bump version to 141 (#2950)

Add SVM retriever class, based on
https://github.com/karpathy/randomfun/blob/master/knn_vs_svm.ipynb.

Testing still WIP, but the logic is correct (I have a local
implementation outside of Langchain working).

---------

Co-authored-by: Lance Martin <122662504+PineappleExpress808@users.noreply.github.com>
Co-authored-by: rlm <31treehaus@31s-MacBook-Pro.local>

README.md

@@ -2,7 +2,7 @@
 
 ⚡ Building applications with LLMs through composability ⚡
 
-[![lint](https://github.com/hwchase17/langchain/actions/workflows/lint.yml/badge.svg)](https://github.com/hwchase17/langchain/actions/workflows/lint.yml) [![test](https://github.com/hwchase17/langchain/actions/workflows/test.yml/badge.svg)](https://github.com/hwchase17/langchain/actions/workflows/test.yml) [![linkcheck](https://github.com/hwchase17/langchain/actions/workflows/linkcheck.yml/badge.svg)](https://github.com/hwchase17/langchain/actions/workflows/linkcheck.yml) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai) [![](https://dcbadge.vercel.app/api/server/6adMQxSpJS?compact=true&style=flat)](https://discord.gg/6adMQxSpJS)
+[![lint](https://github.com/hwchase17/langchain/actions/workflows/lint.yml/badge.svg)](https://github.com/hwchase17/langchain/actions/workflows/lint.yml) [![test](https://github.com/hwchase17/langchain/actions/workflows/test.yml/badge.svg)](https://github.com/hwchase17/langchain/actions/workflows/test.yml) [![linkcheck](https://github.com/hwchase17/langchain/actions/workflows/linkcheck.yml/badge.svg)](https://github.com/hwchase17/langchain/actions/workflows/linkcheck.yml) [![Downloads](https://static.pepy.tech/badge/langchain/month)](https://pepy.tech/project/langchain) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai) [![](https://dcbadge.vercel.app/api/server/6adMQxSpJS?compact=true&style=flat)](https://discord.gg/6adMQxSpJS)
 
 **Production Support:** As you move your LangChains into production, we'd love to offer more comprehensive support.
 Please fill out [this form](https://forms.gle/57d8AmXBYp8PP8tZA) and we'll set up a dedicated support Slack channel.
@@ -10,6 +10,8 @@ Please fill out [this form](https://forms.gle/57d8AmXBYp8PP8tZA) and we'll set u
 ## Quick Install
 
 `pip install langchain`
+or
+`conda install langchain -c conda-forge`
 
 ## 🤔 What is this?
 

docs/_static/css/custom.css

@@ -11,3 +11,7 @@ pre {
     max-width: 2560px !important;
   }
 }
+
+#my-component-root *, #headlessui-portal-root * {
+  z-index: 1000000000000;
+}

docs/_static/js/mendablesearch.js

@@ -0,0 +1,58 @@
+document.addEventListener('DOMContentLoaded', () => {
+  // Load the external dependencies
+  function loadScript(src, onLoadCallback) {
+    const script = document.createElement('script');
+    script.src = src;
+    script.onload = onLoadCallback;
+    document.head.appendChild(script);
+  }
+
+  function createRootElement() {
+    const rootElement = document.createElement('div');
+    rootElement.id = 'my-component-root';
+    document.body.appendChild(rootElement);
+    return rootElement;
+  }
+
+  
+
+  function initializeMendable() {
+    const rootElement = createRootElement();
+    const { MendableFloatingButton } = Mendable;
+    
+
+    const iconSpan1 = React.createElement('span', {
+    }, '🦜');
+
+    const iconSpan2 = React.createElement('span', {
+    }, '🔗');
+
+    const icon = React.createElement('p', {
+      style: { color: '#ffffff', fontSize: '22px',width: '48px', height: '48px', margin: '0px', padding: '0px', display: 'flex', alignItems: 'center', justifyContent: 'center', textAlign: 'center' },
+    }, [iconSpan1, iconSpan2]);
+
+    
+    
+
+    const mendableFloatingButton = React.createElement(
+      MendableFloatingButton,
+      {
+        style: { darkMode: false, accentColor: '#010810' },
+        floatingButtonStyle: { color: '#ffffff', backgroundColor: '#010810' },
+        anon_key: '82842b36-3ea6-49b2-9fb8-52cfc4bde6bf', // Mendable Search Public ANON key, ok to be public
+        messageSettings: {
+          openSourcesInNewTab: false,
+        },
+        icon: icon,
+      }
+    );
+
+    ReactDOM.render(mendableFloatingButton, rootElement);
+  }
+
+  loadScript('https://unpkg.com/react@17/umd/react.production.min.js', () => {
+    loadScript('https://unpkg.com/react-dom@17/umd/react-dom.production.min.js', () => {
+      loadScript('https://unpkg.com/@mendable/search@0.0.83/dist/umd/mendable.min.js', initializeMendable);
+    });
+  });
+});

docs/conf.py

@@ -103,5 +103,10 @@ html_static_path = ["_static"]
 html_css_files = [
     "css/custom.css",
 ]
+
+html_js_files = [
+    "js/mendablesearch.js",
+]
+
 nb_execution_mode = "off"
 myst_enable_extensions = ["colon_fence"]

docs/deployments.md

@@ -33,10 +33,19 @@ It implements a Question Answering app and contains instructions for deploying t
 
 A minimal example on how to run LangChain on Vercel using Flask.
 
+## [Digitalocean App Platform](https://github.com/homanp/digitalocean-langchain)
+
+A minimal example on how to deploy LangChain to DigitalOcean App Platform.
 
 ## [SteamShip](https://github.com/steamship-core/steamship-langchain/)
+
 This repository contains LangChain adapters for Steamship, enabling LangChain developers to rapidly deploy their apps on Steamship.
 This includes: production ready endpoints, horizontal scaling across dependencies, persistant storage of app state, multi-tenancy support, etc.
 
 ## [Langchain-serve](https://github.com/jina-ai/langchain-serve)
+
 This repository allows users to serve local chains and agents as RESTful, gRPC, or Websocket APIs thanks to [Jina](https://docs.jina.ai/). Deploy your chains & agents with ease and enjoy independent scaling, serverless and autoscaling APIs, as well as a Streamlit playground on Jina AI Cloud.
+
+## [BentoML](https://github.com/ssheng/BentoChain)
+
+This repository provides an example of how to deploy a LangChain application with [BentoML](https://github.com/bentoml/BentoML). BentoML is a framework that enables the containerization of machine learning applications as standard OCI images. BentoML also allows for the automatic generation of OpenAPI and gRPC endpoints. With BentoML, you can integrate models from all popular ML frameworks and deploy them as microservices running on the most optimal hardware and scaling independently.

docs/ecosystem/clearml_tracking.ipynb

@@ -19,7 +19,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Getting API Credentials\n",
+    "## Getting API Credentials\n",
     "\n",
     "We'll be using quite some APIs in this notebook, here is a list and where to get them:\n",
     "\n",
@@ -47,7 +47,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Setting Up"
+    "## Setting Up"
    ]
   },
   {
@@ -103,7 +103,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Scenario 1: Just an LLM\n",
+    "## Scenario 1: Just an LLM\n",
     "\n",
     "First, let's just run a single LLM a few times and capture the resulting prompt-answer conversation in ClearML"
    ]
@@ -361,7 +361,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Scenario 2: Creating a agent with tools\n",
+    "## Scenario 2: Creating an agent with tools\n",
     "\n",
     "To show a more advanced workflow, let's create an agent with access to tools. The way ClearML tracks the results is not different though, only the table will look slightly different as there are other types of actions taken when compared to the earlier, simpler example.\n",
     "\n",
@@ -542,7 +542,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Tips and Next Steps\n",
+    "## Tips and Next Steps\n",
     "\n",
     "- Make sure you always use a unique `name` argument for the `clearml_callback.flush_tracker` function. If not, the model parameters used for a run will override the previous run!\n",
     "\n",

docs/ecosystem/comet_tracking.ipynb

@@ -0,0 +1,352 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Comet"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "![](https://user-images.githubusercontent.com/7529846/230328046-a8b18c51-12e3-4617-9b39-97614a571a2d.png)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "In this guide we will demonstrate how to track your Langchain Experiments, Evaluation Metrics, and LLM Sessions with [Comet](https://www.comet.com/site/?utm_source=langchain&utm_medium=referral&utm_campaign=comet_notebook).  \n",
+    "\n",
+    "<a target=\"_blank\" href=\"https://colab.research.google.com/github/hwchase17/langchain/blob/master/docs/ecosystem/comet_tracking.ipynb\">\n",
+    "  <img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/>\n",
+    "</a>\n",
+    "\n",
+    "**Example Project:** [Comet with LangChain](https://www.comet.com/examples/comet-example-langchain/view/b5ZThK6OFdhKWVSP3fDfRtrNF/panels?utm_source=langchain&utm_medium=referral&utm_campaign=comet_notebook)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<img width=\"1280\" alt=\"comet-langchain\" src=\"https://user-images.githubusercontent.com/7529846/230326720-a9711435-9c6f-4edb-a707-94b67271ab25.png\">\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Install Comet and Dependencies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install comet_ml langchain openai google-search-results spacy textstat pandas\n",
+    "\n",
+    "import sys\n",
+    "!{sys.executable} -m spacy download en_core_web_sm"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Initialize Comet and Set your Credentials"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You can grab your [Comet API Key here](https://www.comet.com/signup?utm_source=langchain&utm_medium=referral&utm_campaign=comet_notebook) or click the link after intializing Comet"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import comet_ml\n",
+    "\n",
+    "comet_ml.init(project_name=\"comet-example-langchain\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Set OpenAI and SerpAPI credentials"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You will need an [OpenAI API Key](https://platform.openai.com/account/api-keys) and a [SerpAPI API Key](https://serpapi.com/dashboard) to run the following examples"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"...\"\n",
+    "#os.environ[\"OPENAI_ORGANIZATION\"] = \"...\"\n",
+    "os.environ[\"SERPAPI_API_KEY\"] = \"...\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Scenario 1: Using just an LLM"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from datetime import datetime\n",
+    "\n",
+    "from langchain.callbacks import CometCallbackHandler, StdOutCallbackHandler\n",
+    "from langchain.callbacks.base import CallbackManager\n",
+    "from langchain.llms import OpenAI\n",
+    "\n",
+    "comet_callback = CometCallbackHandler(\n",
+    "    project_name=\"comet-example-langchain\",\n",
+    "    complexity_metrics=True,\n",
+    "    stream_logs=True,\n",
+    "    tags=[\"llm\"],\n",
+    "    visualizations=[\"dep\"],\n",
+    ")\n",
+    "manager = CallbackManager([StdOutCallbackHandler(), comet_callback])\n",
+    "llm = OpenAI(temperature=0.9, callback_manager=manager, verbose=True)\n",
+    "\n",
+    "llm_result = llm.generate([\"Tell me a joke\", \"Tell me a poem\", \"Tell me a fact\"] * 3)\n",
+    "print(\"LLM result\", llm_result)\n",
+    "comet_callback.flush_tracker(llm, finish=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Scenario 2: Using an LLM in a Chain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.callbacks import CometCallbackHandler, StdOutCallbackHandler\n",
+    "from langchain.callbacks.base import CallbackManager\n",
+    "from langchain.chains import LLMChain\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.prompts import PromptTemplate\n",
+    "\n",
+    "comet_callback = CometCallbackHandler(\n",
+    "    complexity_metrics=True,\n",
+    "    project_name=\"comet-example-langchain\",\n",
+    "    stream_logs=True,\n",
+    "    tags=[\"synopsis-chain\"],\n",
+    ")\n",
+    "manager = CallbackManager([StdOutCallbackHandler(), comet_callback])\n",
+    "\n",
+    "llm = OpenAI(temperature=0.9, callback_manager=manager, verbose=True)\n",
+    "\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 = [{\"title\": \"Documentary about Bigfoot in Paris\"}]\n",
+    "print(synopsis_chain.apply(test_prompts))\n",
+    "comet_callback.flush_tracker(synopsis_chain, finish=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Scenario 3: Using An Agent with Tools "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.agents import initialize_agent, load_tools\n",
+    "from langchain.callbacks import CometCallbackHandler, StdOutCallbackHandler\n",
+    "from langchain.callbacks.base import CallbackManager\n",
+    "from langchain.llms import OpenAI\n",
+    "\n",
+    "comet_callback = CometCallbackHandler(\n",
+    "    project_name=\"comet-example-langchain\",\n",
+    "    complexity_metrics=True,\n",
+    "    stream_logs=True,\n",
+    "    tags=[\"agent\"],\n",
+    ")\n",
+    "manager = CallbackManager([StdOutCallbackHandler(), comet_callback])\n",
+    "llm = OpenAI(temperature=0.9, callback_manager=manager, verbose=True)\n",
+    "\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",
+    "comet_callback.flush_tracker(agent, finish=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Scenario 4: Using Custom Evaluation Metrics"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The `CometCallbackManager` also allows you to define and use Custom Evaluation Metrics to assess generated outputs from your model. Let's take a look at how this works. \n",
+    "\n",
+    "\n",
+    "In the snippet below, we will use the [ROUGE](https://huggingface.co/spaces/evaluate-metric/rouge) metric to evaluate the quality of a generated summary of an input prompt. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install rouge-score"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from rouge_score import rouge_scorer\n",
+    "\n",
+    "from langchain.callbacks import CometCallbackHandler, StdOutCallbackHandler\n",
+    "from langchain.callbacks.base import CallbackManager\n",
+    "from langchain.chains import LLMChain\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.prompts import PromptTemplate\n",
+    "\n",
+    "\n",
+    "class Rouge:\n",
+    "    def __init__(self, reference):\n",
+    "        self.reference = reference\n",
+    "        self.scorer = rouge_scorer.RougeScorer([\"rougeLsum\"], use_stemmer=True)\n",
+    "\n",
+    "    def compute_metric(self, generation, prompt_idx, gen_idx):\n",
+    "        prediction = generation.text\n",
+    "        results = self.scorer.score(target=self.reference, prediction=prediction)\n",
+    "\n",
+    "        return {\n",
+    "            \"rougeLsum_score\": results[\"rougeLsum\"].fmeasure,\n",
+    "            \"reference\": self.reference,\n",
+    "        }\n",
+    "\n",
+    "\n",
+    "reference = \"\"\"\n",
+    "The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building.\n",
+    "It was the first structure to reach a height of 300 metres.\n",
+    "\n",
+    "It is now taller than the Chrysler Building in New York City by 5.2 metres (17 ft)\n",
+    "Excluding transmitters, the Eiffel Tower is the second tallest free-standing structure in France .\n",
+    "\"\"\"\n",
+    "rouge_score = Rouge(reference=reference)\n",
+    "\n",
+    "template = \"\"\"Given the following article, it is your job to write a summary.\n",
+    "Article:\n",
+    "{article}\n",
+    "Summary: This is the summary for the above article:\"\"\"\n",
+    "prompt_template = PromptTemplate(input_variables=[\"article\"], template=template)\n",
+    "\n",
+    "comet_callback = CometCallbackHandler(\n",
+    "    project_name=\"comet-example-langchain\",\n",
+    "    complexity_metrics=False,\n",
+    "    stream_logs=True,\n",
+    "    tags=[\"custom_metrics\"],\n",
+    "    custom_metrics=rouge_score.compute_metric,\n",
+    ")\n",
+    "manager = CallbackManager([StdOutCallbackHandler(), comet_callback])\n",
+    "llm = OpenAI(temperature=0.9, callback_manager=manager, verbose=True)\n",
+    "\n",
+    "synopsis_chain = LLMChain(llm=llm, prompt=prompt_template, callback_manager=manager)\n",
+    "\n",
+    "test_prompts = [\n",
+    "    {\n",
+    "        \"article\": \"\"\"\n",
+    "                 The tower is 324 metres (1,063 ft) tall, about the same height as\n",
+    "                 an 81-storey building, and the tallest structure in Paris. Its base is square,\n",
+    "                 measuring 125 metres (410 ft) on each side.\n",
+    "                 During its construction, the Eiffel Tower surpassed the\n",
+    "                 Washington Monument to become the tallest man-made structure in the world,\n",
+    "                 a title it held for 41 years until the Chrysler Building\n",
+    "                 in New York City was finished in 1930.\n",
+    "\n",
+    "                 It was the first structure to reach a height of 300 metres.\n",
+    "                 Due to the addition of a broadcasting aerial at the top of the tower in 1957,\n",
+    "                 it is now taller than the Chrysler Building by 5.2 metres (17 ft).\n",
+    "\n",
+    "                 Excluding transmitters, the Eiffel Tower is the second tallest\n",
+    "                 free-standing structure in France after the Millau Viaduct.\n",
+    "                 \"\"\"\n",
+    "    }\n",
+    "]\n",
+    "print(synopsis_chain.apply(test_prompts))\n",
+    "comet_callback.flush_tracker(synopsis_chain, finish=True)"
+   ]
+  }
+ ],
+ "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": "3.9.15"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/ecosystem/databerry.md

@@ -0,0 +1,25 @@
+# Databerry
+
+This page covers how to use the [Databerry](https://databerry.ai) within LangChain.
+
+## What is Databerry?
+
+Databerry is an [open source](https://github.com/gmpetrov/databerry) document retrievial platform that helps to connect your personal data with Large Language Models.
+
+![Databerry](../_static/DataberryDashboard.png)
+
+## Quick start
+
+Retrieving documents stored in Databerry from LangChain is very easy!
+
+```python
+from langchain.retrievers import DataberryRetriever
+
+retriever = DataberryRetriever(
+    datastore_url="https://api.databerry.ai/query/clg1xg2h80000l708dymr0fxc",
+    # api_key="DATABERRY_API_KEY", # optional if datastore is public
+    # top_k=10 # optional
+)
+
+docs = retriever.get_relevant_documents("What's Databerry?")
+```

docs/ecosystem/gpt4all.md

@@ -1,21 +1,21 @@
 # GPT4All
 
-This page covers how to use the `GPT4All` wrapper within LangChain.
-It is broken into two parts: installation and setup, and then usage with an example.
+This page covers how to use the `GPT4All` wrapper within LangChain. The tutorial is divided into two parts: installation and setup, followed by usage with an example.
 
 ## Installation and Setup
 - Install the Python package with `pip install pyllamacpp`
-- Download a [GPT4All model](https://github.com/nomic-ai/gpt4all) and place it in your desired directory
+- Download a [GPT4All model](https://github.com/nomic-ai/pyllamacpp#supported-model) and place it in your desired directory
 
 ## Usage
 
 ### GPT4All
 
 To use the GPT4All wrapper, you need to provide the path to the pre-trained model file and the model's configuration.
+
 ```python
 from langchain.llms import GPT4All
 
-# Instantiate the model
+# Instantiate the model. Callbacks support token-wise streaming
 model = GPT4All(model="./models/gpt4all-model.bin", n_ctx=512, n_threads=8)
 
 # Generate text
@@ -24,14 +24,24 @@ response = model("Once upon a time, ")
 
 You can also customize the generation parameters, such as n_predict, temp, top_p, top_k, and others.
 
-Example:
+To stream the model's predictions, add in a CallbackManager.
 
 ```python
-model = GPT4All(model="./models/gpt4all-model.bin", n_predict=55, temp=0)
-response = model("Once upon a time, ")
+from langchain.llms import GPT4All
+from langchain.callbacks.base import CallbackManager
+from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
+# There are many CallbackHandlers supported, such as
+# from langchain.callbacks.streamlit import StreamlitCallbackHandler
+
+callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
+model = GPT4All(model="./models/gpt4all-model.bin", n_ctx=512, n_threads=8, callback_handler=callback_handler, verbose=True)
+
+# Generate text. Tokens are streamed through the callback manager.
+model("Once upon a time, ")
 ```
+
 ## Model File
 
-You can find links to model file downloads at the [GPT4all](https://github.com/nomic-ai/gpt4all) repository. They will need to be converted to `ggml` format to work, as specified in the [pyllamacpp](https://github.com/nomic-ai/pyllamacpp) repository.
+You can find links to model file downloads in the [pyllamacpp](https://github.com/nomic-ai/pyllamacpp) repository.
 
-For a more detailed walkthrough of this, see [this notebook](../modules/models/llms/integrations/gpt4all.ipynb)
+For a more detailed walkthrough of this, see [this notebook](../modules/models/llms/integrations/gpt4all.ipynb)

docs/ecosystem/graphsignal.md

@@ -1,6 +1,6 @@
 # Graphsignal
 
-This page covers how to use the Graphsignal ecosystem to trace and monitor LangChain.
+This page covers how to use [Graphsignal](https://app.graphsignal.com) to trace and monitor LangChain. Graphsignal enables full visibility into your application. It provides latency breakdowns by chains and tools, exceptions with full context, data monitoring, compute/GPU utilization, OpenAI cost analytics, and more.
 
 ## Installation and Setup
 
@@ -10,7 +10,7 @@ This page covers how to use the Graphsignal ecosystem to trace and monitor LangC
 
 ## Tracing and Monitoring
 
-Graphsignal automatically instruments and starts tracing and monitoring chains. Traces, metrics and errors are then available in your [Graphsignal dashboard](https://app.graphsignal.com/). No prompts or other sensitive data are sent to Graphsignal cloud, only statistics and metadata.
+Graphsignal automatically instruments and starts tracing and monitoring chains. Traces and metrics are then available in your [Graphsignal dashboards](https://app.graphsignal.com).
 
 Initialize the tracer by providing a deployment name:
 
@@ -20,7 +20,13 @@ import graphsignal
 graphsignal.configure(deployment='my-langchain-app-prod')
 ```
 
-In order to trace full runs and see a breakdown by chains and tools, you can wrap the calling routine or use a decorator:
+To additionally trace any function or code, you can use a decorator or a context manager:
+
+```python
+@graphsignal.trace_function
+def handle_request():    
+    chain.run("some initial text")
+```
 
 ```python
 with graphsignal.start_trace('my-chain'):

docs/ecosystem/zilliz.md

@@ -0,0 +1,21 @@
+# Zilliz
+
+This page covers how to use the Zilliz Cloud ecosystem within LangChain.
+Zilliz uses the Milvus integration. 
+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 Zilliz 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/vectorstores/examples/zilliz.ipynb)

docs/gallery.rst

@@ -1,5 +1,5 @@
 LangChain Gallery
-=============
+=================
 
 Lots of people have built some pretty awesome stuff with LangChain.
 This is a collection of our favorites.
@@ -223,7 +223,7 @@ Open Source
     Answer questions about the documentation of any project    
 
 Misc. Colab Notebooks
-~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~~~~~~~~~
 
 .. panels::
     :body: text-center

docs/getting_started/getting_started.md

@@ -9,6 +9,8 @@ To get started, install LangChain with the following command:
 
 ```bash
 pip install langchain
+# or
+conda install langchain -c conda-forge
 ```
 
 

docs/index.rst

@@ -92,6 +92,7 @@ The above modules can be used in a variety of ways. LangChain also provides guid
    ./use_cases/question_answering.md
    ./use_cases/chatbots.md
    ./use_cases/tabular.rst
+   ./use_cases/code.md
    ./use_cases/apis.md
    ./use_cases/summarization.md
    ./use_cases/extraction.md

docs/modules/agents/agents/custom_agent.ipynb

@@ -77,7 +77,7 @@
     "        Returns:\n",
     "            Action specifying what tool to use.\n",
     "        \"\"\"\n",
-    "        return AgentAction(tool=\"Search\", tool_input=\"foo\", log=\"\")\n",
+    "        return AgentAction(tool=\"Search\", tool_input=kwargs[\"input\"], log=\"\")\n",
     "\n",
     "    async def aplan(\n",
     "        self, intermediate_steps: List[Tuple[AgentAction, str]], **kwargs: Any\n",
@@ -92,7 +92,7 @@
     "        Returns:\n",
     "            Action specifying what tool to use.\n",
     "        \"\"\"\n",
-    "        return AgentAction(tool=\"Search\", tool_input=\"foo\", log=\"\")"
+    "        return AgentAction(tool=\"Search\", tool_input=kwargs[\"input\"], log=\"\")"
    ]
   },
   {

docs/modules/agents/agents/custom_llm_agent.ipynb

@@ -42,7 +42,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 1,
    "id": "9af9734e",
    "metadata": {},
    "outputs": [],
@@ -67,7 +67,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 2,
    "id": "becda2a1",
    "metadata": {},
    "outputs": [],
@@ -99,7 +99,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 3,
    "id": "339b1bb8",
    "metadata": {},
    "outputs": [],
@@ -128,7 +128,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 4,
    "id": "fd969d31",
    "metadata": {},
    "outputs": [],
@@ -159,7 +159,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 5,
    "id": "798ef9fb",
    "metadata": {},
    "outputs": [],
@@ -187,7 +187,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 6,
    "id": "7c6fe0d3",
    "metadata": {},
    "outputs": [],
@@ -216,7 +216,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 7,
    "id": "d278706a",
    "metadata": {},
    "outputs": [],
@@ -236,7 +236,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 8,
    "id": "f9d4c374",
    "metadata": {},
    "outputs": [],
@@ -268,7 +268,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 9,
    "id": "9b1cc2a2",
    "metadata": {},
    "outputs": [],
@@ -279,7 +279,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 10,
    "id": "e4f5092f",
    "metadata": {},
    "outputs": [],
@@ -305,7 +305,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 11,
    "id": "490604e9",
    "metadata": {},
    "outputs": [],
@@ -315,7 +315,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 12,
    "id": "653b1617",
    "metadata": {},
    "outputs": [
@@ -326,11 +326,12 @@
       "\n",
       "\n",
       "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mAction: Search\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to find out the population of Canada in 2023\n",
+      "Action: Search\n",
       "Action Input: Population of Canada in 2023\u001b[0m\n",
       "\n",
-      "Observation:\u001b[36;1m\u001b[1;3m38,648,380\u001b[0m\u001b[32;1m\u001b[1;3m That's a lot of people!\n",
-      "Final Answer: Arrr, there be 38,648,380 people livin' in Canada come 2023!\u001b[0m\n",
+      "Observation:\u001b[36;1m\u001b[1;3mThe current population of Canada is 38,658,314 as of Wednesday, April 12, 2023, based on Worldometer elaboration of the latest United Nations data.\u001b[0m\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: Arrr, there be 38,658,314 people livin' in Canada as of 2023!\u001b[0m\n",
       "\n",
       "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
@@ -338,10 +339,165 @@
     {
      "data": {
       "text/plain": [
-       "\"Arrr, there be 38,648,380 people livin' in Canada come 2023!\""
+       "\"Arrr, there be 38,658,314 people livin' in Canada as of 2023!\""
       ]
      },
-     "execution_count": 27,
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent_executor.run(\"How many people live in canada as of 2023?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d5b4a078",
+   "metadata": {},
+   "source": [
+    "## Adding Memory\n",
+    "\n",
+    "If you want to add memory to the agent, you'll need to:\n",
+    "\n",
+    "1. Add a place in the custom prompt for the chat_history\n",
+    "2. Add a memory object to the agent executor."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "94fffda1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Set up the base template\n",
+    "template_with_history = \"\"\"Answer the following questions as best you can, but speaking as a pirate might speak. You have access to the following tools:\n",
+    "\n",
+    "{tools}\n",
+    "\n",
+    "Use the following format:\n",
+    "\n",
+    "Question: the input question you must answer\n",
+    "Thought: you should always think about what to do\n",
+    "Action: the action to take, should be one of [{tool_names}]\n",
+    "Action Input: the input to the action\n",
+    "Observation: the result of the action\n",
+    "... (this Thought/Action/Action Input/Observation can repeat N times)\n",
+    "Thought: I now know the final answer\n",
+    "Final Answer: the final answer to the original input question\n",
+    "\n",
+    "Begin! Remember to speak as a pirate when giving your final answer. Use lots of \"Arg\"s\n",
+    "\n",
+    "Previous conversation history:\n",
+    "{history}\n",
+    "\n",
+    "New question: {input}\n",
+    "{agent_scratchpad}\"\"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "id": "f58488d7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompt_with_history = CustomPromptTemplate(\n",
+    "    template=template_with_history,\n",
+    "    tools=tools,\n",
+    "    # This omits the `agent_scratchpad`, `tools`, and `tool_names` variables because those are generated dynamically\n",
+    "    # This includes the `intermediate_steps` variable because that is needed\n",
+    "    input_variables=[\"input\", \"intermediate_steps\", \"history\"]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "d28d4b5a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm_chain = LLMChain(llm=llm, prompt=prompt_with_history)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "id": "3e37b32a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tool_names = [tool.name for tool in tools]\n",
+    "agent = LLMSingleActionAgent(\n",
+    "    llm_chain=llm_chain, \n",
+    "    output_parser=output_parser,\n",
+    "    stop=[\"\\nObservation:\"], \n",
+    "    allowed_tools=tool_names\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "97ea1bce",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.memory import ConversationBufferWindowMemory"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "id": "b5ad69ce",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "memory=ConversationBufferWindowMemory(k=2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "id": "b7b5c9b1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agent_executor = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True, memory=memory)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "id": "5ec4c39b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to find out the population of Canada in 2023\n",
+      "Action: Search\n",
+      "Action Input: Population of Canada in 2023\u001b[0m\n",
+      "\n",
+      "Observation:\u001b[36;1m\u001b[1;3mThe current population of Canada is 38,658,314 as of Wednesday, April 12, 2023, based on Worldometer elaboration of the latest United Nations data.\u001b[0m\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: Arrr, there be 38,658,314 people livin' in Canada as of 2023!\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\"Arrr, there be 38,658,314 people livin' in Canada as of 2023!\""
+      ]
+     },
+     "execution_count": 44,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -350,10 +506,48 @@
     "agent_executor.run(\"How many people live in canada as of 2023?\")"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "id": "b2ba45bb",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to find out how many people live in Mexico.\n",
+      "Action: Search\n",
+      "Action Input: How many people live in Mexico as of 2023?\u001b[0m\n",
+      "\n",
+      "Observation:\u001b[36;1m\u001b[1;3mThe current population of Mexico is 132,679,922 as of Tuesday, April 11, 2023, based on Worldometer elaboration of the latest United Nations data. Mexico 2020 ...\u001b[0m\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: Arrr, there be 132,679,922 people livin' in Mexico as of 2023!\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\"Arrr, there be 132,679,922 people livin' in Mexico as of 2023!\""
+      ]
+     },
+     "execution_count": 45,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent_executor.run(\"how about in mexico?\")"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "adefb4c2",
+   "id": "bd820a7a",
    "metadata": {},
    "outputs": [],
    "source": []

docs/modules/agents/tools/examples/chatgpt_plugins.ipynb

@@ -80,8 +80,8 @@
     }
    ],
    "source": [
-    "llm = ChatOpenAI(temperature=0,)\n",
-    "tools = load_tools([\"requests\"] )\n",
+    "llm = ChatOpenAI(temperature=0)\n",
+    "tools = load_tools([\"requests_all\"] )\n",
     "tools += [tool]\n",
     "\n",
     "agent_chain = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)\n",

docs/modules/agents/tools/examples/google_search.ipynb

@@ -9,7 +9,7 @@
     "\n",
     "This notebook goes over how to use the google search component.\n",
     "\n",
-    "First, you need to set up the proper API keys and environment variables. To set it up, follow the instructions found [here](https://stackoverflow.com/questions/37083058/programmatically-searching-google-in-python-using-custom-search).\n",
+    "First, you need to set up the proper API keys and environment variables. To set it up, create the GOOGLE_API_KEY in the Google Cloud credential console (https://console.cloud.google.com/apis/credentials) and a GOOGLE_CSE_ID using the Programmable Search Enginge (https://programmablesearchengine.google.com/controlpanel/create). Next, it is good to follow the instructions found [here](https://stackoverflow.com/questions/37083058/programmatically-searching-google-in-python-using-custom-search).\n",
     "\n",
     "Then we will need to set some environment variables."
    ]

docs/modules/callbacks/getting_started.ipynb

@@ -0,0 +1,388 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "23234b50-e6c6-4c87-9f97-259c15f36894",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "# Callbacks"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "29dd6333-307c-43df-b848-65001c01733b",
+   "metadata": {},
+   "source": [
+    "LangChain provides a callback system that allows you to hook into the various stages of your LLM application. This is useful for logging, [monitoring](https://python.langchain.com/en/latest/tracing.html), [streaming](https://python.langchain.com/en/latest/modules/models/llms/examples/streaming_llm.html), and other tasks.\n",
+    "\n",
+    "You can subscribe to these events by using the `callback_manager` argument available throughout the API. A `CallbackManager` is an object that manages a list of `CallbackHandlers`. The `CallbackManager` will call the appropriate method on each handler when the event is triggered."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fdb72e8d-a02a-474d-96bf-f5759432afc8",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "```python\n",
+    "class CallbackManager(BaseCallbackHandler):\n",
+    "    \"\"\"Base callback manager that can be used to handle callbacks from LangChain.\"\"\"\n",
+    "\n",
+    "    def add_handler(self, callback: BaseCallbackHandler) -> None:\n",
+    "        \"\"\"Add a handler to the callback manager.\"\"\"\n",
+    "\n",
+    "    def remove_handler(self, handler: BaseCallbackHandler) -> None:\n",
+    "        \"\"\"Remove a handler from the callback manager.\"\"\"\n",
+    "\n",
+    "    def set_handler(self, handler: BaseCallbackHandler) -> None:\n",
+    "        \"\"\"Set handler as the only handler on the callback manager.\"\"\"\n",
+    "        self.set_handlers([handler])\n",
+    "\n",
+    "    def set_handlers(self, handlers: List[BaseCallbackHandler]) -> None:\n",
+    "        \"\"\"Set handlers as the only handlers on the callback manager.\"\"\"\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2b6d7dba-cd20-472a-ae05-f68675cc9ea4",
+   "metadata": {},
+   "source": [
+    "`CallbackHandlers` are objects that implement the `CallbackHandler` interface, which has a method for each event that can be subscribed to. The `CallbackManager` will call the appropriate method on each handler when the event is triggered."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e4592215-6604-47e2-89ff-5db3af6d1e40",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "```python\n",
+    "class BaseCallbackHandler(ABC):\n",
+    "    \"\"\"Base callback handler that can be used to handle callbacks from langchain.\"\"\"\n",
+    "\n",
+    "    @abstractmethod\n",
+    "    def on_llm_start(\n",
+    "        self, serialized: Dict[str, Any], prompts: List[str], **kwargs: Any\n",
+    "    ) -> Any:\n",
+    "        \"\"\"Run when LLM starts running.\"\"\"\n",
+    "\n",
+    "    @abstractmethod\n",
+    "    def on_llm_new_token(self, token: str, **kwargs: Any) -> Any:\n",
+    "        \"\"\"Run on new LLM token. Only available when streaming is enabled.\"\"\"\n",
+    "\n",
+    "    @abstractmethod\n",
+    "    def on_llm_end(self, response: LLMResult, **kwargs: Any) -> Any:\n",
+    "        \"\"\"Run when LLM ends running.\"\"\"\n",
+    "\n",
+    "    @abstractmethod\n",
+    "    def on_llm_error(\n",
+    "        self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any\n",
+    "    ) -> Any:\n",
+    "        \"\"\"Run when LLM errors.\"\"\"\n",
+    "\n",
+    "    @abstractmethod\n",
+    "    def on_chain_start(\n",
+    "        self, serialized: Dict[str, Any], inputs: Dict[str, Any], **kwargs: Any\n",
+    "    ) -> Any:\n",
+    "        \"\"\"Run when chain starts running.\"\"\"\n",
+    "\n",
+    "    @abstractmethod\n",
+    "    def on_chain_end(self, outputs: Dict[str, Any], **kwargs: Any) -> Any:\n",
+    "        \"\"\"Run when chain ends running.\"\"\"\n",
+    "\n",
+    "    @abstractmethod\n",
+    "    def on_chain_error(\n",
+    "        self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any\n",
+    "    ) -> Any:\n",
+    "        \"\"\"Run when chain errors.\"\"\"\n",
+    "\n",
+    "    @abstractmethod\n",
+    "    def on_tool_start(\n",
+    "        self, serialized: Dict[str, Any], input_str: str, **kwargs: Any\n",
+    "    ) -> Any:\n",
+    "        \"\"\"Run when tool starts running.\"\"\"\n",
+    "\n",
+    "    @abstractmethod\n",
+    "    def on_tool_end(self, output: str, **kwargs: Any) -> Any:\n",
+    "        \"\"\"Run when tool ends running.\"\"\"\n",
+    "\n",
+    "    @abstractmethod\n",
+    "    def on_tool_error(\n",
+    "        self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any\n",
+    "    ) -> Any:\n",
+    "        \"\"\"Run when tool errors.\"\"\"\n",
+    "\n",
+    "    @abstractmethod\n",
+    "    def on_text(self, text: str, **kwargs: Any) -> Any:\n",
+    "        \"\"\"Run on arbitrary text.\"\"\"\n",
+    "\n",
+    "    @abstractmethod\n",
+    "    def on_agent_action(self, action: AgentAction, **kwargs: Any) -> Any:\n",
+    "        \"\"\"Run on agent action.\"\"\"\n",
+    "\n",
+    "    @abstractmethod\n",
+    "    def on_agent_finish(self, finish: AgentFinish, **kwargs: Any) -> Any:\n",
+    "        \"\"\"Run on agent end.\"\"\"\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d3bf3304-43fb-47ad-ae50-0637a17018a2",
+   "metadata": {},
+   "source": [
+    "## Creating and Using a Custom `CallbackHandler`\n",
+    "\n",
+    "By default, a shared CallbackManager with the StdOutCallbackHandler will be used by models, chains, agents, and tools. However, you can pass in your own CallbackManager with a custom CallbackHandler:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "80532dfc-d687-4147-a0c9-1f90cc3e868c",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "AgentAction(tool='Search', tool_input=\"US Open men's final 2019 winner\", log=' I need to find out who won the US Open men\\'s final in 2019 and then calculate his age raised to the 0.334 power.\\nAction: Search\\nAction Input: \"US Open men\\'s final 2019 winner\"')\n",
+      "Rafael Nadal defeated Daniil Medvedev in the final, 7–5, 6–3, 5–7, 4–6, 6–4 to win the men's singles tennis title at the 2019 US Open. It was his fourth US ...\n",
+      "AgentAction(tool='Search', tool_input='Rafael Nadal age', log=' I need to find out the age of the winner\\nAction: Search\\nAction Input: \"Rafael Nadal age\"')\n",
+      "36 years\n",
+      "AgentAction(tool='Calculator', tool_input='36^0.334', log=' I now need to calculate his age raised to the 0.334 power\\nAction: Calculator\\nAction Input: 36^0.334')\n",
+      "Answer: 3.3098250249682484\n",
+      "\n",
+      " I now know the final answer\n",
+      "Final Answer: Rafael Nadal, aged 36, won the US Open men's final in 2019 and his age raised to the 0.334 power is 3.3098250249682484.\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\"Rafael Nadal, aged 36, won the US Open men's final in 2019 and his age raised to the 0.334 power is 3.3098250249682484.\""
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from typing import Any, Dict, List, Optional, Union\n",
+    "\n",
+    "from langchain.agents import initialize_agent, load_tools\n",
+    "from langchain.agents import AgentType\n",
+    "from langchain.callbacks.base import CallbackManager, BaseCallbackHandler\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.schema import AgentAction, AgentFinish, LLMResult\n",
+    "\n",
+    "class MyCustomCallbackHandler(BaseCallbackHandler):\n",
+    "    \"\"\"Custom CallbackHandler.\"\"\"\n",
+    "\n",
+    "    def on_llm_start(\n",
+    "        self, serialized: Dict[str, Any], prompts: List[str], **kwargs: Any\n",
+    "    ) -> None:\n",
+    "        \"\"\"Print out the prompts.\"\"\"\n",
+    "        pass\n",
+    "\n",
+    "    def on_llm_end(self, response: LLMResult, **kwargs: Any) -> None:\n",
+    "        \"\"\"Do nothing.\"\"\"\n",
+    "        pass\n",
+    "\n",
+    "    def on_llm_new_token(self, token: str, **kwargs: Any) -> None:\n",
+    "        \"\"\"Do nothing.\"\"\"\n",
+    "        pass\n",
+    "\n",
+    "    def on_llm_error(\n",
+    "        self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any\n",
+    "    ) -> None:\n",
+    "        \"\"\"Do nothing.\"\"\"\n",
+    "        pass\n",
+    "\n",
+    "    def on_chain_start(\n",
+    "        self, serialized: Dict[str, Any], inputs: Dict[str, Any], **kwargs: Any\n",
+    "    ) -> None:\n",
+    "        \"\"\"Print out that we are entering a chain.\"\"\"\n",
+    "        class_name = serialized[\"name\"]\n",
+    "        print(f\"\\n\\n\\033[1m> Entering new {class_name} chain...\\033[0m\")\n",
+    "\n",
+    "    def on_chain_end(self, outputs: Dict[str, Any], **kwargs: Any) -> None:\n",
+    "        \"\"\"Print out that we finished a chain.\"\"\"\n",
+    "        print(\"\\n\\033[1m> Finished chain.\\033[0m\")\n",
+    "\n",
+    "    def on_chain_error(\n",
+    "        self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any\n",
+    "    ) -> None:\n",
+    "        \"\"\"Do nothing.\"\"\"\n",
+    "        pass\n",
+    "\n",
+    "    def on_tool_start(\n",
+    "        self,\n",
+    "        serialized: Dict[str, Any],\n",
+    "        input_str: str,\n",
+    "        **kwargs: Any,\n",
+    "    ) -> None:\n",
+    "        \"\"\"Do nothing.\"\"\"\n",
+    "        pass\n",
+    "\n",
+    "    def on_agent_action(\n",
+    "        self, action: AgentAction, color: Optional[str] = None, **kwargs: Any\n",
+    "    ) -> Any:\n",
+    "        \"\"\"Run on agent action.\"\"\"\n",
+    "        print(action)\n",
+    "\n",
+    "    def on_tool_end(\n",
+    "        self,\n",
+    "        output: str,\n",
+    "        color: Optional[str] = None,\n",
+    "        observation_prefix: Optional[str] = None,\n",
+    "        llm_prefix: Optional[str] = None,\n",
+    "        **kwargs: Any,\n",
+    "    ) -> None:\n",
+    "        \"\"\"If not the final action, print out observation.\"\"\"\n",
+    "        print(output)\n",
+    "\n",
+    "    def on_tool_error(\n",
+    "        self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any\n",
+    "    ) -> None:\n",
+    "        \"\"\"Do nothing.\"\"\"\n",
+    "        pass\n",
+    "\n",
+    "    def on_text(\n",
+    "        self,\n",
+    "        text: str,\n",
+    "        color: Optional[str] = None,\n",
+    "        end: str = \"\",\n",
+    "        **kwargs: Optional[str],\n",
+    "    ) -> None:\n",
+    "        \"\"\"Run when agent ends.\"\"\"\n",
+    "        print(text)\n",
+    "\n",
+    "    def on_agent_finish(\n",
+    "        self, finish: AgentFinish, color: Optional[str] = None, **kwargs: Any\n",
+    "    ) -> None:\n",
+    "        \"\"\"Run on agent end.\"\"\"\n",
+    "        print(finish.log)\n",
+    "manager = CallbackManager([MyCustomCallbackHandler()])\n",
+    "llm = OpenAI(temperature=0, callback_manager=manager, verbose=True)\n",
+    "tools = load_tools([\"llm-math\", \"serpapi\"], llm=llm, callback_manager=manager)\n",
+    "agent = initialize_agent(\n",
+    "    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True, callback_manager=manager\n",
+    ")\n",
+    "agent.run(\"Who won the US Open men's final in 2019? What is his age raised to the 0.334 power?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "bc9785fa-4f71-4797-91a3-4fe7e57d0429",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "## Async Support\n",
+    "\n",
+    "If you are planning to use the async API, it is recommended to use `AsyncCallbackHandler` and `AsyncCallbackManager` to avoid blocking the runloop."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "c702e0c9-a961-4897-90c1-cdd13b6f16b2",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "zzzz....\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "zzzz....\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "import asyncio\n",
+    "from aiohttp import ClientSession\n",
+    "\n",
+    "from langchain.callbacks.base import AsyncCallbackHandler, AsyncCallbackManager\n",
+    "\n",
+    "class MyCustomAsyncCallbackHandler(AsyncCallbackHandler):\n",
+    "    \"\"\"Async callback handler that can be used to handle callbacks from langchain.\"\"\"\n",
+    "\n",
+    "    async def on_chain_start(\n",
+    "        self, serialized: Dict[str, Any], inputs: Dict[str, Any], **kwargs: Any\n",
+    "    ) -> None:\n",
+    "        \"\"\"Run when chain starts running.\"\"\"\n",
+    "        print(\"zzzz....\")\n",
+    "        await asyncio.sleep(0.5)\n",
+    "        class_name = serialized[\"name\"]\n",
+    "        print(f\"\\n\\n\\033[1m> Entering new {class_name} chain...\\033[0m\")\n",
+    "\n",
+    "    async def on_chain_end(self, outputs: Dict[str, Any], **kwargs: Any) -> None:\n",
+    "        \"\"\"Run when chain ends running.\"\"\"\n",
+    "        print(\"zzzz....\")\n",
+    "        await asyncio.sleep(0.5)\n",
+    "        print(\"\\n\\033[1m> Finished chain.\\033[0m\")\n",
+    "\n",
+    "manager = AsyncCallbackManager([MyCustomAsyncCallbackHandler()])\n",
+    "\n",
+    "# To make async requests in Tools more efficient, you can pass in your own aiohttp.ClientSession, \n",
+    "# but you must manually close the client session at the end of your program/event loop\n",
+    "aiosession = ClientSession()\n",
+    "llm = OpenAI(temperature=0, callback_manager=manager)\n",
+    "async_tools = load_tools([\"llm-math\", \"serpapi\"], llm=llm, aiosession=aiosession, callback_manager=manager)\n",
+    "async_agent = initialize_agent(async_tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True, callback_manager=manager)\n",
+    "await async_agent.arun(\"Who won the US Open men's final in 2019? What is his age raised to the 0.334 power?\")\n",
+    "await aiosession.close()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "86be6304-e433-4048-880c-a92a73244407",
+   "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
+}

docs/modules/chains/examples/openapi.ipynb

@@ -144,6 +144,160 @@
       "\u001b[32;1m\u001b[1;3mYou are a helpful AI Assistant. Please provide JSON arguments to agentFunc() based on the user's instructions.\n",
       "\n",
       "API_SCHEMA: ```typescript\n",
+      "/* API for fetching Klarna product information */\n",
+      "type productsUsingGET = (_: {\n",
+      "/* A precise query that matches one very small category or product that needs to be searched for to find the products the user is looking for. If the user explicitly stated what they want, use that as a query. The query is as specific as possible to the product name or category mentioned by the user in its singular form, and don't contain any clarifiers like latest, newest, cheapest, budget, premium, expensive or similar. The query is always taken from the latest topic, if there is a new topic a new query is started. */\n",
+      "\t\tq: string,\n",
+      "/* number of products returned */\n",
+      "\t\tsize?: number,\n",
+      "/* (Optional) Minimum price in local currency for the product searched for. Either explicitly stated by the user or implicitly inferred from a combination of the user's request and the kind of product searched for. */\n",
+      "\t\tmin_price?: number,\n",
+      "/* (Optional) Maximum price in local currency for the product searched for. Either explicitly stated by the user or implicitly inferred from a combination of the user's request and the kind of product searched for. */\n",
+      "\t\tmax_price?: number,\n",
+      "}) => any;\n",
+      "```\n",
+      "\n",
+      "USER_INSTRUCTIONS: \"whats the most expensive shirt?\"\n",
+      "\n",
+      "Your arguments must be plain json provided in a markdown block:\n",
+      "\n",
+      "ARGS: ```json\n",
+      "{valid json conforming to API_SCHEMA}\n",
+      "```\n",
+      "\n",
+      "Example\n",
+      "-----\n",
+      "\n",
+      "ARGS: ```json\n",
+      "{\"foo\": \"bar\", \"baz\": {\"qux\": \"quux\"}}\n",
+      "```\n",
+      "\n",
+      "The block must be no more than 1 line long, and all arguments must be valid JSON. All string arguments must be wrapped in double quotes.\n",
+      "You MUST strictly comply to the types indicated by the provided schema, including all required args.\n",
+      "\n",
+      "If you don't have sufficient information to call the function due to things like requiring specific uuid's, you can reply with the following message:\n",
+      "\n",
+      "Message: ```text\n",
+      "Concise response requesting the additional information that would make calling the function successful.\n",
+      "```\n",
+      "\n",
+      "Begin\n",
+      "-----\n",
+      "ARGS:\n",
+      "\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m{\"q\": \"shirt\", \"size\": 1, \"max_price\": null}\u001b[0m\n",
+      "\u001b[36;1m\u001b[1;3m{\"products\":[{\"name\":\"Burberry Check Poplin Shirt\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3201810981/Clothing/Burberry-Check-Poplin-Shirt/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$360.00\",\"attributes\":[\"Material:Cotton\",\"Target Group:Man\",\"Color:Gray,Blue,Beige\",\"Properties:Pockets\",\"Pattern:Checkered\"]}]}\u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new APIResponderChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mYou are a helpful AI assistant trained to answer user queries from API responses.\n",
+      "You attempted to call an API, which resulted in:\n",
+      "API_RESPONSE: {\"products\":[{\"name\":\"Burberry Check Poplin Shirt\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3201810981/Clothing/Burberry-Check-Poplin-Shirt/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$360.00\",\"attributes\":[\"Material:Cotton\",\"Target Group:Man\",\"Color:Gray,Blue,Beige\",\"Properties:Pockets\",\"Pattern:Checkered\"]}]}\n",
+      "\n",
+      "USER_COMMENT: \"whats the most expensive shirt?\"\n",
+      "\n",
+      "\n",
+      "If the API_RESPONSE can answer the USER_COMMENT respond with the following markdown json block:\n",
+      "Response: ```json\n",
+      "{\"response\": \"Human-understandable synthesis of the API_RESPONSE\"}\n",
+      "```\n",
+      "\n",
+      "Otherwise respond with the following markdown json block:\n",
+      "Response Error: ```json\n",
+      "{\"response\": \"What you did and a concise statement of the resulting error. If it can be easily fixed, provide a suggestion.\"}\n",
+      "```\n",
+      "\n",
+      "You MUST respond as a markdown json code block. The person you are responding to CANNOT see the API_RESPONSE, so if there is any relevant information there you must include it in your response.\n",
+      "\n",
+      "Begin:\n",
+      "---\n",
+      "\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\u001b[33;1m\u001b[1;3mThe most expensive shirt in the API response is the Burberry Check Poplin Shirt, which costs $360.00.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "output = chain(\"whats the most expensive shirt?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "c000295e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'request_args': '{\"q\": \"shirt\", \"size\": 1, \"max_price\": null}',\n",
+       " 'response_text': '{\"products\":[{\"name\":\"Burberry Check Poplin Shirt\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3201810981/Clothing/Burberry-Check-Poplin-Shirt/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$360.00\",\"attributes\":[\"Material:Cotton\",\"Target Group:Man\",\"Color:Gray,Blue,Beige\",\"Properties:Pockets\",\"Pattern:Checkered\"]}]}'}"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# View intermediate steps\n",
+    "output[\"intermediate_steps\"]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "092bdb4d",
+   "metadata": {},
+   "source": [
+    "## Return raw response\n",
+    "\n",
+    "We can also run this chain without synthesizing the response. This will have the effect of just returning the raw API output."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "4dff3849",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = OpenAPIEndpointChain.from_api_operation(\n",
+    "    operation, \n",
+    "    llm, \n",
+    "    requests=Requests(), \n",
+    "    verbose=True,\n",
+    "    return_intermediate_steps=True, # Return request and response text\n",
+    "    raw_response=True # Return raw response\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "762499a9",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new OpenAPIEndpointChain chain...\u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new APIRequesterChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mYou are a helpful AI Assistant. Please provide JSON arguments to agentFunc() based on the user's instructions.\n",
+      "\n",
+      "API_SCHEMA: ```typescript\n",
+      "/* API for fetching Klarna product information */\n",
       "type productsUsingGET = (_: {\n",
       "/* A precise query that matches one very small category or product that needs to be searched for to find the products the user is looking for. If the user explicitly stated what they want, use that as a query. The query is as specific as possible to the product name or category mentioned by the user in its singular form, and don't contain any clarifiers like latest, newest, cheapest, budget, premium, expensive or similar. The query is always taken from the latest topic, if there is a new topic a new query is started. */\n",
       "\t\tq: string,\n",
@@ -187,36 +341,7 @@
       "\n",
       "\u001b[1m> Finished chain.\u001b[0m\n",
       "\u001b[32;1m\u001b[1;3m{\"q\": \"shirt\", \"max_price\": null}\u001b[0m\n",
-      "\u001b[36;1m\u001b[1;3m{\"products\":[{\"name\":\"Burberry Check Poplin Shirt\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3201810981/Clothing/Burberry-Check-Poplin-Shirt/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$360.00\",\"attributes\":[\"Material:Cotton\",\"Target Group:Man\",\"Color:Gray,Blue,Beige\",\"Properties:Pockets\",\"Pattern:Checkered\"]},{\"name\":\"Burberry Vintage Check Cotton Shirt - Beige\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl359/3200280807/Children-s-Clothing/Burberry-Vintage-Check-Cotton-Shirt-Beige/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$196.30\",\"attributes\":[\"Material:Cotton,Elastane\",\"Color:Beige\",\"Model:Boy\",\"Pattern:Checkered\"]},{\"name\":\"Burberry Somerton Check Shirt - Camel\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3201112728/Clothing/Burberry-Somerton-Check-Shirt-Camel/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$450.00\",\"attributes\":[\"Material:Elastane/Lycra/Spandex,Cotton\",\"Target Group:Man\",\"Color:Beige\"]},{\"name\":\"Calvin Klein Slim Fit Oxford Dress Shirt\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3201839169/Clothing/Calvin-Klein-Slim-Fit-Oxford-Dress-Shirt/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$24.91\",\"attributes\":[\"Material:Cotton\",\"Target Group:Man\",\"Color:Gray,White,Blue,Black\",\"Pattern:Solid Color\"]},{\"name\":\"Magellan Outdoors Laguna Madre Solid Short Sleeve Fishing Shirt\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3203102142/Clothing/Magellan-Outdoors-Laguna-Madre-Solid-Short-Sleeve-Fishing-Shirt/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$19.99\",\"attributes\":[\"Material:Polyester,Nylon\",\"Target Group:Man\",\"Color:Red,Pink,White,Blue,Purple,Beige,Black,Green\",\"Properties:Pockets\",\"Pattern:Solid Color\"]}]}\u001b[0m\n",
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new APIResponderChain chain...\u001b[0m\n",
-      "Prompt after formatting:\n",
-      "\u001b[32;1m\u001b[1;3mYou are a helpful AI assistant trained to answer user queries from API responses.\n",
-      "You attempted to call an API, which resulted in:\n",
-      "API_RESPONSE: {\"products\":[{\"name\":\"Burberry Check Poplin Shirt\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3201810981/Clothing/Burberry-Check-Poplin-Shirt/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$360.00\",\"attributes\":[\"Material:Cotton\",\"Target Group:Man\",\"Color:Gray,Blue,Beige\",\"Properties:Pockets\",\"Pattern:Checkered\"]},{\"name\":\"Burberry Vintage Check Cotton Shirt - Beige\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl359/3200280807/Children-s-Clothing/Burberry-Vintage-Check-Cotton-Shirt-Beige/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$196.30\",\"attributes\":[\"Material:Cotton,Elastane\",\"Color:Beige\",\"Model:Boy\",\"Pattern:Checkered\"]},{\"name\":\"Burberry Somerton Check Shirt - Camel\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3201112728/Clothing/Burberry-Somerton-Check-Shirt-Camel/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$450.00\",\"attributes\":[\"Material:Elastane/Lycra/Spandex,Cotton\",\"Target Group:Man\",\"Color:Beige\"]},{\"name\":\"Calvin Klein Slim Fit Oxford Dress Shirt\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3201839169/Clothing/Calvin-Klein-Slim-Fit-Oxford-Dress-Shirt/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$24.91\",\"attributes\":[\"Material:Cotton\",\"Target Group:Man\",\"Color:Gray,White,Blue,Black\",\"Pattern:Solid Color\"]},{\"name\":\"Magellan Outdoors Laguna Madre Solid Short Sleeve Fishing Shirt\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3203102142/Clothing/Magellan-Outdoors-Laguna-Madre-Solid-Short-Sleeve-Fishing-Shirt/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$19.99\",\"attributes\":[\"Material:Polyester,Nylon\",\"Target Group:Man\",\"Color:Red,Pink,White,Blue,Purple,Beige,Black,Green\",\"Properties:Pockets\",\"Pattern:Solid Color\"]}]}\n",
-      "\n",
-      "USER_COMMENT: \"whats the most expensive shirt?\"\n",
-      "\n",
-      "\n",
-      "If the API_RESPONSE can answer the USER_COMMENT respond with the following markdown json block:\n",
-      "Response: ```json\n",
-      "{\"response\": \"Concise response to USER_COMMENT based on API_RESPONSE.\"}\n",
-      "```\n",
-      "\n",
-      "Otherwise respond with the following markdown json block:\n",
-      "Response Error: ```json\n",
-      "{\"response\": \"What you did and a concise statement of the resulting error. If it can be easily fixed, provide a suggestion.\"}\n",
-      "```\n",
-      "\n",
-      "You MUST respond as a markdown json code block.\n",
-      "\n",
-      "Begin:\n",
-      "---\n",
-      "\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n",
-      "\u001b[33;1m\u001b[1;3mThe most expensive shirt in this list is the 'Burberry Somerton Check Shirt - Camel' which is priced at $450.00\u001b[0m\n",
+      "\u001b[36;1m\u001b[1;3m{\"products\":[{\"name\":\"Burberry Check Poplin Shirt\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3201810981/Clothing/Burberry-Check-Poplin-Shirt/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$360.00\",\"attributes\":[\"Material:Cotton\",\"Target Group:Man\",\"Color:Gray,Blue,Beige\",\"Properties:Pockets\",\"Pattern:Checkered\"]},{\"name\":\"Burberry Vintage Check Cotton Shirt - Beige\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl359/3200280807/Children-s-Clothing/Burberry-Vintage-Check-Cotton-Shirt-Beige/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$229.02\",\"attributes\":[\"Material:Cotton,Elastane\",\"Color:Beige\",\"Model:Boy\",\"Pattern:Checkered\"]},{\"name\":\"Burberry Vintage Check Stretch Cotton Twill Shirt\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3202342515/Clothing/Burberry-Vintage-Check-Stretch-Cotton-Twill-Shirt/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$309.99\",\"attributes\":[\"Material:Elastane/Lycra/Spandex,Cotton\",\"Target Group:Woman\",\"Color:Beige\",\"Properties:Stretch\",\"Pattern:Checkered\"]},{\"name\":\"Burberry Somerton Check Shirt - Camel\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3201112728/Clothing/Burberry-Somerton-Check-Shirt-Camel/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$450.00\",\"attributes\":[\"Material:Elastane/Lycra/Spandex,Cotton\",\"Target Group:Man\",\"Color:Beige\"]},{\"name\":\"Magellan Outdoors Laguna Madre Solid Short Sleeve Fishing Shirt\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3203102142/Clothing/Magellan-Outdoors-Laguna-Madre-Solid-Short-Sleeve-Fishing-Shirt/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$19.99\",\"attributes\":[\"Material:Polyester,Nylon\",\"Target Group:Man\",\"Color:Red,Pink,White,Blue,Purple,Beige,Black,Green\",\"Properties:Pockets\",\"Pattern:Solid Color\"]}]}\u001b[0m\n",
       "\n",
       "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
@@ -228,25 +353,26 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
-   "id": "c000295e",
+   "execution_count": 12,
+   "id": "4afc021a",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "['{\"q\": \"shirt\", \"max_price\": null}',\n",
-       " '{\"products\":[{\"name\":\"Burberry Check Poplin Shirt\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3201810981/Clothing/Burberry-Check-Poplin-Shirt/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$360.00\",\"attributes\":[\"Material:Cotton\",\"Target Group:Man\",\"Color:Gray,Blue,Beige\",\"Properties:Pockets\",\"Pattern:Checkered\"]},{\"name\":\"Burberry Vintage Check Cotton Shirt - Beige\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl359/3200280807/Children-s-Clothing/Burberry-Vintage-Check-Cotton-Shirt-Beige/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$196.30\",\"attributes\":[\"Material:Cotton,Elastane\",\"Color:Beige\",\"Model:Boy\",\"Pattern:Checkered\"]},{\"name\":\"Burberry Somerton Check Shirt - Camel\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3201112728/Clothing/Burberry-Somerton-Check-Shirt-Camel/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$450.00\",\"attributes\":[\"Material:Elastane/Lycra/Spandex,Cotton\",\"Target Group:Man\",\"Color:Beige\"]},{\"name\":\"Calvin Klein Slim Fit Oxford Dress Shirt\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3201839169/Clothing/Calvin-Klein-Slim-Fit-Oxford-Dress-Shirt/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$24.91\",\"attributes\":[\"Material:Cotton\",\"Target Group:Man\",\"Color:Gray,White,Blue,Black\",\"Pattern:Solid Color\"]},{\"name\":\"Magellan Outdoors Laguna Madre Solid Short Sleeve Fishing Shirt\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3203102142/Clothing/Magellan-Outdoors-Laguna-Madre-Solid-Short-Sleeve-Fishing-Shirt/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$19.99\",\"attributes\":[\"Material:Polyester,Nylon\",\"Target Group:Man\",\"Color:Red,Pink,White,Blue,Purple,Beige,Black,Green\",\"Properties:Pockets\",\"Pattern:Solid Color\"]}]}']"
+       "{'instructions': 'whats the most expensive shirt?',\n",
+       " 'output': '{\"products\":[{\"name\":\"Burberry Check Poplin Shirt\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3201810981/Clothing/Burberry-Check-Poplin-Shirt/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$360.00\",\"attributes\":[\"Material:Cotton\",\"Target Group:Man\",\"Color:Gray,Blue,Beige\",\"Properties:Pockets\",\"Pattern:Checkered\"]},{\"name\":\"Burberry Vintage Check Cotton Shirt - Beige\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl359/3200280807/Children-s-Clothing/Burberry-Vintage-Check-Cotton-Shirt-Beige/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$229.02\",\"attributes\":[\"Material:Cotton,Elastane\",\"Color:Beige\",\"Model:Boy\",\"Pattern:Checkered\"]},{\"name\":\"Burberry Vintage Check Stretch Cotton Twill Shirt\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3202342515/Clothing/Burberry-Vintage-Check-Stretch-Cotton-Twill-Shirt/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$309.99\",\"attributes\":[\"Material:Elastane/Lycra/Spandex,Cotton\",\"Target Group:Woman\",\"Color:Beige\",\"Properties:Stretch\",\"Pattern:Checkered\"]},{\"name\":\"Burberry Somerton Check Shirt - Camel\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3201112728/Clothing/Burberry-Somerton-Check-Shirt-Camel/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$450.00\",\"attributes\":[\"Material:Elastane/Lycra/Spandex,Cotton\",\"Target Group:Man\",\"Color:Beige\"]},{\"name\":\"Magellan Outdoors Laguna Madre Solid Short Sleeve Fishing Shirt\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3203102142/Clothing/Magellan-Outdoors-Laguna-Madre-Solid-Short-Sleeve-Fishing-Shirt/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$19.99\",\"attributes\":[\"Material:Polyester,Nylon\",\"Target Group:Man\",\"Color:Red,Pink,White,Blue,Purple,Beige,Black,Green\",\"Properties:Pockets\",\"Pattern:Solid Color\"]}]}',\n",
+       " 'intermediate_steps': {'request_args': '{\"q\": \"shirt\", \"max_price\": null}',\n",
+       "  'response_text': '{\"products\":[{\"name\":\"Burberry Check Poplin Shirt\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3201810981/Clothing/Burberry-Check-Poplin-Shirt/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$360.00\",\"attributes\":[\"Material:Cotton\",\"Target Group:Man\",\"Color:Gray,Blue,Beige\",\"Properties:Pockets\",\"Pattern:Checkered\"]},{\"name\":\"Burberry Vintage Check Cotton Shirt - Beige\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl359/3200280807/Children-s-Clothing/Burberry-Vintage-Check-Cotton-Shirt-Beige/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$229.02\",\"attributes\":[\"Material:Cotton,Elastane\",\"Color:Beige\",\"Model:Boy\",\"Pattern:Checkered\"]},{\"name\":\"Burberry Vintage Check Stretch Cotton Twill Shirt\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3202342515/Clothing/Burberry-Vintage-Check-Stretch-Cotton-Twill-Shirt/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$309.99\",\"attributes\":[\"Material:Elastane/Lycra/Spandex,Cotton\",\"Target Group:Woman\",\"Color:Beige\",\"Properties:Stretch\",\"Pattern:Checkered\"]},{\"name\":\"Burberry Somerton Check Shirt - Camel\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3201112728/Clothing/Burberry-Somerton-Check-Shirt-Camel/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$450.00\",\"attributes\":[\"Material:Elastane/Lycra/Spandex,Cotton\",\"Target Group:Man\",\"Color:Beige\"]},{\"name\":\"Magellan Outdoors Laguna Madre Solid Short Sleeve Fishing Shirt\",\"url\":\"https://www.klarna.com/us/shopping/pl/cl10001/3203102142/Clothing/Magellan-Outdoors-Laguna-Madre-Solid-Short-Sleeve-Fishing-Shirt/?utm_source=openai&ref-site=openai_plugin\",\"price\":\"$19.99\",\"attributes\":[\"Material:Polyester,Nylon\",\"Target Group:Man\",\"Color:Red,Pink,White,Blue,Purple,Beige,Black,Green\",\"Properties:Pockets\",\"Pattern:Solid Color\"]}]}'}}"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "# View intermediate steps\n",
-    "output[\"intermediate_steps\"]"
+    "output"
    ]
   },
   {
@@ -448,7 +574,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.2"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/modules/chains/examples/sqlite.ipynb

@@ -9,9 +9,9 @@
     }
    },
    "source": [
-    "# SQLite example\n",
+    "# SQL Chain example\n",
     "\n",
-    "This example showcases hooking up an LLM to answer questions over a database."
+    "This example demonstrates the use of the `SQLDatabaseChain` for answering questions over a database."
    ]
   },
   {
@@ -23,8 +23,10 @@
     }
    },
    "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."
+    "Under the hood, LangChain uses SQLAlchemy to connect to SQL databases. The `SQLDatabaseChain` can therefore be used with any SQL dialect supported by SQLAlchemy, such as MS SQL, MySQL, MariaDB, PostgreSQL, Oracle SQL, and SQLite. Please refer to the SQLAlchemy documentation for more information about requirements for connecting to your database. For example, a connection to MySQL requires an appropriate connector such as PyMySQL. A URI for a MySQL connection might look like: `mysql+pymysql://user:pass@some_mysql_db_address/db_name`\n",
+    "\n",
+    "This demonstration uses SQLite and 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."
    ]
   },
   {
@@ -679,7 +681,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.10"
   }
  },
  "nbformat": 4,

docs/modules/chains/index_examples/chat_vector_db.ipynb

@@ -5,14 +5,14 @@
    "id": "134a0785",
    "metadata": {},
    "source": [
-    "# Chat Index\n",
+    "# Chat Over Documents with Chat History\n",
     "\n",
-    "This notebook goes over how to set up a chain to chat with an index. The only difference between this chain and the [RetrievalQAChain](./vector_db_qa.ipynb) is that this allows for passing in of a chat history which can be used to allow for follow up questions."
+    "This notebook goes over how to set up a chain to chat over documents with chat history using a `ConversationalRetrievalChain`. The only difference between this chain and the [RetrievalQAChain](./vector_db_qa.ipynb) is that this allows for passing in of a chat history which can be used to allow for follow up questions."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 3,
    "id": "70c4e529",
    "metadata": {
     "tags": []
@@ -36,7 +36,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 4,
    "id": "01c46e92",
    "metadata": {
     "tags": []
@@ -58,7 +58,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 5,
    "id": "433363a5",
    "metadata": {
     "tags": []
@@ -81,7 +81,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 6,
    "id": "a8930cf7",
    "metadata": {
     "tags": []
@@ -109,12 +109,12 @@
    "id": "3c96b118",
    "metadata": {},
    "source": [
-    "We now initialize the ConversationalRetrievalChain"
+    "We now initialize the `ConversationalRetrievalChain`"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 7,
    "id": "7b4110f3",
    "metadata": {
     "tags": []
@@ -134,7 +134,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 8,
    "id": "7fe3e730",
    "metadata": {
     "tags": []
@@ -148,7 +148,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 9,
    "id": "bfff9cc8",
    "metadata": {
     "tags": []
@@ -160,7 +160,7 @@
        "\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, and from a family of public school educators and police officers. He also said that she is a consensus builder and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
       ]
      },
-     "execution_count": 7,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -179,7 +179,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 10,
    "id": "00b4cf00",
    "metadata": {
     "tags": []
@@ -193,7 +193,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 11,
    "id": "f01828d1",
    "metadata": {
     "tags": []
@@ -202,10 +202,10 @@
     {
      "data": {
       "text/plain": [
-       "' Justice Stephen Breyer'"
+       "' Ketanji Brown Jackson succeeded Justice Stephen Breyer on the United States Supreme Court.'"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -225,9 +225,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 12,
    "id": "562769c6",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "qa = ConversationalRetrievalChain.from_llm(OpenAI(temperature=0), vectorstore.as_retriever(), return_source_documents=True)"
@@ -235,9 +237,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 13,
    "id": "ea478300",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "chat_history = []\n",
@@ -247,17 +251,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 14,
    "id": "4cb75b4e",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Document(page_content='Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0)"
+       "Document(page_content='Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', metadata={'source': '../../state_of_the_union.txt'})"
       ]
      },
-     "execution_count": 13,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -277,9 +283,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 15,
    "id": "5ed8d612",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "vectordbkwargs = {\"search_distance\": 0.9}"
@@ -287,9 +295,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 16,
    "id": "6a7b3459",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "qa = ConversationalRetrievalChain.from_llm(OpenAI(temperature=0), vectorstore.as_retriever(), return_source_documents=True)\n",
@@ -309,21 +319,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 18,
    "id": "e53a9d66",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "from langchain.chains import LLMChain\n",
     "from langchain.chains.question_answering import load_qa_chain\n",
-    "from langchain.chains.chat_index.prompts import CONDENSE_QUESTION_PROMPT"
+    "from langchain.chains.conversational_retrieval.prompts import CONDENSE_QUESTION_PROMPT"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 19,
    "id": "bf205e35",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "llm = OpenAI(temperature=0)\n",
@@ -341,7 +355,9 @@
    "cell_type": "code",
    "execution_count": 20,
    "id": "78155887",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "chat_history = []\n",
@@ -353,7 +369,9 @@
    "cell_type": "code",
    "execution_count": 21,
    "id": "e54b5fa2",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "data": {
@@ -384,7 +402,9 @@
    "cell_type": "code",
    "execution_count": 22,
    "id": "d1058fd2",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "from langchain.chains.qa_with_sources import load_qa_with_sources_chain"
@@ -394,7 +414,9 @@
    "cell_type": "code",
    "execution_count": 23,
    "id": "a6594482",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "llm = OpenAI(temperature=0)\n",
@@ -412,7 +434,9 @@
    "cell_type": "code",
    "execution_count": 24,
    "id": "e2badd21",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "chat_history = []\n",
@@ -424,7 +448,9 @@
    "cell_type": "code",
    "execution_count": 25,
    "id": "edb31fe5",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "data": {
@@ -453,7 +479,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 27,
    "id": "2efacec3-2690-4b05-8de3-a32fd2ac3911",
    "metadata": {
     "tags": []
@@ -463,7 +489,7 @@
     "from langchain.chains.llm import LLMChain\n",
     "from langchain.callbacks.base import CallbackManager\n",
     "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
-    "from langchain.chains.chat_index.prompts import CONDENSE_QUESTION_PROMPT, QA_PROMPT\n",
+    "from langchain.chains.conversational_retrieval.prompts import CONDENSE_QUESTION_PROMPT, QA_PROMPT\n",
     "from langchain.chains.question_answering import load_qa_chain\n",
     "\n",
     "# Construct a ConversationalRetrievalChain with a streaming llm for combine docs\n",
@@ -480,7 +506,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 28,
    "id": "fd6d43f4-7428-44a4-81bc-26fe88a98762",
    "metadata": {
     "tags": []
@@ -502,7 +528,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 29,
    "id": "5ab38978-f3e8-4fa7-808c-c79dec48379a",
    "metadata": {
     "tags": []
@@ -512,7 +538,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " Justice Stephen Breyer"
+      " Ketanji Brown Jackson succeeded Justice Stephen Breyer on the United States Supreme Court."
      ]
     }
    ],
@@ -533,9 +559,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 31,
    "id": "a7ba9d8c",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "def get_chat_history(inputs) -> str:\n",
@@ -543,14 +571,16 @@
     "    for human, ai in inputs:\n",
     "        res.append(f\"Human:{human}\\nAI:{ai}\")\n",
     "    return \"\\n\".join(res)\n",
-    "qa = ConversationalRetrievalChain.from_llm(OpenAI(temperature=0), vectorstore, get_chat_history=get_chat_history)"
+    "qa = ConversationalRetrievalChain.from_llm(OpenAI(temperature=0), vectorstore.as_retriever(), get_chat_history=get_chat_history)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 32,
    "id": "a3e33c0d",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "chat_history = []\n",
@@ -560,9 +590,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 33,
    "id": "936dc62f",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "data": {
@@ -570,7 +602,7 @@
        "\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, and from a family of public school educators and police officers. He also said that she is a consensus builder and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
       ]
      },
-     "execution_count": 31,
+     "execution_count": 33,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -604,7 +636,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.9"
   }
  },
  "nbformat": 4,

docs/modules/chains/index_examples/question_answering.ipynb

@@ -23,7 +23,9 @@
    "cell_type": "code",
    "execution_count": 1,
    "id": "17fcbc0f",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "from langchain.embeddings.openai import OpenAIEmbeddings\n",
@@ -38,17 +40,26 @@
    "cell_type": "code",
    "execution_count": 2,
    "id": "ef9305cc",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
-    "index_creator = VectorstoreIndexCreator()"
+    "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": "291f0117",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -60,27 +71,29 @@
     }
    ],
    "source": [
-    "from langchain.document_loaders import TextLoader\n",
-    "loader = TextLoader(\"../../state_of_the_union.txt\")\n",
-    "docsearch = index_creator.from_loaders([loader])"
+    "docsearch = Chroma.from_texts(texts, embeddings, metadatas=[{\"source\": str(i)} for i in range(len(texts))]).as_retriever()"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 4,
    "id": "d1eaf6e6",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "query = \"What did the president say about Justice Breyer\"\n",
-    "docs = docsearch.similarity_search(query)"
+    "docs = docsearch.get_relevant_documents(query)"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 5,
    "id": "a16e3453",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "from langchain.chains.question_answering import load_qa_chain\n",
@@ -98,17 +111,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 6,
    "id": "fd9e6190",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "' The president said that he was honoring Justice Breyer for his service to the country and that he was a Constitutional scholar, Army veteran, and retiring Justice of the United States Supreme Court.'"
+       "' The president said that Justice Breyer has dedicated his life to serve the country and thanked him for his service.'"
       ]
      },
-     "execution_count": 19,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -139,9 +154,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "id": "180fd4c1",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "chain = load_qa_chain(OpenAI(temperature=0), chain_type=\"stuff\")"
@@ -149,17 +166,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "id": "77fdf1aa",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{'output_text': ' The president said that he was honoring Justice Breyer for his service to the country and that he was a Constitutional scholar, Army veteran, and retiring Justice of the United States Supreme Court.'}"
+       "{'output_text': ' The president said that Justice Breyer has dedicated his life to serve the country and thanked him for his service.'}"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -181,17 +200,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 9,
    "id": "5558c9e0",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{'output_text': ' Il presidente ha detto che Justice Breyer ha dedicato la sua vita a servire questo paese e ha onorato la sua carriera come giudice della Corte Suprema degli Stati Uniti.'}"
+       "{'output_text': ' Il presidente ha detto che Justice Breyer ha dedicato la sua vita a servire questo paese e ha ricevuto una vasta gamma di supporto.'}"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -222,9 +243,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 10,
    "id": "b0060f51",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "chain = load_qa_chain(OpenAI(temperature=0), chain_type=\"map_reduce\")"
@@ -232,17 +255,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 11,
    "id": "fbdb9137",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{'output_text': ' The president said, \"Justice Breyer, thank you for your service.\"'}"
+       "{'output_text': ' The president said that Justice Breyer is an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court, and thanked him for his service.'}"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -264,9 +289,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 12,
    "id": "452c8680",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "chain = load_qa_chain(OpenAI(temperature=0), chain_type=\"map_reduce\", return_map_steps=True)"
@@ -274,21 +301,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 13,
    "id": "90b47a75",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "data": {
       "text/plain": [
        "{'intermediate_steps': [' \"Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service.\"',\n",
-       "  ' None',\n",
+       "  ' A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.',\n",
        "  ' None',\n",
        "  ' None'],\n",
-       " 'output_text': ' The president said, \"Justice Breyer, thank you for your service.\"'}"
+       " 'output_text': ' The president said that Justice Breyer is an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court, and thanked him for his service.'}"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -309,21 +338,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 14,
    "id": "af03a578",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "data": {
       "text/plain": [
        "{'intermediate_steps': [\"\\nStasera vorrei onorare qualcuno che ha dedicato la sua vita a servire questo paese: il giustizia Stephen Breyer - un veterano dell'esercito, uno studioso costituzionale e un giustizia in uscita della Corte Suprema degli Stati Uniti. Giustizia Breyer, grazie per il tuo servizio.\",\n",
        "  '\\nNessun testo pertinente.',\n",
-       "  \"\\nCome ho detto l'anno scorso, soprattutto ai nostri giovani americani transgender, avrò sempre il tuo sostegno come tuo Presidente, in modo che tu possa essere te stesso e raggiungere il tuo potenziale donato da Dio.\",\n",
-       "  '\\nNella mia amministrazione, i guardiani sono stati accolti di nuovo. Stiamo andando dietro ai criminali che hanno rubato miliardi di dollari di aiuti di emergenza destinati alle piccole imprese e a milioni di americani. E stasera, annuncio che il Dipartimento di Giustizia nominerà un procuratore capo per la frode pandemica.'],\n",
-       " 'output_text': ' Non conosco la risposta alla tua domanda su cosa abbia detto il Presidente riguardo al Giustizia Breyer.'}"
+       "  ' Non ha detto nulla riguardo a Justice Breyer.',\n",
+       "  \" Non c'è testo pertinente.\"],\n",
+       " 'output_text': ' Non ha detto nulla riguardo a Justice Breyer.'}"
       ]
      },
-     "execution_count": 13,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -379,9 +410,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 15,
    "id": "fb167057",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "chain = load_qa_chain(OpenAI(temperature=0), chain_type=\"refine\")"
@@ -389,17 +422,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 16,
    "id": "d8b5286e",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{'output_text': '\\n\\nThe president said that he wanted to honor Justice Breyer for his dedication to serving the country, his legacy of excellence, and his commitment to advancing liberty and justice, as well as for his commitment to protecting the rights of LGBTQ+ Americans and his support for the bipartisan Equality Act. He also mentioned his plan to lower costs to give families a fair shot, lower the deficit, and go after criminals who stole pandemic relief funds. He also announced that the Justice Department will name a chief prosecutor for pandemic fraud.'}"
+       "{'output_text': '\\n\\nThe president said that he wanted to honor Justice Breyer for his dedication to serving the country, his legacy of excellence, and his commitment to advancing liberty and justice, as well as for his support of the Equality Act and his commitment to protecting the rights of LGBTQ+ Americans. He also praised Justice Breyer for his role in helping to pass the Bipartisan Infrastructure Law, which he said would be the most sweeping investment to rebuild America in history and would help the country compete for the jobs of the 21st Century.'}"
       ]
      },
-     "execution_count": 13,
+     "execution_count": 16,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -421,9 +456,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 17,
    "id": "a5c64200",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "chain = load_qa_chain(OpenAI(temperature=0), chain_type=\"refine\", return_refine_steps=True)"
@@ -431,21 +468,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 18,
    "id": "817546ac",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "data": {
       "text/plain": [
        "{'intermediate_steps': ['\\nThe president said that he wanted to honor Justice Breyer for his dedication to serving the country and his legacy of excellence.',\n",
-       "  '\\n\\nThe president said that he wanted to honor Justice Breyer for his dedication to serving the country, his legacy of excellence, and his commitment to advancing liberty and justice.',\n",
-       "  '\\n\\nThe president said that he wanted to honor Justice Breyer for his dedication to serving the country, his legacy of excellence, and his commitment to advancing liberty and justice, as well as for his commitment to protecting the rights of LGBTQ+ Americans and his support for the bipartisan Equality Act.',\n",
-       "  '\\n\\nThe president said that he wanted to honor Justice Breyer for his dedication to serving the country, his legacy of excellence, and his commitment to advancing liberty and justice, as well as for his commitment to protecting the rights of LGBTQ+ Americans and his support for the bipartisan Equality Act. He also mentioned his plan to lower costs to give families a fair shot, lower the deficit, and go after criminals who stole pandemic relief funds. He also announced that the Justice Department will name a chief prosecutor for pandemic fraud.'],\n",
-       " 'output_text': '\\n\\nThe president said that he wanted to honor Justice Breyer for his dedication to serving the country, his legacy of excellence, and his commitment to advancing liberty and justice, as well as for his commitment to protecting the rights of LGBTQ+ Americans and his support for the bipartisan Equality Act. He also mentioned his plan to lower costs to give families a fair shot, lower the deficit, and go after criminals who stole pandemic relief funds. He also announced that the Justice Department will name a chief prosecutor for pandemic fraud.'}"
+       "  '\\nThe president said that he wanted to honor Justice Breyer for his dedication to serving the country, his legacy of excellence, and his commitment to advancing liberty and justice.',\n",
+       "  '\\n\\nThe president said that he wanted to honor Justice Breyer for his dedication to serving the country, his legacy of excellence, and his commitment to advancing liberty and justice, as well as for his support of the Equality Act and his commitment to protecting the rights of LGBTQ+ Americans.',\n",
+       "  '\\n\\nThe president said that he wanted to honor Justice Breyer for his dedication to serving the country, his legacy of excellence, and his commitment to advancing liberty and justice, as well as for his support of the Equality Act and his commitment to protecting the rights of LGBTQ+ Americans. He also praised Justice Breyer for his role in helping to pass the Bipartisan Infrastructure Law, which is the most sweeping investment to rebuild America in history.'],\n",
+       " 'output_text': '\\n\\nThe president said that he wanted to honor Justice Breyer for his dedication to serving the country, his legacy of excellence, and his commitment to advancing liberty and justice, as well as for his support of the Equality Act and his commitment to protecting the rights of LGBTQ+ Americans. He also praised Justice Breyer for his role in helping to pass the Bipartisan Infrastructure Law, which is the most sweeping investment to rebuild America in history.'}"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 18,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -466,21 +505,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 19,
    "id": "6664bda7",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{'intermediate_steps': ['\\nIl presidente ha detto che Justice Breyer ha dedicato la sua vita al servizio di questo paese e ha onorato la sua carriera. Ha anche detto che la sua nomina di Circuit Court of Appeals Judge Ketanji Brown Jackson continuerà il suo eccezionale lascito.',\n",
-       "  \"\\nIl presidente ha detto che Justice Breyer ha dedicato la sua vita al servizio di questo paese e ha onorato la sua carriera. Ha anche detto che la sua nomina di Circuit Court of Appeals Judge Ketanji Brown Jackson continuerà il suo eccezionale lascito. Ha sottolineato che la sua esperienza come avvocato di alto livello in pratica privata, come ex difensore federale pubblico e come membro di una famiglia di educatori e agenti di polizia, la rende una costruttrice di consenso. Ha anche sottolineato che, dalla sua nomina, ha ricevuto un ampio sostegno, dall'Ordine Fraterno della Polizia a ex giudici nominati da democratici e repubblicani.\",\n",
-       "  \"\\n\\nIl presidente ha detto che Justice Breyer ha dedicato la sua vita al servizio di questo paese e ha onorato la sua carriera. Ha anche detto che la sua nomina di Circuit Court of Appeals Judge Ketanji Brown Jackson continuerà il suo eccezionale lascito. Ha sottolineato che la sua esperienza come avvocato di alto livello in pratica privata, come ex difensore federale pubblico e come membro di una famiglia di educatori e agenti di polizia, la rende una costruttrice di consenso. Ha anche sottolineato che, dalla sua nomina, ha ricevuto un ampio sostegno, dall'Ordine Fraterno della Polizia a ex giudici nominati da democratici e repubblicani. Ha inoltre sottolineato che la nomina di Justice Breyer è un passo importante verso l'uguaglianza per tutti gli americani, in partic\",\n",
-       "  \"\\n\\nIl presidente ha detto che Justice Breyer ha dedicato la sua vita al servizio di questo paese e ha onorato la sua carriera. Ha anche detto che la sua nomina di Circuit Court of Appeals Judge Ketanji Brown Jackson continuerà il suo eccezionale lascito. Ha sottolineato che la sua esperienza come avvocato di alto livello in pratica privata, come ex difensore federale pubblico e come membro di una famiglia di educatori e agenti di polizia, la rende una costruttrice di consenso. Ha anche sottolineato che, dalla sua nomina, ha ricevuto un ampio sostegno, dall'Ordine Fraterno della Polizia a ex giudici nominati da democratici e repubblicani. Ha inoltre sottolineato che la nomina di Justice Breyer è un passo importante verso l'uguaglianza per tutti gli americani, in partic\"],\n",
-       " 'output_text': \"\\n\\nIl presidente ha detto che Justice Breyer ha dedicato la sua vita al servizio di questo paese e ha onorato la sua carriera. Ha anche detto che la sua nomina di Circuit Court of Appeals Judge Ketanji Brown Jackson continuerà il suo eccezionale lascito. Ha sottolineato che la sua esperienza come avvocato di alto livello in pratica privata, come ex difensore federale pubblico e come membro di una famiglia di educatori e agenti di polizia, la rende una costruttrice di consenso. Ha anche sottolineato che, dalla sua nomina, ha ricevuto un ampio sostegno, dall'Ordine Fraterno della Polizia a ex giudici nominati da democratici e repubblicani. Ha inoltre sottolineato che la nomina di Justice Breyer è un passo importante verso l'uguaglianza per tutti gli americani, in partic\"}"
+       "{'intermediate_steps': ['\\nIl presidente ha detto che Justice Breyer ha dedicato la sua vita al servizio di questo paese e ha reso omaggio al suo servizio.',\n",
+       "  \"\\nIl presidente ha detto che Justice Breyer ha dedicato la sua vita al servizio di questo paese, ha reso omaggio al suo servizio e ha sostenuto la nomina di una top litigatrice in pratica privata, un ex difensore pubblico federale e una famiglia di insegnanti e agenti di polizia delle scuole pubbliche. Ha anche sottolineato l'importanza di avanzare la libertà e la giustizia attraverso la sicurezza delle frontiere e la risoluzione del sistema di immigrazione.\",\n",
+       "  \"\\nIl presidente ha detto che Justice Breyer ha dedicato la sua vita al servizio di questo paese, ha reso omaggio al suo servizio e ha sostenuto la nomina di una top litigatrice in pratica privata, un ex difensore pubblico federale e una famiglia di insegnanti e agenti di polizia delle scuole pubbliche. Ha anche sottolineato l'importanza di avanzare la libertà e la giustizia attraverso la sicurezza delle frontiere, la risoluzione del sistema di immigrazione, la protezione degli americani LGBTQ+ e l'approvazione dell'Equality Act. Ha inoltre sottolineato l'importanza di lavorare insieme per sconfiggere l'epidemia di oppiacei.\",\n",
+       "  \"\\n\\nIl presidente ha detto che Justice Breyer ha dedicato la sua vita al servizio di questo paese, ha reso omaggio al suo servizio e ha sostenuto la nomina di una top litigatrice in pratica privata, un ex difensore pubblico federale e una famiglia di insegnanti e agenti di polizia delle scuole pubbliche. Ha anche sottolineato l'importanza di avanzare la libertà e la giustizia attraverso la sicurezza delle frontiere, la risoluzione del sistema di immigrazione, la protezione degli americani LGBTQ+ e l'approvazione dell'Equality Act. Ha inoltre sottolineato l'importanza di lavorare insieme per sconfiggere l'epidemia di oppiacei e per investire in America, educare gli americani, far crescere la forza lavoro e costruire l'economia dal\"],\n",
+       " 'output_text': \"\\n\\nIl presidente ha detto che Justice Breyer ha dedicato la sua vita al servizio di questo paese, ha reso omaggio al suo servizio e ha sostenuto la nomina di una top litigatrice in pratica privata, un ex difensore pubblico federale e una famiglia di insegnanti e agenti di polizia delle scuole pubbliche. Ha anche sottolineato l'importanza di avanzare la libertà e la giustizia attraverso la sicurezza delle frontiere, la risoluzione del sistema di immigrazione, la protezione degli americani LGBTQ+ e l'approvazione dell'Equality Act. Ha inoltre sottolineato l'importanza di lavorare insieme per sconfiggere l'epidemia di oppiacei e per investire in America, educare gli americani, far crescere la forza lavoro e costruire l'economia dal\"}"
       ]
      },
-     "execution_count": 14,
+     "execution_count": 19,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -532,9 +573,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 20,
    "id": "e2bfe203",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "chain = load_qa_chain(OpenAI(temperature=0), chain_type=\"map_rerank\", return_intermediate_steps=True)"
@@ -542,9 +585,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 21,
    "id": "5c28880c",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "query = \"What did the president say about Justice Breyer\"\n",
@@ -553,17 +598,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 22,
    "id": "80ac2db3",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "' The president thanked Justice Breyer for his service and honored him for dedicating his life to serving the country. '"
+       "' The President thanked Justice Breyer for his service and honored him for dedicating his life to serve the country.'"
       ]
      },
-     "execution_count": 18,
+     "execution_count": 22,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -574,24 +621,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 23,
    "id": "b428fcb9",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[{'answer': ' The president thanked Justice Breyer for his service and honored him for dedicating his life to serving the country. ',\n",
+       "[{'answer': ' The President thanked Justice Breyer for his service and honored him for dedicating his life to serve the country.',\n",
        "  'score': '100'},\n",
-       " {'answer': \" The president said that Justice Breyer is a former top litigator in private practice, a former federal public defender, and from a family of public school educators and police officers. He also said that since she's been nominated, she's received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans, and that she is a consensus builder.\",\n",
-       "  'score': '100'},\n",
-       " {'answer': ' The president did not mention Justice Breyer in this context.',\n",
-       "  'score': '0'},\n",
-       " {'answer': ' The president did not mention Justice Breyer in the given context. ',\n",
-       "  'score': '0'}]"
+       " {'answer': ' This document does not answer the question', 'score': '0'},\n",
+       " {'answer': ' This document does not answer the question', 'score': '0'},\n",
+       " {'answer': ' This document does not answer the question', 'score': '0'}]"
       ]
      },
-     "execution_count": 19,
+     "execution_count": 23,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -612,24 +658,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 24,
    "id": "41b83cd8",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{'intermediate_steps': [{'answer': ' Il presidente ha detto che Justice Breyer ha dedicato la sua vita a servire questo paese e ha onorato la sua carriera.',\n",
+       "{'intermediate_steps': [{'answer': ' Il presidente ha detto che Justice Breyer ha dedicato la sua vita a servire questo paese.',\n",
        "   'score': '100'},\n",
        "  {'answer': ' Il presidente non ha detto nulla sulla Giustizia Breyer.',\n",
        "   'score': '100'},\n",
        "  {'answer': ' Non so.', 'score': '0'},\n",
-       "  {'answer': ' Il presidente non ha detto nulla sulla giustizia Breyer.',\n",
-       "   'score': '100'}],\n",
-       " 'output_text': ' Il presidente ha detto che Justice Breyer ha dedicato la sua vita a servire questo paese e ha onorato la sua carriera.'}"
+       "  {'answer': ' Non so.', 'score': '0'}],\n",
+       " 'output_text': ' Il presidente ha detto che Justice Breyer ha dedicato la sua vita a servire questo paese.'}"
       ]
      },
-     "execution_count": 16,
+     "execution_count": 24,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -694,7 +741,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.9"
   },
   "vscode": {
    "interpreter": {

docs/modules/indexes/document_loaders/examples/bilibili.ipynb

@@ -0,0 +1,87 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "66a7777e",
+   "metadata": {},
+   "source": [
+    "# Bilibili\n",
+    "\n",
+    "This loader utilizes the `bilibili-api` to fetch the text transcript from Bilibili, one of the most beloved long-form video sites in China.\n",
+    "\n",
+    "With this BiliBiliLoader, users can easily obtain the transcript of their desired video content on the platform."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "9ec8a3b3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders.bilibili import BiliBiliLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "43128d8d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#!pip install bilibili-api"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "35d6809a",
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "loader = BiliBiliLoader(\n",
+    "    [\"https://www.bilibili.com/video/BV1xt411o7Xu/\"]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "loader.load()"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  }
+ ],
+ "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
+}

docs/modules/indexes/document_loaders/examples/csv.ipynb

@@ -106,7 +106,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Specify a column to be used identify the document source\n",
+    "## Specify a column to be used identify the document source\n",
     "\n",
     "Use the `source_column` argument to specify a column to be set as the source for the document created from each row. Otherwise `file_path` will be used as the source for all documents created from the csv file.\n",
     "\n",

docs/modules/indexes/document_loaders/examples/example_data/whatsapp_chat.txt

@@ -8,4 +8,5 @@
 1/23/23, 3:02 AM - User 1: I thought you were selling the blue one!
 1/23/23, 3:18 AM - User 2: No Im sorry it was my mistake, the blue one is not for sale
 1/23/23, 3:19 AM - User 1: Oh no worries! Bye
-1/23/23, 3:19 AM - User 2: Bye!
+1/23/23, 3:19 AM - User 2: Bye!
+1/23/23, 3:22_AM - User 1: And let me know if anything changes

docs/modules/indexes/document_loaders/examples/git.ipynb

@@ -0,0 +1,192 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Git\n",
+    "\n",
+    "This notebook shows how to load text files from Git repository."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Load existing repository from disk"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from git import Repo\n",
+    "\n",
+    "repo = Repo.clone_from(\n",
+    "    \"https://github.com/hwchase17/langchain\", to_path=\"./example_data/test_repo1\"\n",
+    ")\n",
+    "branch = repo.head.reference"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import GitLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = GitLoader(repo_path=\"./example_data/test_repo1/\", branch=branch)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "len(data)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "page_content='.venv\\n.github\\n.git\\n.mypy_cache\\n.pytest_cache\\nDockerfile' metadata={'file_path': '.dockerignore', 'file_name': '.dockerignore', 'file_type': ''}\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(data[0])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Clone repository from url"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import GitLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = GitLoader(\n",
+    "    clone_url=\"https://github.com/hwchase17/langchain\",\n",
+    "    repo_path=\"./example_data/test_repo2/\",\n",
+    "    branch=\"master\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "1074"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(data)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Filtering files to load"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import GitLoader\n",
+    "\n",
+    "# eg. loading only python files\n",
+    "loader = GitLoader(repo_path=\"./example_data/test_repo1/\", file_filter=lambda file_path: file_path.endswith(\".py\"))"
+   ]
+  },
+  {
+   "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": "3.11.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/modules/indexes/document_loaders/examples/pdf.ipynb

@@ -104,10 +104,11 @@
       "Efficient Data AnnotationC u s t o m i z e d  M o d e l  T r a i n i n gModel Cust omizationDI A Model HubDI A Pipeline SharingCommunity PlatformLa y out Detection ModelsDocument Images \n",
       "T h e  C o r e  L a y o u t P a r s e r  L i b r a r yOCR ModuleSt or age & VisualizationLa y out Data Structur e\n",
       "Fig. 1: The overall architecture of LayoutParser . For an input document image,\n",
-      "the core LayoutParser library provides a set of o\u000B",
+      "the core LayoutParser library provides a set of o\u000b",
+      "\n",
       "-the-shelf tools for layout\n",
       "detection, OCR, visualization, and storage, backed by a carefully designed layout\n",
-      "data structure. LayoutParser also supports high level customization via e\u000Ecient\n",
+      "data structure. LayoutParser also supports high level customization via e\u000ecient\n",
       "layout annotation and model training functions. These improve model accuracy\n",
       "on the target samples. The community platform enables the easy sharing of DIA\n",
       "models and whole digitization pipelines to promote reusability and reproducibility.\n",
@@ -117,6 +118,7 @@
       "DL-based support for developing and deploying models for general computer\n",
       "vision and natural language processing problems. LayoutParser , on the other\n",
       "hand, specializes speci\f",
+      "\n",
       "cally in DIA tasks. LayoutParser is also equipped with a\n",
       "community platform inspired by established model hubs such as Torch Hub [23]\n",
       "andTensorFlow Hub [1]. It enables the sharing of pretrained models as well as\n",
@@ -125,13 +127,16 @@
       "development of DL models. Some examples include PRImA [ 3](magazine layouts),\n",
       "PubLayNet [ 38](academic paper layouts), Table Bank [ 18](tables in academic\n",
       "papers), Newspaper Navigator Dataset [ 16,17](newspaper \f",
+      "\n",
       "gure layouts) and\n",
       "HJDataset [31](historical Japanese document layouts). A spectrum of models\n",
       "trained on these datasets are currently available in the LayoutParser model zoo\n",
-      "to support di\u000B",
+      "to support di\u000b",
+      "\n",
       "erent use cases.\n",
       "3 The Core LayoutParser Library\n",
-      "At the core of LayoutParser is an o\u000B",
+      "At the core of LayoutParser is an o\u000b",
+      "\n",
       "-the-shelf toolkit that streamlines DL-\n",
       "based document image analysis. Five components support a simple interface\n",
       "with comprehensive functionalities: 1) The layout detection models enable using\n",
@@ -226,7 +231,9 @@
    "outputs": [
     {
      "data": {
-      "text/plain": "Document(page_content='LayoutParser: A Unified Toolkit for Deep\\nLearning Based Document Image Analysis\\nZejiang Shen1 (<28>), Ruochen Zhang2, Melissa Dell3, Benjamin Charles Germain\\nLee4, Jacob Carlson3, and Weining Li5\\n1 Allen Institute for AI\\nshannons@allenai.org\\n2 Brown University\\nruochen zhang@brown.edu\\n3 Harvard University\\n{melissadell,jacob carlson}@fas.harvard.edu\\n4 University of Washington\\nbcgl@cs.washington.edu\\n5 University of Waterloo\\nw422li@uwaterloo.ca\\nAbstract. Recent advances in document image analysis (DIA) have been\\nprimarily driven by the application of neural networks. Ideally, research\\noutcomes could be easily deployed in production and extended for further\\ninvestigation. However, various factors like loosely organized codebases\\nand sophisticated model configurations complicate the easy reuse of im-\\nportant innovations by a wide audience. Though there have been on-going\\nefforts to improve reusability and simplify deep learning (DL) model\\ndevelopment in disciplines like natural language processing and computer\\nvision, none of them are optimized for challenges in the domain of DIA.\\nThis represents a major gap in the existing toolkit, as DIA is central to\\nacademic research across a wide range of disciplines in the social sciences\\nand humanities. This paper introduces LayoutParser, an open-source\\nlibrary for streamlining the usage of DL in DIA research and applica-\\ntions. The core LayoutParser library comes with a set of simple and\\nintuitive interfaces for applying and customizing DL models for layout de-\\ntection, character recognition, and many other document processing tasks.\\nTo promote extensibility, LayoutParser also incorporates a community\\nplatform for sharing both pre-trained models and full document digiti-\\nzation pipelines. We demonstrate that LayoutParser is helpful for both\\nlightweight and large-scale digitization pipelines in real-word use cases.\\nThe library is publicly available at https://layout-parser.github.io.\\nKeywords: Document Image Analysis · Deep Learning · Layout Analysis\\n· Character Recognition · Open Source library · Toolkit.\\n1\\nIntroduction\\nDeep Learning(DL)-based approaches are the state-of-the-art for a wide range of\\ndocument image analysis (DIA) tasks including document image classification [11,\\narXiv:2103.15348v2  [cs.CV]  21 Jun 2021\\n', lookup_str='', metadata={'file_path': 'example_data/layout-parser-paper.pdf', 'page_number': 1, 'total_pages': 16, 'format': 'PDF 1.5', 'title': '', 'author': '', 'subject': '', 'keywords': '', 'creator': 'LaTeX with hyperref', 'producer': 'pdfTeX-1.40.21', 'creationDate': 'D:20210622012710Z', 'modDate': 'D:20210622012710Z', 'trapped': '', 'encryption': None}, lookup_index=0)"
+      "text/plain": [
+       "Document(page_content='LayoutParser: A Unified Toolkit for Deep\\nLearning Based Document Image Analysis\\nZejiang Shen1 (<28>), Ruochen Zhang2, Melissa Dell3, Benjamin Charles Germain\\nLee4, Jacob Carlson3, and Weining Li5\\n1 Allen Institute for AI\\nshannons@allenai.org\\n2 Brown University\\nruochen zhang@brown.edu\\n3 Harvard University\\n{melissadell,jacob carlson}@fas.harvard.edu\\n4 University of Washington\\nbcgl@cs.washington.edu\\n5 University of Waterloo\\nw422li@uwaterloo.ca\\nAbstract. Recent advances in document image analysis (DIA) have been\\nprimarily driven by the application of neural networks. Ideally, research\\noutcomes could be easily deployed in production and extended for further\\ninvestigation. However, various factors like loosely organized codebases\\nand sophisticated model configurations complicate the easy reuse of im-\\nportant innovations by a wide audience. Though there have been on-going\\nefforts to improve reusability and simplify deep learning (DL) model\\ndevelopment in disciplines like natural language processing and computer\\nvision, none of them are optimized for challenges in the domain of DIA.\\nThis represents a major gap in the existing toolkit, as DIA is central to\\nacademic research across a wide range of disciplines in the social sciences\\nand humanities. This paper introduces LayoutParser, an open-source\\nlibrary for streamlining the usage of DL in DIA research and applica-\\ntions. The core LayoutParser library comes with a set of simple and\\nintuitive interfaces for applying and customizing DL models for layout de-\\ntection, character recognition, and many other document processing tasks.\\nTo promote extensibility, LayoutParser also incorporates a community\\nplatform for sharing both pre-trained models and full document digiti-\\nzation pipelines. We demonstrate that LayoutParser is helpful for both\\nlightweight and large-scale digitization pipelines in real-word use cases.\\nThe library is publicly available at https://layout-parser.github.io.\\nKeywords: Document Image Analysis · Deep Learning · Layout Analysis\\n· Character Recognition · Open Source library · Toolkit.\\n1\\nIntroduction\\nDeep Learning(DL)-based approaches are the state-of-the-art for a wide range of\\ndocument image analysis (DIA) tasks including document image classification [11,\\narXiv:2103.15348v2  [cs.CV]  21 Jun 2021\\n', lookup_str='', metadata={'file_path': 'example_data/layout-parser-paper.pdf', 'page_number': 1, 'total_pages': 16, 'format': 'PDF 1.5', 'title': '', 'author': '', 'subject': '', 'keywords': '', 'creator': 'LaTeX with hyperref', 'producer': 'pdfTeX-1.40.21', 'creationDate': 'D:20210622012710Z', 'modDate': 'D:20210622012710Z', 'trapped': '', 'encryption': None}, lookup_index=0)"
+      ]
      },
      "execution_count": 5,
      "metadata": {},
@@ -239,53 +246,51 @@
   },
   {
    "cell_type": "markdown",
+   "id": "278c881f",
+   "metadata": {},
    "source": [
     "### Fetching remote PDFs using Unstructured\n",
     "\n",
     "This covers how to load online pdfs into a document format that we can use downstream. This can be used for various online pdf sites such as https://open.umn.edu/opentextbooks/textbooks/ and https://arxiv.org/archive/\n",
     "\n",
     "Note: all other pdf loaders can also be used to fetch remote PDFs, but `OnlinePDFLoader` is a legacy function, and works specifically with `UnstructuredPDFLoader`.\n"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 6,
+   "id": "0c2686fc",
+   "metadata": {},
    "outputs": [],
    "source": [
     "from langchain.document_loaders import OnlinePDFLoader"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 7,
+   "id": "101e0b82",
+   "metadata": {},
    "outputs": [],
    "source": [
     "loader = OnlinePDFLoader(\"https://arxiv.org/pdf/2302.03803.pdf\")"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 8,
+   "id": "be3ccbfa",
+   "metadata": {},
    "outputs": [],
    "source": [
     "data = loader.load()"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 9,
+   "id": "e1298dd6",
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -297,17 +302,13 @@
    ],
    "source": [
     "print(data)"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+   ]
   },
   {
    "cell_type": "markdown",
-   "source": [],
-   "metadata": {
-    "collapsed": false
-   }
+   "id": "05187b33",
+   "metadata": {},
+   "source": []
   },
   {
    "cell_type": "markdown",
@@ -349,55 +350,101 @@
   },
   {
    "cell_type": "markdown",
+   "id": "c90a5fe8",
+   "metadata": {},
    "source": [
-    "## Using PyMuPDF\n",
-    "\n",
-    "This is the fastest of the PDF parsing options, and contains detailed metadata about the PDF and its pages, as well as returns one document per page."
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+    "## Using PDFMiner to generate HTML text"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "eb785e1c",
+   "metadata": {},
+   "source": [
+    "This can be helpful for chunking texts semantically into sections as the output html content can be parsed via `BeautifulSoup` to get more structured and rich information about font size, page numbers, pdf headers/footers, etc."
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 1,
+   "id": "601000d7",
+   "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.document_loaders import PyMuPDFLoader"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "outputs": [],
-   "source": [
-    "loader = PyMuPDFLoader(\"example_data/layout-parser-paper.pdf\")"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+    "from langchain.document_loaders import PDFMinerPDFasHTMLLoader"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 3,
+   "id": "a5525fb0",
+   "metadata": {},
    "outputs": [],
    "source": [
-    "data = loader.load()"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+    "loader = PDFMinerPDFasHTMLLoader(\"example_data/layout-parser-paper.pdf\")"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 4,
+   "id": "dac7ff68",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cc2c2f4f",
+   "metadata": {},
+   "source": [
+    "## Using PyMuPDF\n",
+    "\n",
+    "This is the fastest of the PDF parsing options, and contains detailed metadata about the PDF and its pages, as well as returns one document per page."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "55f0c4d8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import PyMuPDFLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "718cbfbc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = PyMuPDFLoader(\"example_data/layout-parser-paper.pdf\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "f2f93a15",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "a24dfaa6",
+   "metadata": {},
    "outputs": [
     {
      "data": {
-      "text/plain": "Document(page_content='LayoutParser: A Unified Toolkit for Deep\\nLearning Based Document Image Analysis\\nZejiang Shen1 (<28>), Ruochen Zhang2, Melissa Dell3, Benjamin Charles Germain\\nLee4, Jacob Carlson3, and Weining Li5\\n1 Allen Institute for AI\\nshannons@allenai.org\\n2 Brown University\\nruochen zhang@brown.edu\\n3 Harvard University\\n{melissadell,jacob carlson}@fas.harvard.edu\\n4 University of Washington\\nbcgl@cs.washington.edu\\n5 University of Waterloo\\nw422li@uwaterloo.ca\\nAbstract. Recent advances in document image analysis (DIA) have been\\nprimarily driven by the application of neural networks. Ideally, research\\noutcomes could be easily deployed in production and extended for further\\ninvestigation. However, various factors like loosely organized codebases\\nand sophisticated model configurations complicate the easy reuse of im-\\nportant innovations by a wide audience. Though there have been on-going\\nefforts to improve reusability and simplify deep learning (DL) model\\ndevelopment in disciplines like natural language processing and computer\\nvision, none of them are optimized for challenges in the domain of DIA.\\nThis represents a major gap in the existing toolkit, as DIA is central to\\nacademic research across a wide range of disciplines in the social sciences\\nand humanities. This paper introduces LayoutParser, an open-source\\nlibrary for streamlining the usage of DL in DIA research and applica-\\ntions. The core LayoutParser library comes with a set of simple and\\nintuitive interfaces for applying and customizing DL models for layout de-\\ntection, character recognition, and many other document processing tasks.\\nTo promote extensibility, LayoutParser also incorporates a community\\nplatform for sharing both pre-trained models and full document digiti-\\nzation pipelines. We demonstrate that LayoutParser is helpful for both\\nlightweight and large-scale digitization pipelines in real-word use cases.\\nThe library is publicly available at https://layout-parser.github.io.\\nKeywords: Document Image Analysis · Deep Learning · Layout Analysis\\n· Character Recognition · Open Source library · Toolkit.\\n1\\nIntroduction\\nDeep Learning(DL)-based approaches are the state-of-the-art for a wide range of\\ndocument image analysis (DIA) tasks including document image classification [11,\\narXiv:2103.15348v2  [cs.CV]  21 Jun 2021\\n', lookup_str='', metadata={'file_path': 'example_data/layout-parser-paper.pdf', 'page_number': 1, 'total_pages': 16, 'format': 'PDF 1.5', 'title': '', 'author': '', 'subject': '', 'keywords': '', 'creator': 'LaTeX with hyperref', 'producer': 'pdfTeX-1.40.21', 'creationDate': 'D:20210622012710Z', 'modDate': 'D:20210622012710Z', 'trapped': '', 'encryption': None}, lookup_index=0)"
+      "text/plain": [
+       "Document(page_content='LayoutParser: A Unified Toolkit for Deep\\nLearning Based Document Image Analysis\\nZejiang Shen1 (<28>), Ruochen Zhang2, Melissa Dell3, Benjamin Charles Germain\\nLee4, Jacob Carlson3, and Weining Li5\\n1 Allen Institute for AI\\nshannons@allenai.org\\n2 Brown University\\nruochen zhang@brown.edu\\n3 Harvard University\\n{melissadell,jacob carlson}@fas.harvard.edu\\n4 University of Washington\\nbcgl@cs.washington.edu\\n5 University of Waterloo\\nw422li@uwaterloo.ca\\nAbstract. Recent advances in document image analysis (DIA) have been\\nprimarily driven by the application of neural networks. Ideally, research\\noutcomes could be easily deployed in production and extended for further\\ninvestigation. However, various factors like loosely organized codebases\\nand sophisticated model configurations complicate the easy reuse of im-\\nportant innovations by a wide audience. Though there have been on-going\\nefforts to improve reusability and simplify deep learning (DL) model\\ndevelopment in disciplines like natural language processing and computer\\nvision, none of them are optimized for challenges in the domain of DIA.\\nThis represents a major gap in the existing toolkit, as DIA is central to\\nacademic research across a wide range of disciplines in the social sciences\\nand humanities. This paper introduces LayoutParser, an open-source\\nlibrary for streamlining the usage of DL in DIA research and applica-\\ntions. The core LayoutParser library comes with a set of simple and\\nintuitive interfaces for applying and customizing DL models for layout de-\\ntection, character recognition, and many other document processing tasks.\\nTo promote extensibility, LayoutParser also incorporates a community\\nplatform for sharing both pre-trained models and full document digiti-\\nzation pipelines. We demonstrate that LayoutParser is helpful for both\\nlightweight and large-scale digitization pipelines in real-word use cases.\\nThe library is publicly available at https://layout-parser.github.io.\\nKeywords: Document Image Analysis · Deep Learning · Layout Analysis\\n· Character Recognition · Open Source library · Toolkit.\\n1\\nIntroduction\\nDeep Learning(DL)-based approaches are the state-of-the-art for a wide range of\\ndocument image analysis (DIA) tasks including document image classification [11,\\narXiv:2103.15348v2  [cs.CV]  21 Jun 2021\\n', lookup_str='', metadata={'file_path': 'example_data/layout-parser-paper.pdf', 'page_number': 1, 'total_pages': 16, 'format': 'PDF 1.5', 'title': '', 'author': '', 'subject': '', 'keywords': '', 'creator': 'LaTeX with hyperref', 'producer': 'pdfTeX-1.40.21', 'creationDate': 'D:20210622012710Z', 'modDate': 'D:20210622012710Z', 'trapped': '', 'encryption': None}, lookup_index=0)"
+      ]
      },
      "execution_count": 4,
      "metadata": {},
@@ -406,28 +453,23 @@
    ],
    "source": [
     "data[0]"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+   ]
   },
   {
    "cell_type": "markdown",
+   "id": "83cb52a0",
+   "metadata": {},
    "source": [
     "Additionally, you can pass along any of the options from the [PyMuPDF documentation](https://pymupdf.readthedocs.io/en/latest/app1.html#plain-text/) as keyword arguments in the `load` call, and it will be pass along to the `get_text()` call."
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "1bf73c97",
+   "metadata": {},
    "outputs": [],
-   "source": [],
-   "metadata": {
-    "collapsed": false
-   }
+   "source": []
   }
  ],
  "metadata": {
@@ -446,7 +488,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.8"
   }
  },
  "nbformat": 4,

docs/modules/indexes/document_loaders/examples/slack_directory.ipynb

@@ -0,0 +1,81 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "1dc7df1d",
+   "metadata": {},
+   "source": [
+    "# Slack (Local Exported Zipfile)\n",
+    "\n",
+    "This notebook covers how to load documents from a Zipfile generated from a Slack export.\n",
+    "\n",
+    "In order to get this Slack export, follow these instructions:\n",
+    "\n",
+    "## 🧑 Instructions for ingesting your own dataset\n",
+    "\n",
+    "Export your Slack data. You can do this by going to your Workspace Management page and clicking the Import/Export option ({your_slack_domain}.slack.com/services/export). Then, choose the right date range and click `Start export`. Slack will send you an email and a DM when the export is ready.\n",
+    "\n",
+    "The download will produce a `.zip` file in your Downloads folder (or wherever your downloads can be found, depending on your OS configuration).\n",
+    "\n",
+    "Copy the path to the `.zip` file, and assign it as `LOCAL_ZIPFILE` below."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "007c5cbf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import SlackDirectoryLoader "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a1caec59",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Optionally set your Slack URL. This will give you proper URLs in the docs sources.\n",
+    "SLACK_WORKSPACE_URL = \"https://xxx.slack.com\"\n",
+    "LOCAL_ZIPFILE = \"\" # Paste the local paty to your Slack zip file here.\n",
+    "\n",
+    "loader = SlackDirectoryLoader(LOCAL_ZIPFILE, SLACK_WORKSPACE_URL)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b1c30ff7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "docs = loader.load()\n",
+    "docs"
+   ]
+  }
+ ],
+ "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": "3.11.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/modules/indexes/document_loaders/examples/url.ipynb

@@ -112,6 +112,79 @@
    "source": [
     "data = loader.load()"
    ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "a2c1c79f",
+   "metadata": {},
+   "source": [
+    "# Playwright URL Loader\n",
+    "\n",
+    "This covers how to load HTML documents from a list of URLs using the `PlaywrightURLLoader`.\n",
+    "\n",
+    "As in the Selenium case, Playwright allows us to load pages that need JavaScript to render.\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "To use the `PlaywrightURLLoader`, you will need to install `playwright` and `unstructured`. Additionally, you will need to install the Playwright Chromium browser:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "53158417",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Install playwright\n",
+    "!pip install \"playwright\"\n",
+    "!pip install \"unstructured\"\n",
+    "!playwright install"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0ab4e115",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import PlaywrightURLLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ce5a9a0a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "urls = [\n",
+    "    \"https://www.youtube.com/watch?v=dQw4w9WgXcQ\",\n",
+    "    \"https://goo.gl/maps/NDSHwePEyaHMFGwh8\"\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2dc3e0bc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = PlaywrightURLLoader(urls=urls, remove_selectors=[\"header\", \"footer\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "10b79f80",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
   }
  ],
  "metadata": {
@@ -130,7 +203,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.13"
+   "version": "3.10.6"
   }
  },
  "nbformat": 4,

docs/modules/indexes/document_loaders/examples/web_base.ipynb

@@ -89,7 +89,7 @@
    "id": "150988e6",
    "metadata": {},
    "source": [
-    "# Loading multiple webpages\n",
+    "## Loading multiple webpages\n",
     "\n",
     "You can also load multiple webpages at once by passing in a list of urls to the loader. This will return a list of documents in the same order as the urls passed in."
    ]
@@ -123,7 +123,7 @@
    "id": "641be294",
    "metadata": {},
    "source": [
-    "## Load multiple urls concurrently\n",
+    "### Load multiple urls concurrently\n",
     "\n",
     "You can speed up the scraping process by scraping and parsing multiple urls concurrently.\n",
     "\n",

docs/modules/indexes/getting_started.ipynb

@@ -99,7 +99,7 @@
    "outputs": [],
    "source": [
     "from langchain.document_loaders import TextLoader\n",
-    "loader = TextLoader('../state_of_the_union.txt')"
+    "loader = TextLoader('../state_of_the_union.txt', encoding='utf8')"
    ]
   },
   {

docs/modules/indexes/retrievers/examples/databerry.ipynb

@@ -0,0 +1,95 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "9fc6205b",
+   "metadata": {},
+   "source": [
+    "# Databerry\n",
+    "\n",
+    "This notebook shows how to use [Databerry's](https://www.databerry.ai/) retriever.\n",
+    "\n",
+    "First, you will need to sign up for Databerry, create a datastore, add some data and get your datastore api endpoint url"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "944e172b",
+   "metadata": {},
+   "source": [
+    "## Query\n",
+    "\n",
+    "Now that our index is set up, we can set up a retriever and start querying it."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "d0e6f506",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.retrievers import DataberryRetriever"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "f381f642",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "retriever = DataberryRetriever(\n",
+    "    datastore_url=\"https://clg1xg2h80000l708dymr0fxc.databerry.ai/query\",\n",
+    "    # api_key=\"DATABERRY_API_KEY\", # optional if datastore is public\n",
+    "    # top_k=10 # optional\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "20ae1a74",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='✨ Made with DaftpageOpen main menuPricingTemplatesLoginSearchHelpGetting StartedFeaturesAffiliate ProgramGetting StartedDaftpage is a new type of website builder that works like a doc.It makes website building easy, fun and offers tons of powerful features for free. Just type / in your page to get started!DaftpageCopyright © 2022 Daftpage, Inc.All rights reserved.ProductPricingTemplatesHelp & SupportHelp CenterGetting startedBlogCompanyAboutRoadmapTwitterAffiliate Program👾 Discord', metadata={'source': 'https:/daftpage.com/help/getting-started', 'score': 0.8697265}),\n",
+       " Document(page_content=\"✨ Made with DaftpageOpen main menuPricingTemplatesLoginSearchHelpGetting StartedFeaturesAffiliate ProgramHelp CenterWelcome to Daftpage’s help center—the one-stop shop for learning everything about building websites with Daftpage.Daftpage is the simplest way to create websites for all purposes in seconds. Without knowing how to code, and for free!Get StartedDaftpage is a new type of website builder that works like a doc.It makes website building easy, fun and offers tons of powerful features for free. Just type / in your page to get started!Start here✨ Create your first site🧱 Add blocks🚀 PublishGuides🔖 Add a custom domainFeatures🔥 Drops🎨 Drawings👻 Ghost mode💀 Skeleton modeCant find the answer you're looking for?mail us at support@daftpage.comJoin the awesome Daftpage community on: 👾 DiscordDaftpageCopyright © 2022 Daftpage, Inc.All rights reserved.ProductPricingTemplatesHelp & SupportHelp CenterGetting startedBlogCompanyAboutRoadmapTwitterAffiliate Program👾 Discord\", metadata={'source': 'https:/daftpage.com/help', 'score': 0.86570895}),\n",
+       " Document(page_content=\" is the simplest way to create websites for all purposes in seconds. Without knowing how to code, and for free!Get StartedDaftpage is a new type of website builder that works like a doc.It makes website building easy, fun and offers tons of powerful features for free. Just type / in your page to get started!Start here✨ Create your first site🧱 Add blocks🚀 PublishGuides🔖 Add a custom domainFeatures🔥 Drops🎨 Drawings👻 Ghost mode💀 Skeleton modeCant find the answer you're looking for?mail us at support@daftpage.comJoin the awesome Daftpage community on: 👾 DiscordDaftpageCopyright © 2022 Daftpage, Inc.All rights reserved.ProductPricingTemplatesHelp & SupportHelp CenterGetting startedBlogCompanyAboutRoadmapTwitterAffiliate Program👾 Discord\", metadata={'source': 'https:/daftpage.com/help', 'score': 0.8645384})]"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "retriever.get_relevant_documents(\"What is Daftpage?\")"
+   ]
+  }
+ ],
+ "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": "3.11.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/modules/indexes/retrievers/examples/pinecone_hybrid_search.ipynb

@@ -1,6 +1,7 @@
 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "ab66dd43",
    "metadata": {},
@@ -9,12 +10,12 @@
     "\n",
     "This notebook goes over how to use a retriever that under the hood uses Pinecone and Hybrid Search.\n",
     "\n",
-    "The logic of this retriever is largely taken from [this blog post](https://www.pinecone.io/learn/hybrid-search-intro/)"
+    "The logic of this retriever is taken from [this documentaion](https://docs.pinecone.io/docs/hybrid-search)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 75,
    "id": "393ac030",
    "metadata": {},
    "outputs": [],
@@ -31,43 +32,61 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "15390796",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import pinecone  # !pip install pinecone-client\n",
-    "\n",
-    "pinecone.init(\n",
-    "   api_key=\"...\",  # API key here\n",
-    "   environment=\"...\"  # find next to api key in console\n",
-    ")\n",
-    "# choose a name for your index\n",
-    "index_name = \"...\""
-   ]
-  },
-  {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "95d5d7f9",
    "metadata": {},
    "source": [
-    "You should only have to do this part once."
+    "You should only have to do this part once.\n",
+    "\n",
+    "Note: it's important to make sure that the \"context\" field that holds the document text in the metadata is not indexed. Currently you need to specify explicitly the fields you do want to index. For more information checkout Pinecone's [docs](https://docs.pinecone.io/docs/manage-indexes#selective-metadata-indexing)."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 76,
+   "id": "3b8f7697",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "WhoAmIResponse(username='load', user_label='label', projectname='load-test')"
+      ]
+     },
+     "execution_count": 76,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import os\n",
+    "import pinecone\n",
+    "\n",
+    "api_key = os.getenv(\"PINECONE_API_KEY\") or \"PINECONE_API_KEY\"\n",
+    "# find environment next to your API key in the Pinecone console\n",
+    "env = os.getenv(\"PINECONE_ENVIRONMENT\") or \"PINECONE_ENVIRONMENT\"\n",
+    "\n",
+    "index_name = \"langchain-pinecone-hybrid-search\"\n",
+    "\n",
+    "pinecone.init(api_key=api_key, enviroment=env)\n",
+    "pinecone.whoami()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 77,
    "id": "cfa3a8d8",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# create the index\n",
+    " # create the index\n",
     "pinecone.create_index(\n",
     "   name = index_name,\n",
     "   dimension = 1536,  # dimensionality of dense model\n",
-    "   metric = \"dotproduct\",\n",
-    "   pod_type = \"s1\"\n",
+    "   metric = \"dotproduct\",  # sparse values supported only for dotproduct\n",
+    "   pod_type = \"s1\",\n",
+    "   metadata_config={\"indexed\": []}  # see explaination above\n",
     ")"
    ]
   },
@@ -81,7 +100,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 78,
    "id": "bcb3c8c2",
    "metadata": {},
    "outputs": [],
@@ -90,18 +109,19 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "dbc025d6",
    "metadata": {},
    "source": [
-    "## Get embeddings and tokenizers\n",
+    "## Get embeddings and sparse encoders\n",
     "\n",
     "Embeddings are used for the dense vectors, tokenizer is used for the sparse vector"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 79,
    "id": "2f63c911",
    "metadata": {},
    "outputs": [],
@@ -110,19 +130,51 @@
     "embeddings = OpenAIEmbeddings()"
    ]
   },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "96bf8879",
+   "metadata": {},
+   "source": [
+    "To encode the text to sparse values you can either choose SPLADE or BM25. For out of domain tasks we recommend using BM25.\n",
+    "\n",
+    "For more information about the sparse encoders you can checkout pinecone-text library [docs](https://pinecone-io.github.io/pinecone-text/pinecone_text.html)."
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 80,
    "id": "c3f030e5",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from transformers import BertTokenizerFast  # !pip install transformers\n",
+    "from pinecone_text.sparse import BM25Encoder\n",
+    "# or from pinecone_text.sparse import SpladeEncoder if you wish to work with SPLADE\n",
     "\n",
-    "# load bert tokenizer from huggingface\n",
-    "tokenizer = BertTokenizerFast.from_pretrained(\n",
-    "   'bert-base-uncased'\n",
-    ")"
+    "# use default tf-idf values\n",
+    "bm25_encoder = BM25Encoder().default()"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "23601ddb",
+   "metadata": {},
+   "source": [
+    "The above code is using default tfids values. It's highly recommended to fit the tf-idf values to your own corpus. You can do it as follow:\n",
+    "\n",
+    "```python\n",
+    "corpus = [\"foo\", \"bar\", \"world\", \"hello\"]\n",
+    "\n",
+    "# fit tf-idf values on your corpus\n",
+    "bm25_encoder.fit(corpus)\n",
+    "\n",
+    "# store the values to a json file\n",
+    "bm25_encoder.dump(\"bm25_values.json\")\n",
+    "\n",
+    "# load to your BM25Encoder object\n",
+    "bm25_encoder = BM25Encoder().load(\"bm25_values.json\")\n",
+    "```"
    ]
   },
   {
@@ -137,12 +189,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 81,
    "id": "ac77d835",
    "metadata": {},
    "outputs": [],
    "source": [
-    "retriever = PineconeHybridSearchRetriever(embeddings=embeddings, index=index, tokenizer=tokenizer)"
+    "retriever = PineconeHybridSearchRetriever(embeddings=embeddings, sparse_encoder=bm25_encoder, index=index)"
    ]
   },
   {
@@ -157,23 +209,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 82,
    "id": "98b1c017",
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "4d6f3ee7ca754d07a1a18d100d99e0cd",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "  0%|          | 0/1 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████| 1/1 [00:02<00:00,  2.27s/it]\n"
+     ]
     }
    ],
    "source": [
@@ -192,7 +237,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 83,
    "id": "c0455218",
    "metadata": {},
    "outputs": [],
@@ -202,7 +247,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 84,
    "id": "7dfa5c29",
    "metadata": {},
    "outputs": [
@@ -212,7 +257,7 @@
        "Document(page_content='foo', metadata={})"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 84,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -220,19 +265,11 @@
    "source": [
     "result[0]"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "74bd9256",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": ".venv",
    "language": "python",
    "name": "python3"
   },
@@ -246,7 +283,12 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.9.13"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "7ec0d8babd8cabf695a1d94b1e586d626e046c9df609f6bad065d15d49f67f54"
+   }
   }
  },
  "nbformat": 4,

docs/modules/indexes/retrievers/examples/svm_retriever.ipynb

@@ -0,0 +1,128 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "ab66dd43",
+   "metadata": {},
+   "source": [
+    "# SVM Retriever\n",
+    "\n",
+    "This notebook goes over how to use a retriever that under the hood uses an SVM using scikit-learn.\n",
+    "\n",
+    "Largely based on https://github.com/karpathy/randomfun/blob/master/knn_vs_svm.ipynb"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "393ac030",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.retrievers import SVMRetriever\n",
+    "from langchain.embeddings import OpenAIEmbeddings"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "a801b57c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# !pip install scikit-learn"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "aaf80e7f",
+   "metadata": {},
+   "source": [
+    "## Create New Retriever with Texts"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "98b1c017",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "retriever = SVMRetriever.from_texts([\"foo\", \"bar\", \"world\", \"hello\", \"foo bar\"], OpenAIEmbeddings())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "08437fa2",
+   "metadata": {},
+   "source": [
+    "## Use Retriever\n",
+    "\n",
+    "We can now use the retriever!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "c0455218",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "result = retriever.get_relevant_documents(\"foo\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "7dfa5c29",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='foo', metadata={}),\n",
+       " Document(page_content='foo bar', metadata={}),\n",
+       " Document(page_content='hello', metadata={}),\n",
+       " Document(page_content='world', metadata={})]"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "result"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "74bd9256",
+   "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
+}

docs/modules/indexes/vectorstores/examples/deeplake.ipynb

@@ -17,34 +17,36 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!python3 -m pip install openai deeplake"
+    "!python3 -m pip install openai deeplake tiktoken"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain.embeddings.openai import OpenAIEmbeddings\n",
     "from langchain.text_splitter import CharacterTextSplitter\n",
-    "from langchain.vectorstores import DeepLake\n",
-    "from langchain.document_loaders import TextLoader"
+    "from langchain.vectorstores import DeepLake"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
     "import os\n",
-    "os.environ['OPENAI_API_KEY'] = 'sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx'"
+    "import getpass\n",
+    "\n",
+    "os.environ['OPENAI_API_KEY'] = getpass.getpass('OpenAI API Key:')\n",
+    "embeddings = OpenAIEmbeddings()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -60,9 +62,38 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "mem://langchain loaded successfully.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Evaluating ingest: 100%|██████████| 1/1 [00:04<00:00\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dataset(path='mem://langchain', tensors=['embedding', 'ids', 'metadata', 'text'])\n",
+      "\n",
+      "  tensor     htype     shape     dtype  compression\n",
+      "  -------   -------   -------   -------  ------- \n",
+      " embedding  generic  (4, 1536)  float32   None   \n",
+      "    ids      text     (4, 1)      str     None   \n",
+      " metadata    json     (4, 1)      str     None   \n",
+      "   text      text     (4, 1)      str     None   \n"
+     ]
+    }
+   ],
    "source": [
     "db = DeepLake.from_documents(docs, embeddings)\n",
     "\n",
@@ -72,9 +103,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
+      "\n",
+      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
+      "\n",
+      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
+      "\n",
+      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n"
+     ]
+    }
+   ],
    "source": [
     "print(docs[0].page_content)"
    ]
@@ -89,9 +134,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/media/sdb/davit/.local/lib/python3.10/site-packages/langchain/llms/openai.py:624: UserWarning: You are trying to use a chat model. This way of initializing it is no longer supported. Instead, please use: `from langchain.chat_models import ChatOpenAI`\n",
+      "  warnings.warn(\n"
+     ]
+    }
+   ],
    "source": [
     "from langchain.chains import RetrievalQA\n",
     "from langchain.llms import OpenAIChat\n",
@@ -101,9 +155,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 10,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'The president nominated Circuit Court of Appeals Judge Ketanji Brown Jackson for the United States Supreme Court and praised her qualifications and broad support from both Democrats and Republicans.'"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "query = 'What did the president say about Ketanji Brown Jackson'\n",
     "qa.run(query)"
@@ -119,9 +184,43 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 11,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "mem://langchain loaded successfully.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Evaluating ingest: 100%|██████████| 1/1 [00:04<00:00\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dataset(path='mem://langchain', tensors=['embedding', 'ids', 'metadata', 'text'])\n",
+      "\n",
+      "  tensor     htype     shape      dtype  compression\n",
+      "  -------   -------   -------    -------  ------- \n",
+      " embedding  generic  (42, 1536)  float32   None   \n",
+      "    ids      text     (42, 1)      str     None   \n",
+      " metadata    json     (42, 1)      str     None   \n",
+      "   text      text     (42, 1)      str     None   \n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": []
+    }
+   ],
    "source": [
     "import random\n",
     "\n",
@@ -133,9 +232,30 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 12,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████| 42/42 [00:00<00:00, 3456.17it/s]\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \\n\\nAnd if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \\n\\nWe can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling.  \\n\\nWe’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers.  \\n\\nWe’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \\n\\nWe’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.', metadata={'source': '../../../state_of_the_union.txt', 'year': 2013}),\n",
+       " Document(page_content='And for our LGBTQ+ Americans, let’s finally get the bipartisan Equality Act to my desk. The onslaught of state laws targeting transgender Americans and their families is wrong. \\n\\nAs I said last year, especially to our younger transgender Americans, I will always have your back as your President, so you can be yourself and reach your God-given potential. \\n\\nWhile it often appears that we never agree, that isn’t true. I signed 80 bipartisan bills into law last year. From preventing government shutdowns to protecting Asian-Americans from still-too-common hate crimes to reforming military justice. \\n\\nAnd soon, we’ll strengthen the Violence Against Women Act that I first wrote three decades ago. It is important for us to show the nation that we can come together and do big things. \\n\\nSo tonight I’m offering a Unity Agenda for the Nation. Four big things we can do together.  \\n\\nFirst, beat the opioid epidemic.', metadata={'source': '../../../state_of_the_union.txt', 'year': 2013}),\n",
+       " Document(page_content='Vice President Harris and I ran for office with a new economic vision for America. \\n\\nInvest in America. Educate Americans. Grow the workforce. Build the economy from the bottom up  \\nand the middle out, not from the top down.  \\n\\nBecause we know that when the middle class grows, the poor have a ladder up and the wealthy do very well. \\n\\nAmerica used to have the best roads, bridges, and airports on Earth. \\n\\nNow our infrastructure is ranked 13th in the world. \\n\\nWe won’t be able to compete for the jobs of the 21st Century if we don’t fix that. \\n\\nThat’s why it was so important to pass the Bipartisan Infrastructure Law—the most sweeping investment to rebuild America in history. \\n\\nThis was a bipartisan effort, and I want to thank the members of both parties who worked to make it happen. \\n\\nWe’re done talking about infrastructure weeks. \\n\\nWe’re going to have an infrastructure decade.', metadata={'source': '../../../state_of_the_union.txt', 'year': 2013}),\n",
+       " Document(page_content='It is going to transform America and put us on a path to win the economic competition of the 21st Century that we face with the rest of the world—particularly with China.  \\n\\nAs I’ve told Xi Jinping, it is never a good bet to bet against the American people. \\n\\nWe’ll create good jobs for millions of Americans, modernizing roads, airports, ports, and waterways all across America. \\n\\nAnd we’ll do it all to withstand the devastating effects of the climate crisis and promote environmental justice. \\n\\nWe’ll build a national network of 500,000 electric vehicle charging stations, begin to replace poisonous lead pipes—so every child—and every American—has clean water to drink at home and at school, provide affordable high-speed internet for every American—urban, suburban, rural, and tribal communities. \\n\\n4,000 projects have already been announced. \\n\\nAnd tonight, I’m announcing that this year we will start fixing over 65,000 miles of highway and 1,500 bridges in disrepair.', metadata={'source': '../../../state_of_the_union.txt', 'year': 2013})]"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "db.similarity_search('What did the president say about Ketanji Brown Jackson', filter={'year': 2013})"
    ]
@@ -151,9 +271,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 13,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', metadata={'source': '../../../state_of_the_union.txt', 'year': 2012}),\n",
+       " Document(page_content='A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \\n\\nAnd if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \\n\\nWe can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling.  \\n\\nWe’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers.  \\n\\nWe’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \\n\\nWe’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.', metadata={'source': '../../../state_of_the_union.txt', 'year': 2013}),\n",
+       " Document(page_content='And for our LGBTQ+ Americans, let’s finally get the bipartisan Equality Act to my desk. The onslaught of state laws targeting transgender Americans and their families is wrong. \\n\\nAs I said last year, especially to our younger transgender Americans, I will always have your back as your President, so you can be yourself and reach your God-given potential. \\n\\nWhile it often appears that we never agree, that isn’t true. I signed 80 bipartisan bills into law last year. From preventing government shutdowns to protecting Asian-Americans from still-too-common hate crimes to reforming military justice. \\n\\nAnd soon, we’ll strengthen the Violence Against Women Act that I first wrote three decades ago. It is important for us to show the nation that we can come together and do big things. \\n\\nSo tonight I’m offering a Unity Agenda for the Nation. Four big things we can do together.  \\n\\nFirst, beat the opioid epidemic.', metadata={'source': '../../../state_of_the_union.txt', 'year': 2013}),\n",
+       " Document(page_content='Tonight, I’m announcing a crackdown on these companies overcharging American businesses and consumers. \\n\\nAnd as Wall Street firms take over more nursing homes, quality in those homes has gone down and costs have gone up.  \\n\\nThat ends on my watch. \\n\\nMedicare is going to set higher standards for nursing homes and make sure your loved ones get the care they deserve and expect. \\n\\nWe’ll also cut costs and keep the economy going strong by giving workers a fair shot, provide more training and apprenticeships, hire them based on their skills not degrees. \\n\\nLet’s pass the Paycheck Fairness Act and paid leave.  \\n\\nRaise the minimum wage to $15 an hour and extend the Child Tax Credit, so no one has to raise a family in poverty. \\n\\nLet’s increase Pell Grants and increase our historic support of HBCUs, and invest in what Jill—our First Lady who teaches full-time—calls America’s best-kept secret: community colleges.', metadata={'source': '../../../state_of_the_union.txt', 'year': 2014})]"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "db.similarity_search('What did the president say about Ketanji Brown Jackson?', distance_metric='cos')"
    ]
@@ -169,9 +303,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 14,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', metadata={'source': '../../../state_of_the_union.txt', 'year': 2012}),\n",
+       " Document(page_content='One was stationed at bases and breathing in toxic smoke from “burn pits” that incinerated wastes of war—medical and hazard material, jet fuel, and more. \\n\\nWhen they came home, many of the world’s fittest and best trained warriors were never the same. \\n\\nHeadaches. Numbness. Dizziness. \\n\\nA cancer that would put them in a flag-draped coffin. \\n\\nI know. \\n\\nOne of those soldiers was my son Major Beau Biden. \\n\\nWe don’t know for sure if a burn pit was the cause of his brain cancer, or the diseases of so many of our troops. \\n\\nBut I’m committed to finding out everything we can. \\n\\nCommitted to military families like Danielle Robinson from Ohio. \\n\\nThe widow of Sergeant First Class Heath Robinson.  \\n\\nHe was born a soldier. Army National Guard. Combat medic in Kosovo and Iraq. \\n\\nStationed near Baghdad, just yards from burn pits the size of football fields. \\n\\nHeath’s widow Danielle is here with us tonight. They loved going to Ohio State football games. He loved building Legos with their daughter.', metadata={'source': '../../../state_of_the_union.txt', 'year': 2014}),\n",
+       " Document(page_content='As Ohio Senator Sherrod Brown says, “It’s time to bury the label “Rust Belt.” \\n\\nIt’s time. \\n\\nBut with all the bright spots in our economy, record job growth and higher wages, too many families are struggling to keep up with the bills.  \\n\\nInflation is robbing them of the gains they might otherwise feel. \\n\\nI get it. That’s why my top priority is getting prices under control. \\n\\nLook, our economy roared back faster than most predicted, but the pandemic meant that businesses had a hard time hiring enough workers to keep up production in their factories. \\n\\nThe pandemic also disrupted global supply chains. \\n\\nWhen factories close, it takes longer to make goods and get them from the warehouse to the store, and prices go up. \\n\\nLook at cars. \\n\\nLast year, there weren’t enough semiconductors to make all the cars that people wanted to buy. \\n\\nAnd guess what, prices of automobiles went up. \\n\\nSo—we have a choice. \\n\\nOne way to fight inflation is to drive down wages and make Americans poorer.', metadata={'source': '../../../state_of_the_union.txt', 'year': 2012}),\n",
+       " Document(page_content='We can’t change how divided we’ve been. But we can change how we move forward—on COVID-19 and other issues we must face together. \\n\\nI recently visited the New York City Police Department days after the funerals of Officer Wilbert Mora and his partner, Officer Jason Rivera. \\n\\nThey were responding to a 9-1-1 call when a man shot and killed them with a stolen gun. \\n\\nOfficer Mora was 27 years old. \\n\\nOfficer Rivera was 22. \\n\\nBoth Dominican Americans who’d grown up on the same streets they later chose to patrol as police officers. \\n\\nI spoke with their families and told them that we are forever in debt for their sacrifice, and we will carry on their mission to restore the trust and safety every community deserves. \\n\\nI’ve worked on these issues a long time. \\n\\nI know what works: Investing in crime preventionand community police officers who’ll walk the beat, who’ll know the neighborhood, and who can restore trust and safety.', metadata={'source': '../../../state_of_the_union.txt', 'year': 2012})]"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "db.max_marginal_relevance_search('What did the president say about Ketanji Brown Jackson?')"
    ]
@@ -187,21 +335,87 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [],
    "source": [
-    "!activeloop login -t <token>"
+    "os.environ['ACTIVELOOP_TOKEN'] = getpass.getpass('Activeloop Token:')"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 17,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Your Deep Lake dataset has been successfully created!\n",
+      "The dataset is private so make sure you are logged in!\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\\"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "This dataset can be visualized in Jupyter Notebook by ds.visualize() or at https://app.activeloop.ai/davitbun/linkedin\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " \r"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "hub://davitbun/linkedin loaded successfully.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Evaluating ingest: 100%|██████████| 1/1 [00:23<00:00\n",
+      "/"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dataset(path='hub://davitbun/linkedin', tensors=['embedding', 'ids', 'metadata', 'text'])\n",
+      "\n",
+      "  tensor     htype     shape      dtype  compression\n",
+      "  -------   -------   -------    -------  ------- \n",
+      " embedding  generic  (42, 1536)  float32   None   \n",
+      "    ids      text     (42, 1)      str     None   \n",
+      " metadata    json     (42, 1)      str     None   \n",
+      "   text      text     (42, 1)      str     None   \n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " \r"
+     ]
+    }
+   ],
    "source": [
     "# Embed and store the texts\n",
-    "dataset_path = \"hub://{username}/{dataset_name}\" # could be also ./local/path (much faster locally), s3://bucket/path/to/dataset, gcs://path/to/dataset, etc.\n",
+    "dataset_path = f\"hub://{USERNAME}/{DATASET_NAME}\" # could be also ./local/path (much faster locally), s3://bucket/path/to/dataset, gcs://path/to/dataset, etc.\n",
     "\n",
     "embedding = OpenAIEmbeddings()\n",
     "vectordb = DeepLake.from_documents(documents=docs, embedding=embedding, dataset_path=dataset_path)"
@@ -209,9 +423,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 18,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
+      "\n",
+      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
+      "\n",
+      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
+      "\n",
+      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n"
+     ]
+    }
+   ],
    "source": [
     "query = \"What did the president say about Ketanji Brown Jackson\"\n",
     "docs = db.similarity_search(query)\n",
@@ -220,11 +448,35 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dataset(path='hub://davitbun/linkedin', tensors=['embedding', 'ids', 'metadata', 'text'])\n",
+      "\n",
+      "  tensor     htype     shape      dtype  compression\n",
+      "  -------   -------   -------    -------  ------- \n",
+      " embedding  generic  (42, 1536)  float32   None   \n",
+      "    ids      text     (42, 1)      str     None   \n",
+      " metadata    json     (42, 1)      str     None   \n",
+      "   text      text     (42, 1)      str     None   \n"
+     ]
+    }
+   ],
+   "source": [
+    "vectordb.ds.summary()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
    "metadata": {},
    "outputs": [],
    "source": [
-    "vectordb.ds.summary()"
+    "embeddings = vectordb.ds.embedding.numpy()"
    ]
   },
   {
@@ -232,9 +484,7 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "embeddings = vectordb.ds.embedding.numpy()"
-   ]
+   "source": []
   }
  ],
  "metadata": {

docs/modules/indexes/vectorstores/examples/opensearch.ipynb

@@ -55,7 +55,7 @@
    },
    "outputs": [],
    "source": [
-    "docsearch = OpenSearchVectorSearch.from_texts(texts, embeddings, opensearch_url=\"http://localhost:9200\")\n",
+    "docsearch = OpenSearchVectorSearch.from_documents(docs, embeddings, opensearch_url=\"http://localhost:9200\")\n",
     "\n",
     "query = \"What did the president say about Ketanji Brown Jackson\"\n",
     "docs = docsearch.similarity_search(query)"
@@ -94,7 +94,7 @@
    },
    "outputs": [],
    "source": [
-    "docsearch = OpenSearchVectorSearch.from_texts(texts, embeddings, opensearch_url=\"http://localhost:9200\", engine=\"faiss\", space_type=\"innerproduct\", ef_construction=256, m=48)\n",
+    "docsearch = OpenSearchVectorSearch.from_documents(docs, embeddings, opensearch_url=\"http://localhost:9200\", engine=\"faiss\", space_type=\"innerproduct\", ef_construction=256, m=48)\n",
     "\n",
     "query = \"What did the president say about Ketanji Brown Jackson\"\n",
     "docs = docsearch.similarity_search(query)"
@@ -133,7 +133,7 @@
    },
    "outputs": [],
    "source": [
-    "docsearch = OpenSearchVectorSearch.from_texts(texts, embeddings, opensearch_url=\"http://localhost:9200\", is_appx_search=False)\n",
+    "docsearch = OpenSearchVectorSearch.from_documents(docs, embeddings, opensearch_url=\"http://localhost:9200\", is_appx_search=False)\n",
     "\n",
     "query = \"What did the president say about Ketanji Brown Jackson\"\n",
     "docs = docsearch.similarity_search(\"What did the president say about Ketanji Brown Jackson\", k=1, search_type=\"script_scoring\")"
@@ -172,10 +172,10 @@
    },
    "outputs": [],
    "source": [
-    "docsearch = OpenSearchVectorSearch.from_texts(texts, embeddings, opensearch_url=\"http://localhost:9200\", is_appx_search=False)\n",
+    "docsearch = OpenSearchVectorSearch.from_documents(docs, embeddings, opensearch_url=\"http://localhost:9200\", is_appx_search=False)\n",
     "filter = {\"bool\": {\"filter\": {\"term\": {\"text\": \"smuggling\"}}}}\n",
     "query = \"What did the president say about Ketanji Brown Jackson\"\n",
-    "docs = docsearch.similarity_search(\"What did the president say about Ketanji Brown Jackson\", search_type=\"painless_scripting\", space_type=\"cosinesimil\", pre_filter=filter)"
+    "docs = docsearch.similarity_search(\"What did the president say about Ketanji Brown Jackson\", search_type=\"painless_scripting\", space_type=\"cosineSimilarity\", pre_filter=filter)"
    ]
   },
   {
@@ -238,4 +238,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 5
-}
+}

docs/modules/memory/examples/adding_memory.ipynb

@@ -139,7 +139,7 @@
     }
    ],
    "source": [
-    "llm_chain.predict(human_input=\"Not to bad - how are you?\")"
+    "llm_chain.predict(human_input=\"Not too bad - how are you?\")"
    ]
   },
   {

docs/modules/memory/examples/agent_with_memory_in_db.ipynb

@@ -16,7 +16,7 @@
     "In order to add a memory with an external message store to an agent we are going to do the following steps:\n",
     "\n",
     "1. We are going to create a `RedisChatMessageHistory` to connect to an external database to store the messages in.\n",
-    "2. We are going to create an `LLMChain` useing that chat history as memory.\n",
+    "2. We are going to create an `LLMChain` using that chat history as memory.\n",
     "3. We are going to use that `LLMChain` to create a custom Agent.\n",
     "\n",
     "For the purposes of this exercise, we are going to create a simple custom Agent that has access to a search tool and utilizes the `ConversationBufferMemory` class."

docs/modules/memory/examples/postgres_chat_message_history.ipynb

@@ -0,0 +1,62 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "91c6a7ef",
+   "metadata": {},
+   "source": [
+    "# Postgres Chat Message History\n",
+    "\n",
+    "This notebook goes over how to use Postgres to store chat message history."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d15e3302",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.memory import PostgresChatMessageHistory\n",
+    "\n",
+    "history = PostgresChatMessageHistory(connection_string=\"postgresql://postgres:mypassword@localhost/chat_history\", session_id=\"foo\")\n",
+    "\n",
+    "history.add_user_message(\"hi!\")\n",
+    "\n",
+    "history.add_ai_message(\"whats up?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "64fc465e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "history.messages"
+   ]
+  }
+ ],
+ "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": "3.11.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/modules/memory/getting_started.ipynb

@@ -314,7 +314,7 @@
    "source": [
     "## Saving Message History\n",
     "\n",
-    "You may often to save messages, and then load them to use again. This can be done easily by first converting the messages to normal python dictionaries, saving those (as json or something) and then loading those. Here is an example of doing that."
+    "You may often have to save messages, and then load them to use again. This can be done easily by first converting the messages to normal python dictionaries, saving those (as json or something) and then loading those. Here is an example of doing that."
    ]
   },
   {

docs/modules/memory/types/vectorstore_retriever_memory.ipynb

@@ -0,0 +1,368 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "ff4be5f3",
+   "metadata": {},
+   "source": [
+    "# VectorStore-Backed Memory\n",
+    "\n",
+    "`VectorStoreRetrieverMemory` stores memories in a VectorDB and queries the top-K most \"salient\" docs every time it is called.\n",
+    "\n",
+    "This differs from most of the other Memory classes in that it doesn't explicitly track the order of interactions.\n",
+    "\n",
+    "In this case, the \"docs\" are previous conversation snippets. This can be useful to refer to relevant pieces of information that the AI was told earlier in the conversation."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "da3384db",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from datetime import datetime\n",
+    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.memory import VectorStoreRetrieverMemory\n",
+    "from langchain.chains import ConversationChain\n",
+    "from langchain.prompts import PromptTemplate"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c2e7abdf",
+   "metadata": {},
+   "source": [
+    "### Initialize your VectorStore\n",
+    "\n",
+    "Depending on the store you choose, this step may look different. Consult the relevant VectorStore documentation for more details."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "eef56f65",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import faiss\n",
+    "\n",
+    "from langchain.docstore import InMemoryDocstore\n",
+    "from langchain.vectorstores import FAISS\n",
+    "\n",
+    "\n",
+    "embedding_size = 1536 # Dimensions of the OpenAIEmbeddings\n",
+    "index = faiss.IndexFlatL2(embedding_size)\n",
+    "embedding_fn = OpenAIEmbeddings().embed_query\n",
+    "vectorstore = FAISS(embedding_fn, index, InMemoryDocstore({}), {})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8f4bdf92",
+   "metadata": {},
+   "source": [
+    "### Create your the VectorStoreRetrieverMemory\n",
+    "\n",
+    "The memory object is instantiated from any VectorStoreRetriever."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "id": "e00d4938",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# In actual usage, you would set `k` to be a higher value, but we use k=1 to show that\n",
+    "# the vector lookup still returns the semantically relevant information\n",
+    "retriever = vectorstore.as_retriever(search_kwargs=dict(k=1))\n",
+    "memory = VectorStoreRetrieverMemory(retriever=retriever)\n",
+    "\n",
+    "# When added to an agent, the memory object can save pertinent information from conversations or used tools\n",
+    "memory.save_context({\"input\": \"My favorite food is pizza\"}, {\"output\": \"thats good to know\"})\n",
+    "memory.save_context({\"input\": \"My favorite sport is soccer\"}, {\"output\": \"...\"})\n",
+    "memory.save_context({\"input\": \"I don't the Celtics\"}, {\"output\": \"ok\"}) # "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "2fe28a28",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "input: My favorite sport is soccer\n",
+      "output: ...\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Notice the first result returned is the memory pertaining to tax help, which the language model deems more semantically relevant\n",
+    "# to a 1099 than the other documents, despite them both containing numbers.\n",
+    "print(memory.load_memory_variables({\"prompt\": \"what sport should i watch?\"})[\"history\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a6d2569f",
+   "metadata": {},
+   "source": [
+    "## Using in a chain\n",
+    "Let's walk through an example, again setting `verbose=True` so we can see the prompt."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "id": "ebd68c10",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mThe 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",
+      "\n",
+      "Relevant pieces of previous conversation:\n",
+      "input: My favorite food is pizza\n",
+      "output: thats good to know\n",
+      "\n",
+      "(You do not need to use these pieces of information if not relevant)\n",
+      "\n",
+      "Current conversation:\n",
+      "Human: Hi, my name is Perry, what's up?\n",
+      "AI:\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\" Hi Perry, I'm doing well. How about you?\""
+      ]
+     },
+     "execution_count": 32,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "llm = OpenAI(temperature=0) # Can be any valid LLM\n",
+    "_DEFAULT_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",
+    "\n",
+    "Relevant pieces of previous conversation:\n",
+    "{history}\n",
+    "\n",
+    "(You do not need to use these pieces of information if not relevant)\n",
+    "\n",
+    "Current conversation:\n",
+    "Human: {input}\n",
+    "AI:\"\"\"\n",
+    "PROMPT = PromptTemplate(\n",
+    "    input_variables=[\"history\", \"input\"], template=_DEFAULT_TEMPLATE\n",
+    ")\n",
+    "conversation_with_summary = ConversationChain(\n",
+    "    llm=llm, \n",
+    "    prompt=PROMPT,\n",
+    "    # We set a very low max_token_limit for the purposes of testing.\n",
+    "    memory=memory,\n",
+    "    verbose=True\n",
+    ")\n",
+    "conversation_with_summary.predict(input=\"Hi, my name is Perry, what's up?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "86207a61",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mThe 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",
+      "\n",
+      "Relevant pieces of previous conversation:\n",
+      "input: My favorite sport is soccer\n",
+      "output: ...\n",
+      "\n",
+      "(You do not need to use these pieces of information if not relevant)\n",
+      "\n",
+      "Current conversation:\n",
+      "Human: what's my favorite sport?\n",
+      "AI:\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "' You told me earlier that your favorite sport is soccer.'"
+      ]
+     },
+     "execution_count": 33,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Here, the basketball related content is surfaced\n",
+    "conversation_with_summary.predict(input=\"what's my favorite sport?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "id": "8c669db1",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mThe 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",
+      "\n",
+      "Relevant pieces of previous conversation:\n",
+      "input: My favorite food is pizza\n",
+      "output: thats good to know\n",
+      "\n",
+      "(You do not need to use these pieces of information if not relevant)\n",
+      "\n",
+      "Current conversation:\n",
+      "Human: Whats my favorite food\n",
+      "AI:\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "' You said your favorite food is pizza.'"
+      ]
+     },
+     "execution_count": 34,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Even though the language model is stateless, since relavent memory is fetched, it can \"reason\" about the time.\n",
+    "# Timestamping memories and data is useful in general to let the agent determine temporal relevance\n",
+    "conversation_with_summary.predict(input=\"Whats my favorite food\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "id": "8c09a239",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mThe 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",
+      "\n",
+      "Relevant pieces of previous conversation:\n",
+      "input: Hi, my name is Perry, what's up?\n",
+      "response:  Hi Perry, I'm doing well. How about you?\n",
+      "\n",
+      "(You do not need to use these pieces of information if not relevant)\n",
+      "\n",
+      "Current conversation:\n",
+      "Human: What's my name?\n",
+      "AI:\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "' Your name is Perry.'"
+      ]
+     },
+     "execution_count": 35,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# The memories from the conversation are automatically stored,\n",
+    "# since this query best matches the introduction chat above,\n",
+    "# the agent is able to 'remember' the user's name.\n",
+    "conversation_with_summary.predict(input=\"What's my name?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "df27c7dc",
+   "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
+}

docs/modules/models/chat/integrations/promptlayer_chatopenai.ipynb

@@ -115,7 +115,7 @@
    "id": "a2d76826",
    "metadata": {},
    "source": [
-    "**The above request should now appear on your [PromptLayer dashboard](https://ww.promptlayer.com).**"
+    "**The above request should now appear on your [PromptLayer dashboard](https://www.promptlayer.com).**"
    ]
   },
   {

docs/modules/models/llms/examples/llm_caching.ipynb

@@ -60,14 +60,14 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "CPU times: user 30.7 ms, sys: 18.6 ms, total: 49.3 ms\n",
-      "Wall time: 791 ms\n"
+      "CPU times: user 14.2 ms, sys: 4.9 ms, total: 19.1 ms\n",
+      "Wall time: 1.1 s\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "\"\\n\\nWhy couldn't the bicycle stand up by itself? Because it was...two tired!\""
+       "'\\n\\nWhy did the chicken cross the road?\\n\\nTo get to the other side.'"
       ]
      },
      "execution_count": 4,
@@ -91,14 +91,14 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "CPU times: user 80 µs, sys: 0 ns, total: 80 µs\n",
-      "Wall time: 83.9 µs\n"
+      "CPU times: user 162 µs, sys: 7 µs, total: 169 µs\n",
+      "Wall time: 175 µs\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "\"\\n\\nWhy couldn't the bicycle stand up by itself? Because it was...two tired!\""
+       "'\\n\\nWhy did the chicken cross the road?\\n\\nTo get to the other side.'"
       ]
      },
      "execution_count": 5,
@@ -252,6 +252,249 @@
     "llm(\"Tell me a joke\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "684eab55",
+   "metadata": {},
+   "source": [
+    "## GPTCache\n",
+    "\n",
+    "We can use [GPTCache](https://github.com/zilliztech/GPTCache) for exact match caching OR to cache results based on semantic similarity\n",
+    "\n",
+    "Let's first start with an example of exact match"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "14a82124",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import gptcache\n",
+    "from gptcache.processor.pre import get_prompt\n",
+    "from gptcache.manager.factory import get_data_manager\n",
+    "from langchain.cache import GPTCache\n",
+    "\n",
+    "# Avoid multiple caches using the same file, causing different llm model caches to affect each other\n",
+    "i = 0\n",
+    "file_prefix = \"data_map\"\n",
+    "\n",
+    "def init_gptcache_map(cache_obj: gptcache.Cache):\n",
+    "    global i\n",
+    "    cache_path = f'{file_prefix}_{i}.txt'\n",
+    "    cache_obj.init(\n",
+    "        pre_embedding_func=get_prompt,\n",
+    "        data_manager=get_data_manager(data_path=cache_path),\n",
+    "    )\n",
+    "    i += 1\n",
+    "\n",
+    "langchain.llm_cache = GPTCache(init_gptcache_map)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "9e4ecfd1",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 8.6 ms, sys: 3.82 ms, total: 12.4 ms\n",
+      "Wall time: 881 ms\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'\\n\\nWhy did the chicken cross the road?\\n\\nTo get to the other side.'"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "# The first time, it is not yet in cache, so it should take longer\n",
+    "llm(\"Tell me a joke\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "c98bbe3b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 286 µs, sys: 21 µs, total: 307 µs\n",
+      "Wall time: 316 µs\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'\\n\\nWhy did the chicken cross the road?\\n\\nTo get to the other side.'"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "# The second time it is, so it goes faster\n",
+    "llm(\"Tell me a joke\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "502b6076",
+   "metadata": {},
+   "source": [
+    "Let's now show an example of similarity caching"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "b3c663bb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import gptcache\n",
+    "from gptcache.processor.pre import get_prompt\n",
+    "from gptcache.manager.factory import get_data_manager\n",
+    "from langchain.cache import GPTCache\n",
+    "from gptcache.manager import get_data_manager, CacheBase, VectorBase\n",
+    "from gptcache import Cache\n",
+    "from gptcache.embedding import Onnx\n",
+    "from gptcache.similarity_evaluation.distance import SearchDistanceEvaluation\n",
+    "\n",
+    "# Avoid multiple caches using the same file, causing different llm model caches to affect each other\n",
+    "i = 0\n",
+    "file_prefix = \"data_map\"\n",
+    "llm_cache = Cache()\n",
+    "\n",
+    "\n",
+    "def init_gptcache_map(cache_obj: gptcache.Cache):\n",
+    "    global i\n",
+    "    cache_path = f'{file_prefix}_{i}.txt'\n",
+    "    onnx = Onnx()\n",
+    "    cache_base = CacheBase('sqlite')\n",
+    "    vector_base = VectorBase('faiss', dimension=onnx.dimension)\n",
+    "    data_manager = get_data_manager(cache_base, vector_base, max_size=10, clean_size=2)\n",
+    "    cache_obj.init(\n",
+    "        pre_embedding_func=get_prompt,\n",
+    "        embedding_func=onnx.to_embeddings,\n",
+    "        data_manager=data_manager,\n",
+    "        similarity_evaluation=SearchDistanceEvaluation(),\n",
+    "    )\n",
+    "    i += 1\n",
+    "\n",
+    "langchain.llm_cache = GPTCache(init_gptcache_map)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "8c273ced",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 1.01 s, sys: 153 ms, total: 1.16 s\n",
+      "Wall time: 2.49 s\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'\\n\\nWhy did the chicken cross the road?\\n\\nTo get to the other side.'"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "# The first time, it is not yet in cache, so it should take longer\n",
+    "llm(\"Tell me a joke\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "93e21a5f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 745 ms, sys: 13.2 ms, total: 758 ms\n",
+      "Wall time: 136 ms\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'\\n\\nWhy did the chicken cross the road?\\n\\nTo get to the other side.'"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "# This is an exact match, so it finds it in the cache\n",
+    "llm(\"Tell me a joke\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "c4bb024b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 737 ms, sys: 7.79 ms, total: 745 ms\n",
+      "Wall time: 135 ms\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'\\n\\nWhy did the chicken cross the road?\\n\\nTo get to the other side.'"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "# This is not an exact match, but semantically within distance so it hits!\n",
+    "llm(\"Tell me joke\")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "934943dc",

docs/modules/models/llms/examples/token_usage_tracking.ipynb

@@ -43,22 +43,18 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Total Tokens: 39\n",
-      "Prompt Tokens: 4\n",
-      "Completion Tokens: 35\n",
+      "Tokens Used: 42\n",
+      "\tPrompt Tokens: 4\n",
+      "\tCompletion Tokens: 38\n",
       "Successful Requests: 1\n",
-      "Total Cost (USD): $0.0007800000000000001\n"
+      "Total Cost (USD): $0.00084\n"
      ]
     }
    ],
    "source": [
     "with get_openai_callback() as cb:\n",
     "    result = llm(\"Tell me a joke\")\n",
-    "    print(f\"Total Tokens: {cb.total_tokens}\")\n",
-    "    print(f\"Prompt Tokens: {cb.prompt_tokens}\")\n",
-    "    print(f\"Completion Tokens: {cb.completion_tokens}\")\n",
-    "    print(f\"Successful Requests: {cb.successful_requests}\")\n",
-    "    print(f\"Total Cost (USD): ${cb.total_cost}\")"
+    "    print(cb)"
    ]
   },
   {

docs/modules/models/llms/getting_started.ipynb

@@ -186,7 +186,7 @@
    "source": [
     "**Number of Tokens:** You can also estimate how many tokens a piece of text will be in that model. This is useful because models have a context length (and cost more for more tokens), which means you need to be aware of how long the text you are passing in is.\n",
     "\n",
-    "Notice that by default the tokens are estimated using a HuggingFace tokenizer."
+    "Notice that by default the tokens are estimated using [tiktoken](https://github.com/openai/tiktoken) (except for legacy version <3.8, where a Hugging Face tokenizer is used)"
    ]
   },
   {

docs/modules/models/llms/integrations/gpt4all.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# GPT4all\n",
+    "# GPT4All\n",
     "\n",
     "This example goes over how to use LangChain to interact with GPT4All models"
    ]
@@ -15,7 +15,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install pyllamacpp"
+    "%pip install pyllamacpp > /dev/null"
    ]
   },
   {
@@ -24,8 +24,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "from langchain import PromptTemplate, LLMChain\n",
     "from langchain.llms import GPT4All\n",
-    "from langchain import PromptTemplate, LLMChain"
+    "from langchain.callbacks.base import CallbackManager\n",
+    "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler"
    ]
   },
   {
@@ -41,15 +43,70 @@
     "prompt = PromptTemplate(template=template, input_variables=[\"question\"])"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Specify Model\n",
+    "\n",
+    "To run locally, download a compatible ggml-formatted model. For more info, visit https://github.com/nomic-ai/pyllamacpp\n",
+    "\n",
+    "Note that new models are uploaded regularly - check the link above for the most recent `.bin` URL"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "# You'll need to download a compatible model and convert it to ggml.\n",
-    "# See: https://github.com/nomic-ai/gpt4all for more information.\n",
-    "llm = GPT4All(model=\"./models/gpt4all-model.bin\")"
+    "local_path = './models/gpt4all-lora-quantized-ggml.bin'  # replace with your desired local file path"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Uncomment the below block to download a model. You may want to update `url` to a new version."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# import requests\n",
+    "\n",
+    "# from pathlib import Path\n",
+    "# from tqdm import tqdm\n",
+    "\n",
+    "# Path(local_path).parent.mkdir(parents=True, exist_ok=True)\n",
+    "\n",
+    "# # Example model. Check https://github.com/nomic-ai/pyllamacpp for the latest models.\n",
+    "# url = 'https://the-eye.eu/public/AI/models/nomic-ai/gpt4all/gpt4all-lora-quantized-ggml.bin'\n",
+    "\n",
+    "# # send a GET request to the URL to download the file. Stream since it's large\n",
+    "# response = requests.get(url, stream=True)\n",
+    "\n",
+    "# # open the file in binary mode and write the contents of the response to it in chunks\n",
+    "# # This is a large file, so be prepared to wait.\n",
+    "# with open(local_path, 'wb') as f:\n",
+    "#     for chunk in tqdm(response.iter_content(chunk_size=8192)):\n",
+    "#         if chunk:\n",
+    "#             f.write(chunk)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Callbacks support token-wise streaming\n",
+    "callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])\n",
+    "# Verbose is required to pass to the callback manager\n",
+    "llm = GPT4All(model=local_path, callback_manager=callback_manager, verbose=True)"
    ]
   },
   {
@@ -89,7 +146,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.11.2"
   }
  },
  "nbformat": 4,

docs/modules/models/llms/integrations/huggingface_hub.ipynb

@@ -12,7 +12,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 41,
    "id": "3acf0069",
    "metadata": {},
    "outputs": [
@@ -20,7 +20,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "The Seattle Seahawks won the Super Bowl in 2010. Justin Beiber was born in 2010. The final answer: Seattle Seahawks.\n"
+      "The FIFA World Cup is a football tournament that is played every 4 years. The year 1994 was the 44th FIFA World Cup. The final answer: Brazil.\n"
      ]
     }
    ],
@@ -33,7 +33,7 @@
     "prompt = PromptTemplate(template=template, input_variables=[\"question\"])\n",
     "llm_chain = LLMChain(prompt=prompt, llm=HuggingFaceHub(repo_id=\"google/flan-t5-xl\", model_kwargs={\"temperature\":0, \"max_length\":64}))\n",
     "\n",
-    "question = \"What NFL team won the Super Bowl in the year Justin Beiber was born?\"\n",
+    "question = \"Who won the FIFA World Cup in the year 1994? \"\n",
     "\n",
     "print(llm_chain.run(question))"
    ]
@@ -41,7 +41,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "ae4559c7",
+   "id": "843a3837",
    "metadata": {},
    "outputs": [],
    "source": []
@@ -63,7 +63,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.8.12"
   }
  },
  "nbformat": 4,

docs/reference/integrations.md

@@ -55,6 +55,12 @@ The following use cases require specific installs and api keys:
 - _LlamaCpp_:
   - Install requirements with `pip install llama-cpp-python`
   - Download model and convert following [llama.cpp instructions](https://github.com/ggerganov/llama.cpp)
+- _Milvus_:
+  - Install requirements with `pip install pymilvus`
+  - In order to setup a local cluster, take a look [here](https://milvus.io/docs).
+- _Zilliz_:
+  - Install requirements with `pip install pymilvus`
+  - To get up and running, take a look [here](https://zilliz.com/doc/quick_start).
 
 
 If you are using the `NLTKTextSplitter` or the `SpacyTextSplitter`, you will also need to install the appropriate models. For example, if you want to use the `SpacyTextSplitter`, you will need to install the `en_core_web_sm` model with `python -m spacy download en_core_web_sm`. Similarly, if you want to use the `NLTKTextSplitter`, you will need to install the `punkt` model with `python -m nltk.downloader punkt`.

docs/use_cases/agents/baby_agi.ipynb

@@ -0,0 +1,565 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "517a9fd4",
+   "metadata": {},
+   "source": [
+    "# BabyAGI User Guide\n",
+    "\n",
+    "This notebook demonstrates how to implement [BabyAGI](https://github.com/yoheinakajima/babyagi/tree/main) by [Yohei Nakajima](https://twitter.com/yoheinakajima). BabyAGI is an AI agent that can generate and pretend to execute tasks based on a given objective.\n",
+    "\n",
+    "This guide will help you understand the components to create your own recursive agents.\n",
+    "\n",
+    "Although BabyAGI uses specific vectorstores/model providers (Pinecone, OpenAI), one of the benefits of implementing it with LangChain is that you can easily swap those out for different options. In this implementation we use a FAISS vectorstore (because it runs locally and is free)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "556af556",
+   "metadata": {},
+   "source": [
+    "## Install and Import Required Modules"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 116,
+   "id": "c8a354b6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from collections import deque\n",
+    "from typing import Dict, List, Optional, Any\n",
+    "\n",
+    "from langchain import LLMChain, OpenAI, PromptTemplate\n",
+    "from langchain.embeddings import OpenAIEmbeddings\n",
+    "from langchain.llms import BaseLLM\n",
+    "from langchain.vectorstores.base import VectorStore\n",
+    "from pydantic import BaseModel, Field\n",
+    "from langchain.chains.base import Chain"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "09f70772",
+   "metadata": {},
+   "source": [
+    "## Connect to the Vector Store\n",
+    "\n",
+    "Depending on what vectorstore you use, this step may look different."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 71,
+   "id": "794045d4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.vectorstores import FAISS\n",
+    "from langchain.docstore import InMemoryDocstore"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 72,
+   "id": "6e0305eb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Define your embedding model\n",
+    "embeddings_model = OpenAIEmbeddings()\n",
+    "# Initialize the vectorstore as empty\n",
+    "import faiss\n",
+    "\n",
+    "embedding_size = 1536\n",
+    "index = faiss.IndexFlatL2(embedding_size)\n",
+    "vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0f3b72bf",
+   "metadata": {},
+   "source": [
+    "## Define the Chains\n",
+    "\n",
+    "BabyAGI relies on three LLM chains:\n",
+    "- Task creation chain to select new tasks to add to the list\n",
+    "- Task prioritization chain to re-prioritize tasks\n",
+    "- Execution Chain to execute the tasks"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 73,
+   "id": "bf4bd5cd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class TaskCreationChain(LLMChain):\n",
+    "    \"\"\"Chain to generates tasks.\"\"\"\n",
+    "\n",
+    "    @classmethod\n",
+    "    def from_llm(cls, llm: BaseLLM, verbose: bool = True) -> LLMChain:\n",
+    "        \"\"\"Get the response parser.\"\"\"\n",
+    "        task_creation_template = (\n",
+    "            \"You are an task creation AI that uses the result of an execution agent\"\n",
+    "            \" to create new tasks with the following objective: {objective},\"\n",
+    "            \" The last completed task has the result: {result}.\"\n",
+    "            \" This result was based on this task description: {task_description}.\"\n",
+    "            \" These are incomplete tasks: {incomplete_tasks}.\"\n",
+    "            \" Based on the result, create new tasks to be completed\"\n",
+    "            \" by the AI system that do not overlap with incomplete tasks.\"\n",
+    "            \" Return the tasks as an array.\"\n",
+    "        )\n",
+    "        prompt = PromptTemplate(\n",
+    "            template=task_creation_template,\n",
+    "            input_variables=[\n",
+    "                \"result\",\n",
+    "                \"task_description\",\n",
+    "                \"incomplete_tasks\",\n",
+    "                \"objective\",\n",
+    "            ],\n",
+    "        )\n",
+    "        return cls(prompt=prompt, llm=llm, verbose=verbose)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 74,
+   "id": "b6488ffe",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class TaskPrioritizationChain(LLMChain):\n",
+    "    \"\"\"Chain to prioritize tasks.\"\"\"\n",
+    "\n",
+    "    @classmethod\n",
+    "    def from_llm(cls, llm: BaseLLM, verbose: bool = True) -> LLMChain:\n",
+    "        \"\"\"Get the response parser.\"\"\"\n",
+    "        task_prioritization_template = (\n",
+    "            \"You are an task prioritization AI tasked with cleaning the formatting of and reprioritizing\"\n",
+    "            \" the following tasks: {task_names}.\"\n",
+    "            \" Consider the ultimate objective of your team: {objective}.\"\n",
+    "            \" Do not remove any tasks. Return the result as a numbered list, like:\"\n",
+    "            \" #. First task\"\n",
+    "            \" #. Second task\"\n",
+    "            \" Start the task list with number {next_task_id}.\"\n",
+    "        )\n",
+    "        prompt = PromptTemplate(\n",
+    "            template=task_prioritization_template,\n",
+    "            input_variables=[\"task_names\", \"next_task_id\", \"objective\"],\n",
+    "        )\n",
+    "        return cls(prompt=prompt, llm=llm, verbose=verbose)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 84,
+   "id": "b43cd580",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class ExecutionChain(LLMChain):\n",
+    "    \"\"\"Chain to execute tasks.\"\"\"\n",
+    "\n",
+    "    @classmethod\n",
+    "    def from_llm(cls, llm: BaseLLM, verbose: bool = True) -> LLMChain:\n",
+    "        \"\"\"Get the response parser.\"\"\"\n",
+    "        execution_template = (\n",
+    "            \"You are an AI who performs one task based on the following objective: {objective}.\"\n",
+    "            \" Take into account these previously completed tasks: {context}.\"\n",
+    "            \" Your task: {task}.\"\n",
+    "            \" Response:\"\n",
+    "        )\n",
+    "        prompt = PromptTemplate(\n",
+    "            template=execution_template,\n",
+    "            input_variables=[\"objective\", \"context\", \"task\"],\n",
+    "        )\n",
+    "        return cls(prompt=prompt, llm=llm, verbose=verbose)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3ad996c5",
+   "metadata": {},
+   "source": [
+    "### Define the BabyAGI Controller\n",
+    "\n",
+    "BabyAGI composes the chains defined above in a (potentially-)infinite loop."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 85,
+   "id": "0ada0636",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_next_task(\n",
+    "    task_creation_chain: LLMChain,\n",
+    "    result: Dict,\n",
+    "    task_description: str,\n",
+    "    task_list: List[str],\n",
+    "    objective: str,\n",
+    ") -> List[Dict]:\n",
+    "    \"\"\"Get the next task.\"\"\"\n",
+    "    incomplete_tasks = \", \".join(task_list)\n",
+    "    response = task_creation_chain.run(\n",
+    "        result=result,\n",
+    "        task_description=task_description,\n",
+    "        incomplete_tasks=incomplete_tasks,\n",
+    "        objective=objective,\n",
+    "    )\n",
+    "    new_tasks = response.split(\"\\n\")\n",
+    "    return [{\"task_name\": task_name} for task_name in new_tasks if task_name.strip()]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 86,
+   "id": "d35250ad",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def prioritize_tasks(\n",
+    "    task_prioritization_chain: LLMChain,\n",
+    "    this_task_id: int,\n",
+    "    task_list: List[Dict],\n",
+    "    objective: str,\n",
+    ") -> List[Dict]:\n",
+    "    \"\"\"Prioritize tasks.\"\"\"\n",
+    "    task_names = [t[\"task_name\"] for t in task_list]\n",
+    "    next_task_id = int(this_task_id) + 1\n",
+    "    response = task_prioritization_chain.run(\n",
+    "        task_names=task_names, next_task_id=next_task_id, objective=objective\n",
+    "    )\n",
+    "    new_tasks = response.split(\"\\n\")\n",
+    "    prioritized_task_list = []\n",
+    "    for task_string in new_tasks:\n",
+    "        if not task_string.strip():\n",
+    "            continue\n",
+    "        task_parts = task_string.strip().split(\".\", 1)\n",
+    "        if len(task_parts) == 2:\n",
+    "            task_id = task_parts[0].strip()\n",
+    "            task_name = task_parts[1].strip()\n",
+    "            prioritized_task_list.append({\"task_id\": task_id, \"task_name\": task_name})\n",
+    "    return prioritized_task_list"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 87,
+   "id": "e3f1840c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def _get_top_tasks(vectorstore, query: str, k: int) -> List[str]:\n",
+    "    \"\"\"Get the top k tasks based on the query.\"\"\"\n",
+    "    results = vectorstore.similarity_search_with_score(query, k=k)\n",
+    "    if not results:\n",
+    "        return []\n",
+    "    sorted_results, _ = zip(*sorted(results, key=lambda x: x[1], reverse=True))\n",
+    "    return [str(item.metadata[\"task\"]) for item in sorted_results]\n",
+    "\n",
+    "\n",
+    "def execute_task(\n",
+    "    vectorstore, execution_chain: LLMChain, objective: str, task: str, k: int = 5\n",
+    ") -> str:\n",
+    "    \"\"\"Execute a task.\"\"\"\n",
+    "    context = _get_top_tasks(vectorstore, query=objective, k=k)\n",
+    "    return execution_chain.run(objective=objective, context=context, task=task)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 137,
+   "id": "1e978938",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class BabyAGI(Chain, BaseModel):\n",
+    "    \"\"\"Controller model for the BabyAGI agent.\"\"\"\n",
+    "\n",
+    "    task_list: deque = Field(default_factory=deque)\n",
+    "    task_creation_chain: TaskCreationChain = Field(...)\n",
+    "    task_prioritization_chain: TaskPrioritizationChain = Field(...)\n",
+    "    execution_chain: ExecutionChain = Field(...)\n",
+    "    task_id_counter: int = Field(1)\n",
+    "    vectorstore: VectorStore = Field(init=False)\n",
+    "    max_iterations: Optional[int] = None\n",
+    "\n",
+    "    class Config:\n",
+    "        \"\"\"Configuration for this pydantic object.\"\"\"\n",
+    "\n",
+    "        arbitrary_types_allowed = True\n",
+    "\n",
+    "    def add_task(self, task: Dict):\n",
+    "        self.task_list.append(task)\n",
+    "\n",
+    "    def print_task_list(self):\n",
+    "        print(\"\\033[95m\\033[1m\" + \"\\n*****TASK LIST*****\\n\" + \"\\033[0m\\033[0m\")\n",
+    "        for t in self.task_list:\n",
+    "            print(str(t[\"task_id\"]) + \": \" + t[\"task_name\"])\n",
+    "\n",
+    "    def print_next_task(self, task: Dict):\n",
+    "        print(\"\\033[92m\\033[1m\" + \"\\n*****NEXT TASK*****\\n\" + \"\\033[0m\\033[0m\")\n",
+    "        print(str(task[\"task_id\"]) + \": \" + task[\"task_name\"])\n",
+    "\n",
+    "    def print_task_result(self, result: str):\n",
+    "        print(\"\\033[93m\\033[1m\" + \"\\n*****TASK RESULT*****\\n\" + \"\\033[0m\\033[0m\")\n",
+    "        print(result)\n",
+    "\n",
+    "    @property\n",
+    "    def input_keys(self) -> List[str]:\n",
+    "        return [\"objective\"]\n",
+    "\n",
+    "    @property\n",
+    "    def output_keys(self) -> List[str]:\n",
+    "        return []\n",
+    "\n",
+    "    def _call(self, inputs: Dict[str, Any]) -> Dict[str, Any]:\n",
+    "        \"\"\"Run the agent.\"\"\"\n",
+    "        objective = inputs[\"objective\"]\n",
+    "        first_task = inputs.get(\"first_task\", \"Make a todo list\")\n",
+    "        self.add_task({\"task_id\": 1, \"task_name\": first_task})\n",
+    "        num_iters = 0\n",
+    "        while True:\n",
+    "            if self.task_list:\n",
+    "                self.print_task_list()\n",
+    "\n",
+    "                # Step 1: Pull the first task\n",
+    "                task = self.task_list.popleft()\n",
+    "                self.print_next_task(task)\n",
+    "\n",
+    "                # Step 2: Execute the task\n",
+    "                result = execute_task(\n",
+    "                    self.vectorstore, self.execution_chain, objective, task[\"task_name\"]\n",
+    "                )\n",
+    "                this_task_id = int(task[\"task_id\"])\n",
+    "                self.print_task_result(result)\n",
+    "\n",
+    "                # Step 3: Store the result in Pinecone\n",
+    "                result_id = f\"result_{task['task_id']}\"\n",
+    "                self.vectorstore.add_texts(\n",
+    "                    texts=[result],\n",
+    "                    metadatas=[{\"task\": task[\"task_name\"]}],\n",
+    "                    ids=[result_id],\n",
+    "                )\n",
+    "\n",
+    "                # Step 4: Create new tasks and reprioritize task list\n",
+    "                new_tasks = get_next_task(\n",
+    "                    self.task_creation_chain,\n",
+    "                    result,\n",
+    "                    task[\"task_name\"],\n",
+    "                    [t[\"task_name\"] for t in self.task_list],\n",
+    "                    objective,\n",
+    "                )\n",
+    "                for new_task in new_tasks:\n",
+    "                    self.task_id_counter += 1\n",
+    "                    new_task.update({\"task_id\": self.task_id_counter})\n",
+    "                    self.add_task(new_task)\n",
+    "                self.task_list = deque(\n",
+    "                    prioritize_tasks(\n",
+    "                        self.task_prioritization_chain,\n",
+    "                        this_task_id,\n",
+    "                        list(self.task_list),\n",
+    "                        objective,\n",
+    "                    )\n",
+    "                )\n",
+    "            num_iters += 1\n",
+    "            if self.max_iterations is not None and num_iters == self.max_iterations:\n",
+    "                print(\n",
+    "                    \"\\033[91m\\033[1m\" + \"\\n*****TASK ENDING*****\\n\" + \"\\033[0m\\033[0m\"\n",
+    "                )\n",
+    "                break\n",
+    "        return {}\n",
+    "\n",
+    "    @classmethod\n",
+    "    def from_llm(\n",
+    "        cls, llm: BaseLLM, vectorstore: VectorStore, verbose: bool = False, **kwargs\n",
+    "    ) -> \"BabyAGI\":\n",
+    "        \"\"\"Initialize the BabyAGI Controller.\"\"\"\n",
+    "        task_creation_chain = TaskCreationChain.from_llm(llm, verbose=verbose)\n",
+    "        task_prioritization_chain = TaskPrioritizationChain.from_llm(\n",
+    "            llm, verbose=verbose\n",
+    "        )\n",
+    "        execution_chain = ExecutionChain.from_llm(llm, verbose=verbose)\n",
+    "        return cls(\n",
+    "            task_creation_chain=task_creation_chain,\n",
+    "            task_prioritization_chain=task_prioritization_chain,\n",
+    "            execution_chain=execution_chain,\n",
+    "            vectorstore=vectorstore,\n",
+    "            **kwargs,\n",
+    "        )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "05ba762e",
+   "metadata": {},
+   "source": [
+    "### Run the BabyAGI\n",
+    "\n",
+    "Now it's time to create the BabyAGI controller and watch it try to accomplish your objective."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 138,
+   "id": "3d220b69",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "OBJECTIVE = \"Write a weather report for SF today\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 139,
+   "id": "8a8e5543",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 140,
+   "id": "3d69899b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Logging of LLMChains\n",
+    "verbose = False\n",
+    "# If None, will keep on going forever\n",
+    "max_iterations: Optional[int] = 3\n",
+    "baby_agi = BabyAGI.from_llm(\n",
+    "    llm=llm, vectorstore=vectorstore, verbose=verbose, max_iterations=max_iterations\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 141,
+   "id": "f7957b51",
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[95m\u001b[1m\n",
+      "*****TASK LIST*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "1: Make a todo list\n",
+      "\u001b[92m\u001b[1m\n",
+      "*****NEXT TASK*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "1: Make a todo list\n",
+      "\u001b[93m\u001b[1m\n",
+      "*****TASK RESULT*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "\n",
+      "\n",
+      "1. Check the temperature range for the day.\n",
+      "2. Gather temperature data for SF today.\n",
+      "3. Analyze the temperature data and create a weather report.\n",
+      "4. Publish the weather report.\n",
+      "\u001b[95m\u001b[1m\n",
+      "*****TASK LIST*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "2: Gather data on the expected temperature range for the day.\n",
+      "3: Collect data on the expected precipitation for the day.\n",
+      "4: Analyze the data and create a weather report.\n",
+      "5: Check the current weather conditions in SF.\n",
+      "6: Publish the weather report.\n",
+      "\u001b[92m\u001b[1m\n",
+      "*****NEXT TASK*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "2: Gather data on the expected temperature range for the day.\n",
+      "\u001b[93m\u001b[1m\n",
+      "*****TASK RESULT*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "\n",
+      "\n",
+      "I have gathered data on the expected temperature range for the day in San Francisco. The forecast is for temperatures to range from a low of 55 degrees Fahrenheit to a high of 68 degrees Fahrenheit.\n",
+      "\u001b[95m\u001b[1m\n",
+      "*****TASK LIST*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "3: Check the current weather conditions in SF.\n",
+      "4: Calculate the average temperature for the day in San Francisco.\n",
+      "5: Determine the probability of precipitation for the day in San Francisco.\n",
+      "6: Identify any potential weather warnings or advisories for the day in San Francisco.\n",
+      "7: Research any historical weather patterns for the day in San Francisco.\n",
+      "8: Compare the expected temperature range to the historical average for the day in San Francisco.\n",
+      "9: Collect data on the expected precipitation for the day.\n",
+      "10: Analyze the data and create a weather report.\n",
+      "11: Publish the weather report.\n",
+      "\u001b[92m\u001b[1m\n",
+      "*****NEXT TASK*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "3: Check the current weather conditions in SF.\n",
+      "\u001b[93m\u001b[1m\n",
+      "*****TASK RESULT*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "\n",
+      "\n",
+      "I am checking the current weather conditions in SF. According to the data I have gathered, the temperature in SF today is currently around 65 degrees Fahrenheit with clear skies. The temperature range for the day is expected to be between 60 and 70 degrees Fahrenheit.\n",
+      "\u001b[91m\u001b[1m\n",
+      "*****TASK ENDING*****\n",
+      "\u001b[0m\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'objective': 'Write a weather report for SF today'}"
+      ]
+     },
+     "execution_count": 141,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "baby_agi({\"objective\": OBJECTIVE})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "898a210b",
+   "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
+}

docs/use_cases/agents/baby_agi_with_agent.ipynb

@@ -0,0 +1,647 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "517a9fd4",
+   "metadata": {},
+   "source": [
+    "# BabyAGI with Tools\n",
+    "\n",
+    "This notebook builds on top of [baby agi](baby_agi.ipynb), but shows how you can swap out the execution chain. The previous execution chain was just an LLM which made stuff up. By swapping it out with an agent that has access to tools, we can hopefully get real reliable information"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "556af556",
+   "metadata": {},
+   "source": [
+    "## Install and Import Required Modules"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "c8a354b6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from collections import deque\n",
+    "from typing import Dict, List, Optional, Any\n",
+    "\n",
+    "from langchain import LLMChain, OpenAI, PromptTemplate\n",
+    "from langchain.embeddings import OpenAIEmbeddings\n",
+    "from langchain.llms import BaseLLM\n",
+    "from langchain.vectorstores.base import VectorStore\n",
+    "from pydantic import BaseModel, Field\n",
+    "from langchain.chains.base import Chain"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "09f70772",
+   "metadata": {},
+   "source": [
+    "## Connect to the Vector Store\n",
+    "\n",
+    "Depending on what vectorstore you use, this step may look different."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "794045d4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install faiss-cpu > /dev/null\n",
+    "%pip install google-search-results > /dev/null\n",
+    "from langchain.vectorstores import FAISS\n",
+    "from langchain.docstore import InMemoryDocstore"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "6e0305eb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Define your embedding model\n",
+    "embeddings_model = OpenAIEmbeddings()\n",
+    "# Initialize the vectorstore as empty\n",
+    "import faiss\n",
+    "\n",
+    "embedding_size = 1536\n",
+    "index = faiss.IndexFlatL2(embedding_size)\n",
+    "vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0f3b72bf",
+   "metadata": {},
+   "source": [
+    "## Define the Chains\n",
+    "\n",
+    "BabyAGI relies on three LLM chains:\n",
+    "- Task creation chain to select new tasks to add to the list\n",
+    "- Task prioritization chain to re-prioritize tasks\n",
+    "- Execution Chain to execute the tasks\n",
+    "\n",
+    "\n",
+    "NOTE: in this notebook, the Execution chain will now be an agent."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "bf4bd5cd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class TaskCreationChain(LLMChain):\n",
+    "    \"\"\"Chain to generates tasks.\"\"\"\n",
+    "\n",
+    "    @classmethod\n",
+    "    def from_llm(cls, llm: BaseLLM, verbose: bool = True) -> LLMChain:\n",
+    "        \"\"\"Get the response parser.\"\"\"\n",
+    "        task_creation_template = (\n",
+    "            \"You are an task creation AI that uses the result of an execution agent\"\n",
+    "            \" to create new tasks with the following objective: {objective},\"\n",
+    "            \" The last completed task has the result: {result}.\"\n",
+    "            \" This result was based on this task description: {task_description}.\"\n",
+    "            \" These are incomplete tasks: {incomplete_tasks}.\"\n",
+    "            \" Based on the result, create new tasks to be completed\"\n",
+    "            \" by the AI system that do not overlap with incomplete tasks.\"\n",
+    "            \" Return the tasks as an array.\"\n",
+    "        )\n",
+    "        prompt = PromptTemplate(\n",
+    "            template=task_creation_template,\n",
+    "            input_variables=[\n",
+    "                \"result\",\n",
+    "                \"task_description\",\n",
+    "                \"incomplete_tasks\",\n",
+    "                \"objective\",\n",
+    "            ],\n",
+    "        )\n",
+    "        return cls(prompt=prompt, llm=llm, verbose=verbose)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "b6488ffe",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class TaskPrioritizationChain(LLMChain):\n",
+    "    \"\"\"Chain to prioritize tasks.\"\"\"\n",
+    "\n",
+    "    @classmethod\n",
+    "    def from_llm(cls, llm: BaseLLM, verbose: bool = True) -> LLMChain:\n",
+    "        \"\"\"Get the response parser.\"\"\"\n",
+    "        task_prioritization_template = (\n",
+    "            \"You are an task prioritization AI tasked with cleaning the formatting of and reprioritizing\"\n",
+    "            \" the following tasks: {task_names}.\"\n",
+    "            \" Consider the ultimate objective of your team: {objective}.\"\n",
+    "            \" Do not remove any tasks. Return the result as a numbered list, like:\"\n",
+    "            \" #. First task\"\n",
+    "            \" #. Second task\"\n",
+    "            \" Start the task list with number {next_task_id}.\"\n",
+    "        )\n",
+    "        prompt = PromptTemplate(\n",
+    "            template=task_prioritization_template,\n",
+    "            input_variables=[\"task_names\", \"next_task_id\", \"objective\"],\n",
+    "        )\n",
+    "        return cls(prompt=prompt, llm=llm, verbose=verbose)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "id": "b43cd580",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.agents import ZeroShotAgent, Tool, AgentExecutor\n",
+    "from langchain import OpenAI, SerpAPIWrapper, LLMChain\n",
+    "\n",
+    "todo_prompt = PromptTemplate.from_template(\n",
+    "    \"You are a planner who is an expert at coming up with a todo list for a given objective. Come up with a todo list for this objective: {objective}\"\n",
+    ")\n",
+    "todo_chain = LLMChain(llm=OpenAI(temperature=0), prompt=todo_prompt)\n",
+    "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",
+    "    Tool(\n",
+    "        name=\"TODO\",\n",
+    "        func=todo_chain.run,\n",
+    "        description=\"useful for when you need to come up with todo lists. Input: an objective to create a todo list for. Output: a todo list for that objective. Please be very clear what the objective is!\",\n",
+    "    ),\n",
+    "]\n",
+    "\n",
+    "\n",
+    "prefix = \"\"\"You are an AI who performs one task based on the following objective: {objective}. Take into account these previously completed tasks: {context}.\"\"\"\n",
+    "suffix = \"\"\"Question: {task}\n",
+    "{agent_scratchpad}\"\"\"\n",
+    "prompt = ZeroShotAgent.create_prompt(\n",
+    "    tools,\n",
+    "    prefix=prefix,\n",
+    "    suffix=suffix,\n",
+    "    input_variables=[\"objective\", \"task\", \"context\", \"agent_scratchpad\"],\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3ad996c5",
+   "metadata": {},
+   "source": [
+    "### Define the BabyAGI Controller\n",
+    "\n",
+    "BabyAGI composes the chains defined above in a (potentially-)infinite loop."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "id": "0ada0636",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_next_task(\n",
+    "    task_creation_chain: LLMChain,\n",
+    "    result: Dict,\n",
+    "    task_description: str,\n",
+    "    task_list: List[str],\n",
+    "    objective: str,\n",
+    ") -> List[Dict]:\n",
+    "    \"\"\"Get the next task.\"\"\"\n",
+    "    incomplete_tasks = \", \".join(task_list)\n",
+    "    response = task_creation_chain.run(\n",
+    "        result=result,\n",
+    "        task_description=task_description,\n",
+    "        incomplete_tasks=incomplete_tasks,\n",
+    "        objective=objective,\n",
+    "    )\n",
+    "    new_tasks = response.split(\"\\n\")\n",
+    "    return [{\"task_name\": task_name} for task_name in new_tasks if task_name.strip()]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "id": "d35250ad",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def prioritize_tasks(\n",
+    "    task_prioritization_chain: LLMChain,\n",
+    "    this_task_id: int,\n",
+    "    task_list: List[Dict],\n",
+    "    objective: str,\n",
+    ") -> List[Dict]:\n",
+    "    \"\"\"Prioritize tasks.\"\"\"\n",
+    "    task_names = [t[\"task_name\"] for t in task_list]\n",
+    "    next_task_id = int(this_task_id) + 1\n",
+    "    response = task_prioritization_chain.run(\n",
+    "        task_names=task_names, next_task_id=next_task_id, objective=objective\n",
+    "    )\n",
+    "    new_tasks = response.split(\"\\n\")\n",
+    "    prioritized_task_list = []\n",
+    "    for task_string in new_tasks:\n",
+    "        if not task_string.strip():\n",
+    "            continue\n",
+    "        task_parts = task_string.strip().split(\".\", 1)\n",
+    "        if len(task_parts) == 2:\n",
+    "            task_id = task_parts[0].strip()\n",
+    "            task_name = task_parts[1].strip()\n",
+    "            prioritized_task_list.append({\"task_id\": task_id, \"task_name\": task_name})\n",
+    "    return prioritized_task_list"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "id": "e3f1840c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def _get_top_tasks(vectorstore, query: str, k: int) -> List[str]:\n",
+    "    \"\"\"Get the top k tasks based on the query.\"\"\"\n",
+    "    results = vectorstore.similarity_search_with_score(query, k=k)\n",
+    "    if not results:\n",
+    "        return []\n",
+    "    sorted_results, _ = zip(*sorted(results, key=lambda x: x[1], reverse=True))\n",
+    "    return [str(item.metadata[\"task\"]) for item in sorted_results]\n",
+    "\n",
+    "\n",
+    "def execute_task(\n",
+    "    vectorstore, execution_chain: LLMChain, objective: str, task: str, k: int = 5\n",
+    ") -> str:\n",
+    "    \"\"\"Execute a task.\"\"\"\n",
+    "    context = _get_top_tasks(vectorstore, query=objective, k=k)\n",
+    "    return execution_chain.run(objective=objective, context=context, task=task)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "id": "1e978938",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class BabyAGI(Chain, BaseModel):\n",
+    "    \"\"\"Controller model for the BabyAGI agent.\"\"\"\n",
+    "\n",
+    "    task_list: deque = Field(default_factory=deque)\n",
+    "    task_creation_chain: TaskCreationChain = Field(...)\n",
+    "    task_prioritization_chain: TaskPrioritizationChain = Field(...)\n",
+    "    execution_chain: AgentExecutor = Field(...)\n",
+    "    task_id_counter: int = Field(1)\n",
+    "    vectorstore: VectorStore = Field(init=False)\n",
+    "    max_iterations: Optional[int] = None\n",
+    "\n",
+    "    class Config:\n",
+    "        \"\"\"Configuration for this pydantic object.\"\"\"\n",
+    "\n",
+    "        arbitrary_types_allowed = True\n",
+    "\n",
+    "    def add_task(self, task: Dict):\n",
+    "        self.task_list.append(task)\n",
+    "\n",
+    "    def print_task_list(self):\n",
+    "        print(\"\\033[95m\\033[1m\" + \"\\n*****TASK LIST*****\\n\" + \"\\033[0m\\033[0m\")\n",
+    "        for t in self.task_list:\n",
+    "            print(str(t[\"task_id\"]) + \": \" + t[\"task_name\"])\n",
+    "\n",
+    "    def print_next_task(self, task: Dict):\n",
+    "        print(\"\\033[92m\\033[1m\" + \"\\n*****NEXT TASK*****\\n\" + \"\\033[0m\\033[0m\")\n",
+    "        print(str(task[\"task_id\"]) + \": \" + task[\"task_name\"])\n",
+    "\n",
+    "    def print_task_result(self, result: str):\n",
+    "        print(\"\\033[93m\\033[1m\" + \"\\n*****TASK RESULT*****\\n\" + \"\\033[0m\\033[0m\")\n",
+    "        print(result)\n",
+    "\n",
+    "    @property\n",
+    "    def input_keys(self) -> List[str]:\n",
+    "        return [\"objective\"]\n",
+    "\n",
+    "    @property\n",
+    "    def output_keys(self) -> List[str]:\n",
+    "        return []\n",
+    "\n",
+    "    def _call(self, inputs: Dict[str, Any]) -> Dict[str, Any]:\n",
+    "        \"\"\"Run the agent.\"\"\"\n",
+    "        objective = inputs[\"objective\"]\n",
+    "        first_task = inputs.get(\"first_task\", \"Make a todo list\")\n",
+    "        self.add_task({\"task_id\": 1, \"task_name\": first_task})\n",
+    "        num_iters = 0\n",
+    "        while True:\n",
+    "            if self.task_list:\n",
+    "                self.print_task_list()\n",
+    "\n",
+    "                # Step 1: Pull the first task\n",
+    "                task = self.task_list.popleft()\n",
+    "                self.print_next_task(task)\n",
+    "\n",
+    "                # Step 2: Execute the task\n",
+    "                result = execute_task(\n",
+    "                    self.vectorstore, self.execution_chain, objective, task[\"task_name\"]\n",
+    "                )\n",
+    "                this_task_id = int(task[\"task_id\"])\n",
+    "                self.print_task_result(result)\n",
+    "\n",
+    "                # Step 3: Store the result in Pinecone\n",
+    "                result_id = f\"result_{task['task_id']}\"\n",
+    "                self.vectorstore.add_texts(\n",
+    "                    texts=[result],\n",
+    "                    metadatas=[{\"task\": task[\"task_name\"]}],\n",
+    "                    ids=[result_id],\n",
+    "                )\n",
+    "\n",
+    "                # Step 4: Create new tasks and reprioritize task list\n",
+    "                new_tasks = get_next_task(\n",
+    "                    self.task_creation_chain,\n",
+    "                    result,\n",
+    "                    task[\"task_name\"],\n",
+    "                    [t[\"task_name\"] for t in self.task_list],\n",
+    "                    objective,\n",
+    "                )\n",
+    "                for new_task in new_tasks:\n",
+    "                    self.task_id_counter += 1\n",
+    "                    new_task.update({\"task_id\": self.task_id_counter})\n",
+    "                    self.add_task(new_task)\n",
+    "                self.task_list = deque(\n",
+    "                    prioritize_tasks(\n",
+    "                        self.task_prioritization_chain,\n",
+    "                        this_task_id,\n",
+    "                        list(self.task_list),\n",
+    "                        objective,\n",
+    "                    )\n",
+    "                )\n",
+    "            num_iters += 1\n",
+    "            if self.max_iterations is not None and num_iters == self.max_iterations:\n",
+    "                print(\n",
+    "                    \"\\033[91m\\033[1m\" + \"\\n*****TASK ENDING*****\\n\" + \"\\033[0m\\033[0m\"\n",
+    "                )\n",
+    "                break\n",
+    "        return {}\n",
+    "\n",
+    "    @classmethod\n",
+    "    def from_llm(\n",
+    "        cls, llm: BaseLLM, vectorstore: VectorStore, verbose: bool = False, **kwargs\n",
+    "    ) -> \"BabyAGI\":\n",
+    "        \"\"\"Initialize the BabyAGI Controller.\"\"\"\n",
+    "        task_creation_chain = TaskCreationChain.from_llm(llm, verbose=verbose)\n",
+    "        task_prioritization_chain = TaskPrioritizationChain.from_llm(\n",
+    "            llm, verbose=verbose\n",
+    "        )\n",
+    "        llm_chain = LLMChain(llm=llm, prompt=prompt)\n",
+    "        tool_names = [tool.name for tool in tools]\n",
+    "        agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names)\n",
+    "        agent_executor = AgentExecutor.from_agent_and_tools(\n",
+    "            agent=agent, tools=tools, verbose=True\n",
+    "        )\n",
+    "        return cls(\n",
+    "            task_creation_chain=task_creation_chain,\n",
+    "            task_prioritization_chain=task_prioritization_chain,\n",
+    "            execution_chain=agent_executor,\n",
+    "            vectorstore=vectorstore,\n",
+    "            **kwargs,\n",
+    "        )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "05ba762e",
+   "metadata": {},
+   "source": [
+    "### Run the BabyAGI\n",
+    "\n",
+    "Now it's time to create the BabyAGI controller and watch it try to accomplish your objective."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "id": "3d220b69",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "OBJECTIVE = \"Write a weather report for SF today\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 52,
+   "id": "8a8e5543",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "id": "3d69899b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Logging of LLMChains\n",
+    "verbose = False\n",
+    "# If None, will keep on going forever\n",
+    "max_iterations: Optional[int] = 3\n",
+    "baby_agi = BabyAGI.from_llm(\n",
+    "    llm=llm, vectorstore=vectorstore, verbose=verbose, max_iterations=max_iterations\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "id": "f7957b51",
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[95m\u001b[1m\n",
+      "*****TASK LIST*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "1: Make a todo list\n",
+      "\u001b[92m\u001b[1m\n",
+      "*****NEXT TASK*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "1: Make a todo list\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to gather data on the current weather conditions in SF\n",
+      "Action: Search\n",
+      "Action Input: Current weather conditions in SF\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mHigh 67F. Winds WNW at 10 to 15 mph. Clear to partly cloudy.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to make a todo list\n",
+      "Action: TODO\n",
+      "Action Input: Write a weather report for SF today\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3m\n",
+      "\n",
+      "1. Research current weather conditions in San Francisco\n",
+      "2. Gather data on temperature, humidity, wind speed, and other relevant weather conditions\n",
+      "3. Analyze data to determine current weather trends\n",
+      "4. Write a brief introduction to the weather report\n",
+      "5. Describe current weather conditions in San Francisco\n",
+      "6. Discuss any upcoming weather changes\n",
+      "7. Summarize the weather report\n",
+      "8. Proofread and edit the report\n",
+      "9. Submit the report\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: A weather report for SF today should include research on current weather conditions in San Francisco, gathering data on temperature, humidity, wind speed, and other relevant weather conditions, analyzing data to determine current weather trends, writing a brief introduction to the weather report, describing current weather conditions in San Francisco, discussing any upcoming weather changes, summarizing the weather report, proofreading and editing the report, and submitting the report.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\u001b[93m\u001b[1m\n",
+      "*****TASK RESULT*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "A weather report for SF today should include research on current weather conditions in San Francisco, gathering data on temperature, humidity, wind speed, and other relevant weather conditions, analyzing data to determine current weather trends, writing a brief introduction to the weather report, describing current weather conditions in San Francisco, discussing any upcoming weather changes, summarizing the weather report, proofreading and editing the report, and submitting the report.\n",
+      "\u001b[95m\u001b[1m\n",
+      "*****TASK LIST*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "2: Gather data on temperature, humidity, wind speed, and other relevant weather conditions\n",
+      "3: Analyze data to determine current weather trends\n",
+      "4: Write a brief introduction to the weather report\n",
+      "5: Describe current weather conditions in San Francisco\n",
+      "6: Discuss any upcoming weather changes\n",
+      "7: Summarize the weather report\n",
+      "8: Proofread and edit the report\n",
+      "9: Submit the report\n",
+      "1: Research current weather conditions in San Francisco\n",
+      "\u001b[92m\u001b[1m\n",
+      "*****NEXT TASK*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "2: Gather data on temperature, humidity, wind speed, and other relevant weather conditions\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to search for the current weather conditions in SF\n",
+      "Action: Search\n",
+      "Action Input: Current weather conditions in SF\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mHigh 67F. Winds WNW at 10 to 15 mph. Clear to partly cloudy.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to make a todo list\n",
+      "Action: TODO\n",
+      "Action Input: Create a weather report for SF today\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3m\n",
+      "\n",
+      "1. Gather current weather data for SF, including temperature, wind speed, humidity, and precipitation.\n",
+      "2. Research historical weather data for SF to compare current conditions.\n",
+      "3. Analyze current and historical data to determine any trends or patterns.\n",
+      "4. Create a visual representation of the data, such as a graph or chart.\n",
+      "5. Write a summary of the weather report, including key findings and any relevant information.\n",
+      "6. Publish the weather report on a website or other platform.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: Today in San Francisco, the temperature is 67F with winds WNW at 10 to 15 mph. The sky is clear to partly cloudy.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\u001b[93m\u001b[1m\n",
+      "*****TASK RESULT*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "Today in San Francisco, the temperature is 67F with winds WNW at 10 to 15 mph. The sky is clear to partly cloudy.\n",
+      "\u001b[95m\u001b[1m\n",
+      "*****TASK LIST*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "3: Research current weather conditions in San Francisco\n",
+      "4: Compare the current weather conditions in San Francisco to the average for this time of year.\n",
+      "5: Identify any potential weather-related hazards in the area.\n",
+      "6: Research any historical weather patterns in San Francisco.\n",
+      "7: Analyze data to determine current weather trends\n",
+      "8: Include any relevant data from nearby cities in the report.\n",
+      "9: Include any relevant data from the National Weather Service in the report.\n",
+      "10: Include any relevant data from local news sources in the report.\n",
+      "11: Include any relevant data from online weather sources in the report.\n",
+      "12: Include any relevant data from local meteorologists in the report.\n",
+      "13: Include any relevant data from local weather stations in the report.\n",
+      "14: Include any relevant data from satellite images in the report.\n",
+      "15: Describe current weather conditions in San Francisco\n",
+      "16: Discuss any upcoming weather changes\n",
+      "17: Write a brief introduction to the weather report\n",
+      "18: Summarize the weather report\n",
+      "19: Proofread and edit the report\n",
+      "20: Submit the report\n",
+      "\u001b[92m\u001b[1m\n",
+      "*****NEXT TASK*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "3: Research current weather conditions in San Francisco\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to search for current weather conditions in San Francisco\n",
+      "Action: Search\n",
+      "Action Input: Current weather conditions in San Francisco\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mTodaySun 04/09 High 67 · 1% Precip. ; TonightSun 04/09 Low 49 · 9% Precip. ; TomorrowMon 04/10 High 64 · 11% Precip.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: Today in San Francisco, the high temperature is 67 degrees with 1% chance of precipitation. The low temperature tonight is 49 degrees with 9% chance of precipitation. Tomorrow's high temperature is 64 degrees with 11% chance of precipitation.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\u001b[93m\u001b[1m\n",
+      "*****TASK RESULT*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "Today in San Francisco, the high temperature is 67 degrees with 1% chance of precipitation. The low temperature tonight is 49 degrees with 9% chance of precipitation. Tomorrow's high temperature is 64 degrees with 11% chance of precipitation.\n",
+      "\u001b[91m\u001b[1m\n",
+      "*****TASK ENDING*****\n",
+      "\u001b[0m\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'objective': 'Write a weather report for SF today'}"
+      ]
+     },
+     "execution_count": 54,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "baby_agi({\"objective\": OBJECTIVE})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "898a210b",
+   "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
+}

docs/use_cases/agents/camel_role_playing.ipynb

@@ -0,0 +1,693 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# CAMEL Role-Playing Autonomous Cooperative Agents\n",
+    "\n",
+    "This is a langchain implementation of paper: \"CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society\".\n",
+    "\n",
+    "Overview:\n",
+    "\n",
+    "The rapid advancement of conversational and chat-based language models has led to remarkable progress in complex task-solving. However, their success heavily relies on human input to guide the conversation, which can be challenging and time-consuming. This paper explores the potential of building scalable techniques to facilitate autonomous cooperation among communicative agents and provide insight into their \"cognitive\" processes. To address the challenges of achieving autonomous cooperation, we propose a novel communicative agent framework named role-playing. Our approach involves using inception prompting to guide chat agents toward task completion while maintaining consistency with human intentions. We showcase how role-playing can be used to generate conversational data for studying the behaviors and capabilities of chat agents, providing a valuable resource for investigating conversational language models. Our contributions include introducing a novel communicative agent framework, offering a scalable approach for studying the cooperative behaviors and capabilities of multi-agent systems, and open-sourcing our library to support research on communicative agents and beyond.\n",
+    "\n",
+    "The original implementation: https://github.com/lightaime/camel\n",
+    "\n",
+    "Project website: https://www.camel-ai.org/\n",
+    "\n",
+    "Arxiv paper: https://arxiv.org/abs/2303.17760\n"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Import LangChain related modules "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import List\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.prompts.chat import (\n",
+    "    SystemMessagePromptTemplate,\n",
+    "    HumanMessagePromptTemplate,\n",
+    ")\n",
+    "from langchain.schema import (\n",
+    "    AIMessage,\n",
+    "    HumanMessage,\n",
+    "    SystemMessage,\n",
+    "    BaseMessage,\n",
+    ")"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Define a CAMEL agent helper class"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class CAMELAgent:\n",
+    "\n",
+    "    def __init__(\n",
+    "        self,\n",
+    "        system_message: SystemMessage,\n",
+    "        model: ChatOpenAI,\n",
+    "    ) -> None:\n",
+    "        self.system_message = system_message\n",
+    "        self.model = model\n",
+    "        self.init_messages()\n",
+    "\n",
+    "    def reset(self) -> None:\n",
+    "        self.init_messages()\n",
+    "        return self.stored_messages\n",
+    "\n",
+    "    def init_messages(self) -> None:\n",
+    "        self.stored_messages = [self.system_message]\n",
+    "\n",
+    "    def update_messages(self, message: BaseMessage) -> List[BaseMessage]:\n",
+    "        self.stored_messages.append(message)\n",
+    "        return self.stored_messages\n",
+    "\n",
+    "    def step(\n",
+    "        self,\n",
+    "        input_message: HumanMessage,\n",
+    "    ) -> AIMessage:\n",
+    "        messages = self.update_messages(input_message)\n",
+    "\n",
+    "        output_message = self.model(messages)\n",
+    "        self.update_messages(output_message)\n",
+    "\n",
+    "        return output_message\n"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup OpenAI API key and roles and task for role-playing"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"\"\n",
+    "\n",
+    "assistant_role_name = \"Python Programmer\"\n",
+    "user_role_name = \"Stock Trader\"\n",
+    "task = \"Develop a trading bot for the stock market\"\n",
+    "word_limit = 50 # word limit for task brainstorming"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create a task specify agent for brainstorming and get the specified task"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Specified task: Develop a Python-based swing trading bot that scans market trends, monitors stocks, and generates trading signals to help a stock trader to place optimal buy and sell orders with defined stop losses and profit targets.\n"
+     ]
+    }
+   ],
+   "source": [
+    "task_specifier_sys_msg = SystemMessage(content=\"You can make a task more specific.\")\n",
+    "task_specifier_prompt = (\n",
+    "\"\"\"Here is a task that {assistant_role_name} will help {user_role_name} to complete: {task}.\n",
+    "Please make it more specific. Be creative and imaginative.\n",
+    "Please reply with the specified task in {word_limit} words or less. Do not add anything else.\"\"\"\n",
+    ")\n",
+    "task_specifier_template = HumanMessagePromptTemplate.from_template(template=task_specifier_prompt)\n",
+    "task_specify_agent = CAMELAgent(task_specifier_sys_msg, ChatOpenAI(temperature=1.0))\n",
+    "task_specifier_msg = task_specifier_template.format_messages(assistant_role_name=assistant_role_name,\n",
+    "                                                             user_role_name=user_role_name,\n",
+    "                                                             task=task, word_limit=word_limit)[0]\n",
+    "specified_task_msg = task_specify_agent.step(task_specifier_msg)\n",
+    "print(f\"Specified task: {specified_task_msg.content}\")\n",
+    "specified_task = specified_task_msg.content"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create inception prompts for AI assistant and AI user for role-playing"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "assistant_inception_prompt = (\n",
+    "\"\"\"Never forget you are a {assistant_role_name} and I am a {user_role_name}. Never flip roles! Never instruct me!\n",
+    "We share a common interest in collaborating to successfully complete a task.\n",
+    "You must help me to complete the task.\n",
+    "Here is the task: {task}. Never forget our task!\n",
+    "I must instruct you based on your expertise and my needs to complete the task.\n",
+    "\n",
+    "I must give you one instruction at a time.\n",
+    "You must write a specific solution that appropriately completes the requested instruction.\n",
+    "You must decline my instruction honestly if you cannot perform the instruction due to physical, moral, legal reasons or your capability and explain the reasons.\n",
+    "Do not add anything else other than your solution to my instruction.\n",
+    "You are never supposed to ask me any questions you only answer questions.\n",
+    "You are never supposed to reply with a flake solution. Explain your solutions.\n",
+    "Your solution must be declarative sentences and simple present tense.\n",
+    "Unless I say the task is completed, you should always start with:\n",
+    "\n",
+    "Solution: <YOUR_SOLUTION>\n",
+    "\n",
+    "<YOUR_SOLUTION> should be specific and provide preferable implementations and examples for task-solving.\n",
+    "Always end <YOUR_SOLUTION> with: Next request.\"\"\"\n",
+    ")\n",
+    "\n",
+    "user_inception_prompt = (\n",
+    "\"\"\"Never forget you are a {user_role_name} and I am a {assistant_role_name}. Never flip roles! You will always instruct me.\n",
+    "We share a common interest in collaborating to successfully complete a task.\n",
+    "I must help you to complete the task.\n",
+    "Here is the task: {task}. Never forget our task!\n",
+    "You must instruct me based on my expertise and your needs to complete the task ONLY in the following two ways:\n",
+    "\n",
+    "1. Instruct with a necessary input:\n",
+    "Instruction: <YOUR_INSTRUCTION>\n",
+    "Input: <YOUR_INPUT>\n",
+    "\n",
+    "2. Instruct without any input:\n",
+    "Instruction: <YOUR_INSTRUCTION>\n",
+    "Input: None\n",
+    "\n",
+    "The \"Instruction\" describes a task or question. The paired \"Input\" provides further context or information for the requested \"Instruction\".\n",
+    "\n",
+    "You must give me one instruction at a time.\n",
+    "I must write a response that appropriately completes the requested instruction.\n",
+    "I must decline your instruction honestly if I cannot perform the instruction due to physical, moral, legal reasons or my capability and explain the reasons.\n",
+    "You should instruct me not ask me questions.\n",
+    "Now you must start to instruct me using the two ways described above.\n",
+    "Do not add anything else other than your instruction and the optional corresponding input!\n",
+    "Keep giving me instructions and necessary inputs until you think the task is completed.\n",
+    "When the task is completed, you must only reply with a single word <CAMEL_TASK_DONE>.\n",
+    "Never say <CAMEL_TASK_DONE> unless my responses have solved your task.\"\"\"\n",
+    ")"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create a helper helper to get system messages for AI assistant and AI user from role names and the task"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_sys_msgs(assistant_role_name: str, user_role_name: str, task: str):\n",
+    "    \n",
+    "    assistant_sys_template = SystemMessagePromptTemplate.from_template(template=assistant_inception_prompt)\n",
+    "    assistant_sys_msg = assistant_sys_template.format_messages(assistant_role_name=assistant_role_name, user_role_name=user_role_name, task=task)[0]\n",
+    "    \n",
+    "    user_sys_template = SystemMessagePromptTemplate.from_template(template=user_inception_prompt)\n",
+    "    user_sys_msg = user_sys_template.format_messages(assistant_role_name=assistant_role_name, user_role_name=user_role_name, task=task)[0]\n",
+    "    \n",
+    "    return assistant_sys_msg, user_sys_msg"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create AI assistant agent and AI user agent from obtained system messages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "assistant_sys_msg, user_sys_msg = get_sys_msgs(assistant_role_name, user_role_name, specified_task)\n",
+    "assistant_agent = CAMELAgent(assistant_sys_msg, ChatOpenAI(temperature=0.2))\n",
+    "user_agent = CAMELAgent(user_sys_msg, ChatOpenAI(temperature=0.2))\n",
+    "\n",
+    "# Reset agents\n",
+    "assistant_agent.reset()\n",
+    "user_agent.reset()\n",
+    "\n",
+    "# Initialize chats \n",
+    "assistant_msg = HumanMessage(\n",
+    "    content=(f\"{user_sys_msg.content}. \"\n",
+    "                \"Now start to give me introductions one by one. \"\n",
+    "                \"Only reply with Instruction and Input.\"))\n",
+    "\n",
+    "user_msg = HumanMessage(content=f\"{assistant_sys_msg.content}\")\n",
+    "user_msg = assistant_agent.step(user_msg)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Start role-playing session to solve the task!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Original task prompt:\n",
+      "Develop a trading bot for the stock market\n",
+      "\n",
+      "Specified task prompt:\n",
+      "Develop a Python-based swing trading bot that scans market trends, monitors stocks, and generates trading signals to help a stock trader to place optimal buy and sell orders with defined stop losses and profit targets.\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Install the necessary Python libraries for data analysis and trading.\n",
+      "Input: None\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can install the necessary Python libraries using pip, a package installer for Python. We can install pandas, numpy, matplotlib, and ta-lib for data analysis and trading. We can use the following command to install these libraries:\n",
+      "\n",
+      "```\n",
+      "pip install pandas numpy matplotlib ta-lib\n",
+      "```\n",
+      "\n",
+      "Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Import the necessary libraries in the Python script.\n",
+      "Input: None\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can import the necessary libraries in the Python script using the import statement. We need to import pandas, numpy, matplotlib, and ta-lib for data analysis and trading. We can use the following code to import these libraries:\n",
+      "\n",
+      "```\n",
+      "import pandas as pd\n",
+      "import numpy as np\n",
+      "import matplotlib.pyplot as plt\n",
+      "import talib as ta\n",
+      "```\n",
+      "\n",
+      "Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Load historical stock data into a pandas DataFrame.\n",
+      "Input: The path to the CSV file containing the historical stock data.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can load historical stock data into a pandas DataFrame using the `read_csv()` function from pandas. We need to pass the path to the CSV file containing the historical stock data as an argument to this function. We can use the following code to load the historical stock data:\n",
+      "\n",
+      "```\n",
+      "df = pd.read_csv('path/to/csv/file.csv')\n",
+      "```\n",
+      "\n",
+      "This will load the historical stock data into a pandas DataFrame called `df`. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Preprocess the historical stock data by setting the date column as the index and sorting the DataFrame in ascending order by date.\n",
+      "Input: None.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can preprocess the historical stock data by setting the date column as the index and sorting the DataFrame in ascending order by date using the `set_index()` and `sort_index()` functions from pandas. We can use the following code to preprocess the historical stock data:\n",
+      "\n",
+      "```\n",
+      "df = df.set_index('date')\n",
+      "df = df.sort_index(ascending=True)\n",
+      "```\n",
+      "\n",
+      "This will set the date column as the index and sort the DataFrame in ascending order by date. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Calculate the short-term and long-term moving averages for the stock data using the `ta.SMA()` function from ta-lib.\n",
+      "Input: The period for the short-term moving average and the period for the long-term moving average.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can calculate the short-term and long-term moving averages for the stock data using the `ta.SMA()` function from ta-lib. We need to pass the period for the short-term moving average and the period for the long-term moving average as arguments to this function. We can use the following code to calculate the short-term and long-term moving averages:\n",
+      "\n",
+      "```\n",
+      "short_ma = ta.SMA(df['close'], timeperiod=short_period)\n",
+      "long_ma = ta.SMA(df['close'], timeperiod=long_period)\n",
+      "```\n",
+      "\n",
+      "This will calculate the short-term and long-term moving averages for the stock data and store them in the `short_ma` and `long_ma` variables, respectively. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Create a new DataFrame that combines the historical stock data with the short-term and long-term moving averages.\n",
+      "Input: None.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can create a new DataFrame that combines the historical stock data with the short-term and long-term moving averages using the `concat()` function from pandas. We need to pass the historical stock data, the short-term moving average, and the long-term moving average as arguments to this function. We can use the following code to create the new DataFrame:\n",
+      "\n",
+      "```\n",
+      "new_df = pd.concat([df, short_ma, long_ma], axis=1)\n",
+      "new_df.columns = ['open', 'high', 'low', 'close', 'volume', 'short_ma', 'long_ma']\n",
+      "```\n",
+      "\n",
+      "This will create a new DataFrame called `new_df` that combines the historical stock data with the short-term and long-term moving averages. The columns of the new DataFrame are named 'open', 'high', 'low', 'close', 'volume', 'short_ma', and 'long_ma'. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Create a new column in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages.\n",
+      "Input: None.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can create a new column in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages. We can use the following code to create the new column:\n",
+      "\n",
+      "```\n",
+      "new_df['signal'] = np.where(new_df['short_ma'] > new_df['long_ma'], 1, -1)\n",
+      "```\n",
+      "\n",
+      "This will create a new column called 'signal' in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages. If the short-term moving average is greater than the long-term moving average, the signal is 1 (buy), otherwise the signal is -1 (sell). Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Create a new column in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target.\n",
+      "Input: The stop loss and profit target as percentages.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can create a new column in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target. We need to pass the stop loss and profit target as percentages as arguments to this function. We can use the following code to create the new column:\n",
+      "\n",
+      "```\n",
+      "stop_loss = stop_loss_percent / 100\n",
+      "profit_target = profit_target_percent / 100\n",
+      "\n",
+      "new_df['pnl'] = 0.0\n",
+      "buy_price = 0.0\n",
+      "for i in range(1, len(new_df)):\n",
+      "    if new_df['signal'][i] == 1 and new_df['signal'][i-1] == -1:\n",
+      "        buy_price = new_df['close'][i]\n",
+      "    elif new_df['signal'][i] == -1 and new_df['signal'][i-1] == 1:\n",
+      "        sell_price = new_df['close'][i]\n",
+      "        if sell_price <= buy_price * (1 - stop_loss):\n",
+      "            new_df['pnl'][i] = -stop_loss\n",
+      "        elif sell_price >= buy_price * (1 + profit_target):\n",
+      "            new_df['pnl'][i] = profit_target\n",
+      "        else:\n",
+      "            new_df['pnl'][i] = (sell_price - buy_price) / buy_price\n",
+      "```\n",
+      "\n",
+      "This will create a new column called 'pnl' in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target. The stop loss and profit target are calculated based on the stop_loss_percent and profit_target_percent variables, respectively. The buy and sell prices are stored in the buy_price and sell_price variables, respectively. If the sell price is less than or equal to the stop loss, the profit or loss is set to -stop_loss. If the sell price is greater than or equal to the profit target, the profit or loss is set to profit_target. Otherwise, the profit or loss is calculated as (sell_price - buy_price) / buy_price. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Calculate the total profit or loss for all trades.\n",
+      "Input: None.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can calculate the total profit or loss for all trades by summing the values in the 'pnl' column of the DataFrame. We can use the following code to calculate the total profit or loss:\n",
+      "\n",
+      "```\n",
+      "total_pnl = new_df['pnl'].sum()\n",
+      "```\n",
+      "\n",
+      "This will calculate the total profit or loss for all trades and store it in the total_pnl variable. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Visualize the stock data, short-term moving average, and long-term moving average using a line chart.\n",
+      "Input: None.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can visualize the stock data, short-term moving average, and long-term moving average using a line chart using the `plot()` function from pandas. We can use the following code to visualize the data:\n",
+      "\n",
+      "```\n",
+      "plt.figure(figsize=(12,6))\n",
+      "plt.plot(new_df.index, new_df['close'], label='Close')\n",
+      "plt.plot(new_df.index, new_df['short_ma'], label='Short MA')\n",
+      "plt.plot(new_df.index, new_df['long_ma'], label='Long MA')\n",
+      "plt.xlabel('Date')\n",
+      "plt.ylabel('Price')\n",
+      "plt.title('Stock Data with Moving Averages')\n",
+      "plt.legend()\n",
+      "plt.show()\n",
+      "```\n",
+      "\n",
+      "This will create a line chart that visualizes the stock data, short-term moving average, and long-term moving average. The x-axis represents the date and the y-axis represents the price. The chart also includes a legend that labels each line. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Visualize the buy and sell signals using a scatter plot.\n",
+      "Input: None.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can visualize the buy and sell signals using a scatter plot using the `scatter()` function from matplotlib. We can use the following code to visualize the signals:\n",
+      "\n",
+      "```\n",
+      "buy_signals = new_df[new_df['signal'] == 1]\n",
+      "sell_signals = new_df[new_df['signal'] == -1]\n",
+      "\n",
+      "plt.figure(figsize=(12,6))\n",
+      "plt.scatter(buy_signals.index, buy_signals['close'], label='Buy', marker='^', color='green')\n",
+      "plt.scatter(sell_signals.index, sell_signals['close'], label='Sell', marker='v', color='red')\n",
+      "plt.plot(new_df.index, new_df['close'], label='Close')\n",
+      "plt.xlabel('Date')\n",
+      "plt.ylabel('Price')\n",
+      "plt.title('Buy and Sell Signals')\n",
+      "plt.legend()\n",
+      "plt.show()\n",
+      "```\n",
+      "\n",
+      "This will create a scatter plot that visualizes the buy and sell signals. The x-axis represents the date and the y-axis represents the price. The chart also includes a legend that labels each point. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Print the total profit or loss for all trades.\n",
+      "Input: None.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can print the total profit or loss for all trades using the `print()` function. We can use the following code to print the total profit or loss:\n",
+      "\n",
+      "```\n",
+      "print('Total Profit/Loss: {:.2%}'.format(total_pnl))\n",
+      "```\n",
+      "\n",
+      "This will print the total profit or loss for all trades in percentage format with two decimal places. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Finalize the code by putting all the code snippets together in a single Python script.\n",
+      "Input: The necessary inputs for each code snippet.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: Here is the complete Python script that puts all the code snippets together:\n",
+      "\n",
+      "```\n",
+      "import pandas as pd\n",
+      "import numpy as np\n",
+      "import matplotlib.pyplot as plt\n",
+      "import talib as ta\n",
+      "\n",
+      "# Load historical stock data into a pandas DataFrame\n",
+      "df = pd.read_csv('path/to/csv/file.csv')\n",
+      "\n",
+      "# Preprocess the historical stock data\n",
+      "df = df.set_index('date')\n",
+      "df = df.sort_index(ascending=True)\n",
+      "\n",
+      "# Calculate the short-term and long-term moving averages\n",
+      "short_period = 10\n",
+      "long_period = 30\n",
+      "short_ma = ta.SMA(df['close'], timeperiod=short_period)\n",
+      "long_ma = ta.SMA(df['close'], timeperiod=long_period)\n",
+      "\n",
+      "# Create a new DataFrame that combines the historical stock data with the short-term and long-term moving averages\n",
+      "new_df = pd.concat([df, short_ma, long_ma], axis=1)\n",
+      "new_df.columns = ['open', 'high', 'low', 'close', 'volume', 'short_ma', 'long_ma']\n",
+      "\n",
+      "# Create a new column in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages\n",
+      "new_df['signal'] = np.where(new_df['short_ma'] > new_df['long_ma'], 1, -1)\n",
+      "\n",
+      "# Create a new column in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target\n",
+      "stop_loss_percent = 5\n",
+      "profit_target_percent = 10\n",
+      "stop_loss = stop_loss_percent / 100\n",
+      "profit_target = profit_target_percent / 100\n",
+      "new_df['pnl'] = 0.0\n",
+      "buy_price = 0.0\n",
+      "for i in range(1, len(new_df)):\n",
+      "    if new_df['signal'][i] == 1 and new_df['signal'][i-1] == -1:\n",
+      "        buy_price = new_df['close'][i]\n",
+      "    elif new_df['signal'][i] == -1 and new_df['signal'][i-1] == 1:\n",
+      "        sell_price = new_df['close'][i]\n",
+      "        if sell_price <= buy_price * (1 - stop_loss):\n",
+      "            new_df['pnl'][i] = -stop_loss\n",
+      "        elif sell_price >= buy_price * (1 + profit_target):\n",
+      "            new_df['pnl'][i] = profit_target\n",
+      "        else:\n",
+      "            new_df['pnl'][i] = (sell_price - buy_price) / buy_price\n",
+      "\n",
+      "# Calculate the total profit or loss for all trades\n",
+      "total_pnl = new_df['pnl'].sum()\n",
+      "\n",
+      "# Visualize the stock data, short-term moving average, and long-term moving average using a line chart\n",
+      "plt.figure(figsize=(12,6))\n",
+      "plt.plot(new_df.index, new_df['close'], label='Close')\n",
+      "plt.plot(new_df.index, new_df['short_ma'], label='Short MA')\n",
+      "plt.plot(new_df.index, new_df['long_ma'], label='Long MA')\n",
+      "plt.xlabel('Date')\n",
+      "plt.ylabel('Price')\n",
+      "plt.title('Stock Data with Moving Averages')\n",
+      "plt.legend()\n",
+      "plt.show()\n",
+      "\n",
+      "# Visualize the buy and sell signals using a scatter plot\n",
+      "buy_signals = new_df[new_df['signal'] == 1]\n",
+      "sell_signals = new_df[new_df['signal'] == -1]\n",
+      "plt.figure(figsize=(12,6))\n",
+      "plt.scatter(buy_signals.index, buy_signals['close'], label='Buy', marker='^', color='green')\n",
+      "plt.scatter(sell_signals.index, sell_signals['close'], label='Sell', marker='v', color='red')\n",
+      "plt.plot(new_df.index, new_df['close'], label='Close')\n",
+      "plt.xlabel('Date')\n",
+      "plt.ylabel('Price')\n",
+      "plt.title('Buy and Sell Signals')\n",
+      "plt.legend()\n",
+      "plt.show()\n",
+      "\n",
+      "# Print the total profit or loss for all trades\n",
+      "print('Total Profit/Loss: {:.2%}'.format(total_pnl))\n",
+      "```\n",
+      "\n",
+      "You need to replace the path/to/csv/file.csv with the actual path to the CSV file containing the historical stock data. You can also adjust the short_period, long_period, stop_loss_percent, and profit_target_percent variables to suit your needs.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "<CAMEL_TASK_DONE>\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Great! Let me know if you need any further assistance.\n",
+      "\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(f\"Original task prompt:\\n{task}\\n\")\n",
+    "print(f\"Specified task prompt:\\n{specified_task}\\n\")\n",
+    "\n",
+    "chat_turn_limit, n = 30, 0\n",
+    "while n < chat_turn_limit:\n",
+    "    n += 1\n",
+    "    user_ai_msg = user_agent.step(assistant_msg)\n",
+    "    user_msg = HumanMessage(content=user_ai_msg.content)\n",
+    "    print(f\"AI User ({user_role_name}):\\n\\n{user_msg.content}\\n\\n\")\n",
+    "    \n",
+    "    assistant_ai_msg = assistant_agent.step(user_msg)\n",
+    "    assistant_msg = HumanMessage(content=assistant_ai_msg.content)\n",
+    "    print(f\"AI Assistant ({assistant_role_name}):\\n\\n{assistant_msg.content}\\n\\n\")\n",
+    "    if \"<CAMEL_TASK_DONE>\" in user_msg.content:\n",
+    "        break"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "camel",
+   "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"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/use_cases/agents/custom_agent_with_plugin_retrieval.ipynb

@@ -0,0 +1,538 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "ba5f8741",
+   "metadata": {},
+   "source": [
+    "# Custom Agent with PlugIn Retrieval\n",
+    "\n",
+    "This notebook combines two concepts in order to build a custom agent that can interact with AI Plugins:\n",
+    "\n",
+    "1. [Custom Agent with Retrieval](../../modules/agents/agents/custom_agent_with_plugin_retrieval.ipynb): This introduces the concept of retrieving many tools, which is useful when trying to work with arbitrarily many plugins.\n",
+    "2. [Natural Language API Chains](../../modules/chains/examples/openapi.ipynb): This creates Natural Language wrappers around OpenAPI endpoints. This is useful because (1) plugins use OpenAPI endpoints under the hood, (2) wrapping them in an NLAChain allows the router agent to call it more easily.\n",
+    "\n",
+    "The novel idea introduced in this notebook is the idea of using retrieval to select not the tools explicitly, but the set of OpenAPI specs to use. We can then generate tools from those OpenAPI specs. The use case for this is when trying to get agents to use plugins. It may be more efficient to choose plugins first, then the endpoints, rather than the endpoints directly. This is because the plugins may contain more useful information for selection."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fea4812c",
+   "metadata": {},
+   "source": [
+    "## Set up environment\n",
+    "\n",
+    "Do necessary imports, etc."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "9af9734e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.agents import Tool, AgentExecutor, LLMSingleActionAgent, AgentOutputParser\n",
+    "from langchain.prompts import StringPromptTemplate\n",
+    "from langchain import OpenAI, SerpAPIWrapper, LLMChain\n",
+    "from typing import List, Union\n",
+    "from langchain.schema import AgentAction, AgentFinish\n",
+    "from langchain.agents.agent_toolkits import NLAToolkit\n",
+    "from langchain.tools.plugin import AIPlugin\n",
+    "import re"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2f91d8b4",
+   "metadata": {},
+   "source": [
+    "## Setup LLM"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "a1a3b59c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6df0253f",
+   "metadata": {},
+   "source": [
+    "## Set up plugins\n",
+    "\n",
+    "Load and index plugins"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "becda2a1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "urls = [\n",
+    "    \"https://datasette.io/.well-known/ai-plugin.json\",\n",
+    "    \"https://api.speak.com/.well-known/ai-plugin.json\",\n",
+    "    \"https://www.wolframalpha.com/.well-known/ai-plugin.json\",\n",
+    "    \"https://www.zapier.com/.well-known/ai-plugin.json\",\n",
+    "    \"https://www.klarna.com/.well-known/ai-plugin.json\",\n",
+    "    \"https://www.joinmilo.com/.well-known/ai-plugin.json\",\n",
+    "    \"https://slack.com/.well-known/ai-plugin.json\",\n",
+    "    \"https://schooldigger.com/.well-known/ai-plugin.json\",\n",
+    "]\n",
+    "\n",
+    "AI_PLUGINS = [AIPlugin.from_url(url) for url in urls]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "17362717",
+   "metadata": {},
+   "source": [
+    "## Tool Retriever\n",
+    "\n",
+    "We will use a vectorstore to create embeddings for each tool description. Then, for an incoming query we can create embeddings for that query and do a similarity search for relevant tools."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "77c4be4b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.vectorstores import FAISS\n",
+    "from langchain.embeddings import OpenAIEmbeddings\n",
+    "from langchain.schema import Document"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "9092a158",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
+      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
+      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
+      "Attempting to load an OpenAPI 3.0.2 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
+      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
+      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
+      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
+      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
+      "Attempting to load a Swagger 2.0 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n"
+     ]
+    }
+   ],
+   "source": [
+    "embeddings = OpenAIEmbeddings()\n",
+    "docs = [\n",
+    "    Document(page_content=plugin.description_for_model, \n",
+    "             metadata={\"plugin_name\": plugin.name_for_model}\n",
+    "            )\n",
+    "    for plugin in AI_PLUGINS\n",
+    "]\n",
+    "vector_store = FAISS.from_documents(docs, embeddings)\n",
+    "toolkits_dict = {plugin.name_for_model: \n",
+    "                 NLAToolkit.from_llm_and_ai_plugin(llm, plugin) \n",
+    "                 for plugin in AI_PLUGINS}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "735a7566",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "retriever = vector_store.as_retriever()\n",
+    "\n",
+    "def get_tools(query):\n",
+    "    # Get documents, which contain the Plugins to use\n",
+    "    docs = retriever.get_relevant_documents(query)\n",
+    "    # Get the toolkits, one for each plugin\n",
+    "    tool_kits = [toolkits_dict[d.metadata[\"plugin_name\"]] for d in docs]\n",
+    "    # Get the tools: a separate NLAChain for each endpoint\n",
+    "    tools = []\n",
+    "    for tk in tool_kits:\n",
+    "        tools.extend(tk.nla_tools)\n",
+    "    return tools"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7699afd7",
+   "metadata": {},
+   "source": [
+    "We can now test this retriever to see if it seems to work."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "425f2886",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['Milo.askMilo',\n",
+       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.search_all_actions',\n",
+       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.preview_a_zap',\n",
+       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.get_configuration_link',\n",
+       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.list_exposed_actions',\n",
+       " 'SchoolDigger_API_V2.0.Autocomplete_GetSchools',\n",
+       " 'SchoolDigger_API_V2.0.Districts_GetAllDistricts2',\n",
+       " 'SchoolDigger_API_V2.0.Districts_GetDistrict2',\n",
+       " 'SchoolDigger_API_V2.0.Rankings_GetSchoolRank2',\n",
+       " 'SchoolDigger_API_V2.0.Rankings_GetRank_District',\n",
+       " 'SchoolDigger_API_V2.0.Schools_GetAllSchools20',\n",
+       " 'SchoolDigger_API_V2.0.Schools_GetSchool20',\n",
+       " 'Speak.translate',\n",
+       " 'Speak.explainPhrase',\n",
+       " 'Speak.explainTask']"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tools = get_tools(\"What could I do today with my kiddo\")\n",
+    "[t.name for t in tools]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "3aa88768",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['Open_AI_Klarna_product_Api.productsUsingGET',\n",
+       " 'Milo.askMilo',\n",
+       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.search_all_actions',\n",
+       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.preview_a_zap',\n",
+       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.get_configuration_link',\n",
+       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.list_exposed_actions',\n",
+       " 'SchoolDigger_API_V2.0.Autocomplete_GetSchools',\n",
+       " 'SchoolDigger_API_V2.0.Districts_GetAllDistricts2',\n",
+       " 'SchoolDigger_API_V2.0.Districts_GetDistrict2',\n",
+       " 'SchoolDigger_API_V2.0.Rankings_GetSchoolRank2',\n",
+       " 'SchoolDigger_API_V2.0.Rankings_GetRank_District',\n",
+       " 'SchoolDigger_API_V2.0.Schools_GetAllSchools20',\n",
+       " 'SchoolDigger_API_V2.0.Schools_GetSchool20']"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tools = get_tools(\"what shirts can i buy?\")\n",
+    "[t.name for t in tools]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2e7a075c",
+   "metadata": {},
+   "source": [
+    "## Prompt Template\n",
+    "\n",
+    "The prompt template is pretty standard, because we're not actually changing that much logic in the actual prompt template, but rather we are just changing how retrieval is done."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "339b1bb8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Set up the base template\n",
+    "template = \"\"\"Answer the following questions as best you can, but speaking as a pirate might speak. You have access to the following tools:\n",
+    "\n",
+    "{tools}\n",
+    "\n",
+    "Use the following format:\n",
+    "\n",
+    "Question: the input question you must answer\n",
+    "Thought: you should always think about what to do\n",
+    "Action: the action to take, should be one of [{tool_names}]\n",
+    "Action Input: the input to the action\n",
+    "Observation: the result of the action\n",
+    "... (this Thought/Action/Action Input/Observation can repeat N times)\n",
+    "Thought: I now know the final answer\n",
+    "Final Answer: the final answer to the original input question\n",
+    "\n",
+    "Begin! Remember to speak as a pirate when giving your final answer. Use lots of \"Arg\"s\n",
+    "\n",
+    "Question: {input}\n",
+    "{agent_scratchpad}\"\"\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1583acdc",
+   "metadata": {},
+   "source": [
+    "The custom prompt template now has the concept of a tools_getter, which we call on the input to select the tools to use"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "fd969d31",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import Callable\n",
+    "# Set up a prompt template\n",
+    "class CustomPromptTemplate(StringPromptTemplate):\n",
+    "    # The template to use\n",
+    "    template: str\n",
+    "    ############## NEW ######################\n",
+    "    # The list of tools available\n",
+    "    tools_getter: Callable\n",
+    "    \n",
+    "    def format(self, **kwargs) -> str:\n",
+    "        # Get the intermediate steps (AgentAction, Observation tuples)\n",
+    "        # Format them in a particular way\n",
+    "        intermediate_steps = kwargs.pop(\"intermediate_steps\")\n",
+    "        thoughts = \"\"\n",
+    "        for action, observation in intermediate_steps:\n",
+    "            thoughts += action.log\n",
+    "            thoughts += f\"\\nObservation: {observation}\\nThought: \"\n",
+    "        # Set the agent_scratchpad variable to that value\n",
+    "        kwargs[\"agent_scratchpad\"] = thoughts\n",
+    "        ############## NEW ######################\n",
+    "        tools = self.tools_getter(kwargs[\"input\"])\n",
+    "        # Create a tools variable from the list of tools provided\n",
+    "        kwargs[\"tools\"] = \"\\n\".join([f\"{tool.name}: {tool.description}\" for tool in tools])\n",
+    "        # Create a list of tool names for the tools provided\n",
+    "        kwargs[\"tool_names\"] = \", \".join([tool.name for tool in tools])\n",
+    "        return self.template.format(**kwargs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "798ef9fb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompt = CustomPromptTemplate(\n",
+    "    template=template,\n",
+    "    tools_getter=get_tools,\n",
+    "    # This omits the `agent_scratchpad`, `tools`, and `tool_names` variables because those are generated dynamically\n",
+    "    # This includes the `intermediate_steps` variable because that is needed\n",
+    "    input_variables=[\"input\", \"intermediate_steps\"]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ef3a1af3",
+   "metadata": {},
+   "source": [
+    "## Output Parser\n",
+    "\n",
+    "The output parser is unchanged from the previous notebook, since we are not changing anything about the output format."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "7c6fe0d3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class CustomOutputParser(AgentOutputParser):\n",
+    "    \n",
+    "    def parse(self, llm_output: str) -> Union[AgentAction, AgentFinish]:\n",
+    "        # Check if agent should finish\n",
+    "        if \"Final Answer:\" in llm_output:\n",
+    "            return AgentFinish(\n",
+    "                # Return values is generally always a dictionary with a single `output` key\n",
+    "                # It is not recommended to try anything else at the moment :)\n",
+    "                return_values={\"output\": llm_output.split(\"Final Answer:\")[-1].strip()},\n",
+    "                log=llm_output,\n",
+    "            )\n",
+    "        # Parse out the action and action input\n",
+    "        regex = r\"Action: (.*?)[\\n]*Action Input:[\\s]*(.*)\"\n",
+    "        match = re.search(regex, llm_output, re.DOTALL)\n",
+    "        if not match:\n",
+    "            raise ValueError(f\"Could not parse LLM output: `{llm_output}`\")\n",
+    "        action = match.group(1).strip()\n",
+    "        action_input = match.group(2)\n",
+    "        # Return the action and action input\n",
+    "        return AgentAction(tool=action, tool_input=action_input.strip(\" \").strip('\"'), log=llm_output)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "d278706a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "output_parser = CustomOutputParser()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "170587b1",
+   "metadata": {},
+   "source": [
+    "## Set up LLM, stop sequence, and the agent\n",
+    "\n",
+    "Also the same as the previous notebook"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "f9d4c374",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "9b1cc2a2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# LLM chain consisting of the LLM and a prompt\n",
+    "llm_chain = LLMChain(llm=llm, prompt=prompt)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "e4f5092f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tool_names = [tool.name for tool in tools]\n",
+    "agent = LLMSingleActionAgent(\n",
+    "    llm_chain=llm_chain, \n",
+    "    output_parser=output_parser,\n",
+    "    stop=[\"\\nObservation:\"], \n",
+    "    allowed_tools=tool_names\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "aa8a5326",
+   "metadata": {},
+   "source": [
+    "## Use the Agent\n",
+    "\n",
+    "Now we can use it!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "490604e9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agent_executor = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "653b1617",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to find a product API\n",
+      "Action: Open_AI_Klarna_product_Api.productsUsingGET\n",
+      "Action Input: shirts\u001b[0m\n",
+      "\n",
+      "Observation:\u001b[36;1m\u001b[1;3mI found 10 shirts from the API response. They range in price from $9.99 to $450.00 and come in a variety of materials, colors, and patterns.\u001b[0m\u001b[32;1m\u001b[1;3m I now know what shirts I can buy\n",
+      "Final Answer: Arg, I found 10 shirts from the API response. They range in price from $9.99 to $450.00 and come in a variety of materials, colors, and patterns.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'Arg, I found 10 shirts from the API response. They range in price from $9.99 to $450.00 and come in a variety of materials, colors, and patterns.'"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent_executor.run(\"what shirts can i buy?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2481ee76",
+   "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": "18784188d7ecd866c0586ac068b02361a6896dc3a29b64f5cc957f09c590acef"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/use_cases/code.md

@@ -23,3 +23,4 @@ Query Understanding: GPT-4 processes user queries, grasping the context and extr
 
 The full tutorial is available below.
 - [Twitter the-algorithm codebase analysis with Deep Lake](code/twitter-the-algorithm-analysis-deeplake.ipynb): A notebook walking through how to parse github source code and run queries conversation.
+- [LangChain codebase analysis with Deep Lake](code/code-analysis-deeplake.ipynb): A notebook walking through how to analyze and do question answering over THIS code base.

docs/use_cases/code/code-analysis-deeplake.ipynb

@@ -0,0 +1,644 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Use LangChain, GPT and Deep Lake to work with code base\n",
+    "In this tutorial, we are going to use Langchain + Deep Lake with GPT to analyze the code base of the LangChain itself. "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Design"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "1. Prepare data:\n",
+    "   1. Upload all python project files using the `langchain.document_loaders.TextLoader`. We will call these files the **documents**.\n",
+    "   2. Split all documents to chunks using the `langchain.text_splitter.CharacterTextSplitter`.\n",
+    "   3. Embed chunks and upload them into the DeepLake using `langchain.embeddings.openai.OpenAIEmbeddings` and `langchain.vectorstores.DeepLake`\n",
+    "2. Question-Answering:\n",
+    "   1. Build a chain from `langchain.chat_models.ChatOpenAI` and `langchain.chains.ConversationalRetrievalChain`\n",
+    "   2. Prepare questions.\n",
+    "   3. Get answers running the chain.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Implementation"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "### Integration preparations"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We need to set up keys for external services and install necessary python libraries."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "#!python3 -m pip install --upgrade langchain deeplake openai"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Set up OpenAI embeddings, Deep Lake multi-modal vector store api and authenticate. \n",
+    "\n",
+    "For full documentation of Deep Lake please follow https://docs.activeloop.ai/ and API reference https://docs.deeplake.ai/en/latest/"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " ········\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "os.environ['OPENAI_API_KEY'] = getpass()\n",
+    "# Please manually enter OpenAI Key"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Authenticate into Deep Lake if you want to create your own dataset and publish it. You can get an API key from the platform at [app.activeloop.ai](https://app.activeloop.ai)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " ········\n"
+     ]
+    }
+   ],
+   "source": [
+    "os.environ['ACTIVELOOP_TOKEN'] = getpass.getpass('Activeloop Token:')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Prepare data "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Load all repository files. Here we assume this notebook is downloaded as the part of the langchain fork and we work with the python files of the `langchain` repo.\n",
+    "\n",
+    "If you want to use files from different repo, change `root_dir` to the root dir of your repo."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1147\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain.document_loaders import TextLoader\n",
+    "\n",
+    "root_dir = '../../../..'\n",
+    "\n",
+    "docs = []\n",
+    "for dirpath, dirnames, filenames in os.walk(root_dir):\n",
+    "    for file in filenames:\n",
+    "        if file.endswith('.py') and '/.venv/' not in dirpath:\n",
+    "            try: \n",
+    "                loader = TextLoader(os.path.join(dirpath, file), encoding='utf-8')\n",
+    "                docs.extend(loader.load_and_split())\n",
+    "            except Exception as e: \n",
+    "                pass\n",
+    "print(f'{len(docs)}')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Then, chunk the files"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Created a chunk of size 1620, which is longer than the specified 1000\n",
+      "Created a chunk of size 1213, which is longer than the specified 1000\n",
+      "Created a chunk of size 1263, which is longer than the specified 1000\n",
+      "Created a chunk of size 1448, which is longer than the specified 1000\n",
+      "Created a chunk of size 1120, which is longer than the specified 1000\n",
+      "Created a chunk of size 1148, which is longer than the specified 1000\n",
+      "Created a chunk of size 1826, which is longer than the specified 1000\n",
+      "Created a chunk of size 1260, which is longer than the specified 1000\n",
+      "Created a chunk of size 1195, which is longer than the specified 1000\n",
+      "Created a chunk of size 2147, which is longer than the specified 1000\n",
+      "Created a chunk of size 1410, which is longer than the specified 1000\n",
+      "Created a chunk of size 1269, which is longer than the specified 1000\n",
+      "Created a chunk of size 1030, which is longer than the specified 1000\n",
+      "Created a chunk of size 1046, which is longer than the specified 1000\n",
+      "Created a chunk of size 1024, which is longer than the specified 1000\n",
+      "Created a chunk of size 1026, which is longer than the specified 1000\n",
+      "Created a chunk of size 1285, which is longer than the specified 1000\n",
+      "Created a chunk of size 1370, which is longer than the specified 1000\n",
+      "Created a chunk of size 1031, which is longer than the specified 1000\n",
+      "Created a chunk of size 1999, which is longer than the specified 1000\n",
+      "Created a chunk of size 1029, which is longer than the specified 1000\n",
+      "Created a chunk of size 1120, which is longer than the specified 1000\n",
+      "Created a chunk of size 1033, which is longer than the specified 1000\n",
+      "Created a chunk of size 1143, which is longer than the specified 1000\n",
+      "Created a chunk of size 1416, which is longer than the specified 1000\n",
+      "Created a chunk of size 2482, which is longer than the specified 1000\n",
+      "Created a chunk of size 1890, which is longer than the specified 1000\n",
+      "Created a chunk of size 1418, which is longer than the specified 1000\n",
+      "Created a chunk of size 1848, which is longer than the specified 1000\n",
+      "Created a chunk of size 1069, which is longer than the specified 1000\n",
+      "Created a chunk of size 2369, which is longer than the specified 1000\n",
+      "Created a chunk of size 1045, which is longer than the specified 1000\n",
+      "Created a chunk of size 1501, which is longer than the specified 1000\n",
+      "Created a chunk of size 1208, which is longer than the specified 1000\n",
+      "Created a chunk of size 1950, which is longer than the specified 1000\n",
+      "Created a chunk of size 1283, which is longer than the specified 1000\n",
+      "Created a chunk of size 1414, which is longer than the specified 1000\n",
+      "Created a chunk of size 1304, which is longer than the specified 1000\n",
+      "Created a chunk of size 1224, which is longer than the specified 1000\n",
+      "Created a chunk of size 1060, which is longer than the specified 1000\n",
+      "Created a chunk of size 2461, which is longer than the specified 1000\n",
+      "Created a chunk of size 1099, which is longer than the specified 1000\n",
+      "Created a chunk of size 1178, which is longer than the specified 1000\n",
+      "Created a chunk of size 1449, which is longer than the specified 1000\n",
+      "Created a chunk of size 1345, which is longer than the specified 1000\n",
+      "Created a chunk of size 3359, which is longer than the specified 1000\n",
+      "Created a chunk of size 2248, which is longer than the specified 1000\n",
+      "Created a chunk of size 1589, which is longer than the specified 1000\n",
+      "Created a chunk of size 2104, which is longer than the specified 1000\n",
+      "Created a chunk of size 1505, which is longer than the specified 1000\n",
+      "Created a chunk of size 1387, which is longer than the specified 1000\n",
+      "Created a chunk of size 1215, which is longer than the specified 1000\n",
+      "Created a chunk of size 1240, which is longer than the specified 1000\n",
+      "Created a chunk of size 1635, which is longer than the specified 1000\n",
+      "Created a chunk of size 1075, which is longer than the specified 1000\n",
+      "Created a chunk of size 2180, which is longer than the specified 1000\n",
+      "Created a chunk of size 1791, which is longer than the specified 1000\n",
+      "Created a chunk of size 1555, which is longer than the specified 1000\n",
+      "Created a chunk of size 1082, which is longer than the specified 1000\n",
+      "Created a chunk of size 1225, which is longer than the specified 1000\n",
+      "Created a chunk of size 1287, which is longer than the specified 1000\n",
+      "Created a chunk of size 1085, which is longer than the specified 1000\n",
+      "Created a chunk of size 1117, which is longer than the specified 1000\n",
+      "Created a chunk of size 1966, which is longer than the specified 1000\n",
+      "Created a chunk of size 1150, which is longer than the specified 1000\n",
+      "Created a chunk of size 1285, which is longer than the specified 1000\n",
+      "Created a chunk of size 1150, which is longer than the specified 1000\n",
+      "Created a chunk of size 1585, which is longer than the specified 1000\n",
+      "Created a chunk of size 1208, which is longer than the specified 1000\n",
+      "Created a chunk of size 1267, which is longer than the specified 1000\n",
+      "Created a chunk of size 1542, which is longer than the specified 1000\n",
+      "Created a chunk of size 1183, which is longer than the specified 1000\n",
+      "Created a chunk of size 2424, which is longer than the specified 1000\n",
+      "Created a chunk of size 1017, which is longer than the specified 1000\n",
+      "Created a chunk of size 1304, which is longer than the specified 1000\n",
+      "Created a chunk of size 1379, which is longer than the specified 1000\n",
+      "Created a chunk of size 1324, which is longer than the specified 1000\n",
+      "Created a chunk of size 1205, which is longer than the specified 1000\n",
+      "Created a chunk of size 1056, which is longer than the specified 1000\n",
+      "Created a chunk of size 1195, which is longer than the specified 1000\n",
+      "Created a chunk of size 3608, which is longer than the specified 1000\n",
+      "Created a chunk of size 1058, which is longer than the specified 1000\n",
+      "Created a chunk of size 1075, which is longer than the specified 1000\n",
+      "Created a chunk of size 1217, which is longer than the specified 1000\n",
+      "Created a chunk of size 1109, which is longer than the specified 1000\n",
+      "Created a chunk of size 1440, which is longer than the specified 1000\n",
+      "Created a chunk of size 1046, which is longer than the specified 1000\n",
+      "Created a chunk of size 1220, which is longer than the specified 1000\n",
+      "Created a chunk of size 1403, which is longer than the specified 1000\n",
+      "Created a chunk of size 1241, which is longer than the specified 1000\n",
+      "Created a chunk of size 1427, which is longer than the specified 1000\n",
+      "Created a chunk of size 1049, which is longer than the specified 1000\n",
+      "Created a chunk of size 1580, which is longer than the specified 1000\n",
+      "Created a chunk of size 1565, which is longer than the specified 1000\n",
+      "Created a chunk of size 1131, which is longer than the specified 1000\n",
+      "Created a chunk of size 1425, which is longer than the specified 1000\n",
+      "Created a chunk of size 1054, which is longer than the specified 1000\n",
+      "Created a chunk of size 1027, which is longer than the specified 1000\n",
+      "Created a chunk of size 2559, which is longer than the specified 1000\n",
+      "Created a chunk of size 1028, which is longer than the specified 1000\n",
+      "Created a chunk of size 1382, which is longer than the specified 1000\n",
+      "Created a chunk of size 1888, which is longer than the specified 1000\n",
+      "Created a chunk of size 1475, which is longer than the specified 1000\n",
+      "Created a chunk of size 1652, which is longer than the specified 1000\n",
+      "Created a chunk of size 1891, which is longer than the specified 1000\n",
+      "Created a chunk of size 1899, which is longer than the specified 1000\n",
+      "Created a chunk of size 1021, which is longer than the specified 1000\n",
+      "Created a chunk of size 1085, which is longer than the specified 1000\n",
+      "Created a chunk of size 1854, which is longer than the specified 1000\n",
+      "Created a chunk of size 1672, which is longer than the specified 1000\n",
+      "Created a chunk of size 2537, which is longer than the specified 1000\n",
+      "Created a chunk of size 1251, which is longer than the specified 1000\n",
+      "Created a chunk of size 1734, which is longer than the specified 1000\n",
+      "Created a chunk of size 1642, which is longer than the specified 1000\n",
+      "Created a chunk of size 1376, which is longer than the specified 1000\n",
+      "Created a chunk of size 1253, which is longer than the specified 1000\n",
+      "Created a chunk of size 1642, which is longer than the specified 1000\n",
+      "Created a chunk of size 1419, which is longer than the specified 1000\n",
+      "Created a chunk of size 1438, which is longer than the specified 1000\n",
+      "Created a chunk of size 1427, which is longer than the specified 1000\n",
+      "Created a chunk of size 1684, which is longer than the specified 1000\n",
+      "Created a chunk of size 1760, which is longer than the specified 1000\n",
+      "Created a chunk of size 1157, which is longer than the specified 1000\n",
+      "Created a chunk of size 2504, which is longer than the specified 1000\n",
+      "Created a chunk of size 1082, which is longer than the specified 1000\n",
+      "Created a chunk of size 2268, which is longer than the specified 1000\n",
+      "Created a chunk of size 1784, which is longer than the specified 1000\n",
+      "Created a chunk of size 1311, which is longer than the specified 1000\n",
+      "Created a chunk of size 2972, which is longer than the specified 1000\n",
+      "Created a chunk of size 1144, which is longer than the specified 1000\n",
+      "Created a chunk of size 1825, which is longer than the specified 1000\n",
+      "Created a chunk of size 1508, which is longer than the specified 1000\n",
+      "Created a chunk of size 2901, which is longer than the specified 1000\n",
+      "Created a chunk of size 1715, which is longer than the specified 1000\n",
+      "Created a chunk of size 1062, which is longer than the specified 1000\n",
+      "Created a chunk of size 1206, which is longer than the specified 1000\n",
+      "Created a chunk of size 1102, which is longer than the specified 1000\n",
+      "Created a chunk of size 1184, which is longer than the specified 1000\n",
+      "Created a chunk of size 1002, which is longer than the specified 1000\n",
+      "Created a chunk of size 1065, which is longer than the specified 1000\n",
+      "Created a chunk of size 1871, which is longer than the specified 1000\n",
+      "Created a chunk of size 1754, which is longer than the specified 1000\n",
+      "Created a chunk of size 2413, which is longer than the specified 1000\n",
+      "Created a chunk of size 1771, which is longer than the specified 1000\n",
+      "Created a chunk of size 2054, which is longer than the specified 1000\n",
+      "Created a chunk of size 2000, which is longer than the specified 1000\n",
+      "Created a chunk of size 2061, which is longer than the specified 1000\n",
+      "Created a chunk of size 1066, which is longer than the specified 1000\n",
+      "Created a chunk of size 1419, which is longer than the specified 1000\n",
+      "Created a chunk of size 1368, which is longer than the specified 1000\n",
+      "Created a chunk of size 1008, which is longer than the specified 1000\n",
+      "Created a chunk of size 1227, which is longer than the specified 1000\n",
+      "Created a chunk of size 1745, which is longer than the specified 1000\n",
+      "Created a chunk of size 2296, which is longer than the specified 1000\n",
+      "Created a chunk of size 1083, which is longer than the specified 1000\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "3477\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "\n",
+    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
+    "texts = text_splitter.split_documents(docs)\n",
+    "print(f\"{len(texts)}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Then embed chunks and upload them to the DeepLake.\n",
+    "\n",
+    "This can take several minutes. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "OpenAIEmbeddings(client=<class 'openai.api_resources.embedding.Embedding'>, model='text-embedding-ada-002', document_model_name='text-embedding-ada-002', query_model_name='text-embedding-ada-002', embedding_ctx_length=8191, openai_api_key=None, openai_organization=None, allowed_special=set(), disallowed_special='all', chunk_size=1000, max_retries=6)"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "\n",
+    "embeddings = OpenAIEmbeddings()\n",
+    "embeddings"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.vectorstores import DeepLake\n",
+    "\n",
+    "db = DeepLake.from_documents(texts, embeddings, dataset_path=f\"hub://{DEEPLAKE_ACCOUNT_NAME}/langchain-code\")\n",
+    "db"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Question Answering\n",
+    "First load the dataset, construct the retriever, then construct the Conversational Chain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "-"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "This dataset can be visualized in Jupyter Notebook by ds.visualize() or at https://app.activeloop.ai/user_name/langchain-code\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "hub://user_name/langchain-code loaded successfully.\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Deep Lake Dataset in hub://user_name/langchain-code already exists, loading from the storage\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dataset(path='hub://user_name/langchain-code', read_only=True, tensors=['embedding', 'ids', 'metadata', 'text'])\n",
+      "\n",
+      "  tensor     htype      shape       dtype  compression\n",
+      "  -------   -------    -------     -------  ------- \n",
+      " embedding  generic  (3477, 1536)  float32   None   \n",
+      "    ids      text     (3477, 1)      str     None   \n",
+      " metadata    json     (3477, 1)      str     None   \n",
+      "   text      text     (3477, 1)      str     None   \n"
+     ]
+    }
+   ],
+   "source": [
+    "db = DeepLake(dataset_path=f\"hub://{DEEPLAKE_ACCOUNT_NAME}/langchain-code\", read_only=True, embedding_function=embeddings)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "retriever = db.as_retriever()\n",
+    "retriever.search_kwargs['distance_metric'] = 'cos'\n",
+    "retriever.search_kwargs['fetch_k'] = 20\n",
+    "retriever.search_kwargs['maximal_marginal_relevance'] = True\n",
+    "retriever.search_kwargs['k'] = 20"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You can also specify user defined functions using [Deep Lake filters](https://docs.deeplake.ai/en/latest/deeplake.core.dataset.html#deeplake.core.dataset.Dataset.filter)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "def filter(x):\n",
+    "    # filter based on source code\n",
+    "    if 'something' in x['text'].data()['value']:\n",
+    "        return False\n",
+    "    \n",
+    "    # filter based on path e.g. extension\n",
+    "    metadata =  x['metadata'].data()['value']\n",
+    "    return 'only_this' in metadata['source'] or 'also_that' in metadata['source']\n",
+    "\n",
+    "### turn on below for custom filtering\n",
+    "# retriever.search_kwargs['filter'] = filter"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.chains import ConversationalRetrievalChain\n",
+    "\n",
+    "model = ChatOpenAI(model='gpt-3.5-turbo') # 'ada' 'gpt-3.5-turbo' 'gpt-4',\n",
+    "qa = ConversationalRetrievalChain.from_llm(model,retriever=retriever)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "questions = [\n",
+    "    \"What is the class hierarchy?\",\n",
+    "    # \"What classes are derived from the Chain class?\",\n",
+    "    # \"What classes and functions in the ./langchain/utilities/ forlder are not covered by unit tests?\",\n",
+    "    # \"What one improvement do you propose in code in relation to the class herarchy for the Chain class?\",\n",
+    "] \n",
+    "chat_history = []\n",
+    "\n",
+    "for question in questions:  \n",
+    "    result = qa({\"question\": question, \"chat_history\": chat_history})\n",
+    "    chat_history.append((question, result['answer']))\n",
+    "    print(f\"-> **Question**: {question} \\n\")\n",
+    "    print(f\"**Answer**: {result['answer']} \\n\")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "-> **Question**: What is the class hierarchy? \n",
+    "\n",
+    "**Answer**: There are several class hierarchies in the provided code, so I'll list a few:\n",
+    "\n",
+    "1. `BaseModel` -> `ConstitutionalPrinciple`: `ConstitutionalPrinciple` is a subclass of `BaseModel`.\n",
+    "2. `BasePromptTemplate` -> `StringPromptTemplate`, `AIMessagePromptTemplate`, `BaseChatPromptTemplate`, `ChatMessagePromptTemplate`, `ChatPromptTemplate`, `HumanMessagePromptTemplate`, `MessagesPlaceholder`, `SystemMessagePromptTemplate`, `FewShotPromptTemplate`, `FewShotPromptWithTemplates`, `Prompt`, `PromptTemplate`: All of these classes are subclasses of `BasePromptTemplate`.\n",
+    "3. `APIChain`, `Chain`, `MapReduceDocumentsChain`, `MapRerankDocumentsChain`, `RefineDocumentsChain`, `StuffDocumentsChain`, `HypotheticalDocumentEmbedder`, `LLMChain`, `LLMBashChain`, `LLMCheckerChain`, `LLMMathChain`, `LLMRequestsChain`, `PALChain`, `QAWithSourcesChain`, `VectorDBQAWithSourcesChain`, `VectorDBQA`, `SQLDatabaseChain`: All of these classes are subclasses of `Chain`.\n",
+    "4. `BaseLoader`: `BaseLoader` is a subclass of `ABC`.\n",
+    "5. `BaseTracer` -> `ChainRun`, `LLMRun`, `SharedTracer`, `ToolRun`, `Tracer`, `TracerException`, `TracerSession`: All of these classes are subclasses of `BaseTracer`.\n",
+    "6. `OpenAIEmbeddings`, `HuggingFaceEmbeddings`, `CohereEmbeddings`, `JinaEmbeddings`, `LlamaCppEmbeddings`, `HuggingFaceHubEmbeddings`, `TensorflowHubEmbeddings`, `SagemakerEndpointEmbeddings`, `HuggingFaceInstructEmbeddings`, `SelfHostedEmbeddings`, `SelfHostedHuggingFaceEmbeddings`, `SelfHostedHuggingFaceInstructEmbeddings`, `FakeEmbeddings`, `AlephAlphaAsymmetricSemanticEmbedding`, `AlephAlphaSymmetricSemanticEmbedding`: All of these classes are subclasses of `BaseLLM`. \n",
+    "\n",
+    "\n",
+    "-> **Question**: What classes are derived from the Chain class? \n",
+    "\n",
+    "**Answer**: There are multiple classes that are derived from the Chain class. Some of them are:\n",
+    "- APIChain\n",
+    "- AnalyzeDocumentChain\n",
+    "- ChatVectorDBChain\n",
+    "- CombineDocumentsChain\n",
+    "- ConstitutionalChain\n",
+    "- ConversationChain\n",
+    "- GraphQAChain\n",
+    "- HypotheticalDocumentEmbedder\n",
+    "- LLMChain\n",
+    "- LLMCheckerChain\n",
+    "- LLMRequestsChain\n",
+    "- LLMSummarizationCheckerChain\n",
+    "- MapReduceChain\n",
+    "- OpenAPIEndpointChain\n",
+    "- PALChain\n",
+    "- QAWithSourcesChain\n",
+    "- RetrievalQA\n",
+    "- RetrievalQAWithSourcesChain\n",
+    "- SequentialChain\n",
+    "- SQLDatabaseChain\n",
+    "- TransformChain\n",
+    "- VectorDBQA\n",
+    "- VectorDBQAWithSourcesChain\n",
+    "\n",
+    "There might be more classes that are derived from the Chain class as it is possible to create custom classes that extend the Chain class.\n",
+    "\n",
+    "\n",
+    "-> **Question**: What classes and functions in the ./langchain/utilities/ forlder are not covered by unit tests? \n",
+    "\n",
+    "**Answer**: All classes and functions in the `./langchain/utilities/` folder seem to have unit tests written for them. \n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "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": "3.10.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

docs/use_cases/code/twitter-the-algorithm-analysis-deeplake.ipynb

@@ -18,31 +18,13 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Define OpenAI embeddings, Deep Lake multi-modal vector store api and authenticate. For full documentation of Deep Lake please follow https://docs.activeloop.ai/ and API reference https://docs.deeplake.ai/en/latest/"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
-    "from langchain.vectorstores import DeepLake\n",
+    "Define OpenAI embeddings, Deep Lake multi-modal vector store api and authenticate. For full documentation of Deep Lake please follow [docs](https://docs.activeloop.ai/) and [API reference](https://docs.deeplake.ai/en/latest/).\n",
     "\n",
-    "os.environ['OPENAI_API_KEY']='sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx'\n",
-    "embeddings = OpenAIEmbeddings()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Authenticate into Deep Lake if you want to create your own dataset and publish it. You can get an API key from the platform at https://app.activeloop.ai"
+    "Authenticate into Deep Lake if you want to create your own dataset and publish it. You can get an API key from the [platform](https://app.activeloop.ai)"
    ]
   },
   {
@@ -51,7 +33,15 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!activeloop login -t <TOKEN>"
+    "import os\n",
+    "import getpass\n",
+    "\n",
+    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "from langchain.vectorstores import DeepLake\n",
+    "\n",
+    "os.environ['OPENAI_API_KEY'] = getpass.getpass('OpenAI API Key:')\n",
+    "os.environ['ACTIVELOOP_TOKEN'] = getpass.getpass('Activeloop Token:')\n",
+    "embeddings = OpenAIEmbeddings()"
    ]
   },
   {
@@ -143,15 +133,35 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "-"
+     ]
+    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
       "This dataset can be visualized in Jupyter Notebook by ds.visualize() or at https://app.activeloop.ai/davitbun/twitter-algorithm\n",
-      "\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "-"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
       "hub://davitbun/twitter-algorithm loaded successfully.\n",
       "\n"
      ]
@@ -184,7 +194,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -205,7 +215,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -224,7 +234,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -267,9 +277,14 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "-> **Question**: What does favCountParams do? \n",
+    "\n",
+    "**Answer**: `favCountParams` is an optional ThriftLinearFeatureRankingParams instance that represents the parameters related to the \"favorite count\" feature in the ranking process. It is used to control the weight of the favorite count feature while ranking tweets. The favorite count is the number of times a tweet has been marked as a favorite by users, and it is considered an important signal in the ranking of tweets. By using `favCountParams`, the system can adjust the importance of the favorite count while calculating the final ranking score of a tweet. \n",
+    "\n",
     "-> **Question**: is it Likes + Bookmarks, or not clear from the code?\n",
     "\n",
     "**Answer**: From the provided code, it is not clear if the favorite count metric is determined by the sum of likes and bookmarks. The favorite count is mentioned in the code, but there is no explicit reference to how it is calculated in terms of likes and bookmarks. \n",
@@ -423,7 +438,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.0"
   }
  },
  "nbformat": 4,

docs/use_cases/evaluation.rst

@@ -1,5 +1,5 @@
 Evaluation
-==============
+==========
 
 .. note::
    `Conceptual Guide <https://docs.langchain.com/docs/use-cases/evaluation>`_
@@ -83,7 +83,7 @@ The existing examples we have are:
 
 
 Other Examples
-------------
+--------------
 
 In addition, we also have some more generic resources for evaluation.
 

docs/use_cases/personal_assistants.md

@@ -1,4 +1,4 @@
-# Personal Assistants
+# Personal Assistants (Agents)
 
 > [Conceptual Guide](https://docs.langchain.com/docs/use-cases/personal-assistants)
 
@@ -16,3 +16,10 @@ Highlighting specific parts:
 - [Agent Documentation](../modules/agents.rst) (for interacting with the outside world)
 - [Index Documentation](../modules/indexes.rst) (for giving them knowledge of your data)
 - [Memory](../modules/memory.rst) (for helping them remember interactions)
+
+Specific examples of this include:
+
+- [Baby AGI](agents/baby_agi.ipynb): a notebook implementing [BabyAGI](https://github.com/yoheinakajima/babyagi) by Yohei Nakajima as LLM Chains
+- [Baby AGI with Tools](agents/baby_agi_with_agent.ipynb): building off the above notebook, this example substitutes in an agent with tools as the execution tools, allowing it to actually take actions.
+- [CAMEL](agents/camel_role_playing.ipynb): an implementation of the CAMEL (Communicative Agents for “Mind” Exploration of Large Scale Language Model Society) paper, where two agents communicate with eachother.
+- [AI Plugins](agents/custom_agent_with_plugin_retrieval.ipynb): an implementation of an agent that is designed to be able to use all AI Plugins.

langchain/agents/agent.py

@@ -99,6 +99,16 @@ class BaseSingleActionAgent(BaseModel):
                 f"Got unsupported early_stopping_method `{early_stopping_method}`"
             )
 
+    @classmethod
+    def from_llm_and_tools(
+        cls,
+        llm: BaseLanguageModel,
+        tools: Sequence[BaseTool],
+        callback_manager: Optional[BaseCallbackManager] = None,
+        **kwargs: Any,
+    ) -> BaseSingleActionAgent:
+        raise NotImplementedError
+
     @property
     def _agent_type(self) -> str:
         """Return Identifier of agent type."""

langchain/agents/agent_toolkits/nla/toolkit.py

@@ -1,5 +1,5 @@
 """Toolkit for interacting with API's using natural language."""
-
+from __future__ import annotations
 
 from typing import Any, List, Optional, Sequence
 
@@ -11,6 +11,7 @@ from langchain.llms.base import BaseLLM
 from langchain.requests import Requests
 from langchain.tools.base import BaseTool
 from langchain.tools.openapi.utils.openapi_utils import OpenAPISpec
+from langchain.tools.plugin import AIPlugin
 
 
 class NLAToolkit(BaseToolkit):
@@ -23,19 +24,18 @@ class NLAToolkit(BaseToolkit):
         """Get the tools for all the API operations."""
         return list(self.nla_tools)
 
-    @classmethod
-    def from_llm_and_spec(
-        cls,
+    @staticmethod
+    def _get_http_operation_tools(
         llm: BaseLLM,
         spec: OpenAPISpec,
         requests: Optional[Requests] = None,
         verbose: bool = False,
-        **kwargs: Any
-    ) -> "NLAToolkit":
-        """Instantiate the toolkit by creating tools for each operation."""
-        http_operation_tools: List[NLATool] = []
+        **kwargs: Any,
+    ) -> List[NLATool]:
+        """Get the tools for all the API operations."""
         if not spec.paths:
-            return cls(nla_tools=http_operation_tools)
+            return []
+        http_operation_tools = []
         for path in spec.paths:
             for method in spec.get_methods_for_path(path):
                 endpoint_tool = NLATool.from_llm_and_method(
@@ -45,9 +45,24 @@ class NLAToolkit(BaseToolkit):
                     spec=spec,
                     requests=requests,
                     verbose=verbose,
-                    **kwargs
+                    **kwargs,
                 )
                 http_operation_tools.append(endpoint_tool)
+        return http_operation_tools
+
+    @classmethod
+    def from_llm_and_spec(
+        cls,
+        llm: BaseLLM,
+        spec: OpenAPISpec,
+        requests: Optional[Requests] = None,
+        verbose: bool = False,
+        **kwargs: Any,
+    ) -> NLAToolkit:
+        """Instantiate the toolkit by creating tools for each operation."""
+        http_operation_tools = cls._get_http_operation_tools(
+            llm=llm, spec=spec, requests=requests, verbose=verbose, **kwargs
+        )
         return cls(nla_tools=http_operation_tools)
 
     @classmethod
@@ -57,10 +72,45 @@ class NLAToolkit(BaseToolkit):
         open_api_url: str,
         requests: Optional[Requests] = None,
         verbose: bool = False,
-        **kwargs: Any
-    ) -> "NLAToolkit":
+        **kwargs: Any,
+    ) -> NLAToolkit:
         """Instantiate the toolkit from an OpenAPI Spec URL"""
         spec = OpenAPISpec.from_url(open_api_url)
         return cls.from_llm_and_spec(
             llm=llm, spec=spec, requests=requests, verbose=verbose, **kwargs
         )
+
+    @classmethod
+    def from_llm_and_ai_plugin(
+        cls,
+        llm: BaseLLM,
+        ai_plugin: AIPlugin,
+        requests: Optional[Requests] = None,
+        verbose: bool = False,
+        **kwargs: Any,
+    ) -> NLAToolkit:
+        """Instantiate the toolkit from an OpenAPI Spec URL"""
+        spec = OpenAPISpec.from_url(ai_plugin.api.url)
+        # TODO: Merge optional Auth information with the `requests` argument
+        return cls.from_llm_and_spec(
+            llm=llm,
+            spec=spec,
+            requests=requests,
+            verbose=verbose,
+            **kwargs,
+        )
+
+    @classmethod
+    def from_llm_and_ai_plugin_url(
+        cls,
+        llm: BaseLLM,
+        ai_plugin_url: str,
+        requests: Optional[Requests] = None,
+        verbose: bool = False,
+        **kwargs: Any,
+    ) -> NLAToolkit:
+        """Instantiate the toolkit from an OpenAPI Spec URL"""
+        plugin = AIPlugin.from_url(ai_plugin_url)
+        return cls.from_llm_and_ai_plugin(
+            llm=llm, ai_plugin=plugin, requests=requests, verbose=verbose, **kwargs
+        )

langchain/agents/agent_toolkits/openapi/base.py

@@ -22,6 +22,9 @@ def create_openapi_agent(
     suffix: str = OPENAPI_SUFFIX,
     format_instructions: str = FORMAT_INSTRUCTIONS,
     input_variables: Optional[List[str]] = None,
+    max_iterations: Optional[int] = 15,
+    max_execution_time: Optional[float] = None,
+    early_stopping_method: str = "force",
     verbose: bool = False,
     return_intermediate_steps: bool = False,
     **kwargs: Any,
@@ -47,4 +50,7 @@ def create_openapi_agent(
         tools=toolkit.get_tools(),
         verbose=verbose,
         return_intermediate_steps=return_intermediate_steps,
+        max_iterations=max_iterations,
+        max_execution_time=max_execution_time,
+        early_stopping_method=early_stopping_method,
     )

langchain/agents/agent_toolkits/openapi/planner.py

@@ -14,9 +14,13 @@ from langchain.agents.agent_toolkits.openapi.planner_prompt import (
     API_PLANNER_PROMPT,
     API_PLANNER_TOOL_DESCRIPTION,
     API_PLANNER_TOOL_NAME,
+    PARSING_DELETE_PROMPT,
     PARSING_GET_PROMPT,
+    PARSING_PATCH_PROMPT,
     PARSING_POST_PROMPT,
+    REQUESTS_DELETE_TOOL_DESCRIPTION,
     REQUESTS_GET_TOOL_DESCRIPTION,
+    REQUESTS_PATCH_TOOL_DESCRIPTION,
     REQUESTS_POST_TOOL_DESCRIPTION,
 )
 from langchain.agents.agent_toolkits.openapi.spec import ReducedOpenAPISpec
@@ -24,6 +28,7 @@ from langchain.agents.mrkl.base import ZeroShotAgent
 from langchain.agents.tools import Tool
 from langchain.chains.llm import LLMChain
 from langchain.llms.openai import OpenAI
+from langchain.memory import ReadOnlySharedMemory
 from langchain.prompts import PromptTemplate
 from langchain.requests import RequestsWrapper
 from langchain.schema import BaseLanguageModel
@@ -53,7 +58,8 @@ class RequestsGetToolWithParsing(BaseRequestsTool, BaseTool):
             data = json.loads(text)
         except json.JSONDecodeError as e:
             raise e
-        response = self.requests_wrapper.get(data["url"])
+        data_params = data.get("params")
+        response = self.requests_wrapper.get(data["url"], params=data_params)
         response = response[: self.response_length]
         return self.llm_chain.predict(
             response=response, instructions=data["output_instructions"]
@@ -88,6 +94,56 @@ class RequestsPostToolWithParsing(BaseRequestsTool, BaseTool):
         raise NotImplementedError()
 
 
+class RequestsPatchToolWithParsing(BaseRequestsTool, BaseTool):
+    name = "requests_patch"
+    description = REQUESTS_PATCH_TOOL_DESCRIPTION
+
+    response_length: Optional[int] = MAX_RESPONSE_LENGTH
+    llm_chain = LLMChain(
+        llm=OpenAI(),
+        prompt=PARSING_PATCH_PROMPT,
+    )
+
+    def _run(self, text: str) -> str:
+        try:
+            data = json.loads(text)
+        except json.JSONDecodeError as e:
+            raise e
+        response = self.requests_wrapper.patch(data["url"], data["data"])
+        response = response[: self.response_length]
+        return self.llm_chain.predict(
+            response=response, instructions=data["output_instructions"]
+        ).strip()
+
+    async def _arun(self, text: str) -> str:
+        raise NotImplementedError()
+
+
+class RequestsDeleteToolWithParsing(BaseRequestsTool, BaseTool):
+    name = "requests_delete"
+    description = REQUESTS_DELETE_TOOL_DESCRIPTION
+
+    response_length: Optional[int] = MAX_RESPONSE_LENGTH
+    llm_chain = LLMChain(
+        llm=OpenAI(),
+        prompt=PARSING_DELETE_PROMPT,
+    )
+
+    def _run(self, text: str) -> str:
+        try:
+            data = json.loads(text)
+        except json.JSONDecodeError as e:
+            raise e
+        response = self.requests_wrapper.delete(data["url"])
+        response = response[: self.response_length]
+        return self.llm_chain.predict(
+            response=response, instructions=data["output_instructions"]
+        ).strip()
+
+    async def _arun(self, text: str) -> str:
+        raise NotImplementedError()
+
+
 #
 # Orchestrator, planner, controller.
 #
@@ -155,7 +211,7 @@ def _create_api_controller_tool(
     base_url = api_spec.servers[0]["url"]  # TODO: do better.
 
     def _create_and_run_api_controller_agent(plan_str: str) -> str:
-        pattern = r"\b(GET|POST)\s+(/\S+)*"
+        pattern = r"\b(GET|POST|PATCH|DELETE)\s+(/\S+)*"
         matches = re.findall(pattern, plan_str)
         endpoint_names = [
             "{method} {route}".format(method=method, route=route.split("?")[0])
@@ -183,6 +239,8 @@ def create_openapi_agent(
     api_spec: ReducedOpenAPISpec,
     requests_wrapper: RequestsWrapper,
     llm: BaseLanguageModel,
+    shared_memory: Optional[ReadOnlySharedMemory] = None,
+    verbose: bool = True,
 ) -> AgentExecutor:
     """Instantiate API planner and controller for a given spec.
 
@@ -207,7 +265,7 @@ def create_openapi_agent(
         },
     )
     agent = ZeroShotAgent(
-        llm_chain=LLMChain(llm=llm, prompt=prompt),
+        llm_chain=LLMChain(llm=llm, prompt=prompt, memory=shared_memory),
         allowed_tools=[tool.name for tool in tools],
     )
-    return AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True)
+    return AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=verbose)

langchain/agents/agent_toolkits/openapi/planner_prompt.py

@@ -2,13 +2,16 @@
 
 from langchain.prompts.prompt import PromptTemplate
 
+
 API_PLANNER_PROMPT = """You are a planner that plans a sequence of API calls to assist with user queries against an API.
 
 You should:
 1) evaluate whether the user query can be solved by the API documentated below. If no, say why.
 2) if yes, generate a plan of API calls and say what they are doing step by step.
+3) If the plan includes a DELETE call, you should always return an ask from the User for authorization first unless the User has specifically asked to delete something.
 
 You should only use API endpoints documented below ("Endpoints you can use:").
+You can only use the DELETE tool if the User has specifically asked to delete something. Otherwise, you should return a request authorization from the User first.
 Some user queries can be resolved in a single API call, but some will require several API calls.
 The plan will be passed to an API controller that can format it into web requests and return the responses.
 
@@ -20,15 +23,31 @@ Fake endpoints for examples:
 GET /user to get information about the current user
 GET /products/search search across products
 POST /users/{{id}}/cart to add products to a user's cart
+PATCH /users/{{id}}/cart to update a user's cart
+DELETE /users/{{id}}/cart to delete a user's cart
 
 User query: tell me a joke
 Plan: Sorry, this API's domain is shopping, not comedy.
 
 Usery query: I want to buy a couch
-Plan: 1. GET /products/search to search for couches
+Plan: 1. GET /products with a query param to search for couches
 2. GET /user to find the user's id
 3. POST /users/{{id}}/cart to add a couch to the user's cart
 
+User query: I want to add a lamp to my cart
+Plan: 1. GET /products with a query param to search for lamps
+2. GET /user to find the user's id
+3. PATCH /users/{{id}}/cart to add a lamp to the user's cart
+
+User query: I want to delete my cart
+Plan: 1. GET /user to find the user's id
+2. DELETE required. Did user specify DELETE or previously authorize? Yes, proceed.
+3. DELETE /users/{{id}}/cart to delete the user's cart
+
+User query: I want to start a new cart
+Plan: 1. GET /user to find the user's id
+2. DELETE required. Did user specify DELETE or previously authorize? No, ask for authorization.
+3. Are you sure you want to delete your cart? 
 ----
 
 Here are endpoints you can use. Do not reference any of the endpoints above.
@@ -40,7 +59,7 @@ Here are endpoints you can use. Do not reference any of the endpoints above.
 User query: {query}
 Plan:"""
 API_PLANNER_TOOL_NAME = "api_planner"
-API_PLANNER_TOOL_DESCRIPTION = f"Can be used to generate the right API calls to assist with a user query, like {API_PLANNER_TOOL_NAME}(query). Should always be called before trying to calling the API controller."
+API_PLANNER_TOOL_DESCRIPTION = f"Can be used to generate the right API calls to assist with a user query, like {API_PLANNER_TOOL_NAME}(query). Should always be called before trying to call the API controller."
 
 # Execution.
 API_CONTROLLER_PROMPT = """You are an agent that gets a sequence of API calls and given their documentation, should execute them and return the final response.
@@ -81,8 +100,9 @@ API_CONTROLLER_TOOL_DESCRIPTION = f"Can be used to execute a plan of API calls,
 # The goal is to have an agent at the top-level (e.g. so it can recover from errors and re-plan) while
 # keeping planning (and specifically the planning prompt) simple.
 API_ORCHESTRATOR_PROMPT = """You are an agent that assists with user queries against API, things like querying information or creating resources.
-Some user queries can be resolved in a single API call though some require several API call.
+Some user queries can be resolved in a single API call, particularly if you can find appropriate params from the OpenAPI spec; though some require several API call.
 You should always plan your API calls first, and then execute the plan second.
+If the plan includes a DELETE call, be sure to ask the User for authorization first unless the User has specifically asked to delete something.
 You should never return information without executing the api_controller tool.
 
 
@@ -106,12 +126,12 @@ User query: can you add some trendy stuff to my shopping cart.
 Thought: I should plan API calls first.
 Action: api_planner
 Action Input: I need to find the right API calls to add trendy items to the users shopping cart
-Observation: 1) GET /items/trending to get trending item ids
+Observation: 1) GET /items with params 'trending' is 'True' to get trending item ids
 2) GET /user to get user
 3) POST /cart to post the trending items to the user's cart
 Thought: I'm ready to execute the API calls.
 Action: api_controller
-Action Input: 1) GET /items/trending to get trending item ids
+Action Input: 1) GET /items params 'trending' is 'True' to get trending item ids
 2) GET /user to get user
 3) POST /cart to post the trending items to the user's cart
 ...
@@ -123,8 +143,12 @@ Thought: I should generate a plan to help with this query and then copy that pla
 {agent_scratchpad}"""
 
 REQUESTS_GET_TOOL_DESCRIPTION = """Use this to GET content from a website.
-Input to the tool should be a json string with 2 keys: "url" and "output_instructions".
-The value of "url" should be a string. The value of "output_instructions" should be instructions on what information to extract from the response, for example the id(s) for a resource(s) that the GET request fetches.
+Input to the tool should be a json string with 3 keys: "url", "params" and "output_instructions".
+The value of "url" should be a string. 
+The value of "params" should be a dict of the needed and available parameters from the OpenAPI spec related to the endpoint. 
+If parameters are not needed, or not available, leave it empty.
+The value of "output_instructions" should be instructions on what information to extract from the response, 
+for example the id(s) for a resource(s) that the GET request fetches.
 """
 
 PARSING_GET_PROMPT = PromptTemplate(
@@ -141,7 +165,7 @@ REQUESTS_POST_TOOL_DESCRIPTION = """Use this when you want to POST to a website.
 Input to the tool should be a json string with 3 keys: "url", "data", and "output_instructions".
 The value of "url" should be a string.
 The value of "data" should be a dictionary of key-value pairs you want to POST to the url.
-The value of "summary_instructions" should be instructions on what information to extract from the response, for example the id(s) for a resource(s) that the POST request creates.
+The value of "output_instructions" should be instructions on what information to extract from the response, for example the id(s) for a resource(s) that the POST request creates.
 Always use double quotes for strings in the json string."""
 
 PARSING_POST_PROMPT = PromptTemplate(
@@ -153,3 +177,37 @@ If the response indicates an error, you should instead output a summary of the e
 Output:""",
     input_variables=["response", "instructions"],
 )
+
+REQUESTS_PATCH_TOOL_DESCRIPTION = """Use this when you want to PATCH content on a website.
+Input to the tool should be a json string with 3 keys: "url", "data", and "output_instructions".
+The value of "url" should be a string.
+The value of "data" should be a dictionary of key-value pairs of the body params available in the OpenAPI spec you want to PATCH the content with at the url.
+The value of "output_instructions" should be instructions on what information to extract from the response, for example the id(s) for a resource(s) that the PATCH request creates.
+Always use double quotes for strings in the json string."""
+
+PARSING_PATCH_PROMPT = PromptTemplate(
+    template="""Here is an API response:\n\n{response}\n\n====
+Your task is to extract some information according to these instructions: {instructions}
+When working with API objects, you should usually use ids over names. Do not return any ids or names that are not in the response.
+If the response indicates an error, you should instead output a summary of the error.
+
+Output:""",
+    input_variables=["response", "instructions"],
+)
+
+REQUESTS_DELETE_TOOL_DESCRIPTION = """ONLY USE THIS TOOL WHEN THE USER HAS SPECIFICALLY REQUESTED TO DELETE CONTENT FROM A WEBSITE.
+Input to the tool should be a json string with 2 keys: "url", and "output_instructions".
+The value of "url" should be a string.
+The value of "output_instructions" should be instructions on what information to extract from the response, for example the id(s) for a resource(s) that the DELETE request creates.
+Always use double quotes for strings in the json string.
+ONLY USE THIS TOOL IF THE USER HAS SPECIFICALLY REQUESTED TO DELETE SOMETHING."""
+
+PARSING_DELETE_PROMPT = PromptTemplate(
+    template="""Here is an API response:\n\n{response}\n\n====
+Your task is to extract some information according to these instructions: {instructions}
+When working with API objects, you should usually use ids over names. Do not return any ids or names that are not in the response.
+If the response indicates an error, you should instead output a summary of the error.
+
+Output:""",
+    input_variables=["response", "instructions"],
+)

langchain/agents/agent_toolkits/openapi/spec.py

@@ -68,12 +68,12 @@ def reduce_openapi_spec(spec: dict, dereference: bool = True) -> ReducedOpenAPIS
     I was hoping https://openapi.tools/ would have some useful bits
     to this end, but doesn't seem so.
     """
-    # 1. Consider only get, post endpoints.
+    # 1. Consider only get, post, patch, delete endpoints.
     endpoints = [
         (f"{operation_name.upper()} {route}", docs.get("description"), docs)
         for route, operation in spec["paths"].items()
         for operation_name, docs in operation.items()
-        if operation_name in ["get", "post"]
+        if operation_name in ["get", "post", "patch", "delete"]
     ]
 
     # 2. Replace any refs so that complete docs are retrieved.

langchain/agents/agent_toolkits/pandas/base.py

@@ -20,6 +20,7 @@ def create_pandas_dataframe_agent(
     verbose: bool = False,
     return_intermediate_steps: bool = False,
     max_iterations: Optional[int] = 15,
+    max_execution_time: Optional[float] = None,
     early_stopping_method: str = "force",
     **kwargs: Any,
 ) -> AgentExecutor:
@@ -48,5 +49,6 @@ def create_pandas_dataframe_agent(
         verbose=verbose,
         return_intermediate_steps=return_intermediate_steps,
         max_iterations=max_iterations,
+        max_execution_time=max_execution_time,
         early_stopping_method=early_stopping_method,
     )

langchain/agents/agent_toolkits/sql/base.py

@@ -21,6 +21,7 @@ def create_sql_agent(
     input_variables: Optional[List[str]] = None,
     top_k: int = 10,
     max_iterations: Optional[int] = 15,
+    max_execution_time: Optional[float] = None,
     early_stopping_method: str = "force",
     verbose: bool = False,
     **kwargs: Any,
@@ -44,8 +45,9 @@ def create_sql_agent(
     agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names, **kwargs)
     return AgentExecutor.from_agent_and_tools(
         agent=agent,
-        tools=toolkit.get_tools(),
+        tools=tools,
         verbose=verbose,
         max_iterations=max_iterations,
+        max_execution_time=max_execution_time,
         early_stopping_method=early_stopping_method,
     )

langchain/agents/agent_toolkits/sql/toolkit.py

@@ -4,6 +4,8 @@ from typing import List
 from pydantic import Field
 
 from langchain.agents.agent_toolkits.base import BaseToolkit
+from langchain.llms.base import BaseLLM
+from langchain.llms.openai import OpenAI
 from langchain.sql_database import SQLDatabase
 from langchain.tools import BaseTool
 from langchain.tools.sql_database.tool import (
@@ -18,6 +20,7 @@ class SQLDatabaseToolkit(BaseToolkit):
     """Toolkit for interacting with SQL databases."""
 
     db: SQLDatabase = Field(exclude=True)
+    llm: BaseLLM = Field(default_factory=lambda: OpenAI(temperature=0))
 
     @property
     def dialect(self) -> str:
@@ -35,5 +38,5 @@ class SQLDatabaseToolkit(BaseToolkit):
             QuerySQLDataBaseTool(db=self.db),
             InfoSQLDatabaseTool(db=self.db),
             ListSQLDatabaseTool(db=self.db),
-            QueryCheckerTool(db=self.db),
+            QueryCheckerTool(db=self.db, llm=self.llm),
         ]

langchain/agents/agent_types.py

@@ -8,3 +8,4 @@ class AgentType(str, Enum):
     CONVERSATIONAL_REACT_DESCRIPTION = "conversational-react-description"
     CHAT_ZERO_SHOT_REACT_DESCRIPTION = "chat-zero-shot-react-description"
     CHAT_CONVERSATIONAL_REACT_DESCRIPTION = "chat-conversational-react-description"
+    CHAT_ZERO_SHOT_REACT_DESCRIPTION_V2 = "chat-zero-shot-react-description-002"

langchain/agents/chat_v2/base.py

@@ -0,0 +1,53 @@
+from typing import Any, List, Optional, Sequence
+
+from langchain.agents.agent import AgentOutputParser, LLMSingleActionAgent
+from langchain.agents.chat_v2.prompt import (
+    FORMAT_INSTRUCTIONS,
+    PREFIX,
+    SUFFIX,
+    ChatOutputParser,
+    create_prompt,
+)
+from langchain.callbacks.base import BaseCallbackManager
+from langchain.chains.llm import LLMChain
+from langchain.schema import BaseLanguageModel
+from langchain.tools import BaseTool
+
+
+class ChatAgentV2(LLMSingleActionAgent):
+    @classmethod
+    def from_llm_and_tools(
+        cls,
+        llm: BaseLanguageModel,
+        tools: Sequence[BaseTool],
+        callback_manager: Optional[BaseCallbackManager] = None,
+        prefix: str = PREFIX,
+        suffix: str = SUFFIX,
+        format_instructions: str = FORMAT_INSTRUCTIONS,
+        input_variables: Optional[List[str]] = None,
+        output_parser: Optional[AgentOutputParser] = None,
+        stop: Optional[List[str]] = None,
+        **kwargs: Any,
+    ) -> LLMSingleActionAgent:
+        """Construct an agent from an LLM and tools."""
+        _stop = stop or ["Observation:"]
+        _output_parser = output_parser or ChatOutputParser()
+        prompt = create_prompt(
+            tools,
+            prefix=prefix,
+            suffix=suffix,
+            format_instructions=format_instructions,
+            input_variables=input_variables,
+        )
+        llm_chain = LLMChain(
+            llm=llm,
+            prompt=prompt,
+            callback_manager=callback_manager,
+        )
+        return cls(
+            llm_chain=llm_chain, output_parser=_output_parser, stop=_stop, **kwargs
+        )
+
+    @property
+    def _agent_type(self) -> str:
+        raise ValueError

langchain/agents/chat_v2/prompt.py

@@ -0,0 +1,84 @@
+# flake8: noqa
+import json
+from langchain.prompts.chat import (
+    HumanMessagePromptTemplate,
+    SystemMessagePromptTemplate,
+)
+from langchain.agents.schema import AgentScratchPadChatPromptTemplate
+from langchain.prompts.base import BasePromptTemplate
+from langchain.schema import AgentAction, AgentFinish
+from langchain.tools.base import BaseTool
+from typing import Sequence, Optional, List, Union
+from langchain.agents.agent import AgentOutputParser
+
+PREFIX = """Answer the following questions as best you can. You have access to the following tools:"""
+FORMAT_INSTRUCTIONS = """The way you use the tools is by specifying a json blob.
+Specifically, this json should have a `action` key (with the name of the tool to use) and a `action_input` key (with the input to the tool going here).
+
+The only values that should be in the "action" field are: {tool_names}
+
+The $JSON_BLOB should only contain a SINGLE action, do NOT return a list of multiple actions. Here is an example of a valid $JSON_BLOB:
+
+```
+{{{{
+  "action": $TOOL_NAME,
+  "action_input": $INPUT
+}}}}
+```
+
+ALWAYS use the following format:
+
+Question: the input question you must answer
+Thought: you should always think about what to do
+Action:
+```
+$JSON_BLOB
+```
+Observation: the result of the action
+... (this Thought/Action/Observation can repeat N times)
+Thought: I now know the final answer
+Final Answer: the final answer to the original input question"""
+SUFFIX = """Begin! Reminder to always use the exact characters `Final Answer` when responding."""
+
+
+def create_prompt(
+    tools: Sequence[BaseTool],
+    prefix: str = PREFIX,
+    suffix: str = SUFFIX,
+    format_instructions: str = FORMAT_INSTRUCTIONS,
+    input_variables: Optional[List[str]] = None,
+) -> BasePromptTemplate:
+    tool_strings = "\n".join([f"{tool.name}: {tool.description}" for tool in tools])
+    tool_names = ", ".join([tool.name for tool in tools])
+    format_instructions = format_instructions.format(tool_names=tool_names)
+    template = "\n\n".join([prefix, tool_strings, format_instructions, suffix])
+    messages = [
+        SystemMessagePromptTemplate.from_template(template),
+        HumanMessagePromptTemplate.from_template("{input}\n\n{agent_scratchpad}"),
+    ]
+    if input_variables is None:
+        input_variables = ["input", "intermediate_steps"]
+    return AgentScratchPadChatPromptTemplate(
+        input_variables=input_variables, messages=messages
+    )
+
+
+class ChatOutputParser(AgentOutputParser):
+    def parse(self, text: str) -> Union[AgentAction, AgentFinish]:
+        if "Final Answer:" in text:
+            return AgentFinish(
+                # Return values is generally always a dictionary with a single `output` key
+                # It is not recommended to try anything else at the moment :)
+                return_values={"output": text.split("Final Answer:")[-1].strip()},
+                log=text,
+            )
+        try:
+            _, action, _ = text.split("```")
+            response = json.loads(action.strip())
+            agent_action = AgentAction(
+                tool=response["action"], tool_input=response["action_input"], log=text
+            )
+            return agent_action
+
+        except Exception:
+            raise ValueError(f"Could not parse LLM output: {text}")

langchain/agents/loading.py

@@ -5,9 +5,10 @@ from typing import Any, List, Optional, Union
 
 import yaml
 
-from langchain.agents.agent import Agent
+from langchain.agents.agent import BaseSingleActionAgent
 from langchain.agents.agent_types import AgentType
 from langchain.agents.chat.base import ChatAgent
+from langchain.agents.chat_v2.base import ChatAgentV2
 from langchain.agents.conversational.base import ConversationalAgent
 from langchain.agents.conversational_chat.base import ConversationalChatAgent
 from langchain.agents.mrkl.base import ZeroShotAgent
@@ -25,6 +26,7 @@ AGENT_TO_CLASS = {
     AgentType.CONVERSATIONAL_REACT_DESCRIPTION: ConversationalAgent,
     AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION: ChatAgent,
     AgentType.CHAT_CONVERSATIONAL_REACT_DESCRIPTION: ConversationalChatAgent,
+    AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION_V2: ChatAgentV2,
 }
 
 URL_BASE = "https://raw.githubusercontent.com/hwchase17/langchain-hub/master/agents/"
@@ -32,7 +34,7 @@ URL_BASE = "https://raw.githubusercontent.com/hwchase17/langchain-hub/master/age
 
 def _load_agent_from_tools(
     config: dict, llm: BaseLLM, tools: List[Tool], **kwargs: Any
-) -> Agent:
+) -> BaseSingleActionAgent:
     config_type = config.pop("_type")
     if config_type not in AGENT_TO_CLASS:
         raise ValueError(f"Loading {config_type} agent not supported")
@@ -49,7 +51,7 @@ def load_agent_from_config(
     llm: Optional[BaseLLM] = None,
     tools: Optional[List[Tool]] = None,
     **kwargs: Any,
-) -> Agent:
+) -> BaseSingleActionAgent:
     """Load agent from Config Dict."""
     if "_type" not in config:
         raise ValueError("Must specify an agent Type in config")
@@ -82,7 +84,7 @@ def load_agent_from_config(
     return agent_cls(**combined_config)  # type: ignore
 
 
-def load_agent(path: Union[str, Path], **kwargs: Any) -> Agent:
+def load_agent(path: Union[str, Path], **kwargs: Any) -> BaseSingleActionAgent:
     """Unified method for loading a agent from LangChainHub or local fs."""
     if hub_result := try_load_from_hub(
         path, _load_agent_from_file, "agents", {"json", "yaml"}
@@ -92,7 +94,9 @@ def load_agent(path: Union[str, Path], **kwargs: Any) -> Agent:
         return _load_agent_from_file(path, **kwargs)
 
 
-def _load_agent_from_file(file: Union[str, Path], **kwargs: Any) -> Agent:
+def _load_agent_from_file(
+    file: Union[str, Path], **kwargs: Any
+) -> BaseSingleActionAgent:
     """Load agent from file."""
     # Convert file to Path object.
     if isinstance(file, str):

langchain/agents/schema.py

@@ -0,0 +1,28 @@
+from typing import Any, Dict, List, Tuple
+
+from langchain.prompts.chat import ChatPromptTemplate
+from langchain.schema import AgentAction
+
+
+class AgentScratchPadChatPromptTemplate(ChatPromptTemplate):
+    def _construct_agent_scratchpad(
+        self, intermediate_steps: List[Tuple[AgentAction, str]]
+    ) -> str:
+        if len(intermediate_steps) == 0:
+            return ""
+        thoughts = ""
+        for action, observation in intermediate_steps:
+            thoughts += action.log
+            thoughts += f"\nObservation: {observation}\nThought: "
+        return (
+            f"This was your previous work "
+            f"(but I haven't seen any of it! I only see what "
+            f"you return as final answer):\n{thoughts}"
+        )
+
+    def _merge_partial_and_user_variables(self, **kwargs: Any) -> Dict[str, Any]:
+        intermediate_steps = kwargs.pop("intermediate_steps")
+        kwargs["agent_scratchpad"] = self._construct_agent_scratchpad(
+            intermediate_steps
+        )
+        return kwargs

langchain/cache.py

@@ -1,6 +1,7 @@
 """Beta Feature: base interface for cache."""
+import json
 from abc import ABC, abstractmethod
-from typing import Any, Dict, List, Optional, Tuple
+from typing import Any, Callable, Dict, List, Optional, Tuple
 
 from sqlalchemy import Column, Integer, String, create_engine, select
 from sqlalchemy.engine.base import Engine
@@ -137,3 +138,125 @@ class RedisCache(BaseCache):
         """Update cache based on prompt and llm_string."""
         for i, generation in enumerate(return_val):
             self.redis.set(self._key(prompt, llm_string, i), generation.text)
+
+
+class GPTCache(BaseCache):
+    """Cache that uses GPTCache as a backend."""
+
+    def __init__(self, init_func: Callable[[Any], None]):
+        """Initialize by passing in the `init` GPTCache func
+
+        Args:
+            init_func (Callable[[Any], None]): init `GPTCache` function
+
+        Example:
+        .. code-block:: python
+
+            import gptcache
+            from gptcache.processor.pre import get_prompt
+            from gptcache.manager.factory import get_data_manager
+
+            # Avoid multiple caches using the same file,
+            causing different llm model caches to affect each other
+            i = 0
+            file_prefix = "data_map"
+
+            def init_gptcache_map(cache_obj: gptcache.Cache):
+                nonlocal i
+                cache_path = f'{file_prefix}_{i}.txt'
+                cache_obj.init(
+                    pre_embedding_func=get_prompt,
+                    data_manager=get_data_manager(data_path=cache_path),
+                )
+                i += 1
+
+            langchain.llm_cache = GPTCache(init_gptcache_map)
+
+        """
+        try:
+            import gptcache  # noqa: F401
+        except ImportError:
+            raise ValueError(
+                "Could not import gptcache python package. "
+                "Please install it with `pip install gptcache`."
+            )
+        self.init_gptcache_func: Callable[[Any], None] = init_func
+        self.gptcache_dict: Dict[str, Any] = {}
+
+    @staticmethod
+    def _update_cache_callback_none(*_: Any, **__: Any) -> None:
+        """When updating cached data, do nothing.
+
+        Because currently only cached queries are processed."""
+        return None
+
+    @staticmethod
+    def _llm_handle_none(*_: Any, **__: Any) -> None:
+        """Do nothing on a cache miss"""
+        return None
+
+    @staticmethod
+    def _cache_data_converter(data: str) -> RETURN_VAL_TYPE:
+        """Convert the `data` in the cache to the `RETURN_VAL_TYPE` data format."""
+        return [Generation(**generation_dict) for generation_dict in json.loads(data)]
+
+    def _get_gptcache(self, llm_string: str) -> Any:
+        """Get a cache object.
+
+        When the corresponding llm model cache does not exist, it will be created."""
+        from gptcache import Cache
+
+        _gptcache = self.gptcache_dict.get(llm_string, None)
+        if _gptcache is None:
+            _gptcache = Cache()
+            self.init_gptcache_func(_gptcache)
+            self.gptcache_dict[llm_string] = _gptcache
+        return _gptcache
+
+    def lookup(self, prompt: str, llm_string: str) -> Optional[RETURN_VAL_TYPE]:
+        """Look up the cache data.
+        First, retrieve the corresponding cache object using the `llm_string` parameter,
+        and then retrieve the data from the cache based on the `prompt`.
+        """
+        from gptcache.adapter.adapter import adapt
+
+        _gptcache = self.gptcache_dict.get(llm_string)
+        if _gptcache is None:
+            return None
+        res = adapt(
+            GPTCache._llm_handle_none,
+            GPTCache._cache_data_converter,
+            GPTCache._update_cache_callback_none,
+            cache_obj=_gptcache,
+            prompt=prompt,
+        )
+        return res
+
+    @staticmethod
+    def _update_cache_callback(
+        llm_data: RETURN_VAL_TYPE, update_cache_func: Callable[[Any], None]
+    ) -> None:
+        """Save the `llm_data` to cache storage"""
+        handled_data = json.dumps([generation.dict() for generation in llm_data])
+        update_cache_func(handled_data)
+
+    def update(self, prompt: str, llm_string: str, return_val: RETURN_VAL_TYPE) -> None:
+        """Update cache.
+        First, retrieve the corresponding cache object using the `llm_string` parameter,
+        and then store the `prompt` and `return_val` in the cache object.
+        """
+        from gptcache.adapter.adapter import adapt
+
+        _gptcache = self._get_gptcache(llm_string)
+
+        def llm_handle(*_: Any, **__: Any) -> RETURN_VAL_TYPE:
+            return return_val
+
+        return adapt(
+            llm_handle,
+            GPTCache._cache_data_converter,
+            GPTCache._update_cache_callback,
+            cache_obj=_gptcache,
+            cache_skip=True,
+            prompt=prompt,
+        )

langchain/callbacks/__init__.py

@@ -11,6 +11,7 @@ from langchain.callbacks.base import (
     CallbackManager,
 )
 from langchain.callbacks.clearml_callback import ClearMLCallbackHandler
+from langchain.callbacks.comet_ml_callback import CometCallbackHandler
 from langchain.callbacks.openai_info import OpenAICallbackHandler
 from langchain.callbacks.shared import SharedCallbackManager
 from langchain.callbacks.stdout import StdOutCallbackHandler
@@ -78,6 +79,7 @@ __all__ = [
     "AimCallbackHandler",
     "WandbCallbackHandler",
     "ClearMLCallbackHandler",
+    "CometCallbackHandler",
     "AsyncIteratorCallbackHandler",
     "get_openai_callback",
     "set_tracing_callback_manager",

langchain/callbacks/comet_ml_callback.py

@@ -0,0 +1,625 @@
+import tempfile
+from copy import deepcopy
+from pathlib import Path
+from typing import Any, Callable, Dict, List, Optional, Sequence, Union
+
+import langchain
+from langchain.callbacks.base import BaseCallbackHandler
+from langchain.callbacks.utils import (
+    BaseMetadataCallbackHandler,
+    flatten_dict,
+    import_pandas,
+    import_spacy,
+    import_textstat,
+)
+from langchain.schema import AgentAction, AgentFinish, Generation, LLMResult
+
+LANGCHAIN_MODEL_NAME = "langchain-model"
+
+
+def import_comet_ml() -> Any:
+    try:
+        import comet_ml  # noqa: F401
+    except ImportError:
+        raise ImportError(
+            "To use the comet_ml callback manager you need to have the "
+            "`comet_ml` python package installed. Please install it with"
+            " `pip install comet_ml`"
+        )
+    return comet_ml
+
+
+def _get_experiment(
+    workspace: Optional[str] = None, project_name: Optional[str] = None
+) -> Any:
+    comet_ml = import_comet_ml()
+
+    experiment = comet_ml.Experiment(  # type: ignore
+        workspace=workspace,
+        project_name=project_name,
+    )
+
+    return experiment
+
+
+def _fetch_text_complexity_metrics(text: str) -> dict:
+    textstat = import_textstat()
+    text_complexity_metrics = {
+        "flesch_reading_ease": textstat.flesch_reading_ease(text),
+        "flesch_kincaid_grade": textstat.flesch_kincaid_grade(text),
+        "smog_index": textstat.smog_index(text),
+        "coleman_liau_index": textstat.coleman_liau_index(text),
+        "automated_readability_index": textstat.automated_readability_index(text),
+        "dale_chall_readability_score": textstat.dale_chall_readability_score(text),
+        "difficult_words": textstat.difficult_words(text),
+        "linsear_write_formula": textstat.linsear_write_formula(text),
+        "gunning_fog": textstat.gunning_fog(text),
+        "text_standard": textstat.text_standard(text),
+        "fernandez_huerta": textstat.fernandez_huerta(text),
+        "szigriszt_pazos": textstat.szigriszt_pazos(text),
+        "gutierrez_polini": textstat.gutierrez_polini(text),
+        "crawford": textstat.crawford(text),
+        "gulpease_index": textstat.gulpease_index(text),
+        "osman": textstat.osman(text),
+    }
+    return text_complexity_metrics
+
+
+def _summarize_metrics_for_generated_outputs(metrics: Sequence) -> dict:
+    pd = import_pandas()
+    metrics_df = pd.DataFrame(metrics)
+    metrics_summary = metrics_df.describe()
+
+    return metrics_summary.to_dict()
+
+
+class CometCallbackHandler(BaseMetadataCallbackHandler, BaseCallbackHandler):
+    """Callback Handler that logs to Comet.
+
+    Parameters:
+        job_type (str): The type of comet_ml task such as "inference",
+            "testing" or "qc"
+        project_name (str): The comet_ml project name
+        tags (list): Tags to add to the task
+        task_name (str): Name of the comet_ml task
+        visualize (bool): Whether to visualize the run.
+        complexity_metrics (bool): Whether to log complexity metrics
+        stream_logs (bool): Whether to stream callback actions to Comet
+
+    This handler will utilize the associated callback method and formats
+    the input of each callback function with metadata regarding the state of LLM run,
+    and adds the response to the list of records for both the {method}_records and
+    action. It then logs the response to Comet.
+    """
+
+    def __init__(
+        self,
+        task_type: Optional[str] = "inference",
+        workspace: Optional[str] = None,
+        project_name: Optional[str] = "comet-langchain-demo",
+        tags: Optional[Sequence] = None,
+        name: Optional[str] = None,
+        visualizations: Optional[List[str]] = None,
+        complexity_metrics: bool = False,
+        custom_metrics: Optional[Callable] = None,
+        stream_logs: bool = True,
+    ) -> None:
+        """Initialize callback handler."""
+
+        comet_ml = import_comet_ml()
+        super().__init__()
+
+        self.task_type = task_type
+        self.workspace = workspace
+        self.project_name = project_name
+        self.tags = tags
+        self.visualizations = visualizations
+        self.complexity_metrics = complexity_metrics
+        self.custom_metrics = custom_metrics
+        self.stream_logs = stream_logs
+        self.temp_dir = tempfile.TemporaryDirectory()
+
+        self.experiment = _get_experiment(workspace, project_name)
+        self.experiment.log_other("Created from", "langchain")
+        if tags:
+            self.experiment.add_tags(tags)
+        self.name = name
+        if self.name:
+            self.experiment.set_name(self.name)
+
+        warning = (
+            "The comet_ml callback is currently in beta and is subject to change "
+            "based on updates to `langchain`. Please report any issues to "
+            "https://github.com/comet-ml/issue_tracking/issues with the tag "
+            "`langchain`."
+        )
+        comet_ml.LOGGER.warning(warning)
+
+        self.callback_columns: list = []
+        self.action_records: list = []
+        self.complexity_metrics = complexity_metrics
+        if self.visualizations:
+            spacy = import_spacy()
+            self.nlp = spacy.load("en_core_web_sm")
+        else:
+            self.nlp = None
+
+    def _init_resp(self) -> Dict:
+        return {k: None for k in self.callback_columns}
+
+    def on_llm_start(
+        self, serialized: Dict[str, Any], prompts: List[str], **kwargs: Any
+    ) -> None:
+        """Run when LLM starts."""
+        self.step += 1
+        self.llm_starts += 1
+        self.starts += 1
+
+        metadata = self._init_resp()
+        metadata.update({"action": "on_llm_start"})
+        metadata.update(flatten_dict(serialized))
+        metadata.update(self.get_custom_callback_meta())
+
+        for prompt in prompts:
+            prompt_resp = deepcopy(metadata)
+            prompt_resp["prompts"] = prompt
+            self.on_llm_start_records.append(prompt_resp)
+            self.action_records.append(prompt_resp)
+
+            if self.stream_logs:
+                self._log_stream(prompt, metadata, self.step)
+
+    def on_llm_new_token(self, token: str, **kwargs: Any) -> None:
+        """Run when LLM generates a new token."""
+        self.step += 1
+        self.llm_streams += 1
+
+        resp = self._init_resp()
+        resp.update({"action": "on_llm_new_token", "token": token})
+        resp.update(self.get_custom_callback_meta())
+
+        self.action_records.append(resp)
+
+    def on_llm_end(self, response: LLMResult, **kwargs: Any) -> None:
+        """Run when LLM ends running."""
+        self.step += 1
+        self.llm_ends += 1
+        self.ends += 1
+
+        metadata = self._init_resp()
+        metadata.update({"action": "on_llm_end"})
+        metadata.update(flatten_dict(response.llm_output or {}))
+        metadata.update(self.get_custom_callback_meta())
+
+        output_complexity_metrics = []
+        output_custom_metrics = []
+
+        for prompt_idx, generations in enumerate(response.generations):
+            for gen_idx, generation in enumerate(generations):
+                text = generation.text
+
+                generation_resp = deepcopy(metadata)
+                generation_resp.update(flatten_dict(generation.dict()))
+
+                complexity_metrics = self._get_complexity_metrics(text)
+                if complexity_metrics:
+                    output_complexity_metrics.append(complexity_metrics)
+                    generation_resp.update(complexity_metrics)
+
+                custom_metrics = self._get_custom_metrics(
+                    generation, prompt_idx, gen_idx
+                )
+                if custom_metrics:
+                    output_custom_metrics.append(custom_metrics)
+                    generation_resp.update(custom_metrics)
+
+                if self.stream_logs:
+                    self._log_stream(text, metadata, self.step)
+
+                self.action_records.append(generation_resp)
+                self.on_llm_end_records.append(generation_resp)
+
+        self._log_text_metrics(output_complexity_metrics, step=self.step)
+        self._log_text_metrics(output_custom_metrics, step=self.step)
+
+    def on_llm_error(
+        self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any
+    ) -> None:
+        """Run when LLM errors."""
+        self.step += 1
+        self.errors += 1
+
+    def on_chain_start(
+        self, serialized: Dict[str, Any], inputs: Dict[str, Any], **kwargs: Any
+    ) -> None:
+        """Run when chain starts running."""
+        self.step += 1
+        self.chain_starts += 1
+        self.starts += 1
+
+        resp = self._init_resp()
+        resp.update({"action": "on_chain_start"})
+        resp.update(flatten_dict(serialized))
+        resp.update(self.get_custom_callback_meta())
+
+        comet_ml = import_comet_ml()
+
+        for chain_input_key, chain_input_val in inputs.items():
+            if isinstance(chain_input_val, str):
+                input_resp = deepcopy(resp)
+                if self.stream_logs:
+                    self._log_stream(chain_input_val, resp, self.step)
+                input_resp.update({chain_input_key: chain_input_val})
+                self.action_records.append(input_resp)
+
+            else:
+                comet_ml.LOGGER.warning(
+                    f"Unexpected data format provided! "
+                    f"Input Value for {chain_input_key} will not be logged"
+                )
+
+    def on_chain_end(self, outputs: Dict[str, Any], **kwargs: Any) -> None:
+        """Run when chain ends running."""
+        self.step += 1
+        self.chain_ends += 1
+        self.ends += 1
+
+        resp = self._init_resp()
+        resp.update({"action": "on_chain_end"})
+        resp.update(self.get_custom_callback_meta())
+
+        comet_ml = import_comet_ml()
+
+        for chain_output_key, chain_output_val in outputs.items():
+            if isinstance(chain_output_val, str):
+                output_resp = deepcopy(resp)
+                if self.stream_logs:
+                    self._log_stream(chain_output_val, resp, self.step)
+                output_resp.update({chain_output_key: chain_output_val})
+                self.action_records.append(output_resp)
+            else:
+                comet_ml.LOGGER.warning(
+                    f"Unexpected data format provided! "
+                    f"Output Value for {chain_output_key} will not be logged"
+                )
+
+    def on_chain_error(
+        self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any
+    ) -> None:
+        """Run when chain errors."""
+        self.step += 1
+        self.errors += 1
+
+    def on_tool_start(
+        self, serialized: Dict[str, Any], input_str: str, **kwargs: Any
+    ) -> None:
+        """Run when tool starts running."""
+        self.step += 1
+        self.tool_starts += 1
+        self.starts += 1
+
+        resp = self._init_resp()
+        resp.update({"action": "on_tool_start"})
+        resp.update(flatten_dict(serialized))
+        resp.update(self.get_custom_callback_meta())
+        if self.stream_logs:
+            self._log_stream(input_str, resp, self.step)
+
+        resp.update({"input_str": input_str})
+        self.action_records.append(resp)
+
+    def on_tool_end(self, output: str, **kwargs: Any) -> None:
+        """Run when tool ends running."""
+        self.step += 1
+        self.tool_ends += 1
+        self.ends += 1
+
+        resp = self._init_resp()
+        resp.update({"action": "on_tool_end"})
+        resp.update(self.get_custom_callback_meta())
+        if self.stream_logs:
+            self._log_stream(output, resp, self.step)
+
+        resp.update({"output": output})
+        self.action_records.append(resp)
+
+    def on_tool_error(
+        self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any
+    ) -> None:
+        """Run when tool errors."""
+        self.step += 1
+        self.errors += 1
+
+    def on_text(self, text: str, **kwargs: Any) -> None:
+        """
+        Run when agent is ending.
+        """
+        self.step += 1
+        self.text_ctr += 1
+
+        resp = self._init_resp()
+        resp.update({"action": "on_text"})
+        resp.update(self.get_custom_callback_meta())
+        if self.stream_logs:
+            self._log_stream(text, resp, self.step)
+
+        resp.update({"text": text})
+        self.action_records.append(resp)
+
+    def on_agent_finish(self, finish: AgentFinish, **kwargs: Any) -> None:
+        """Run when agent ends running."""
+        self.step += 1
+        self.agent_ends += 1
+        self.ends += 1
+
+        resp = self._init_resp()
+        output = finish.return_values["output"]
+        log = finish.log
+
+        resp.update({"action": "on_agent_finish", "log": log})
+        resp.update(self.get_custom_callback_meta())
+        if self.stream_logs:
+            self._log_stream(output, resp, self.step)
+
+        resp.update({"output": output})
+        self.action_records.append(resp)
+
+    def on_agent_action(self, action: AgentAction, **kwargs: Any) -> Any:
+        """Run on agent action."""
+        self.step += 1
+        self.tool_starts += 1
+        self.starts += 1
+
+        tool = action.tool
+        tool_input = action.tool_input
+        log = action.log
+
+        resp = self._init_resp()
+        resp.update({"action": "on_agent_action", "log": log, "tool": tool})
+        resp.update(self.get_custom_callback_meta())
+        if self.stream_logs:
+            self._log_stream(tool_input, resp, self.step)
+
+        resp.update({"tool_input": tool_input})
+        self.action_records.append(resp)
+
+    def _get_complexity_metrics(self, text: str) -> dict:
+        """Compute text complexity metrics using textstat.
+
+        Parameters:
+            text (str): The text to analyze.
+
+        Returns:
+            (dict): A dictionary containing the complexity metrics.
+        """
+        resp = {}
+        if self.complexity_metrics:
+            text_complexity_metrics = _fetch_text_complexity_metrics(text)
+            resp.update(text_complexity_metrics)
+
+        return resp
+
+    def _get_custom_metrics(
+        self, generation: Generation, prompt_idx: int, gen_idx: int
+    ) -> dict:
+        """Compute Custom Metrics for an LLM Generated Output
+
+        Args:
+            generation (LLMResult): Output generation from an LLM
+            prompt_idx (int): List index of the input prompt
+            gen_idx (int): List index of the generated output
+
+        Returns:
+            dict: A dictionary containing the custom metrics.
+        """
+
+        resp = {}
+        if self.custom_metrics:
+            custom_metrics = self.custom_metrics(generation, prompt_idx, gen_idx)
+            resp.update(custom_metrics)
+
+        return resp
+
+    def flush_tracker(
+        self,
+        langchain_asset: Any = None,
+        task_type: Optional[str] = "inference",
+        workspace: Optional[str] = None,
+        project_name: Optional[str] = "comet-langchain-demo",
+        tags: Optional[Sequence] = None,
+        name: Optional[str] = None,
+        visualizations: Optional[List[str]] = None,
+        complexity_metrics: bool = False,
+        custom_metrics: Optional[Callable] = None,
+        finish: bool = False,
+        reset: bool = False,
+    ) -> None:
+        """Flush the tracker and setup the session.
+
+        Everything after this will be a new table.
+
+        Args:
+            name: Name of the preformed session so far so it is identifyable
+            langchain_asset: The langchain asset to save.
+            finish: Whether to finish the run.
+
+            Returns:
+                None
+        """
+        self._log_session(langchain_asset)
+
+        if langchain_asset:
+            self._log_model(langchain_asset)
+
+        if finish:
+            self.experiment.end()
+
+        if reset:
+            self._reset(
+                task_type,
+                workspace,
+                project_name,
+                tags,
+                name,
+                visualizations,
+                complexity_metrics,
+                custom_metrics,
+            )
+
+    def _log_stream(self, prompt: str, metadata: dict, step: int) -> None:
+        self.experiment.log_text(prompt, metadata=metadata, step=step)
+
+    def _log_model(self, langchain_asset: Any) -> None:
+        comet_ml = import_comet_ml()
+
+        model_parameters = self._get_llm_parameters(langchain_asset)
+        self.experiment.log_parameters(model_parameters, prefix="model")
+
+        langchain_asset_path = Path(self.temp_dir.name, "model.json")
+        model_name = self.name if self.name else LANGCHAIN_MODEL_NAME
+
+        try:
+            if hasattr(langchain_asset, "save"):
+                langchain_asset.save(langchain_asset_path)
+                self.experiment.log_model(model_name, str(langchain_asset_path))
+        except (ValueError, AttributeError, NotImplementedError) as e:
+            if hasattr(langchain_asset, "save_agent"):
+                langchain_asset.save_agent(langchain_asset_path)
+                self.experiment.log_model(model_name, str(langchain_asset_path))
+            else:
+                comet_ml.LOGGER.warning(
+                    f"{e}"
+                    " Could not save Langchain Asset "
+                    f"for {langchain_asset.__class__.__name__}"
+                )
+
+    def _log_session(self, langchain_asset: Optional[Any] = None) -> None:
+        llm_session_df = self._create_session_analysis_dataframe(langchain_asset)
+        # Log the cleaned dataframe as a table
+        self.experiment.log_table("langchain-llm-session.csv", llm_session_df)
+
+        metadata = {"langchain_version": str(langchain.__version__)}
+        # Log the langchain low-level records as a JSON file directly
+        self.experiment.log_asset_data(
+            self.action_records, "langchain-action_records.json", metadata=metadata
+        )
+
+        self._log_visualizations(llm_session_df)
+
+    def _log_text_metrics(self, metrics: Sequence[dict], step: int) -> None:
+        if not metrics:
+            return
+
+        metrics_summary = _summarize_metrics_for_generated_outputs(metrics)
+        for key, value in metrics_summary.items():
+            self.experiment.log_metrics(value, prefix=key, step=step)
+
+    def _log_visualizations(self, session_df: Any) -> None:
+        if not (self.visualizations and self.nlp):
+            return
+
+        spacy = import_spacy()
+        comet_ml = import_comet_ml()
+
+        prompts = session_df["prompts"].tolist()
+        outputs = session_df["text"].tolist()
+
+        for idx, (prompt, output) in enumerate(zip(prompts, outputs)):
+            doc = self.nlp(output)
+            sentence_spans = list(doc.sents)
+
+            for visualization in self.visualizations:
+                try:
+                    html = spacy.displacy.render(
+                        sentence_spans,
+                        style=visualization,
+                        options={"compact": True},
+                        jupyter=False,
+                        page=True,
+                    )
+                    self.experiment.log_asset_data(
+                        html,
+                        name=f"langchain-viz-{visualization}-{idx}.html",
+                        metadata={"prompt": prompt},
+                        step=idx,
+                    )
+                except Exception as e:
+                    comet_ml.LOGGER.warning(e)
+
+        return
+
+    def _reset(
+        self,
+        task_type: Optional[str] = None,
+        workspace: Optional[str] = None,
+        project_name: Optional[str] = None,
+        tags: Optional[Sequence] = None,
+        name: Optional[str] = None,
+        visualizations: Optional[List[str]] = None,
+        complexity_metrics: bool = False,
+        custom_metrics: Optional[Callable] = None,
+    ) -> None:
+        _task_type = task_type if task_type else self.task_type
+        _workspace = workspace if workspace else self.workspace
+        _project_name = project_name if project_name else self.project_name
+        _tags = tags if tags else self.tags
+        _name = name if name else self.name
+        _visualizations = visualizations if visualizations else self.visualizations
+        _complexity_metrics = (
+            complexity_metrics if complexity_metrics else self.complexity_metrics
+        )
+        _custom_metrics = custom_metrics if custom_metrics else self.custom_metrics
+
+        self.__init__(  # type: ignore
+            task_type=_task_type,
+            workspace=_workspace,
+            project_name=_project_name,
+            tags=_tags,
+            name=_name,
+            visualizations=_visualizations,
+            complexity_metrics=_complexity_metrics,
+            custom_metrics=_custom_metrics,
+        )
+
+        self.reset_callback_meta()
+        self.temp_dir = tempfile.TemporaryDirectory()
+
+    def _create_session_analysis_dataframe(self, langchain_asset: Any = None) -> dict:
+        pd = import_pandas()
+
+        llm_parameters = self._get_llm_parameters(langchain_asset)
+        num_generations_per_prompt = llm_parameters.get("n", 1)
+
+        llm_start_records_df = pd.DataFrame(self.on_llm_start_records)
+        # Repeat each input row based on the number of outputs generated per prompt
+        llm_start_records_df = llm_start_records_df.loc[
+            llm_start_records_df.index.repeat(num_generations_per_prompt)
+        ].reset_index(drop=True)
+        llm_end_records_df = pd.DataFrame(self.on_llm_end_records)
+
+        llm_session_df = pd.merge(
+            llm_start_records_df,
+            llm_end_records_df,
+            left_index=True,
+            right_index=True,
+            suffixes=["_llm_start", "_llm_end"],
+        )
+
+        return llm_session_df
+
+    def _get_llm_parameters(self, langchain_asset: Any = None) -> dict:
+        if not langchain_asset:
+            return {}
+        try:
+            if hasattr(langchain_asset, "agent"):
+                llm_parameters = langchain_asset.agent.llm_chain.llm.dict()
+            elif hasattr(langchain_asset, "llm_chain"):
+                llm_parameters = langchain_asset.llm_chain.llm.dict()
+            elif hasattr(langchain_asset, "llm"):
+                llm_parameters = langchain_asset.llm.dict()
+            else:
+                llm_parameters = langchain_asset.dict()
+        except Exception:
+            return {}
+
+        return llm_parameters

langchain/callbacks/openai_info.py

@@ -53,6 +53,15 @@ class OpenAICallbackHandler(BaseCallbackHandler):
     successful_requests: int = 0
     total_cost: float = 0.0
 
+    def __repr__(self) -> str:
+        return (
+            f"Tokens Used: {self.total_tokens}\n"
+            f"\tPrompt Tokens: {self.prompt_tokens}\n"
+            f"\tCompletion Tokens: {self.completion_tokens}\n"
+            f"Successful Requests: {self.successful_requests}\n"
+            f"Total Cost (USD): ${self.total_cost}"
+        )
+
     @property
     def always_verbose(self) -> bool:
         """Whether to call verbose callbacks even if verbose is False."""

langchain/callbacks/streaming_aiter.py

@@ -47,14 +47,19 @@ class AsyncIteratorCallbackHandler(AsyncCallbackHandler):
         while not self.queue.empty() or not self.done.is_set():
             # Wait for the next token in the queue,
             # but stop waiting if the done event is set
-            done, _ = await asyncio.wait(
+            done, other = await asyncio.wait(
                 [
+                    # NOTE: If you add other tasks here, update the code below,
+                    # which assumes each set has exactly one task each
                     asyncio.ensure_future(self.queue.get()),
                     asyncio.ensure_future(self.done.wait()),
                 ],
                 return_when=asyncio.FIRST_COMPLETED,
             )
 
+            # Cancel the other task
+            other.pop().cancel()
+
             # Extract the value of the first completed task
             token_or_done = cast(Union[str, Literal[True]], done.pop().result())
 

langchain/chains/api/base.py

@@ -81,6 +81,26 @@ class APIChain(Chain):
         )
         return {self.output_key: answer}
 
+    async def _acall(self, inputs: Dict[str, str]) -> Dict[str, str]:
+        question = inputs[self.question_key]
+        api_url = await self.api_request_chain.apredict(
+            question=question, api_docs=self.api_docs
+        )
+        self.callback_manager.on_text(
+            api_url, color="green", end="\n", verbose=self.verbose
+        )
+        api_response = await self.requests_wrapper.aget(api_url)
+        self.callback_manager.on_text(
+            api_response, color="yellow", end="\n", verbose=self.verbose
+        )
+        answer = await self.api_answer_chain.apredict(
+            question=question,
+            api_docs=self.api_docs,
+            api_url=api_url,
+            api_response=api_response,
+        )
+        return {self.output_key: answer}
+
     @classmethod
     def from_llm_and_api_docs(
         cls,

langchain/chains/api/openapi/chain.py

@@ -28,7 +28,7 @@ class OpenAPIEndpointChain(Chain, BaseModel):
     """Chain interacts with an OpenAPI endpoint using natural language."""
 
     api_request_chain: LLMChain
-    api_response_chain: LLMChain
+    api_response_chain: Optional[LLMChain]
     api_operation: APIOperation
     requests: Requests = Field(exclude=True, default_factory=Requests)
     param_mapping: _ParamMapping = Field(alias="param_mapping")
@@ -144,15 +144,18 @@ class OpenAPIEndpointChain(Chain, BaseModel):
         self.callback_manager.on_text(
             response_text, color="blue", end="\n", verbose=self.verbose
         )
-        _answer = self.api_response_chain.predict_and_parse(
-            response=response_text,
-            instructions=instructions,
-        )
-        answer = cast(str, _answer)
-        self.callback_manager.on_text(
-            answer, color="yellow", end="\n", verbose=self.verbose
-        )
-        return self._get_output(answer, intermediate_steps)
+        if self.api_response_chain is not None:
+            _answer = self.api_response_chain.predict_and_parse(
+                response=response_text,
+                instructions=instructions,
+            )
+            answer = cast(str, _answer)
+            self.callback_manager.on_text(
+                answer, color="yellow", end="\n", verbose=self.verbose
+            )
+            return self._get_output(answer, intermediate_steps)
+        else:
+            return self._get_output(response_text, intermediate_steps)
 
     @classmethod
     def from_url_and_method(
@@ -184,6 +187,7 @@ class OpenAPIEndpointChain(Chain, BaseModel):
         requests: Optional[Requests] = None,
         verbose: bool = False,
         return_intermediate_steps: bool = False,
+        raw_response: bool = False,
         **kwargs: Any
         # TODO: Handle async
     ) -> "OpenAPIEndpointChain":
@@ -196,7 +200,10 @@ class OpenAPIEndpointChain(Chain, BaseModel):
         requests_chain = APIRequesterChain.from_llm_and_typescript(
             llm, typescript_definition=operation.to_typescript(), verbose=verbose
         )
-        response_chain = APIResponderChain.from_llm(llm, verbose=verbose)
+        if raw_response:
+            response_chain = None
+        else:
+            response_chain = APIResponderChain.from_llm(llm, verbose=verbose)
         _requests = requests or Requests()
         return cls(
             api_request_chain=requests_chain,

langchain/chains/combine_documents/map_reduce.py

@@ -14,7 +14,7 @@ from langchain.docstore.document import Document
 class CombineDocsProtocol(Protocol):
     """Interface for the combine_docs method."""
 
-    def __call__(self, docs: List[Document], **kwargs: Any) -> Tuple[str, dict]:
+    def __call__(self, docs: List[Document], **kwargs: Any) -> str:
         """Interface for the combine_docs method."""
 
 
@@ -48,7 +48,7 @@ def _collapse_docs(
     combine_document_func: CombineDocsProtocol,
     **kwargs: Any,
 ) -> Document:
-    result, _ = combine_document_func(docs, **kwargs)
+    result = combine_document_func(docs, **kwargs)
     combined_metadata = {k: str(v) for k, v in docs[0].metadata.items()}
     for doc in docs[1:]:
         for k, v in doc.metadata.items():
@@ -171,15 +171,17 @@ class MapReduceDocumentsChain(BaseCombineDocumentsChain):
         ]
         length_func = self.combine_document_chain.prompt_length
         num_tokens = length_func(result_docs, **kwargs)
+
+        def _collapse_docs_func(docs: List[Document], **kwargs: Any) -> str:
+            return self._collapse_chain.run(input_documents=docs, **kwargs)
+
         while num_tokens is not None and num_tokens > token_max:
             new_result_doc_list = _split_list_of_docs(
                 result_docs, length_func, token_max, **kwargs
             )
             result_docs = []
             for docs in new_result_doc_list:
-                new_doc = _collapse_docs(
-                    docs, self._collapse_chain.combine_docs, **kwargs
-                )
+                new_doc = _collapse_docs(docs, _collapse_docs_func, **kwargs)
                 result_docs.append(new_doc)
             num_tokens = self.combine_document_chain.prompt_length(
                 result_docs, **kwargs
@@ -189,7 +191,7 @@ class MapReduceDocumentsChain(BaseCombineDocumentsChain):
             extra_return_dict = {"intermediate_steps": _results}
         else:
             extra_return_dict = {}
-        output, _ = self.combine_document_chain.combine_docs(result_docs, **kwargs)
+        output = self.combine_document_chain.run(input_documents=result_docs, **kwargs)
         return output, extra_return_dict
 
     @property

langchain/chains/conversational_retrieval/base.py

@@ -80,7 +80,7 @@ class BaseConversationalRetrievalChain(Chain):
         new_inputs = inputs.copy()
         new_inputs["question"] = new_question
         new_inputs["chat_history"] = chat_history_str
-        answer, _ = self.combine_docs_chain.combine_docs(docs, **new_inputs)
+        answer = self.combine_docs_chain.run(input_documents=docs, **new_inputs)
         if self.return_source_documents:
             return {self.output_key: answer, "source_documents": docs}
         else:
@@ -104,7 +104,7 @@ class BaseConversationalRetrievalChain(Chain):
         new_inputs = inputs.copy()
         new_inputs["question"] = new_question
         new_inputs["chat_history"] = chat_history_str
-        answer, _ = await self.combine_docs_chain.acombine_docs(docs, **new_inputs)
+        answer = await self.combine_docs_chain.arun(input_documents=docs, **new_inputs)
         if self.return_source_documents:
             return {self.output_key: answer, "source_documents": docs}
         else:

langchain/chains/llm_math/base.py

@@ -7,8 +7,8 @@ from langchain.chains.base import Chain
 from langchain.chains.llm import LLMChain
 from langchain.chains.llm_math.prompt import PROMPT
 from langchain.prompts.base import BasePromptTemplate
-from langchain.python import PythonREPL
 from langchain.schema import BaseLanguageModel
+from langchain.utilities import PythonREPL
 
 
 class LLMMathChain(Chain):
@@ -68,6 +68,35 @@ class LLMMathChain(Chain):
             raise ValueError(f"unknown format from LLM: {t}")
         return {self.output_key: answer}
 
+    async def _aprocess_llm_result(self, t: str) -> Dict[str, str]:
+        python_executor = PythonREPL()
+        if self.callback_manager.is_async:
+            await self.callback_manager.on_text(t, color="green", verbose=self.verbose)
+        else:
+            self.callback_manager.on_text(t, color="green", verbose=self.verbose)
+        t = t.strip()
+        if t.startswith("```python"):
+            code = t[9:-4]
+            output = python_executor.run(code)
+            if self.callback_manager.is_async:
+                await self.callback_manager.on_text("\nAnswer: ", verbose=self.verbose)
+                await self.callback_manager.on_text(
+                    output, color="yellow", verbose=self.verbose
+                )
+            else:
+                await self.callback_manager.on_text("\nAnswer: ", verbose=self.verbose)
+                await self.callback_manager.on_text(
+                    output, color="yellow", verbose=self.verbose
+                )
+            answer = "Answer: " + output
+        elif t.startswith("Answer:"):
+            answer = t
+        elif "Answer:" in t:
+            answer = "Answer: " + t.split("Answer:")[-1]
+        else:
+            raise ValueError(f"unknown format from LLM: {t}")
+        return {self.output_key: answer}
+
     def _call(self, inputs: Dict[str, str]) -> Dict[str, str]:
         llm_executor = LLMChain(
             prompt=self.prompt, llm=self.llm, callback_manager=self.callback_manager
@@ -80,11 +109,16 @@ class LLMMathChain(Chain):
         llm_executor = LLMChain(
             prompt=self.prompt, llm=self.llm, callback_manager=self.callback_manager
         )
-        self.callback_manager.on_text(inputs[self.input_key], verbose=self.verbose)
+        if self.callback_manager.is_async:
+            await self.callback_manager.on_text(
+                inputs[self.input_key], verbose=self.verbose
+            )
+        else:
+            self.callback_manager.on_text(inputs[self.input_key], verbose=self.verbose)
         t = await llm_executor.apredict(
             question=inputs[self.input_key], stop=["```output"]
         )
-        return self._process_llm_result(t)
+        return await self._aprocess_llm_result(t)
 
     @property
     def _chain_type(self) -> str:

langchain/chains/llm_requests.py

@@ -57,7 +57,7 @@ class LLMRequestsChain(Chain):
         except ImportError:
             raise ValueError(
                 "Could not import bs4 python package. "
-                "Please it install it with `pip install bs4`."
+                "Please install it with `pip install bs4`."
             )
         return values
 

langchain/chains/mapreduce.py

@@ -70,5 +70,5 @@ class MapReduceChain(Chain):
         # Split the larger text into smaller chunks.
         texts = self.text_splitter.split_text(inputs[self.input_key])
         docs = [Document(page_content=text) for text in texts]
-        outputs, _ = self.combine_documents_chain.combine_docs(docs)
+        outputs = self.combine_documents_chain.run(input_documents=docs)
         return {self.output_key: outputs}

langchain/chains/moderation.py

@@ -55,7 +55,7 @@ class OpenAIModerationChain(Chain):
         except ImportError:
             raise ValueError(
                 "Could not import openai python package. "
-                "Please it install it with `pip install openai`."
+                "Please install it with `pip install openai`."
             )
         return values
 

langchain/chains/natbot/crawler.py

@@ -53,7 +53,7 @@ class Crawler:
         except ImportError:
             raise ValueError(
                 "Could not import playwright python package. "
-                "Please it install it with `pip install playwright`."
+                "Please install it with `pip install playwright`."
             )
         self.browser: Browser = (
             sync_playwright().start().chromium.launch(headless=False)

langchain/chains/pal/base.py

@@ -13,8 +13,8 @@ from langchain.chains.llm import LLMChain
 from langchain.chains.pal.colored_object_prompt import COLORED_OBJECT_PROMPT
 from langchain.chains.pal.math_prompt import MATH_PROMPT
 from langchain.prompts.base import BasePromptTemplate
-from langchain.python import PythonREPL
 from langchain.schema import BaseLanguageModel
+from langchain.utilities import PythonREPL
 
 
 class PALChain(Chain):

langchain/chains/qa_with_sources/base.py

@@ -116,7 +116,7 @@ class BaseQAWithSourcesChain(Chain, ABC):
 
     def _call(self, inputs: Dict[str, Any]) -> Dict[str, Any]:
         docs = self._get_docs(inputs)
-        answer, _ = self.combine_documents_chain.combine_docs(docs, **inputs)
+        answer = self.combine_documents_chain.run(input_documents=docs, **inputs)
         if re.search(r"SOURCES:\s", answer):
             answer, sources = re.split(r"SOURCES:\s", answer)
         else:
@@ -135,7 +135,7 @@ class BaseQAWithSourcesChain(Chain, ABC):
 
     async def _acall(self, inputs: Dict[str, Any]) -> Dict[str, Any]:
         docs = await self._aget_docs(inputs)
-        answer, _ = await self.combine_documents_chain.acombine_docs(docs, **inputs)
+        answer = await self.combine_documents_chain.arun(input_documents=docs, **inputs)
         if re.search(r"SOURCES:\s", answer):
             answer, sources = re.split(r"SOURCES:\s", answer)
         else:

langchain/chains/question_answering/__init__.py

@@ -196,7 +196,7 @@ def load_qa_chain(
     Args:
         llm: Language Model to use in the chain.
         chain_type: Type of document combining chain to use. Should be one of "stuff",
-            "map_reduce", and "refine".
+            "map_reduce", "map_rerank", and "refine".
         verbose: Whether chains should be run in verbose mode or not. Note that this
             applies to all chains that make up the final chain.
         callback_manager: Callback manager to use for the chain.

langchain/chains/retrieval_qa/base.py

@@ -107,7 +107,9 @@ class BaseRetrievalQA(Chain):
         question = inputs[self.input_key]
 
         docs = self._get_docs(question)
-        answer, _ = self.combine_documents_chain.combine_docs(docs, question=question)
+        answer = self.combine_documents_chain.run(
+            input_documents=docs, question=question
+        )
 
         if self.return_source_documents:
             return {self.output_key: answer, "source_documents": docs}
@@ -133,8 +135,8 @@ class BaseRetrievalQA(Chain):
         question = inputs[self.input_key]
 
         docs = await self._aget_docs(question)
-        answer, _ = await self.combine_documents_chain.acombine_docs(
-            docs, question=question
+        answer = await self.combine_documents_chain.arun(
+            input_documents=docs, question=question
         )
 
         if self.return_source_documents:

langchain/chains/sql_database/base.py

@@ -1,13 +1,13 @@
 """Chain for interacting with SQL Database."""
 from __future__ import annotations
 
-from typing import Any, Dict, List
+from typing import Any, Dict, List, Optional
 
 from pydantic import Extra, Field
 
 from langchain.chains.base import Chain
 from langchain.chains.llm import LLMChain
-from langchain.chains.sql_database.prompt import DECIDER_PROMPT, PROMPT
+from langchain.chains.sql_database.prompt import DECIDER_PROMPT, PROMPT, SQL_PROMPTS
 from langchain.prompts.base import BasePromptTemplate
 from langchain.schema import BaseLanguageModel
 from langchain.sql_database import SQLDatabase
@@ -28,7 +28,7 @@ class SQLDatabaseChain(Chain):
     """LLM wrapper to use."""
     database: SQLDatabase = Field(exclude=True)
     """SQL Database to connect to."""
-    prompt: BasePromptTemplate = PROMPT
+    prompt: Optional[BasePromptTemplate] = None
     """Prompt to use to translate natural language to SQL."""
     top_k: int = 5
     """Number of results to return from the query"""
@@ -65,8 +65,9 @@ class SQLDatabaseChain(Chain):
             return [self.output_key, "intermediate_steps"]
 
     def _call(self, inputs: Dict[str, Any]) -> Dict[str, Any]:
-        llm_chain = LLMChain(llm=self.llm, prompt=self.prompt)
-        input_text = f"{inputs[self.input_key]} \nSQLQuery:"
+        prompt = self.prompt or SQL_PROMPTS.get(self.database.dialect, PROMPT)
+        llm_chain = LLMChain(llm=self.llm, prompt=prompt)
+        input_text = f"{inputs[self.input_key]}\nSQLQuery:"
         self.callback_manager.on_text(input_text, verbose=self.verbose)
         # If not present, then defaults to None which is all tables.
         table_names_to_use = inputs.get("table_names_to_use")

langchain/chains/sql_database/prompt.py

@@ -2,6 +2,7 @@
 from langchain.output_parsers.list import CommaSeparatedListOutputParser
 from langchain.prompts.prompt import PromptTemplate
 
+
 _DEFAULT_TEMPLATE = """Given an input question, first create a syntactically correct {dialect} query to run, then look at the results of the query and return the answer. Unless the user specifies in his question a specific number of examples he wishes to obtain, always limit your query to at most {top_k} results. You can order the results by a relevant column to return the most interesting examples in the database.
 
 Never query for all the columns from a specific table, only ask for a the few relevant columns given the question.
@@ -38,3 +39,149 @@ DECIDER_PROMPT = PromptTemplate(
     template=_DECIDER_TEMPLATE,
     output_parser=CommaSeparatedListOutputParser(),
 )
+
+
+_mssql_prompt = """You are an MS SQL expert. Given an input question, first create a syntactically correct MS SQL query to run, then look at the results of the query and return the answer to the input question.
+Unless the user specifies in the question a specific number of examples to obtain, query for at most {top_k} results using the TOP clause as per MS SQL. You can order the results to return the most informative data in the database.
+Never query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in square brackets ([]) to denote them as delimited identifiers.
+Pay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.
+
+Use the following format:
+
+Question: "Question here"
+SQLQuery: "SQL Query to run"
+SQLResult: "Result of the SQLQuery"
+Answer: "Final answer here"
+
+Only use the following tables:
+{table_info}
+
+Question: {input}"""
+
+MSSQL_PROMPT = PromptTemplate(
+    input_variables=["input", "table_info", "top_k"], template=_mssql_prompt
+)
+
+
+_mysql_prompt = """You are a MySQL expert. Given an input question, first create a syntactically correct MySQL query to run, then look at the results of the query and return the answer to the input question.
+Unless the user specifies in the question a specific number of examples to obtain, query for at most {top_k} results using the LIMIT clause as per MySQL. You can order the results to return the most informative data in the database.
+Never query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in backticks (`) to denote them as delimited identifiers.
+Pay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.
+
+Use the following format:
+
+Question: "Question here"
+SQLQuery: "SQL Query to run"
+SQLResult: "Result of the SQLQuery"
+Answer: "Final answer here"
+
+Only use the following tables:
+{table_info}
+
+Question: {input}"""
+
+MYSQL_PROMPT = PromptTemplate(
+    input_variables=["input", "table_info", "top_k"],
+    template=_mysql_prompt,
+)
+
+
+_mariadb_prompt = """You are a MariaDB expert. Given an input question, first create a syntactically correct MariaDB query to run, then look at the results of the query and return the answer to the input question.
+Unless the user specifies in the question a specific number of examples to obtain, query for at most {top_k} results using the LIMIT clause as per MariaDB. You can order the results to return the most informative data in the database.
+Never query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in backticks (`) to denote them as delimited identifiers.
+Pay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.
+
+Use the following format:
+
+Question: "Question here"
+SQLQuery: "SQL Query to run"
+SQLResult: "Result of the SQLQuery"
+Answer: "Final answer here"
+
+Only use the following tables:
+{table_info}
+
+Question: {input}"""
+
+MARIADB_PROMPT = PromptTemplate(
+    input_variables=["input", "table_info", "top_k"],
+    template=_mariadb_prompt,
+)
+
+
+_oracle_prompt = """You are an Oracle SQL expert. Given an input question, first create a syntactically correct Oracle SQL query to run, then look at the results of the query and return the answer to the input question.
+Unless the user specifies in the question a specific number of examples to obtain, query for at most {top_k} results using the FETCH FIRST n ROWS ONLY clause as per Oracle SQL. You can order the results to return the most informative data in the database.
+Never query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in double quotes (") to denote them as delimited identifiers.
+Pay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.
+
+Use the following format:
+
+Question: "Question here"
+SQLQuery: "SQL Query to run"
+SQLResult: "Result of the SQLQuery"
+Answer: "Final answer here"
+
+Only use the following tables:
+{table_info}
+
+Question: {input}"""
+
+ORACLE_PROMPT = PromptTemplate(
+    input_variables=["input", "table_info", "top_k"],
+    template=_oracle_prompt,
+)
+
+
+_postgres_prompt = """You are a PostgreSQL expert. Given an input question, first create a syntactically correct PostgreSQL query to run, then look at the results of the query and return the answer to the input question.
+Unless the user specifies in the question a specific number of examples to obtain, query for at most {top_k} results using the LIMIT clause as per PostgreSQL. You can order the results to return the most informative data in the database.
+Never query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in double quotes (") to denote them as delimited identifiers.
+Pay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.
+
+Use the following format:
+
+Question: "Question here"
+SQLQuery: "SQL Query to run"
+SQLResult: "Result of the SQLQuery"
+Answer: "Final answer here"
+
+Only use the following tables:
+{table_info}
+
+Question: {input}"""
+
+POSTGRES_PROMPT = PromptTemplate(
+    input_variables=["input", "table_info", "top_k"], template=_postgres_prompt
+)
+
+
+_sqlite_prompt = """You are a SQLite expert. Given an input question, first create a syntactically correct SQLite query to run, then look at the results of the query and return the answer to the input question.
+Unless the user specifies in the question a specific number of examples to obtain, query for at most {top_k} results using the LIMIT clause as per SQLite. You can order the results to return the most informative data in the database.
+Never query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in double quotes (") to denote them as delimited identifiers.
+Pay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.
+
+Use the following format:
+
+Question: "Question here"
+SQLQuery: "SQL Query to run"
+SQLResult: "Result of the SQLQuery"
+Answer: "Final answer here"
+
+Only use the following tables:
+{table_info}
+
+Question: {input}"""
+
+SQLITE_PROMPT = PromptTemplate(
+    input_variables=["input", "table_info", "top_k"],
+    template=_sqlite_prompt,
+)
+
+
+SQL_PROMPTS = {
+    "mssql": MSSQL_PROMPT,
+    "mysql": MYSQL_PROMPT,
+    "mariadb": MARIADB_PROMPT,
+    "oracle": ORACLE_PROMPT,
+    "postgresql": POSTGRES_PROMPT,
+    "sqlite": SQLITE_PROMPT,
+}

langchain/chat_models/__init__.py

@@ -1,5 +1,6 @@
+from langchain.chat_models.anthropic import ChatAnthropic
 from langchain.chat_models.azure_openai import AzureChatOpenAI
 from langchain.chat_models.openai import ChatOpenAI
 from langchain.chat_models.promptlayer_openai import PromptLayerChatOpenAI
 
-__all__ = ["ChatOpenAI", "AzureChatOpenAI", "PromptLayerChatOpenAI"]
+__all__ = ["ChatOpenAI", "AzureChatOpenAI", "PromptLayerChatOpenAI", "ChatAnthropic"]

langchain/chat_models/anthropic.py

@@ -0,0 +1,139 @@
+from typing import Any, Dict, List, Optional
+
+from pydantic import Extra
+
+from langchain.chat_models.base import BaseChatModel
+from langchain.llms.anthropic import _AnthropicCommon
+from langchain.schema import (
+    AIMessage,
+    BaseMessage,
+    ChatGeneration,
+    ChatMessage,
+    ChatResult,
+    HumanMessage,
+    SystemMessage,
+)
+
+
+class ChatAnthropic(BaseChatModel, _AnthropicCommon):
+    r"""Wrapper around Anthropic's large language model.
+
+    To use, you should have the ``anthropic`` python package installed, and the
+    environment variable ``ANTHROPIC_API_KEY`` set with your API key, or pass
+    it as a named parameter to the constructor.
+
+    Example:
+        .. code-block:: python
+            import anthropic
+            from langchain.llms import Anthropic
+            model = ChatAnthropic(model="<model_name>", anthropic_api_key="my-api-key")
+    """
+
+    class Config:
+        """Configuration for this pydantic object."""
+
+        extra = Extra.forbid
+
+    @property
+    def _llm_type(self) -> str:
+        """Return type of chat model."""
+        return "anthropic-chat"
+
+    def _convert_one_message_to_text(self, message: BaseMessage) -> str:
+        if isinstance(message, ChatMessage):
+            message_text = f"\n\n{message.role.capitalize()}: {message.content}"
+        elif isinstance(message, HumanMessage):
+            message_text = f"{self.HUMAN_PROMPT} {message.content}"
+        elif isinstance(message, AIMessage):
+            message_text = f"{self.AI_PROMPT} {message.content}"
+        elif isinstance(message, SystemMessage):
+            message_text = f"{self.HUMAN_PROMPT} <admin>{message.content}</admin>"
+        else:
+            raise ValueError(f"Got unknown type {message}")
+        return message_text
+
+    def _convert_messages_to_text(self, messages: List[BaseMessage]) -> str:
+        """Format a list of strings into a single string with necessary newlines.
+
+        Args:
+            messages (List[BaseMessage]): List of BaseMessage to combine.
+
+        Returns:
+            str: Combined string with necessary newlines.
+        """
+        return "".join(
+            self._convert_one_message_to_text(message) for message in messages
+        )
+
+    def _convert_messages_to_prompt(self, messages: List[BaseMessage]) -> str:
+        """Format a list of messages into a full prompt for the Anthropic model
+
+        Args:
+            messages (List[BaseMessage]): List of BaseMessage to combine.
+
+        Returns:
+            str: Combined string with necessary HUMAN_PROMPT and AI_PROMPT tags.
+        """
+        if not self.AI_PROMPT:
+            raise NameError("Please ensure the anthropic package is loaded")
+
+        if not isinstance(messages[-1], AIMessage):
+            messages.append(AIMessage(content=""))
+        text = self._convert_messages_to_text(messages)
+        return (
+            text.rstrip()
+        )  # trim off the trailing ' ' that might come from the "Assistant: "
+
+    def _generate(
+        self, messages: List[BaseMessage], stop: Optional[List[str]] = None
+    ) -> ChatResult:
+        prompt = self._convert_messages_to_prompt(messages)
+        params: Dict[str, Any] = {"prompt": prompt, **self._default_params}
+        if stop:
+            params["stop_sequences"] = stop
+
+        if self.streaming:
+            completion = ""
+            stream_resp = self.client.completion_stream(**params)
+            for data in stream_resp:
+                delta = data["completion"][len(completion) :]
+                completion = data["completion"]
+                self.callback_manager.on_llm_new_token(
+                    delta,
+                    verbose=self.verbose,
+                )
+        else:
+            response = self.client.completion(**params)
+            completion = response["completion"]
+        message = AIMessage(content=completion)
+        return ChatResult(generations=[ChatGeneration(message=message)])
+
+    async def _agenerate(
+        self, messages: List[BaseMessage], stop: Optional[List[str]] = None
+    ) -> ChatResult:
+        prompt = self._convert_messages_to_prompt(messages)
+        params: Dict[str, Any] = {"prompt": prompt, **self._default_params}
+        if stop:
+            params["stop_sequences"] = stop
+
+        if self.streaming:
+            completion = ""
+            stream_resp = await self.client.acompletion_stream(**params)
+            async for data in stream_resp:
+                delta = data["completion"][len(completion) :]
+                completion = data["completion"]
+                if self.callback_manager.is_async:
+                    await self.callback_manager.on_llm_new_token(
+                        delta,
+                        verbose=self.verbose,
+                    )
+                else:
+                    self.callback_manager.on_llm_new_token(
+                        delta,
+                        verbose=self.verbose,
+                    )
+        else:
+            response = await self.client.acompletion(**params)
+            completion = response["completion"]
+        message = AIMessage(content=completion)
+        return ChatResult(generations=[ChatGeneration(message=message)])

langchain/chat_models/azure_openai.py

@@ -87,7 +87,7 @@ class AzureChatOpenAI(ChatOpenAI):
         except ImportError:
             raise ValueError(
                 "Could not import openai python package. "
-                "Please it install it with `pip install openai`."
+                "Please install it with `pip install openai`."
             )
         try:
             values["client"] = openai.ChatCompletion

langchain/chat_models/openai.py

@@ -32,8 +32,8 @@ logger = logging.getLogger(__file__)
 def _create_retry_decorator(llm: ChatOpenAI) -> Callable[[Any], Any]:
     import openai
 
-    min_seconds = 4
-    max_seconds = 10
+    min_seconds = 1
+    max_seconds = 60
     # Wait 2^x * 1 second between each retry starting with
     # 4 seconds, then up to 10 seconds, then 10 seconds afterwards
     return retry(
@@ -167,7 +167,7 @@ class ChatOpenAI(BaseChatModel):
         except ImportError:
             raise ValueError(
                 "Could not import openai python package. "
-                "Please it install it with `pip install openai`."
+                "Please install it with `pip install openai`."
             )
         try:
             values["client"] = openai.ChatCompletion
@@ -199,8 +199,8 @@ class ChatOpenAI(BaseChatModel):
     def _create_retry_decorator(self) -> Callable[[Any], Any]:
         import openai
 
-        min_seconds = 4
-        max_seconds = 10
+        min_seconds = 1
+        max_seconds = 60
         # Wait 2^x * 1 second between each retry starting with
         # 4 seconds, then up to 10 seconds, then 10 seconds afterwards
         return retry(
@@ -327,8 +327,8 @@ class ChatOpenAI(BaseChatModel):
 
     def get_num_tokens(self, text: str) -> int:
         """Calculate num tokens with tiktoken package."""
-        # tiktoken NOT supported for Python 3.8 or below
-        if sys.version_info[1] <= 8:
+        # tiktoken NOT supported for Python 3.7 or below
+        if sys.version_info[1] <= 7:
             return super().get_num_tokens(text)
         try:
             import tiktoken
@@ -336,7 +336,7 @@ class ChatOpenAI(BaseChatModel):
             raise ValueError(
                 "Could not import tiktoken python package. "
                 "This is needed in order to calculate get_num_tokens. "
-                "Please it install it with `pip install tiktoken`."
+                "Please install it with `pip install tiktoken`."
             )
         # create a GPT-3.5-Turbo encoder instance
         enc = tiktoken.encoding_for_model(self.model_name)
@@ -358,7 +358,7 @@ class ChatOpenAI(BaseChatModel):
             raise ValueError(
                 "Could not import tiktoken python package. "
                 "This is needed in order to calculate get_num_tokens. "
-                "Please it install it with `pip install tiktoken`."
+                "Please install it with `pip install tiktoken`."
             )
 
         model = self.model_name

langchain/document_loaders/__init__.py

@@ -10,6 +10,7 @@ from langchain.document_loaders.azure_blob_storage_file import (
     AzureBlobStorageFileLoader,
 )
 from langchain.document_loaders.bigquery import BigQueryLoader
+from langchain.document_loaders.bilibili import BiliBiliLoader
 from langchain.document_loaders.blackboard import BlackboardLoader
 from langchain.document_loaders.college_confidential import CollegeConfidentialLoader
 from langchain.document_loaders.conllu import CoNLLULoader
@@ -26,6 +27,7 @@ from langchain.document_loaders.evernote import EverNoteLoader
 from langchain.document_loaders.facebook_chat import FacebookChatLoader
 from langchain.document_loaders.gcs_directory import GCSDirectoryLoader
 from langchain.document_loaders.gcs_file import GCSFileLoader
+from langchain.document_loaders.git import GitLoader
 from langchain.document_loaders.gitbook import GitbookLoader
 from langchain.document_loaders.googledrive import GoogleDriveLoader
 from langchain.document_loaders.gutenberg import GutenbergLoader
@@ -43,6 +45,7 @@ from langchain.document_loaders.obsidian import ObsidianLoader
 from langchain.document_loaders.pdf import (
     OnlinePDFLoader,
     PDFMinerLoader,
+    PDFMinerPDFasHTMLLoader,
     PyMuPDFLoader,
     PyPDFLoader,
     UnstructuredPDFLoader,
@@ -53,6 +56,7 @@ from langchain.document_loaders.roam import RoamLoader
 from langchain.document_loaders.s3_directory import S3DirectoryLoader
 from langchain.document_loaders.s3_file import S3FileLoader
 from langchain.document_loaders.sitemap import SitemapLoader
+from langchain.document_loaders.slack_directory import SlackDirectoryLoader
 from langchain.document_loaders.srt import SRTLoader
 from langchain.document_loaders.telegram import TelegramChatLoader
 from langchain.document_loaders.text import TextLoader
@@ -61,6 +65,7 @@ from langchain.document_loaders.unstructured import (
     UnstructuredFileLoader,
 )
 from langchain.document_loaders.url import UnstructuredURLLoader
+from langchain.document_loaders.url_playwright import PlaywrightURLLoader
 from langchain.document_loaders.url_selenium import SeleniumURLLoader
 from langchain.document_loaders.web_base import WebBaseLoader
 from langchain.document_loaders.whatsapp_chat import WhatsAppChatLoader
@@ -79,6 +84,7 @@ __all__ = [
     "UnstructuredFileIOLoader",
     "UnstructuredURLLoader",
     "SeleniumURLLoader",
+    "PlaywrightURLLoader",
     "DirectoryLoader",
     "NotionDirectoryLoader",
     "NotionDBLoader",
@@ -116,6 +122,7 @@ __all__ = [
     "AirbyteJSONLoader",
     "OnlinePDFLoader",
     "PDFMinerLoader",
+    "PDFMinerPDFasHTMLLoader",
     "PyMuPDFLoader",
     "TelegramChatLoader",
     "SRTLoader",
@@ -134,4 +141,7 @@ __all__ = [
     "SitemapLoader",
     "DuckDBLoader",
     "BigQueryLoader",
+    "BiliBiliLoader",
+    "SlackDirectoryLoader",
+    "GitLoader",
 ]