180c5cc8",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"template=\"You are a helpful assistant that translates {input_language} to {output_language}.\"\n",
|
||||||
|
"system_message_prompt = SystemMessagePromptTemplate.from_template(template)\n",
|
||||||
|
"human_template=\"{text}\"\n",
|
||||||
|
"human_message_prompt = HumanMessagePromptTemplate.from_template(human_template)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 8,
|
||||||
|
"id": "fbb043e6",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"AIMessage(content=\"J'adore la programmation.\", additional_kwargs={})"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 8,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"chat_prompt = ChatPromptTemplate.from_messages([system_message_prompt, human_message_prompt])\n",
|
||||||
|
"\n",
|
||||||
|
"# get a chat completion from the formatted messages\n",
|
||||||
|
"chat(chat_prompt.format_prompt(input_language=\"English\", output_language=\"French\", text=\"I love programming.\").to_messages())"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "e28b98da",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"If you wanted to construct the MessagePromptTemplate more directly, you could create a PromptTemplate outside and then pass it in, eg:"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 9,
|
||||||
|
"id": "d5b1ab1c",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"prompt=PromptTemplate(\n",
|
||||||
|
" template=\"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
|
||||||
|
" input_variables=[\"input_language\", \"output_language\"],\n",
|
||||||
|
")\n",
|
||||||
|
"system_message_prompt = SystemMessagePromptTemplate(prompt=prompt)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "92af0bba",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## LLMChain\n",
|
||||||
|
"You can use the existing LLMChain in a very similar way to before - provide a prompt and a model."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 10,
|
||||||
|
"id": "f2cbfe3d",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"chain = LLMChain(llm=chat, prompt=chat_prompt)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 11,
|
||||||
|
"id": "268543b1",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"\"J'adore la programmation.\""
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 11,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"chain.run(input_language=\"English\", output_language=\"French\", text=\"I love programming.\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "eb779f3f",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Streaming\n",
|
||||||
|
"\n",
|
||||||
|
"Streaming is supported for `ChatOpenAI` through callback handling."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 10,
|
||||||
|
"id": "509181be",
|
||||||
|
"metadata": {
|
||||||
|
"tags": []
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"Verse 1:\n",
|
||||||
|
"Bubbles rising to the top\n",
|
||||||
|
"A refreshing drink that never stops\n",
|
||||||
|
"Clear and crisp, it's pure delight\n",
|
||||||
|
"A taste that's sure to excite\n",
|
||||||
|
"\n",
|
||||||
|
"Chorus:\n",
|
||||||
|
"Sparkling water, oh so fine\n",
|
||||||
|
"A drink that's always on my mind\n",
|
||||||
|
"With every sip, I feel alive\n",
|
||||||
|
"Sparkling water, you're my vibe\n",
|
||||||
|
"\n",
|
||||||
|
"Verse 2:\n",
|
||||||
|
"No sugar, no calories, just pure bliss\n",
|
||||||
|
"A drink that's hard to resist\n",
|
||||||
|
"It's the perfect way to quench my thirst\n",
|
||||||
|
"A drink that always comes first\n",
|
||||||
|
"\n",
|
||||||
|
"Chorus:\n",
|
||||||
|
"Sparkling water, oh so fine\n",
|
||||||
|
"A drink that's always on my mind\n",
|
||||||
|
"With every sip, I feel alive\n",
|
||||||
|
"Sparkling water, you're my vibe\n",
|
||||||
|
"\n",
|
||||||
|
"Bridge:\n",
|
||||||
|
"From the mountains to the sea\n",
|
||||||
|
"Sparkling water, you're the key\n",
|
||||||
|
"To a healthy life, a happy soul\n",
|
||||||
|
"A drink that makes me feel whole\n",
|
||||||
|
"\n",
|
||||||
|
"Chorus:\n",
|
||||||
|
"Sparkling water, oh so fine\n",
|
||||||
|
"A drink that's always on my mind\n",
|
||||||
|
"With every sip, I feel alive\n",
|
||||||
|
"Sparkling water, you're my vibe\n",
|
||||||
|
"\n",
|
||||||
|
"Outro:\n",
|
||||||
|
"Sparkling water, you're the one\n",
|
||||||
|
"A drink that's always so much fun\n",
|
||||||
|
"I'll never let you go, my friend\n",
|
||||||
|
"Sparkling"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"from langchain.callbacks.base import CallbackManager\n",
|
||||||
|
"from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
|
||||||
|
"chat = ChatOpenAI(streaming=True, callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), verbose=True, temperature=0)\n",
|
||||||
|
"resp = chat([HumanMessage(content=\"Write me a song about sparkling water.\")])\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "c095285d",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": []
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "Python 3 (ipykernel)",
|
||||||
|
"language": "python",
|
||||||
|
"name": "python3"
|
||||||
|
},
|
||||||
|
"language_info": {
|
||||||
|
"codemirror_mode": {
|
||||||
|
"name": "ipython",
|
||||||
|
"version": 3
|
||||||
|
},
|
||||||
|
"file_extension": ".py",
|
||||||
|
"mimetype": "text/x-python",
|
||||||
|
"name": "python",
|
||||||
|
"nbconvert_exporter": "python",
|
||||||
|
"pygments_lexer": "ipython3",
|
||||||
|
"version": "3.9.1"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 5
|
||||||
|
}
|
@ -0,0 +1,10 @@
|
|||||||
|
How-To Guides
|
||||||
|
=============
|
||||||
|
|
||||||
|
The examples here all address certain "how-to" guides for working with chat models.
|
||||||
|
|
||||||
|
.. toctree::
|
||||||
|
:maxdepth: 1
|
||||||
|
:glob:
|
||||||
|
|
||||||
|
./examples/*
|
@ -0,0 +1,29 @@
|
|||||||
|
# Key Concepts
|
||||||
|
|
||||||
|
## ChatMessage
|
||||||
|
A chat message is what we refer to as the modular unit of information.
|
||||||
|
At the moment, this consists of "content", which refers to the content of the chat message.
|
||||||
|
At the moment, most chat models are trained to predict sequences of Human <> AI messages.
|
||||||
|
This is because so far the primary interaction mode has been between a human user and a singular AI system.
|
||||||
|
|
||||||
|
At the moment, there are four different classes of Chat Messages
|
||||||
|
|
||||||
|
### HumanMessage
|
||||||
|
A HumanMessage is a ChatMessage that is sent as if from a Human's point of view.
|
||||||
|
|
||||||
|
### AIMessage
|
||||||
|
An AIMessage is a ChatMessage that is sent from the point of view of the AI system to which the Human is corresponding.
|
||||||
|
|
||||||
|
### SystemMessage
|
||||||
|
A SystemMessage is still a bit ambiguous, and so far seems to be a concept unique to OpenAI
|
||||||
|
|
||||||
|
### ChatMessage
|
||||||
|
A chat message is a generic chat message, with not only a "content" field but also a "role" field.
|
||||||
|
With this field, arbitrary roles may be assigned to a message.
|
||||||
|
|
||||||
|
## ChatGeneration
|
||||||
|
The output of a single prediction of a chat message.
|
||||||
|
Currently this is just a chat message itself (eg content and a role)
|
||||||
|
|
||||||
|
## Chat Model
|
||||||
|
A model which takes in a list of chat messages, and predicts a chat message in response.
|
@ -0,0 +1,38 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"attachments": {},
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# Blackboard\n",
|
||||||
|
"\n",
|
||||||
|
"This covers how to load data from a Blackboard Learn instance."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.document_loaders import BlackboardLoader\n",
|
||||||
|
"\n",
|
||||||
|
"loader = BlackboardLoader(\n",
|
||||||
|
" blackboard_course_url=\"https://blackboard.example.com/webapps/blackboard/execute/announcement?method=search&context=course_entry&course_id=_123456_1\",\n",
|
||||||
|
" bbrouter=\"expires:12345...\",\n",
|
||||||
|
" load_all_recursively=True,\n",
|
||||||
|
")\n",
|
||||||
|
"documents = loader.load()"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"language_info": {
|
||||||
|
"name": "python"
|
||||||
|
},
|
||||||
|
"orig_nbformat": 4
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 2
|
||||||
|
}
|
File diff suppressed because one or more lines are too long
@ -0,0 +1,32 @@
|
|||||||
|
"Team", "Payroll (millions)", "Wins"
|
||||||
|
"Nationals", 81.34, 98
|
||||||
|
"Reds", 82.20, 97
|
||||||
|
"Yankees", 197.96, 95
|
||||||
|
"Giants", 117.62, 94
|
||||||
|
"Braves", 83.31, 94
|
||||||
|
"Athletics", 55.37, 94
|
||||||
|
"Rangers", 120.51, 93
|
||||||
|
"Orioles", 81.43, 93
|
||||||
|
"Rays", 64.17, 90
|
||||||
|
"Angels", 154.49, 89
|
||||||
|
"Tigers", 132.30, 88
|
||||||
|
"Cardinals", 110.30, 88
|
||||||
|
"Dodgers", 95.14, 86
|
||||||
|
"White Sox", 96.92, 85
|
||||||
|
"Brewers", 97.65, 83
|
||||||
|
"Phillies", 174.54, 81
|
||||||
|
"Diamondbacks", 74.28, 81
|
||||||
|
"Pirates", 63.43, 79
|
||||||
|
"Padres", 55.24, 76
|
||||||
|
"Mariners", 81.97, 75
|
||||||
|
"Mets", 93.35, 74
|
||||||
|
"Blue Jays", 75.48, 73
|
||||||
|
"Royals", 60.91, 72
|
||||||
|
"Marlins", 118.07, 69
|
||||||
|
"Red Sox", 173.18, 69
|
||||||
|
"Indians", 78.43, 68
|
||||||
|
"Twins", 94.08, 66
|
||||||
|
"Rockies", 78.06, 64
|
||||||
|
"Cubs", 88.19, 61
|
||||||
|
"Astros", 60.65, 55
|
||||||
|
|
|
@ -0,0 +1,79 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "33205b12",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# Figma\n",
|
||||||
|
"\n",
|
||||||
|
"This notebook covers how to load data from the Figma REST API into a format that can be ingested into LangChain."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "90b69c94",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"import os\n",
|
||||||
|
"\n",
|
||||||
|
"from langchain.document_loaders import FigmaFileLoader"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 2,
|
||||||
|
"id": "13deb0f5",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"loader = FigmaFileLoader(\n",
|
||||||
|
" os.environ.get('ACCESS_TOKEN'),\n",
|
||||||
|
" os.environ.get('NODE_IDS'),\n",
|
||||||
|
" os.environ.get('FILE_KEY')\n",
|
||||||
|
")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "9ccc1e2f",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"loader.load()"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "3e64cac2",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": []
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "Python 3 (ipykernel)",
|
||||||
|
"language": "python",
|
||||||
|
"name": "python3"
|
||||||
|
},
|
||||||
|
"language_info": {
|
||||||
|
"codemirror_mode": {
|
||||||
|
"name": "ipython",
|
||||||
|
"version": 3
|
||||||
|
},
|
||||||
|
"file_extension": ".py",
|
||||||
|
"mimetype": "text/x-python",
|
||||||
|
"name": "python",
|
||||||
|
"nbconvert_exporter": "python",
|
||||||
|
"pygments_lexer": "ipython3",
|
||||||
|
"version": "3.9.1"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 5
|
||||||
|
}
|
File diff suppressed because one or more lines are too long
@ -1,145 +0,0 @@
|
|||||||
{
|
|
||||||
"cells": [
|
|
||||||
{
|
|
||||||
"cell_type": "markdown",
|
|
||||||
"id": "34c90eed",
|
|
||||||
"metadata": {},
|
|
||||||
"source": [
|
|
||||||
"# Microsoft Word\n",
|
|
||||||
"\n",
|
|
||||||
"This notebook shows how to load text from Microsoft word documents."
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 1,
|
|
||||||
"id": "28ded768",
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [],
|
|
||||||
"source": [
|
|
||||||
"from langchain.document_loaders import UnstructuredDocxLoader"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 2,
|
|
||||||
"id": "f1f26035",
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [],
|
|
||||||
"source": [
|
|
||||||
"loader = UnstructuredDocxLoader('example_data/fake.docx')"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 3,
|
|
||||||
"id": "2c87dde9",
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [],
|
|
||||||
"source": [
|
|
||||||
"data = loader.load()"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 4,
|
|
||||||
"id": "0e4a884c",
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [
|
|
||||||
{
|
|
||||||
"data": {
|
|
||||||
"text/plain": [
|
|
||||||
"[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': 'example_data/fake.docx'}, lookup_index=0)]"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
"execution_count": 4,
|
|
||||||
"metadata": {},
|
|
||||||
"output_type": "execute_result"
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"source": [
|
|
||||||
"data"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "markdown",
|
|
||||||
"id": "5d1472e9",
|
|
||||||
"metadata": {},
|
|
||||||
"source": [
|
|
||||||
"## Retain Elements\n",
|
|
||||||
"\n",
|
|
||||||
"Under the hood, Unstructured creates different \"elements\" for different chunks of text. By default we combine those together, but you can easily keep that separation by specifying `mode=\"elements\"`."
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 2,
|
|
||||||
"id": "93abf60b",
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [],
|
|
||||||
"source": [
|
|
||||||
"loader = UnstructuredDocxLoader('example_data/fake.docx', mode=\"elements\")"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 3,
|
|
||||||
"id": "c35cdbcc",
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [],
|
|
||||||
"source": [
|
|
||||||
"data = loader.load()"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 4,
|
|
||||||
"id": "fae2d730",
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [
|
|
||||||
{
|
|
||||||
"data": {
|
|
||||||
"text/plain": [
|
|
||||||
"[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': 'example_data/fake.docx'}, lookup_index=0)]"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
"execution_count": 4,
|
|
||||||
"metadata": {},
|
|
||||||
"output_type": "execute_result"
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"source": [
|
|
||||||
"data"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": null,
|
|
||||||
"id": "961a7b1d",
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [],
|
|
||||||
"source": []
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"metadata": {
|
|
||||||
"kernelspec": {
|
|
||||||
"display_name": "Python 3 (ipykernel)",
|
|
||||||
"language": "python",
|
|
||||||
"name": "python3"
|
|
||||||
},
|
|
||||||
"language_info": {
|
|
||||||
"codemirror_mode": {
|
|
||||||
"name": "ipython",
|
|
||||||
"version": 3
|
|
||||||
},
|
|
||||||
"file_extension": ".py",
|
|
||||||
"mimetype": "text/x-python",
|
|
||||||
"name": "python",
|
|
||||||
"nbconvert_exporter": "python",
|
|
||||||
"pygments_lexer": "ipython3",
|
|
||||||
"version": "3.9.1"
|
|
||||||
}
|
|
||||||
},
|
|
||||||
"nbformat": 4,
|
|
||||||
"nbformat_minor": 5
|
|
||||||
}
|
|
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue