bump version (#1057)

* Support a callback `on_llm_new_token` that users can implement when
`OpenAI.streaming` is set to `True`

.coveragerc

@@ -1,2 +0,0 @@
-[run]
-omit = tests/*

.github/workflows/test.yml

@@ -31,4 +31,4 @@ jobs:
         run: poetry install
       - name: Run unit tests
         run: |
-          make tests
+          make test

CITATION.cff

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

CONTRIBUTING.md

@@ -47,7 +47,7 @@ good code into the codebase.
 ### 🏭Release process
 
 As of now, LangChain has an ad hoc release process: releases are cut with high frequency via by
-a developer and published to [PyPI](https://pypi.org/project/ruff/).
+a developer and published to [PyPI](https://pypi.org/project/langchain/).
 
 LangChain follows the [semver](https://semver.org/) versioning standard. However, as pre-1.0 software,
 even patch releases may contain [non-backwards-compatible changes](https://semver.org/#spec-item-4).
@@ -77,6 +77,8 @@ Now, you should be able to run the common tasks in the following section.
 
 ## ✅Common Tasks
 
+Type `make` for a list of common tasks.
+
 ### Code Formatting
 
 Formatting for this project is done via a combination of [Black](https://black.readthedocs.io/en/stable/) and [isort](https://pycqa.github.io/isort/).
@@ -116,7 +118,7 @@ Unit tests cover modular logic that does not require calls to outside APIs.
 To run unit tests:
 
 ```bash
-make tests
+make test
 ```
 
 If you add new logic, please add a unit test.

Makefile

@@ -1,11 +1,15 @@
-.PHONY: format lint tests tests_watch integration_tests
+.PHONY: all clean format lint test test_watch integration_tests help
 
+all: help
+	
 coverage:
 	poetry run pytest --cov \
 		--cov-config=.coveragerc \
 		--cov-report xml \
 		--cov-report term-missing:skip-covered
 
+clean: docs_clean
+
 docs_build:
 	cd docs && poetry run make html
 
@@ -25,11 +29,26 @@ lint:
 	poetry run isort . --check
 	poetry run flake8 .
 
+test:
+	poetry run pytest tests/unit_tests
+
 tests:
 	poetry run pytest tests/unit_tests
 
-tests_watch:
+test_watch:
 	poetry run ptw --now . -- tests/unit_tests
 
 integration_tests:
 	poetry run pytest tests/integration_tests
+
+help:
+	@echo '----'
+	@echo 'coverage            - run unit tests and generate coverage report'
+	@echo 'docs_build          - build the documentation'
+	@echo 'docs_clean          - clean the documentation build artifacts'
+	@echo 'docs_linkcheck      - run linkchecker on the documentation'
+	@echo 'format              - run code formatters'
+	@echo 'lint                - run linters'
+	@echo 'test                - run unit tests'
+	@echo 'test_watch          - run unit tests in watch mode'
+	@echo 'integration_tests   - run integration tests'

README.md

@@ -4,6 +4,9 @@
 
 [![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)
 
+**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.
+
 ## Quick Install
 
 `pip install langchain`
@@ -15,7 +18,22 @@ developers to build applications that they previously could not.
 But using these LLMs in isolation is often not enough to
 create a truly powerful app - the real power comes when you can combine them with other sources of computation or knowledge.
 
-This library is aimed at assisting in the development of those types of applications.
+This library is aimed at assisting in the development of those types of applications. Common examples of these types of applications include:
+
+**❓ Question Answering over specific documents**
+
+- [Documentation](https://langchain.readthedocs.io/en/latest/use_cases/question_answering.html)
+- End-to-end Example: [Question Answering over Notion Database](https://github.com/hwchase17/notion-qa)
+
+**💬 Chatbots**
+
+- [Documentation](https://langchain.readthedocs.io/en/latest/use_cases/chatbots.html)
+- End-to-end Example: [Chat-LangChain](https://github.com/hwchase17/chat-langchain)
+
+**🤖 Agents**
+
+- [Documentation](https://langchain.readthedocs.io/en/latest/use_cases/agents.html)
+- End-to-end Example: [GPT+WolframAlpha](https://huggingface.co/spaces/JavaFXpert/Chat-GPT-LangChain)
 
 ## 📖 Documentation
 

docs/deployments.md

@@ -22,3 +22,18 @@ This repo serves as a template for how deploy a LangChain with Gradio.
 It implements a chatbot interface, with a "Bring-Your-Own-Token" approach (nice for not wracking up big bills).
 It also contains instructions for how to deploy this app on the Hugging Face platform.
 This is heavily influenced by James Weaver's [excellent examples](https://huggingface.co/JavaFXpert).
+
+## [Beam](https://github.com/slai-labs/get-beam/tree/main/examples/langchain-question-answering)
+
+This repo serves as a template for how deploy a LangChain with [Beam](https://beam.cloud).
+
+It implements a Question Answering app and contains instructions for deploying the app as a serverless REST API.
+
+## [Vercel](https://github.com/homanp/vercel-langchain)
+
+A minimal example on how to run LangChain on Vercel using Flask.
+
+
+## [SteamShip](https://github.com/steamship-core/steamship-langchain/)
+This repository contains LangChain adapters for Steamship, enabling LangChain developers to rapidly deploy their apps on Steamship.
+This includes: production ready endpoints, horizontal scaling across dependencies, persistant storage of app state, multi-tenancy support, etc.

docs/ecosystem/cerebriumai.md

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

docs/ecosystem/chroma.md

@@ -0,0 +1,20 @@
+# Chroma
+
+This page covers how to use the Chroma ecosystem within LangChain.
+It is broken into two parts: installation and setup, and then references to specific Chroma wrappers.
+
+## Installation and Setup
+- Install the Python package with `pip install chromadb`
+## Wrappers
+
+### VectorStore
+
+There exists a wrapper around Chroma vector databases, allowing you to use it as a vectorstore,
+whether for semantic search or example selection.
+
+To import this vectorstore:
+```python
+from langchain.vectorstores import Chroma
+```
+
+For a more detailed walkthrough of the Chroma wrapper, see [this notebook](../modules/utils/combine_docs_examples/vectorstores.ipynb)

docs/ecosystem/forefrontai.md

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

docs/ecosystem/google_search.md

@@ -1,7 +1,7 @@
 # Google Search Wrapper
 
 This page covers how to use the Google Search API within LangChain.
-It is broken into two parts: installation and setup, and then references to specific Pinecone wrappers.
+It is broken into two parts: installation and setup, and then references to the specific Google Search wrapper.
 
 ## Installation and Setup
 - Install requirements with `pip install google-api-python-client`

docs/ecosystem/gooseai.md

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

docs/ecosystem/helicone.md

@@ -0,0 +1,21 @@
+# Helicone
+
+This page covers how to use the [Helicone](https://helicone.ai) within LangChain.
+
+## What is Helicone?
+
+Helicone is an [open source](https://github.com/Helicone/helicone) observability platform that proxies your OpenAI traffic and provides you key insights into your spend, latency and usage.
+
+![Helicone](../_static/HeliconeDashboard.png)
+
+## Quick start
+
+With your LangChain environment you can just add the following parameter.
+
+```bash
+export OPENAI_API_BASE="https://oai.hconeai.com/v1"
+```
+
+Now head over to [helicone.ai](https://helicone.ai/onboarding?step=2) to create your account, and add your OpenAI API key within our dashboard to view your logs.
+
+![Helicone](../_static/HeliconeKeys.png)

docs/ecosystem/petals.md

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

docs/ecosystem/promptlayer.md

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

docs/ecosystem/serpapi.md

@@ -1,7 +1,7 @@
 # SerpAPI
 
 This page covers how to use the SerpAPI search APIs within LangChain.
-It is broken into two parts: installation and setup, and then references to specific Pinecone wrappers.
+It is broken into two parts: installation and setup, and then references to the specific SerpAPI wrapper.
 
 ## Installation and Setup
 - Install requirements with `pip install google-search-results`

docs/gallery.rst

@@ -77,6 +77,17 @@ Open Source
 
     +++
 
+    A jupyter notebook demonstrating how you could create a semantic search engine on documents in one of your Google Folders
+
+    ---
+
+    .. link-button:: https://github.com/venuv/langchain_semantic_search
+        :type: url
+        :text: Google Folder Semantic Search
+        :classes: stretched-link btn-lg
+
+    +++
+
     Build a GitHub support bot with GPT3, LangChain, and Python.
 
     ---
@@ -188,6 +199,17 @@ Open Source
     +++
 
     This repo is a simple demonstration of using LangChain to do fact-checking with prompt chaining.
+    
+    ---
+
+    .. link-button:: https://github.com/arc53/docsgpt
+        :type: url
+        :text: DocsGPT
+        :classes: stretched-link btn-lg
+    
+    +++
+
+    Answer questions about the documentation of any project    
 
 Misc. Colab Notebooks
 ~~~~~~~~~~~~~~~

docs/getting_started/getting_started.md

@@ -162,7 +162,7 @@ This is one of the simpler types of chains, but understanding how it works will
 
 `````{dropdown} Agents: Dynamically call chains based on user input
 
-So for the chains we've looked at run in a predetermined order.
+So far the chains we've looked at run in a predetermined order.
 
 Agents no longer do: they use an LLM to determine which actions to take and in what order. An action can either be using a tool and observing its output, or returning to the user.
 
@@ -179,6 +179,20 @@ In order to load agents, you should understand the following concepts:
 
 **Tools**: For a list of predefined tools and their specifications, see [here](../modules/agents/tools.md).
 
+For this example, you will also need to install the SerpAPI Python package.
+
+```bash
+pip install google-search-results
+```
+
+And set the appropriate environment variables.
+
+```python
+import os
+os.environ["SERPAPI_API_KEY"] = "..."
+```
+
+Now we can get started!
 
 ```python
 from langchain.agents import load_tools

docs/index.rst

@@ -7,7 +7,22 @@ But using these LLMs in isolation is often not enough to
 create a truly powerful app - the real power comes when you are able to
 combine them with other sources of computation or knowledge.
 
-This library is aimed at assisting in the development of those types of applications.
+This library is aimed at assisting in the development of those types of applications. Common examples of these types of applications include:
+
+**❓ Question Answering over specific documents**
+
+- `Documentation <./use_cases/question_answering.html>`_
+- End-to-end Example: `Question Answering over Notion Database <https://github.com/hwchase17/notion-qa>`_
+
+**💬 Chatbots**
+
+- `Documentation <./use_cases/chatbots.html>`_
+- End-to-end Example: `Chat-LangChain <https://github.com/hwchase17/chat-langchain>`_
+
+**🤖 Agents**
+
+- `Documentation <./use_cases/agents.html>`_
+- End-to-end Example: `GPT+WolframAlpha <https://huggingface.co/spaces/JavaFXpert/Chat-GPT-LangChain>`_
 
 Getting Started
 ----------------
@@ -36,6 +51,8 @@ These modules are, in increasing order of complexity:
 
 - `LLMs <./modules/llms.html>`_: This includes a generic interface for all LLMs, and common utilities for working with LLMs.
 
+- `Document Loaders <./modules/document_loaders.html>`_: This includes a standard interface for loading documents, as well as specific integrations to all types of text data sources.
+
 - `Utils <./modules/utils.html>`_: Language models are often more powerful when interacting with other sources of knowledge or computation. This can include Python REPLs, embeddings, search engines, and more. LangChain provides a large collection of common utils to use in your application.
 
 - `Chains <./modules/chains.html>`_: Chains go beyond just a single LLM call, and are sequences of calls (whether to an LLM or a different utility). LangChain provides a standard interface for chains, lots of integrations with other tools, and end-to-end chains for common applications.
@@ -53,6 +70,7 @@ These modules are, in increasing order of complexity:
 
    ./modules/prompts.md
    ./modules/llms.md
+   ./modules/document_loaders.md
    ./modules/utils.md
    ./modules/chains.md
    ./modules/agents.md
@@ -137,6 +155,8 @@ Additional Resources
 
 Additional collection of resources we think may be useful as you develop your application!
 
+- `LangChainHub <https://github.com/hwchase17/langchain-hub>`_: The LangChainHub is a place to share and explore other prompts, chains, and agents.
+
 - `Glossary <./glossary.html>`_: A glossary of all related terms, papers, methods, etc. Whether implemented in LangChain or not!
 
 - `Gallery <./gallery.html>`_: A collection of our favorite projects that use LangChain. Useful for finding inspiration or seeing how things were done in other applications.
@@ -145,6 +165,10 @@ Additional collection of resources we think may be useful as you develop your ap
 
 - `Discord <https://discord.gg/6adMQxSpJS>`_: Join us on our Discord to discuss all things LangChain!
 
+- `Tracing <./tracing.html>`_: A guide on using tracing in LangChain to visualize the execution of chains and agents.
+
+- `Production Support <https://forms.gle/57d8AmXBYp8PP8tZA>`_: As you move your LangChains into production, we'd love to offer more comprehensive support. Please fill out this form and we'll set up a dedicated support Slack channel.
+
 
 .. toctree::
    :maxdepth: 1
@@ -152,6 +176,10 @@ Additional collection of resources we think may be useful as you develop your ap
    :name: resources
    :hidden:
 
+   LangChainHub <https://github.com/hwchase17/langchain-hub>
    ./glossary.md
    ./gallery.rst
    ./deployments.md
+   ./tracing.md
+   Discord <https://discord.gg/6adMQxSpJS>
+   Production Support <https://forms.gle/57d8AmXBYp8PP8tZA>

docs/modules/agents/examples/async_agent.ipynb

@@ -0,0 +1,423 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "6fb92deb-d89e-439b-855d-c7f2607d794b",
+   "metadata": {},
+   "source": [
+    "# Async API for Agent\n",
+    "\n",
+    "LangChain provides async support for Agents by leveraging the [asyncio](https://docs.python.org/3/library/asyncio.html) library.\n",
+    "\n",
+    "Async methods are currently supported for the following `Tools`: [`SerpAPIWrapper`](https://github.com/hwchase17/langchain/blob/master/langchain/serpapi.py) and [`LLMMathChain`](https://github.com/hwchase17/langchain/blob/master/langchain/chains/llm_math/base.py). Async support for other agent tools are on the roadmap.\n",
+    "\n",
+    "For `Tool`s that have a `coroutine` implemented (the two mentioned above), the `AgentExecutor` will `await` them directly. Otherwise, the `AgentExecutor` will call the `Tool`'s `func` via `asyncio.get_event_loop().run_in_executor` to avoid blocking the main runloop.\n",
+    "\n",
+    "You can use `arun` to call an `AgentExecutor` asynchronously."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "97800378-cc34-4283-9bd0-43f336bc914c",
+   "metadata": {},
+   "source": [
+    "## Serial vs. Concurrent Execution\n",
+    "\n",
+    "In this example, we kick off agents to answer some questions serially vs. concurrently. You can see that concurrent execution significantly speeds this up."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "da5df06c-af6f-4572-b9f5-0ab971c16487",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import asyncio\n",
+    "import time\n",
+    "\n",
+    "from langchain.agents import initialize_agent, load_tools\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.callbacks.stdout import StdOutCallbackHandler\n",
+    "from langchain.callbacks.base import CallbackManager\n",
+    "from langchain.callbacks.tracers import LangChainTracer\n",
+    "from aiohttp import ClientSession\n",
+    "\n",
+    "questions = [\n",
+    "    \"Who won the US Open men's final in 2019? What is his age raised to the 0.334 power?\",\n",
+    "    \"Who is Olivia Wilde's boyfriend? What is his current age raised to the 0.23 power?\",\n",
+    "    \"Who won the most recent formula 1 grand prix? What is their age raised to the 0.23 power?\",\n",
+    "    \"Who won the US Open women's final in 2019? What is her age raised to the 0.34 power?\",\n",
+    "    \"Who is Beyonce's husband? What is his age raised to the 0.19 power?\"\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "fd4c294e-b1d6-44b8-b32e-2765c017e503",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I need to find out who won the US Open men's final in 2019 and then calculate his age raised to the 0.334 power.\n",
+      "Action: Search\n",
+      "Action Input: \"US Open men's final 2019 winner\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mRafael Nadal\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to find out Rafael Nadal's age\n",
+      "Action: Search\n",
+      "Action Input: \"Rafael Nadal age\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3m36 years\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to calculate 36 raised to the 0.334 power\n",
+      "Action: Calculator\n",
+      "Action Input: 36^0.334\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 3.3098250249682484\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m 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.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I need to find out who Olivia Wilde's boyfriend is and then calculate his age raised to the 0.23 power.\n",
+      "Action: Search\n",
+      "Action Input: \"Olivia Wilde boyfriend\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mJason Sudeikis\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to find out Jason Sudeikis' age\n",
+      "Action: Search\n",
+      "Action Input: \"Jason Sudeikis age\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mDaniel Jason Sudeikis is an American actor, comedian, writer, and producer. In the 1990s, he began his career in improv comedy and performed with ComedySportz, iO Chicago, and The Second City.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to find out Jason Sudeikis' exact age\n",
+      "Action: Search\n",
+      "Action Input: \"Jason Sudeikis age exact\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mDaniel Jason Sudeikis. (1975-09-18) September 18, 1975 (age 47). Fairfax, Virginia, U.S. · Fort Scott Community College · Actor; comedian; producer; writer · 1997– ...\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now have the information I need to calculate the age raised to the 0.23 power\n",
+      "Action: Calculator\n",
+      "Action Input: 47^0.23\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.4242784855673896\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: Jason Sudeikis, Olivia Wilde's boyfriend, is 47 years old and his age raised to the 0.23 power is 2.4242784855673896.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I need to find out who won the grand prix and then calculate their age raised to the 0.23 power.\n",
+      "Action: Search\n",
+      "Action Input: \"Formula 1 Grand Prix Winner\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mMax Emilian Verstappen is a Belgian-Dutch racing driver and the 2021 and 2022 Formula One World Champion. He competes under the Dutch flag in Formula One with Red Bull Racing. Verstappen is the son of racing drivers Jos Verstappen, who also competed in Formula One, and Sophie Kumpen.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to find out Max Emilian Verstappen's age.\n",
+      "Action: Search\n",
+      "Action Input: \"Max Emilian Verstappen age\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3m25 years\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now need to calculate 25 raised to the 0.23 power.\n",
+      "Action: Calculator\n",
+      "Action Input: 25^0.23\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.096651272316035\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: Max Emilian Verstappen, who is 25 years old, won the most recent Formula 1 Grand Prix and his age raised to the 0.23 power is 2.096651272316035.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I need to find out who won the US Open women's final in 2019 and then calculate her age raised to the 0.34 power.\n",
+      "Action: Search\n",
+      "Action Input: \"US Open women's final 2019 winner\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mBianca Andreescu defeated Serena Williams in the final, 6–3, 7–5 to win the women's singles tennis title at the 2019 US Open. It was her first major title, and she became the first Canadian, as well as the first player born in the 2000s, to win a major singles title.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to find out Bianca Andreescu's age.\n",
+      "Action: Search\n",
+      "Action Input: \"Bianca Andreescu age\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mBianca Vanessa Andreescu is a Canadian-Romanian professional tennis player. She has a career-high ranking of No. 4 in the world, and is the highest-ranked Canadian in the history of the Women's Tennis Association.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the age of Bianca Andreescu.\n",
+      "Action: Calculator\n",
+      "Action Input: 19^0.34\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.7212987634680084\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: Bianca Andreescu, aged 19, won the US Open women's final in 2019. Her age raised to the 0.34 power is 2.7212987634680084.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I need to find out who Beyonce's husband is and then calculate his age raised to the 0.19 power.\n",
+      "Action: Search\n",
+      "Action Input: \"Who is Beyonce's husband?\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mJay-Z\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to find out Jay-Z's age\n",
+      "Action: Search\n",
+      "Action Input: \"How old is Jay-Z?\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3m53 years\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to calculate 53 raised to the 0.19 power\n",
+      "Action: Calculator\n",
+      "Action Input: 53^0.19\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.12624064206896\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: Jay-Z is Beyonce's husband and his age raised to the 0.19 power is 2.12624064206896.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "Serial executed in 94.83 seconds.\n"
+     ]
+    }
+   ],
+   "source": [
+    "def generate_serially():\n",
+    "    for q in questions:\n",
+    "        llm = OpenAI(temperature=0)\n",
+    "        tools = load_tools([\"llm-math\", \"serpapi\"], llm=llm)\n",
+    "        agent = initialize_agent(\n",
+    "            tools, llm, agent=\"zero-shot-react-description\", verbose=True\n",
+    "        )\n",
+    "        agent.run(q)\n",
+    "\n",
+    "s = time.perf_counter()\n",
+    "generate_serially()\n",
+    "elapsed = time.perf_counter() - s\n",
+    "print(f\"Serial executed in {elapsed:0.2f} seconds.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "076d7b85-45ec-465d-8b31-c2ad119c3438",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[33;1m\u001b[1;3m I need to find out who Beyonce's husband is and then calculate his age raised to the 0.19 power.\n",
+      "Action: Search\n",
+      "Action Input: \"Who is Beyonce's husband?\"\u001b[0m\u001b[31;1m\u001b[1;3m I need to find out who won the grand prix and then calculate their age raised to the 0.23 power.\n",
+      "Action: Search\n",
+      "Action Input: \"Formula 1 Grand Prix Winner\"\u001b[0m\u001b[32;1m\u001b[1;3m I need to find out who Olivia Wilde's boyfriend is and then calculate his age raised to the 0.23 power.\n",
+      "Action: Search\n",
+      "Action Input: \"Olivia Wilde boyfriend\"\u001b[0m\u001b[38;5;200m\u001b[1;3m I need to find out who won the US Open women's final in 2019 and then calculate her age raised to the 0.34 power.\n",
+      "Action: Search\n",
+      "Action Input: \"US Open women's final 2019 winner\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mJay-Z\u001b[0m\n",
+      "Thought:\n",
+      "Observation: \u001b[33;1m\u001b[1;3mMax Emilian Verstappen is a Belgian-Dutch racing driver and the 2021 and 2022 Formula One World Champion. He competes under the Dutch flag in Formula One with Red Bull Racing. Verstappen is the son of racing drivers Jos Verstappen, who also competed in Formula One, and Sophie Kumpen.\u001b[0m\n",
+      "Thought:\n",
+      "Observation: \u001b[33;1m\u001b[1;3mJason Sudeikis\u001b[0m\n",
+      "Thought:\n",
+      "Observation: \u001b[33;1m\u001b[1;3mBianca Andreescu defeated Serena Williams in the final, 6–3, 7–5 to win the women's singles tennis title at the 2019 US Open. It was her first major title, and she became the first Canadian, as well as the first player born in the 2000s, to win a major singles title.\u001b[0m\n",
+      "Thought:\u001b[31;1m\u001b[1;3m I need to find out Max Emilian Verstappen's age.\n",
+      "Action: Search\n",
+      "Action Input: \"Max Emilian Verstappen age\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3m25 years\u001b[0m\n",
+      "Thought:\u001b[38;5;200m\u001b[1;3m I need to find out Bianca Andreescu's age.\n",
+      "Action: Search\n",
+      "Action Input: \"Bianca Andreescu age\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mBianca Vanessa Andreescu is a Canadian-Romanian professional tennis player. She has a career-high ranking of No. 4 in the world, and is the highest-ranked Canadian in the history of the Women's Tennis Association.\u001b[0m\n",
+      "Thought:\u001b[36;1m\u001b[1;3m 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.\n",
+      "Action: Search\n",
+      "Action Input: \"US Open men's final 2019 winner\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mRafael Nadal\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to find out Jason Sudeikis' age\n",
+      "Action: Search\n",
+      "Action Input: \"Jason Sudeikis age\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mDaniel Jason Sudeikis is an American actor, comedian, writer, and producer. In the 1990s, he began his career in improv comedy and performed with ComedySportz, iO Chicago, and The Second City.\u001b[0m\n",
+      "Thought:\u001b[33;1m\u001b[1;3m I need to find out Jay-Z's age\n",
+      "Action: Search\n",
+      "Action Input: \"How old is Jay-Z?\"\u001b[0m\u001b[36;1m\u001b[1;3m I need to find out Rafael Nadal's age\n",
+      "Action: Search\n",
+      "Action Input: \"Rafael Nadal age\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3m36 years\u001b[0m\n",
+      "Thought:\n",
+      "Observation: \u001b[33;1m\u001b[1;3m53 years\u001b[0m\n",
+      "Thought:\u001b[38;5;200m\u001b[1;3m I now know the age of Bianca Andreescu.\n",
+      "Action: Calculator\n",
+      "Action Input: 19^0.34\u001b[0m\u001b[31;1m\u001b[1;3m I now need to calculate 25 raised to the 0.23 power.\n",
+      "Action: Calculator\n",
+      "Action Input: 25^0.23\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.7212987634680084\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to find out Jason Sudeikis' exact age\n",
+      "Action: Search\n",
+      "Action Input: \"Jason Sudeikis age exact\"\u001b[0m\u001b[33;1m\u001b[1;3m I need to calculate 53 raised to the 0.19 power\n",
+      "Action: Calculator\n",
+      "Action Input: 53^0.19\u001b[0m\u001b[36;1m\u001b[1;3m I need to calculate 36 raised to the 0.334 power\n",
+      "Action: Calculator\n",
+      "Action Input: 36^0.334\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mDaniel Jason Sudeikis. (1975-09-18) September 18, 1975 (age 47). Fairfax, Virginia, U.S. · Fort Scott Community College · Actor; comedian; producer; writer · 1997– ...\u001b[0m\n",
+      "Thought:\n",
+      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.096651272316035\n",
+      "\u001b[0m\n",
+      "Thought:\n",
+      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.12624064206896\n",
+      "\u001b[0m\n",
+      "Thought:\n",
+      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 3.3098250249682484\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now have the information I need to calculate the age raised to the 0.23 power\n",
+      "Action: Calculator\n",
+      "Action Input: 47^0.23\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.4242784855673896\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: Bianca Andreescu, aged 19, won the US Open women's final in 2019. Her age raised to the 0.34 power is 2.7212987634680084.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: Jay-Z is Beyonce's husband and his age raised to the 0.19 power is 2.12624064206896.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m 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.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: Jason Sudeikis, Olivia Wilde's boyfriend, is 47 years old and his age raised to the 0.23 power is 2.4242784855673896.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: Max Emilian Verstappen, who is 25 years old, won the most recent Formula 1 Grand Prix and his age raised to the 0.23 power is 2.096651272316035.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "Concurrent executed in 25.06 seconds.\n"
+     ]
+    }
+   ],
+   "source": [
+    "async def generate_concurrently():\n",
+    "    agents = []\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",
+    "    colors = [\"blue\", \"green\", \"red\", \"pink\", \"yellow\"]\n",
+    "    for color in colors:\n",
+    "        # Use a custom CallbackManager to print in different colors.\n",
+    "        manager = CallbackManager([StdOutCallbackHandler(color=color)])\n",
+    "        llm = OpenAI(temperature=0, callback_manager=manager)\n",
+    "        async_tools = load_tools([\"llm-math\", \"serpapi\"], llm=llm, aiosession=aiosession)\n",
+    "        agents.append(\n",
+    "            initialize_agent(async_tools, llm, agent=\"zero-shot-react-description\", verbose=True, callback_manager=manager)\n",
+    "        )\n",
+    "    tasks = [async_agent.arun(q) for async_agent, q in zip(agents, questions)]\n",
+    "    await asyncio.gather(*tasks)\n",
+    "    await aiosession.close()\n",
+    "\n",
+    "s = time.perf_counter()\n",
+    "# If running this outside of Jupyter, use asyncio.run(generate_concurrently())\n",
+    "await generate_concurrently()\n",
+    "elapsed = time.perf_counter() - s\n",
+    "print(f\"Concurrent executed in {elapsed:0.2f} seconds.\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "97ef285c-4a43-4a4e-9698-cd52a1bc56c9",
+   "metadata": {},
+   "source": [
+    "## Using Tracing with Asynchronous Agents\n",
+    "\n",
+    "To use tracing with async agents, you must pass in a custom `CallbackManager` with `LangChainTracer` to each agent running asynchronously. This way, you avoid collisions while the trace is being collected."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "44bda05a-d33e-4e91-9a71-a0f3f96aae95",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I need to find out who won the US Open men's final in 2019 and then calculate his age raised to the 0.334 power.\n",
+      "Action: Search\n",
+      "Action Input: \"US Open men's final 2019 winner\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mRafael Nadal\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to find out Rafael Nadal's age\n",
+      "Action: Search\n",
+      "Action Input: \"Rafael Nadal age\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3m36 years\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to calculate 36 raised to the 0.334 power\n",
+      "Action: Calculator\n",
+      "Action Input: 36^0.334\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 3.3098250249682484\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m 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.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "# 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",
+    "tracer = LangChainTracer()\n",
+    "tracer.load_default_session()\n",
+    "manager = CallbackManager([StdOutCallbackHandler(), tracer])\n",
+    "\n",
+    "# Pass the manager into the llm if you want llm calls traced.\n",
+    "llm = OpenAI(temperature=0, callback_manager=manager)\n",
+    "\n",
+    "async_tools = load_tools([\"llm-math\", \"serpapi\"], llm=llm, aiosession=aiosession)\n",
+    "async_agent = initialize_agent(async_tools, llm, agent=\"zero-shot-react-description\", verbose=True, callback_manager=manager)\n",
+    "await async_agent.arun(questions[0])\n",
+    "await aiosession.close()"
+   ]
+  }
+ ],
+ "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/agents/examples/custom_agent.ipynb

@@ -53,7 +53,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 2,
    "id": "becda2a1",
    "metadata": {},
    "outputs": [],
@@ -70,7 +70,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 3,
    "id": "339b1bb8",
    "metadata": {},
    "outputs": [],
@@ -99,7 +99,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 4,
    "id": "e21d2098",
    "metadata": {},
    "outputs": [
@@ -133,9 +133,19 @@
     "print(prompt.template)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "5e028e6d",
+   "metadata": {},
+   "source": [
+    "Note that we are able to feed agents a self-defined prompt template, i.e. not restricted to the prompt generated by the `create_prompt` function, assuming it meets the agent's requirements. \n",
+    "\n",
+    "For example, for `ZeroShotAgent`, we will need to ensure that it meets the following requirements. There should a string starting with \"Action:\" and a following string starting with \"Action Input:\", and both should be separated by a newline.\n"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 5,
    "id": "9b1cc2a2",
    "metadata": {},
    "outputs": [],
@@ -145,17 +155,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 7,
    "id": "e4f5092f",
    "metadata": {},
    "outputs": [],
    "source": [
-    "agent = ZeroShotAgent(llm_chain=llm_chain, tools=tools)"
+    "tool_names = [tool.name for tool in tools]\n",
+    "agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 8,
    "id": "490604e9",
    "metadata": {},
    "outputs": [],
@@ -165,7 +176,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 9,
    "id": "653b1617",
    "metadata": {},
    "outputs": [
@@ -180,22 +191,23 @@
       "Action: Search\n",
       "Action Input: Population of Canada\u001b[0m\n",
       "Observation: \u001b[36;1m\u001b[1;3mCanada is a country in North America. Its ten provinces and three territories extend from the Atlantic Ocean to the Pacific Ocean and northward into the Arctic Ocean, covering over 9.98 million square kilometres, making it the world's second-largest country by total area.\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I need to find out the exact population of Canada\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to find out the population of Canada\n",
       "Action: Search\n",
-      "Action Input: Population of Canada 2020\u001b[0m\n",
+      "Action Input: Population of Canada\u001b[0m\n",
       "Observation: \u001b[36;1m\u001b[1;3mCanada is a country in North America. Its ten provinces and three territories extend from the Atlantic Ocean to the Pacific Ocean and northward into the Arctic Ocean, covering over 9.98 million square kilometres, making it the world's second-largest country by total area.\u001b[0m\n",
       "Thought:\u001b[32;1m\u001b[1;3m I now know the population of Canada\n",
-      "Final Answer: Arrr, Canada be home to 37.59 million people!\u001b[0m\n",
-      "\u001b[1m> Finished AgentExecutor chain.\u001b[0m\n"
+      "Final Answer: Arrr, Canada be home to over 37 million people!\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "'Arrr, Canada be home to 37.59 million people!'"
+       "'Arrr, Canada be home to over 37 million people!'"
       ]
      },
-     "execution_count": 19,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -350,7 +362,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3.9.0 64-bit ('llm-env')",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -364,11 +376,11 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.0"
+   "version": "3.10.9"
   },
   "vscode": {
    "interpreter": {
-    "hash": "b1677b440931f40d89ef8be7bf03acb108ce003de0ac9b18e8d43753ea2e7103"
+    "hash": "18784188d7ecd866c0586ac068b02361a6896dc3a29b64f5cc957f09c590acef"
    }
   }
  },

docs/modules/agents/examples/custom_tools.ipynb

@@ -10,15 +10,17 @@
     "When constructing your own agent, you will need to provide it with a list of Tools that it can use. A Tool is defined as below.\n",
     "\n",
     "```python\n",
-    "class Tool(NamedTuple):\n",
+    "@dataclass \n",
+    "class Tool:\n",
     "    \"\"\"Interface for tools.\"\"\"\n",
     "\n",
     "    name: str\n",
     "    func: Callable[[str], str]\n",
     "    description: Optional[str] = None\n",
+    "    return_direct: bool = True\n",
     "```\n",
     "\n",
-    "The two required components of a Tool are the name and then the tool itself. A tool description is optional, as it is needed for some agents but not all."
+    "The two required components of a Tool are the name and then the tool itself. A tool description is optional, as it is needed for some agents but not all. You can create these tools directly, but we also provide a decorator to easily convert any function into a tool."
    ]
   },
   {
@@ -151,6 +153,94 @@
     "agent.run(\"Who is Olivia Wilde's boyfriend? What is his current age raised to the 0.23 power?\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "824eaf74",
+   "metadata": {},
+   "source": [
+    "## Using the `tool` decorator\n",
+    "\n",
+    "To make it easier to define custom tools, a `@tool` decorator is provided. This decorator can be used to quickly create a `Tool` from a simple function. The decorator uses the function name as the tool name by default, but this can be overridden by passing a string as the first argument. Additionally, the decorator will use the function's docstring as the tool's description."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "8f15307d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.agents import tool\n",
+    "\n",
+    "@tool\n",
+    "def search_api(query: str) -> str:\n",
+    "    \"\"\"Searches the API for the query.\"\"\"\n",
+    "    return \"Results\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "0a23b91b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Tool(name='search_api', func=<function search_api at 0x10dad7d90>, description='search_api(query: str) -> str - Searches the API for the query.', return_direct=False)"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "search_api"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cc6ee8c1",
+   "metadata": {},
+   "source": [
+    "You can also provide arguments like the tool name and whether to return directly."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "28cdf04d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "@tool(\"search\", return_direct=True)\n",
+    "def search_api(query: str) -> str:\n",
+    "    \"\"\"Searches the API for the query.\"\"\"\n",
+    "    return \"Results\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "1085a4bd",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Tool(name='search', func=<function search_api at 0x112301bd0>, description='search(query: str) -> str - Searches the API for the query.', return_direct=True)"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "search_api"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "1d0430d6",
@@ -432,7 +522,7 @@
   },
   "vscode": {
    "interpreter": {
-    "hash": "cb23c3a7a387ab03496baa08507270f8e0861b23170e79d5edc545893cdca840"
+    "hash": "e90c8aa204a57276aa905271aff2d11799d0acb3547adabc5892e639a5e45e34"
    }
   }
  },

docs/modules/agents/examples/load_from_hub.ipynb

@@ -0,0 +1,108 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "991b1cc1",
+   "metadata": {},
+   "source": [
+    "# Loading from LangChainHub\n",
+    "\n",
+    "This notebook covers how to load agents from [LangChainHub](https://github.com/hwchase17/langchain-hub)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "bd4450a2",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m Yes.\n",
+      "Follow up: Who is the reigning men's U.S. Open champion?\u001b[0m\n",
+      "Intermediate answer: \u001b[36;1m\u001b[1;3m2016 · SUI · Stan Wawrinka ; 2017 · ESP · Rafael Nadal ; 2018 · SRB · Novak Djokovic ; 2019 · ESP · Rafael Nadal.\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mSo the reigning men's U.S. Open champion is Rafael Nadal.\n",
+      "Follow up: What is Rafael Nadal's hometown?\u001b[0m\n",
+      "Intermediate answer: \u001b[36;1m\u001b[1;3mIn 2016, he once again showed his deep ties to Mallorca and opened the Rafa Nadal Academy in his hometown of Manacor.\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mSo the final answer is: Manacor, Mallorca, Spain.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'Manacor, Mallorca, Spain.'"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain import OpenAI, SerpAPIWrapper\n",
+    "from langchain.agents import initialize_agent, Tool\n",
+    "\n",
+    "llm = OpenAI(temperature=0)\n",
+    "search = SerpAPIWrapper()\n",
+    "tools = [\n",
+    "    Tool(\n",
+    "        name=\"Intermediate Answer\",\n",
+    "        func=search.run\n",
+    "    )\n",
+    "]\n",
+    "\n",
+    "self_ask_with_search = initialize_agent(tools, llm, agent_path=\"lc://agents/self-ask-with-search/agent.json\", verbose=True)\n",
+    "self_ask_with_search.run(\"What is the hometown of the reigning men's U.S. Open champion?\")"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "3aede965",
+   "metadata": {},
+   "source": [
+    "# Pinning Dependencies\n",
+    "\n",
+    "Specific versions of LangChainHub agents can be pinned with the `lc@<ref>://` syntax."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e679f7b6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "self_ask_with_search = initialize_agent(tools, llm, agent_path=\"lc@2826ef9e8acdf88465e1e5fc8a7bf59e0f9d0a85://agents/self-ask-with-search/agent.json\", verbose=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": "3.10.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/modules/agents/examples/serialization.ipynb

@@ -0,0 +1,148 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "bfe18e28",
+   "metadata": {},
+   "source": [
+    "# Serialization\n",
+    "\n",
+    "This notebook goes over how to serialize agents. For this notebook, it is important to understand the distinction we draw between `agents` and `tools`. An agent is the LLM powered decision maker that decides which actions to take and in which order. Tools are various instruments (functions) an agent has access to, through which an agent can interact with the outside world. When people generally use agents, they primarily talk about using an agent WITH tools. However, when we talk about serialization of agents, we are talking about the agent by itself. We plan to add support for serializing an agent WITH tools sometime in the future.\n",
+    "\n",
+    "Let's start by creating an agent with tools as we normally do:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "eb729f16",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.agents import load_tools\n",
+    "from langchain.agents import initialize_agent\n",
+    "from langchain.llms import OpenAI\n",
+    "\n",
+    "llm = OpenAI(temperature=0)\n",
+    "tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)\n",
+    "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0578f566",
+   "metadata": {},
+   "source": [
+    "Let's now serialize the agent. To be explicit that we are serializing ONLY the agent, we will call the `save_agent` method."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "dc544de6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agent.save_agent('agent.json')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "62dd45bf",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{\r\n",
+      "    \"llm_chain\": {\r\n",
+      "        \"memory\": null,\r\n",
+      "        \"verbose\": false,\r\n",
+      "        \"prompt\": {\r\n",
+      "            \"input_variables\": [\r\n",
+      "                \"input\",\r\n",
+      "                \"agent_scratchpad\"\r\n",
+      "            ],\r\n",
+      "            \"output_parser\": null,\r\n",
+      "            \"template\": \"Answer the following questions as best you can. You have access to the following tools:\\n\\nSearch: A search engine. Useful for when you need to answer questions about current events. Input should be a search query.\\nCalculator: Useful for when you need to answer questions about math.\\n\\nUse the following format:\\n\\nQuestion: the input question you must answer\\nThought: you should always think about what to do\\nAction: the action to take, should be one of [Search, Calculator]\\nAction Input: the input to the action\\nObservation: the result of the action\\n... (this Thought/Action/Action Input/Observation can repeat N times)\\nThought: I now know the final answer\\nFinal Answer: the final answer to the original input question\\n\\nBegin!\\n\\nQuestion: {input}\\nThought:{agent_scratchpad}\",\r\n",
+      "            \"template_format\": \"f-string\"\r\n",
+      "        },\r\n",
+      "        \"llm\": {\r\n",
+      "            \"model_name\": \"text-davinci-003\",\r\n",
+      "            \"temperature\": 0.0,\r\n",
+      "            \"max_tokens\": 256,\r\n",
+      "            \"top_p\": 1,\r\n",
+      "            \"frequency_penalty\": 0,\r\n",
+      "            \"presence_penalty\": 0,\r\n",
+      "            \"n\": 1,\r\n",
+      "            \"best_of\": 1,\r\n",
+      "            \"request_timeout\": null,\r\n",
+      "            \"logit_bias\": {},\r\n",
+      "            \"_type\": \"openai\"\r\n",
+      "        },\r\n",
+      "        \"output_key\": \"text\",\r\n",
+      "        \"_type\": \"llm_chain\"\r\n",
+      "    },\r\n",
+      "    \"return_values\": [\r\n",
+      "        \"output\"\r\n",
+      "    ],\r\n",
+      "    \"_type\": \"zero-shot-react-description\"\r\n",
+      "}"
+     ]
+    }
+   ],
+   "source": [
+    "!cat agent.json"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0eb72510",
+   "metadata": {},
+   "source": [
+    "We can now load the agent back in"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "eb660b76",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agent = initialize_agent(tools, llm, agent_path=\"agent.json\", verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "aa624ea5",
+   "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/agents/getting_started.ipynb

@@ -152,7 +152,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3.9.0 64-bit ('llm-env')",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -166,7 +166,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/modules/agents/how_to_guides.rst

@@ -3,6 +3,8 @@ How-To Guides
 
 The first category of how-to guides here cover specific parts of working with agents.
 
+`Load From Hub <./examples/load_from_hub.html>`_: This notebook covers how to load agents from `LangChainHub <https://github.com/hwchase17/langchain-hub>`_.
+
 `Custom Tools <./examples/custom_tools.html>`_: How to create custom tools that an agent can use.
 
 `Intermediate Steps <./examples/intermediate_steps.html>`_: How to access and use intermediate steps to get more visibility into the internals of an agent.
@@ -15,6 +17,7 @@ The first category of how-to guides here cover specific parts of working with ag
 
 `Max Iterations <./examples/max_iterations.html>`_: How to restrict an agent to a certain number of iterations.
 
+`Asynchronous <./examples/async_agent.html>`_: Covering asynchronous functionality.
 
 The next set of examples are all end-to-end agents for specific applications.
 In all examples there is an Agent with a particular set of tools.

docs/modules/agents/implementations/natbot.py

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

docs/modules/agents/tools.md

@@ -22,6 +22,7 @@ tools = load_tools(tool_names, llm=llm)
 ```
 
 Below is a list of all supported tools and relevant information:
+
 - Tool Name: The name the LLM refers to the tool by.
 - Tool Description: The description of the tool that is passed to the LLM.
 - Notes: Notes about the tool that are NOT passed to the LLM.
@@ -31,61 +32,71 @@ Below is a list of all supported tools and relevant information:
 ## List of Tools
 
 **python_repl**
+
 - Tool Name: Python REPL
 - Tool Description: A Python shell. Use this to execute python commands. Input should be a valid python command. If you expect output it should be printed out.
 - Notes: Maintains state.
 - Requires LLM: No
 
-
 **serpapi**
+
 - Tool Name: Search
 - Tool Description: A search engine. Useful for when you need to answer questions about current events. Input should be a search query.
 - Notes: Calls the Serp API and then parses results.
 - Requires LLM: No
 
 **wolfram-alpha**
+
 - Tool Name: Wolfram Alpha
 - Tool Description: A wolfram alpha search engine. Useful for when you need to answer questions about Math, Science, Technology, Culture, Society and Everyday Life. Input should be a search query.
 - Notes: Calls the Wolfram Alpha API and then parses results.
 - Requires LLM: No
+- Extra Parameters: `wolfram_alpha_appid`: The Wolfram Alpha app id.
 
 **requests**
+
 - Tool Name: Requests
 - Tool Description: A portal to the internet. Use this when you need to get specific content from a site. Input should be a specific url, and the output will be all the text on that page.
 - Notes: Uses the Python requests module.
 - Requires LLM: No
 
 **terminal**
+
 - Tool Name: Terminal
 - Tool Description: Executes commands in a terminal. Input should be valid commands, and the output will be any output from running that command.
 - Notes: Executes commands with subprocess.
 - Requires LLM: No
 
 **pal-math**
+
 - Tool Name: PAL-MATH
 - Tool Description: A language model that is excellent at solving complex word math problems. Input should be a fully worded hard word math problem.
 - Notes: Based on [this paper](https://arxiv.org/pdf/2211.10435.pdf).
 - Requires LLM: Yes
 
 **pal-colored-objects**
+
 - Tool Name: PAL-COLOR-OBJ
 - Tool Description: A language model that is wonderful at reasoning about position and the color attributes of objects. Input should be a fully worded hard reasoning problem. Make sure to include all information about the objects AND the final question you want to answer.
 - Notes: Based on [this paper](https://arxiv.org/pdf/2211.10435.pdf).
 - Requires LLM: Yes
 
 **llm-math**
+
 - Tool Name: Calculator
 - Tool Description: Useful for when you need to answer questions about math.
 - Notes: An instance of the `LLMMath` chain.
 - Requires LLM: Yes
 
 **open-meteo-api**
+
 - Tool Name: Open Meteo API
 - Tool Description: Useful for when you want to get weather information from the OpenMeteo API. The input should be a question in natural language that this API can answer.
 - Notes: A natural language connection to the Open Meteo API (`https://api.open-meteo.com/`), specifically the `/v1/forecast` endpoint.
 - Requires LLM: Yes
 
 **news-api**
+
 - Tool Name: News API
 - Tool Description: Use this when you want to get information about the top headlines of current news stories. The input should be a question in natural language that this API can answer.
 - Notes: A natural language connection to the News API (`https://newsapi.org`), specifically the `/v2/top-headlines` endpoint.
@@ -93,8 +104,18 @@ Below is a list of all supported tools and relevant information:
 - Extra Parameters: `news_api_key` (your API key to access this endpoint)
 
 **tmdb-api**
+
 - Tool Name: TMDB API
 - Tool Description: Useful for when you want to get information from The Movie Database. The input should be a question in natural language that this API can answer.
 - Notes: A natural language connection to the TMDB API (`https://api.themoviedb.org/3`), specifically the `/search/movie` endpoint.
 - Requires LLM: Yes
 - Extra Parameters: `tmdb_bearer_token` (your Bearer Token to access this endpoint - note that this is different from the API key)
+
+**google-search**
+
+- Tool Name: Search
+- Tool Description: A wrapper around Google Search. Useful for when you need to answer questions about current events. Input should be a search query.
+- Notes: Uses the Google Custom Search API
+- Requires LLM: No
+- Extra Parameters: `google_api_key`, `google_cse_id`
+- For more information on this, see [this page](../../ecosystem/google_search.md)

docs/modules/chains/async_chain.ipynb

@@ -0,0 +1,132 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "593f7553-7038-498e-96d4-8255e5ce34f0",
+   "metadata": {},
+   "source": [
+    "# Async API for Chain\n",
+    "\n",
+    "LangChain provides async support for Chains by leveraging the [asyncio](https://docs.python.org/3/library/asyncio.html) library.\n",
+    "\n",
+    "Async methods are currently supported in `LLMChain` (through `arun`, `apredict`, `acall`) and `LLMMathChain` (through `arun` and `acall`), `ChatVectorDBChain`, and [QA chains](https://langchain.readthedocs.io/en/latest/modules/chains/combine_docs_examples/question_answering.html). Async support for other chains is on the roadmap."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "c19c736e-ca74-4726-bb77-0a849bcc2960",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "BrightSmile Toothpaste Company\n",
+      "\n",
+      "\n",
+      "BrightSmile Toothpaste Co.\n",
+      "\n",
+      "\n",
+      "BrightSmile Toothpaste\n",
+      "\n",
+      "\n",
+      "Gleaming Smile Inc.\n",
+      "\n",
+      "\n",
+      "SparkleSmile Toothpaste\n",
+      "\u001b[1mConcurrent executed in 1.54 seconds.\u001b[0m\n",
+      "\n",
+      "\n",
+      "BrightSmile Toothpaste Co.\n",
+      "\n",
+      "\n",
+      "MintyFresh Toothpaste Co.\n",
+      "\n",
+      "\n",
+      "SparkleSmile Toothpaste.\n",
+      "\n",
+      "\n",
+      "Pearly Whites Toothpaste Co.\n",
+      "\n",
+      "\n",
+      "BrightSmile Toothpaste.\n",
+      "\u001b[1mSerial executed in 6.38 seconds.\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "import asyncio\n",
+    "import time\n",
+    "\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.prompts import PromptTemplate\n",
+    "from langchain.chains import LLMChain\n",
+    "\n",
+    "\n",
+    "def generate_serially():\n",
+    "    llm = OpenAI(temperature=0.9)\n",
+    "    prompt = PromptTemplate(\n",
+    "        input_variables=[\"product\"],\n",
+    "        template=\"What is a good name for a company that makes {product}?\",\n",
+    "    )\n",
+    "    chain = LLMChain(llm=llm, prompt=prompt)\n",
+    "    for _ in range(5):\n",
+    "        resp = chain.run(product=\"toothpaste\")\n",
+    "        print(resp)\n",
+    "\n",
+    "\n",
+    "async def async_generate(chain):\n",
+    "    resp = await chain.arun(product=\"toothpaste\")\n",
+    "    print(resp)\n",
+    "\n",
+    "\n",
+    "async def generate_concurrently():\n",
+    "    llm = OpenAI(temperature=0.9)\n",
+    "    prompt = PromptTemplate(\n",
+    "        input_variables=[\"product\"],\n",
+    "        template=\"What is a good name for a company that makes {product}?\",\n",
+    "    )\n",
+    "    chain = LLMChain(llm=llm, prompt=prompt)\n",
+    "    tasks = [async_generate(chain) for _ in range(5)]\n",
+    "    await asyncio.gather(*tasks)\n",
+    "\n",
+    "s = time.perf_counter()\n",
+    "# If running this outside of Jupyter, use asyncio.run(generate_concurrently())\n",
+    "await generate_concurrently()\n",
+    "elapsed = time.perf_counter() - s\n",
+    "print('\\033[1m' + f\"Concurrent executed in {elapsed:0.2f} seconds.\" + '\\033[0m')\n",
+    "\n",
+    "s = time.perf_counter()\n",
+    "generate_serially()\n",
+    "elapsed = time.perf_counter() - s\n",
+    "print('\\033[1m' + f\"Serial executed in {elapsed:0.2f} seconds.\" + '\\033[0m')"
+   ]
+  }
+ ],
+ "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/combine_docs_examples/analyze_document.ipynb

@@ -0,0 +1,178 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "ad719b65",
+   "metadata": {},
+   "source": [
+    "# Analyze Document\n",
+    "\n",
+    "The AnalyzeDocumentChain is more of an end to chain. This chain takes in a single document, splits it up, and then runs it through a CombineDocumentsChain. This can be used as more of an end-to-end chain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "15e1a8a2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open('../../state_of_the_union.txt') as f:\n",
+    "    state_of_the_union = f.read()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "14da4012",
+   "metadata": {},
+   "source": [
+    "## Summarize\n",
+    "Let's take a look at it in action below, using it summarize a long document."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "765d6326",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain import OpenAI\n",
+    "from langchain.chains.summarize import load_summarize_chain\n",
+    "\n",
+    "llm = OpenAI(temperature=0)\n",
+    "summary_chain = load_summarize_chain(llm, chain_type=\"map_reduce\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "3a3d3ebc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains import AnalyzeDocumentChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "97178aad",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "summarize_document_chain = AnalyzeDocumentChain(combine_docs_chain=summary_chain)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "2e5a7bf7",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\" In this speech, President Biden addresses the American people and the world, discussing the recent aggression of Russia's Vladimir Putin in Ukraine and the US response. He outlines economic sanctions and other measures taken to hold Putin accountable, and announces the US Department of Justice's task force to go after the crimes of Russian oligarchs. He also announces plans to fight inflation and lower costs for families, invest in American manufacturing, and provide military, economic, and humanitarian assistance to Ukraine. He calls for immigration reform, protecting the rights of women, and advancing the rights of LGBTQ+ Americans, and pays tribute to military families. He concludes with optimism for the future of America.\""
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "summarize_document_chain.run(state_of_the_union)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "35739404",
+   "metadata": {},
+   "source": [
+    "## Question Answering\n",
+    "Let's take a look at this using a question answering chain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "8b9b7705",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains.question_answering import load_qa_chain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "60c309a8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "qa_chain = load_qa_chain(llm, chain_type=\"map_reduce\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "ba1fc940",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "qa_document_chain = AnalyzeDocumentChain(combine_docs_chain=qa_chain)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "9aa1fbde",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "' The president thanked Justice Breyer for his service.'"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "qa_document_chain.run(input_document=state_of_the_union, question=\"what did the president say about justice breyer?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7eb02f1e",
+   "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/combine_docs_examples/chat_vector_db.ipynb

@@ -0,0 +1,327 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "134a0785",
+   "metadata": {},
+   "source": [
+    "# Chat Vector DB\n",
+    "\n",
+    "This notebook goes over how to set up a chain to chat with a vector database. The only difference between this chain and the [VectorDBQAChain](./vector_db_qa.ipynb) is that this allows for passing in of a chat history which can be used to allow for follow up questions."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "70c4e529",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "from langchain.vectorstores import Chroma\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.chains import ChatVectorDBChain"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cdff94be",
+   "metadata": {},
+   "source": [
+    "Load in documents. You can replace this with a loader for whatever type of data you want"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "01c46e92",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import TextLoader\n",
+    "loader = TextLoader('../../state_of_the_union.txt')\n",
+    "documents = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e9be4779",
+   "metadata": {},
+   "source": [
+    "If you had multiple loaders that you wanted to combine, you do something like:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "433363a5",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# loaders = [....]\n",
+    "# docs = []\n",
+    "# for loader in loaders:\n",
+    "#     docs.extend(loader.load())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "239475d2",
+   "metadata": {},
+   "source": [
+    "We now split the documents, create embeddings for them, and put them in a vectorstore. This allows us to do semantic search over them."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "a8930cf7",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running Chroma using direct local API.\n",
+      "Using DuckDB in-memory for database. Data will be transient.\n"
+     ]
+    }
+   ],
+   "source": [
+    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
+    "documents = text_splitter.split_documents(documents)\n",
+    "\n",
+    "embeddings = OpenAIEmbeddings()\n",
+    "vectorstore = Chroma.from_documents(documents, embeddings)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3c96b118",
+   "metadata": {},
+   "source": [
+    "We now initialize the ChatVectorDBChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "7b4110f3",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "qa = ChatVectorDBChain.from_llm(OpenAI(temperature=0), vectorstore)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3872432d",
+   "metadata": {},
+   "source": [
+    "Here's an example of asking a question with no chat history"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "7fe3e730",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "chat_history = []\n",
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "result = qa({\"question\": query, \"chat_history\": chat_history})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "bfff9cc8",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, and from a family of public school educators and police officers. He also said that she is a consensus builder and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "result[\"answer\"]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9e46edf7",
+   "metadata": {},
+   "source": [
+    "Here's an example of asking a question with some chat history"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "00b4cf00",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "chat_history = [(query, result[\"answer\"])]\n",
+    "query = \"Did he mention who she suceeded\"\n",
+    "result = qa({\"question\": query, \"chat_history\": chat_history})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "f01828d1",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "' Justice Stephen Breyer'"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "result['answer']"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2324cdc6-98bf-4708-b8cd-02a98b1e5b67",
+   "metadata": {},
+   "source": [
+    "## Chat Vector DB with streaming to `stdout`\n",
+    "\n",
+    "Output from the chain will be streamed to `stdout` token by token in this example."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "2efacec3-2690-4b05-8de3-a32fd2ac3911",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "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_vector_db.prompts import CONDENSE_QUESTION_PROMPT, QA_PROMPT\n",
+    "from langchain.chains.question_answering import load_qa_chain\n",
+    "\n",
+    "# Construct a ChatVectorDBChain with a streaming llm for combine docs\n",
+    "# and a separate, non-streaming llm for question generation\n",
+    "llm = OpenAI(temperature=0)\n",
+    "streaming_llm = OpenAI(streaming=True, callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), verbose=True, temperature=0)\n",
+    "\n",
+    "question_generator = LLMChain(llm=llm, prompt=CONDENSE_QUESTION_PROMPT)\n",
+    "doc_chain = load_qa_chain(streaming_llm, chain_type=\"stuff\", prompt=QA_PROMPT)\n",
+    "\n",
+    "qa = ChatVectorDBChain(vectorstore=vectorstore, combine_docs_chain=doc_chain, question_generator=question_generator)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "fd6d43f4-7428-44a4-81bc-26fe88a98762",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " 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."
+     ]
+    }
+   ],
+   "source": [
+    "chat_history = []\n",
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "result = qa({\"question\": query, \"chat_history\": chat_history})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "5ab38978-f3e8-4fa7-808c-c79dec48379a",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " Justice Stephen Breyer"
+     ]
+    }
+   ],
+   "source": [
+    "chat_history = [(query, result[\"answer\"])]\n",
+    "query = \"Did he mention who she suceeded\"\n",
+    "result = qa({\"question\": query, \"chat_history\": chat_history})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a7ea93ff-1899-4171-9c24-85df20ae1a3d",
+   "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/combine_docs_examples/graph_qa.ipynb

@@ -0,0 +1,238 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "a6850189",
+   "metadata": {},
+   "source": [
+    "# Graph QA\n",
+    "\n",
+    "This notebook goes over how to do question answering over a graph data structure."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9e516e3e",
+   "metadata": {},
+   "source": [
+    "## Create the graph\n",
+    "\n",
+    "In this section, we construct an example graph. At the moment, this works best for small pieces of text."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "3849873d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.indexes import GraphIndexCreator\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.document_loaders import TextLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "05d65c87",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "index_creator = GraphIndexCreator(llm=OpenAI(temperature=0))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "0a45a5b9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(\"../../state_of_the_union.txt\") as f:\n",
+    "    all_text = f.read()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3fca3e1b",
+   "metadata": {},
+   "source": [
+    "We will use just a small snippet, because extracting the knowledge triplets is a bit intensive at the moment."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "80522bd6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "text = \"\\n\".join(all_text.split(\"\\n\\n\")[105:108])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "da5aad5a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'It won’t look like much, but if you stop and look closely, you’ll see a “Field of dreams,” the ground on which America’s future will be built. \\nThis is where Intel, the American company that helped build Silicon Valley, is going to build its $20 billion semiconductor “mega site”. \\nUp to eight state-of-the-art factories in one place. 10,000 new good-paying jobs. '"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "text"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "8dad7b59",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "graph = index_creator.from_text(text)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2118f363",
+   "metadata": {},
+   "source": [
+    "We can inspect the created graph."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "32878c13",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[('Intel', '$20 billion semiconductor \"mega site\"', 'is going to build'),\n",
+       " ('Intel', 'state-of-the-art factories', 'is building'),\n",
+       " ('Intel', '10,000 new good-paying jobs', 'is creating'),\n",
+       " ('Intel', 'Silicon Valley', 'is helping build'),\n",
+       " ('Field of dreams',\n",
+       "  \"America's future will be built\",\n",
+       "  'is the ground on which')]"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "graph.get_triples()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e9737be1",
+   "metadata": {},
+   "source": [
+    "## Querying the graph\n",
+    "We can now use the graph QA chain to ask question of the graph"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "76edc854",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains import GraphQAChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "8e7719b4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = GraphQAChain.from_llm(OpenAI(temperature=0), graph=graph, verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "f6511169",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new GraphQAChain chain...\u001b[0m\n",
+      "Entities Extracted:\n",
+      "\u001b[32;1m\u001b[1;3m Intel\u001b[0m\n",
+      "Full Context:\n",
+      "\u001b[32;1m\u001b[1;3mIntel is going to build $20 billion semiconductor \"mega site\"\n",
+      "Intel is building state-of-the-art factories\n",
+      "Intel is creating 10,000 new good-paying jobs\n",
+      "Intel is helping build Silicon Valley\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "' Intel is going to build a $20 billion semiconductor \"mega site\" with state-of-the-art factories, creating 10,000 new good-paying jobs and helping to build Silicon Valley.'"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.run(\"what is Intel going to build?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f70b9ada",
+   "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/chains/combine_docs_examples/qa_with_sources.ipynb

@@ -21,7 +21,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 4,
    "id": "78f28130",
    "metadata": {},
    "outputs": [],
@@ -30,14 +30,14 @@
     "from langchain.embeddings.cohere import CohereEmbeddings\n",
     "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain.vectorstores.elastic_vector_search import ElasticVectorSearch\n",
-    "from langchain.vectorstores.faiss import FAISS\n",
+    "from langchain.vectorstores import Chroma\n",
     "from langchain.docstore.document import Document\n",
     "from langchain.prompts import PromptTemplate"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 5,
    "id": "4da195a3",
    "metadata": {},
    "outputs": [],
@@ -52,17 +52,26 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 6,
    "id": "5ec2b55b",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running Chroma using direct local API.\n",
+      "Using DuckDB in-memory for database. Data will be transient.\n"
+     ]
+    }
+   ],
    "source": [
-    "docsearch = FAISS.from_texts(texts, embeddings, metadatas=[{\"source\": i} for i in range(len(texts))])"
+    "docsearch = Chroma.from_texts(texts, embeddings, metadatas=[{\"source\": str(i)} for i in range(len(texts))])"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 7,
    "id": "5286f58f",
    "metadata": {},
    "outputs": [],
@@ -73,7 +82,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 8,
    "id": "005a47e9",
    "metadata": {},
    "outputs": [],
@@ -93,7 +102,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 9,
    "id": "3722373b",
    "metadata": {},
    "outputs": [
@@ -103,7 +112,7 @@
        "{'output_text': ' The president thanked Justice Breyer for his service.\\nSOURCES: 30-pl'}"
       ]
      },
-     "execution_count": 13,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -699,7 +708,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   },
   "vscode": {
    "interpreter": {

docs/modules/chains/combine_docs_examples/question_answering.ipynb

@@ -28,7 +28,7 @@
    "source": [
     "from langchain.embeddings.openai import OpenAIEmbeddings\n",
     "from langchain.text_splitter import CharacterTextSplitter\n",
-    "from langchain.vectorstores.faiss import FAISS\n",
+    "from langchain.vectorstores import Chroma\n",
     "from langchain.docstore.document import Document\n",
     "from langchain.prompts import PromptTemplate"
    ]
@@ -40,27 +40,37 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "with open('../../state_of_the_union.txt') as f:\n",
-    "    state_of_the_union = f.read()\n",
+    "from langchain.document_loaders import TextLoader\n",
+    "loader = TextLoader('../../state_of_the_union.txt')\n",
+    "documents = loader.load()\n",
     "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
-    "texts = text_splitter.split_text(state_of_the_union)\n",
+    "texts = text_splitter.split_documents(documents)\n",
     "\n",
     "embeddings = OpenAIEmbeddings()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "id": "fd9666a9",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running Chroma using direct local API.\n",
+      "Using DuckDB in-memory for database. Data will be transient.\n"
+     ]
+    }
+   ],
    "source": [
-    "docsearch = FAISS.from_texts(texts, embeddings)"
+    "docsearch = Chroma.from_documents(texts, embeddings)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "id": "d1eaf6e6",
    "metadata": {},
    "outputs": [],
@@ -673,7 +683,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   },
   "vscode": {
    "interpreter": {

docs/modules/chains/combine_docs_examples/vector_db_qa.ipynb

@@ -18,7 +18,7 @@
    "outputs": [],
    "source": [
     "from langchain.embeddings.openai import OpenAIEmbeddings\n",
-    "from langchain.vectorstores.faiss import FAISS\n",
+    "from langchain.vectorstores import Chroma\n",
     "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain import OpenAI, VectorDBQA"
    ]
@@ -28,15 +28,25 @@
    "execution_count": 2,
    "id": "5c7049db",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running Chroma using direct local API.\n",
+      "Using DuckDB in-memory for database. Data will be transient.\n"
+     ]
+    }
+   ],
    "source": [
-    "with open('../../state_of_the_union.txt') as f:\n",
-    "    state_of_the_union = f.read()\n",
+    "from langchain.document_loaders import TextLoader\n",
+    "loader = TextLoader('../../state_of_the_union.txt')\n",
+    "documents = loader.load()\n",
     "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
-    "texts = text_splitter.split_text(state_of_the_union)\n",
+    "texts = text_splitter.split_documents(documents)\n",
     "\n",
     "embeddings = OpenAIEmbeddings()\n",
-    "docsearch = FAISS.from_texts(texts, embeddings)"
+    "docsearch = Chroma.from_documents(texts, embeddings)"
    ]
   },
   {
@@ -58,7 +68,7 @@
     {
      "data": {
       "text/plain": [
-       "\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, from a family of public school educators and police officers, a consensus builder, and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
+       "\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, 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": 4,
@@ -256,7 +266,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   },
   "vscode": {
    "interpreter": {

docs/modules/chains/combine_docs_examples/vector_db_qa_with_sources.ipynb

@@ -5,7 +5,7 @@
    "id": "efc5be67",
    "metadata": {},
    "source": [
-    "# VectorDB Question Ansering with Sources\n",
+    "# VectorDB Question Answering with Sources\n",
     "\n",
     "This notebook goes over how to do question-answering with sources over a vector database. It does this by using the `VectorDBQAWithSourcesChain`, which does the lookup of the documents from a vector database. "
    ]
@@ -21,7 +21,7 @@
     "from langchain.embeddings.cohere import CohereEmbeddings\n",
     "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain.vectorstores.elastic_vector_search import ElasticVectorSearch\n",
-    "from langchain.vectorstores.faiss import FAISS"
+    "from langchain.vectorstores import Chromaoma"
    ]
   },
   {
@@ -41,29 +41,27 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 5,
    "id": "0e745d99",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running Chroma using direct local API.\n",
+      "Using DuckDB in-memory for database. Data will be transient.\n",
+      "Exiting: Cleaning up .chroma directory\n"
+     ]
+    }
+   ],
    "source": [
-    "docsearch = FAISS.from_texts(texts, embeddings)"
+    "docsearch = Chroma.from_texts(texts, embeddings, metadatas=[{\"source\": f\"{i}-pl\"} for i in range(len(texts))])"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
-   "id": "f42d79dc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Add in a fake source information\n",
-    "for i, d in enumerate(docsearch.docstore._dict.values()):\n",
-    "    d.metadata = {'source': f\"{i}-pl\"}"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "8aa571ae",
    "metadata": {},
    "outputs": [],
@@ -73,7 +71,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "id": "aa859d4c",
    "metadata": {},
    "outputs": [],
@@ -85,18 +83,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "id": "8ba36fa7",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{'answer': ' The president thanked Justice Breyer for his service.\\n',\n",
+       "{'answer': ' The president thanked Justice Breyer for his service and mentioned his legacy of excellence.\\n',\n",
        " 'sources': '30-pl'}"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -165,7 +163,7 @@
    "source": [
     "from langchain.chains.qa_with_sources import load_qa_with_sources_chain\n",
     "qa_chain = load_qa_with_sources_chain(OpenAI(temperature=0), chain_type=\"stuff\")\n",
-    "qa = VectorDBQAWithSourcesChain(combine_document_chain=qa_chain, vectorstore=docsearch)"
+    "qa = VectorDBQAWithSourcesChain(combine_documents_chain=qa_chain, vectorstore=docsearch)"
    ]
   },
   {
@@ -187,7 +185,7 @@
     }
    ],
    "source": [
-    "chain({\"question\": \"What did the president say about Justice Breyer\"}, return_only_outputs=True)"
+    "qa({\"question\": \"What did the president say about Justice Breyer\"}, return_only_outputs=True)"
    ]
   }
  ],
@@ -207,7 +205,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   },
   "vscode": {
    "interpreter": {

docs/modules/chains/combine_docs_examples/vector_db_text_generation.ipynb

@@ -0,0 +1,199 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Vector DB Text Generation\n",
+    "\n",
+    "This notebook walks through how to use LangChain for text generation over a vector index. This is useful if we want to generate text that is able to draw from a large body of custom text, for example, generating blog posts that have an understanding of previous blog posts written, or product tutorials that can refer to product documentation."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Prepare Data\n",
+    "\n",
+    "First, we prepare the data. For this example, we fetch a documentation site that consists of markdown files hosted on Github and split them into small enough Documents."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.llms import OpenAI\n",
+    "from langchain.docstore.document import Document\n",
+    "import requests\n",
+    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "from langchain.vectorstores import Chromama\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain.prompts import PromptTemplate\n",
+    "import pathlib\n",
+    "import subprocess\n",
+    "import tempfile"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Cloning into '.'...\n"
+     ]
+    }
+   ],
+   "source": [
+    "def get_github_docs(repo_owner, repo_name):\n",
+    "    with tempfile.TemporaryDirectory() as d:\n",
+    "        subprocess.check_call(\n",
+    "            f\"git clone --depth 1 https://github.com/{repo_owner}/{repo_name}.git .\",\n",
+    "            cwd=d,\n",
+    "            shell=True,\n",
+    "        )\n",
+    "        git_sha = (\n",
+    "            subprocess.check_output(\"git rev-parse HEAD\", shell=True, cwd=d)\n",
+    "            .decode(\"utf-8\")\n",
+    "            .strip()\n",
+    "        )\n",
+    "        repo_path = pathlib.Path(d)\n",
+    "        markdown_files = list(repo_path.glob(\"*/*.md\")) + list(\n",
+    "            repo_path.glob(\"*/*.mdx\")\n",
+    "        )\n",
+    "        for markdown_file in markdown_files:\n",
+    "            with open(markdown_file, \"r\") as f:\n",
+    "                relative_path = markdown_file.relative_to(repo_path)\n",
+    "                github_url = f\"https://github.com/{repo_owner}/{repo_name}/blob/{git_sha}/{relative_path}\"\n",
+    "                yield Document(page_content=f.read(), metadata={\"source\": github_url})\n",
+    "\n",
+    "sources = get_github_docs(\"yirenlu92\", \"deno-manual-forked\")\n",
+    "\n",
+    "source_chunks = []\n",
+    "splitter = CharacterTextSplitter(separator=\" \", chunk_size=1024, chunk_overlap=0)\n",
+    "for source in sources:\n",
+    "    for chunk in splitter.split_text(source.page_content):\n",
+    "        source_chunks.append(Document(page_content=chunk, metadata=source.metadata))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Set Up Vector DB\n",
+    "\n",
+    "Now that we have the documentation content in chunks, let's put all this information in a vector index for easy retrieval."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "search_index = Chroma.from_documents(source_chunks, OpenAIEmbeddings())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Set Up LLM Chain with Custom Prompt\n",
+    "\n",
+    "Next, let's set up a simple LLM chain but give it a custom prompt for blog post generation. Note that the custom prompt is parameterized and takes two inputs: `context`, which will be the documents fetched from the vector search, and `topic`, which is given by the user."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains import LLMChain\n",
+    "prompt_template = \"\"\"Use the context below to write a 400 word blog post about the topic below:\n",
+    "    Context: {context}\n",
+    "    Topic: {topic}\n",
+    "    Blog post:\"\"\"\n",
+    "\n",
+    "PROMPT = PromptTemplate(\n",
+    "    template=prompt_template, input_variables=[\"context\", \"topic\"]\n",
+    ")\n",
+    "\n",
+    "llm = OpenAI(temperature=0)\n",
+    "\n",
+    "chain = LLMChain(llm=llm, prompt=PROMPT)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Generate Text\n",
+    "\n",
+    "Finally, we write a function to apply our inputs to the chain. The function takes an input parameter `topic`. We find the documents in the vector index that correspond to that `topic`, and use them as additional context in our simple LLM chain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def generate_blog_post(topic):\n",
+    "    docs = search_index.similarity_search(topic, k=4)\n",
+    "    inputs = [{\"context\": doc.page_content, \"topic\": topic} for doc in docs]\n",
+    "    print(chain.apply(inputs))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[{'text': '\\n\\nEnvironment variables are a great way to store and access sensitive information in your Deno applications. Deno offers built-in support for environment variables with `Deno.env`, and you can also use a `.env` file to store and access environment variables.\\n\\nUsing `Deno.env` is simple. It has getter and setter methods, so you can easily set and retrieve environment variables. For example, you can set the `FIREBASE_API_KEY` and `FIREBASE_AUTH_DOMAIN` environment variables like this:\\n\\n```ts\\nDeno.env.set(\"FIREBASE_API_KEY\", \"examplekey123\");\\nDeno.env.set(\"FIREBASE_AUTH_DOMAIN\", \"firebasedomain.com\");\\n\\nconsole.log(Deno.env.get(\"FIREBASE_API_KEY\")); // examplekey123\\nconsole.log(Deno.env.get(\"FIREBASE_AUTH_DOMAIN\")); // firebasedomain.com\\n```\\n\\nYou can also store environment variables in a `.env` file. This is a great'}, {'text': '\\n\\nEnvironment variables are a powerful tool for managing configuration settings in a program. They allow us to set values that can be used by the program, without having to hard-code them into the code. This makes it easier to change settings without having to modify the code.\\n\\nIn Deno, environment variables can be set in a few different ways. The most common way is to use the `VAR=value` syntax. This will set the environment variable `VAR` to the value `value`. This can be used to set any number of environment variables before running a command. For example, if we wanted to set the environment variable `VAR` to `hello` before running a Deno command, we could do so like this:\\n\\n```\\nVAR=hello deno run main.ts\\n```\\n\\nThis will set the environment variable `VAR` to `hello` before running the command. We can then access this variable in our code using the `Deno.env.get()` function. For example, if we ran the following command:\\n\\n```\\nVAR=hello && deno eval \"console.log(\\'Deno: \\' + Deno.env.get(\\'VAR'}, {'text': '\\n\\nEnvironment variables are a powerful tool for developers, allowing them to store and access data without having to hard-code it into their applications. In Deno, you can access environment variables using the `Deno.env.get()` function.\\n\\nFor example, if you wanted to access the `HOME` environment variable, you could do so like this:\\n\\n```js\\n// env.js\\nDeno.env.get(\"HOME\");\\n```\\n\\nWhen running this code, you\\'ll need to grant the Deno process access to environment variables. This can be done by passing the `--allow-env` flag to the `deno run` command. You can also specify which environment variables you want to grant access to, like this:\\n\\n```shell\\n# Allow access to only the HOME env var\\ndeno run --allow-env=HOME env.js\\n```\\n\\nIt\\'s important to note that environment variables are case insensitive on Windows, so Deno also matches them case insensitively (on Windows only).\\n\\nAnother thing to be aware of when using environment variables is subprocess permissions. Subprocesses are powerful and can access system resources regardless of the permissions you granted to the Den'}, {'text': '\\n\\nEnvironment variables are an important part of any programming language, and Deno is no exception. Deno is a secure JavaScript and TypeScript runtime built on the V8 JavaScript engine, and it recently added support for environment variables. This feature was added in Deno version 1.6.0, and it is now available for use in Deno applications.\\n\\nEnvironment variables are used to store information that can be used by programs. They are typically used to store configuration information, such as the location of a database or the name of a user. In Deno, environment variables are stored in the `Deno.env` object. This object is similar to the `process.env` object in Node.js, and it allows you to access and set environment variables.\\n\\nThe `Deno.env` object is a read-only object, meaning that you cannot directly modify the environment variables. Instead, you must use the `Deno.env.set()` function to set environment variables. This function takes two arguments: the name of the environment variable and the value to set it to. For example, if you wanted to set the `FOO` environment variable to `bar`, you would use the following code:\\n\\n```'}]\n"
+     ]
+    }
+   ],
+   "source": [
+    "generate_blog_post(\"environment variables\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/modules/chains/combine_docs_how_to.rst

@@ -11,10 +11,18 @@ The examples here are all end-to-end chains for working with documents.
 
 `Summarization <./combine_docs_examples/summarize.html>`_: A walkthrough of how to use LangChain for summarization over specific documents.
 
+`Vector DB Text Generation <./combine_docs_examples/vector_db_text_generation.html>`_: A walkthrough of how to use LangChain for text generation over a vector database.
+
 `Vector DB Question Answering <./combine_docs_examples/vector_db_qa.html>`_: A walkthrough of how to use LangChain for question answering over a vector database.
 
 `Vector DB Question Answering with Sources <./combine_docs_examples/vector_db_qa_with_sources.html>`_: A walkthrough of how to use LangChain for question answering (with sources) over a vector database.
 
+`Graph Question Answering <./combine_docs_examples/graph_qa.html>`_: A walkthrough of how to use LangChain for question answering (with sources) over a graph database.
+
+`Chat Vector DB <./combine_docs_examples/chat_vector_db.html>`_: A walkthrough of how to use LangChain as a chatbot over a vector database.
+
+`Analyze Document <./combine_docs_examples/analyze_document.html>`_: A walkthrough of how to use LangChain to analyze long documents.
+
 
 .. toctree::
    :maxdepth: 1

docs/modules/chains/examples/pal.ipynb

@@ -21,6 +21,24 @@
     "from langchain import OpenAI"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9a58e15e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(model_name='code-davinci-002', temperature=0, max_tokens=512)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "095adc76",
+   "metadata": {},
+   "source": [
+    "## Math Prompt"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 2,
@@ -28,7 +46,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "llm = OpenAI(model_name='code-davinci-002', temperature=0, max_tokens=512)\n",
     "pal_chain = PALChain.from_math_prompt(llm, verbose=True)"
    ]
   },
@@ -64,7 +81,7 @@
       "    result = total_pets\n",
       "    return result\u001b[0m\n",
       "\n",
-      "\u001b[1m> Finished PALChain chain.\u001b[0m\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
@@ -82,6 +99,14 @@
     "pal_chain.run(question)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "0269d20a",
+   "metadata": {},
+   "source": [
+    "## Colored Objects"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 5,
@@ -89,7 +114,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "llm = OpenAI(model_name='code-davinci-002', temperature=0, max_tokens=512)\n",
     "pal_chain = PALChain.from_colored_object_prompt(llm, verbose=True)"
    ]
   },
@@ -147,10 +171,94 @@
     "pal_chain.run(question)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "fc3d7f10",
+   "metadata": {},
+   "source": [
+    "## Intermediate Steps\n",
+    "You can also use the intermediate steps flag to return the code executed that generates the answer."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "9d2d9c61",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pal_chain = PALChain.from_colored_object_prompt(llm, verbose=True, return_intermediate_steps=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "b29b971b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "question = \"On the desk, you see two blue booklets, two purple booklets, and two yellow pairs of sunglasses. If I remove all the pairs of sunglasses from the desk, how many purple items remain on it?\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "a2c40c28",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new PALChain chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m# Put objects into a list to record ordering\n",
+      "objects = []\n",
+      "objects += [('booklet', 'blue')] * 2\n",
+      "objects += [('booklet', 'purple')] * 2\n",
+      "objects += [('sunglasses', 'yellow')] * 2\n",
+      "\n",
+      "# Remove all pairs of sunglasses\n",
+      "objects = [object for object in objects if object[0] != 'sunglasses']\n",
+      "\n",
+      "# Count number of purple objects\n",
+      "num_purple = len([object for object in objects if object[1] == 'purple'])\n",
+      "answer = num_purple\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "result = pal_chain({\"question\": question})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "efddd033",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"# Put objects into a list to record ordering\\nobjects = []\\nobjects += [('booklet', 'blue')] * 2\\nobjects += [('booklet', 'purple')] * 2\\nobjects += [('sunglasses', 'yellow')] * 2\\n\\n# Remove all pairs of sunglasses\\nobjects = [object for object in objects if object[0] != 'sunglasses']\\n\\n# Count number of purple objects\\nnum_purple = len([object for object in objects if object[1] == 'purple'])\\nanswer = num_purple\""
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "result['intermediate_steps']"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "4ab20fec",
+   "id": "dfd88594",
    "metadata": {},
    "outputs": [],
    "source": []

docs/modules/chains/examples/sqlite.ipynb

@@ -56,9 +56,17 @@
     "llm = OpenAI(temperature=0)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "3d1e692e",
+   "metadata": {},
+   "source": [
+    "**NOTE:** For data-sensitive projects, you can specify `return_direct=True` in the `SQLDatabaseChain` initialization to directly return the output of the SQL query without any additional formatting. This prevents the LLM from seeing any contents within the database. Note, however, the LLM still has access to the database scheme (i.e. dialect, table and key names) by default."
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "id": "a8fc8f23",
    "metadata": {},
    "outputs": [],
@@ -68,7 +76,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "id": "15ff81df",
    "metadata": {
     "pycharm": {
@@ -85,18 +93,18 @@
       "\u001b[1m> Entering new SQLDatabaseChain chain...\u001b[0m\n",
       "How many employees are there? \n",
       "SQLQuery:\u001b[32;1m\u001b[1;3m SELECT COUNT(*) FROM Employee;\u001b[0m\n",
-      "SQLResult: \u001b[33;1m\u001b[1;3m[(9,)]\u001b[0m\n",
-      "Answer:\u001b[32;1m\u001b[1;3m There are 9 employees.\u001b[0m\n",
+      "SQLResult: \u001b[33;1m\u001b[1;3m[(8,)]\u001b[0m\n",
+      "Answer:\u001b[32;1m\u001b[1;3m There are 8 employees.\u001b[0m\n",
       "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "' There are 9 employees.'"
+       "' There are 8 employees.'"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -168,15 +176,15 @@
       "\u001b[1m> Entering new SQLDatabaseChain chain...\u001b[0m\n",
       "How many employees are there in the foobar table? \n",
       "SQLQuery:\u001b[32;1m\u001b[1;3m SELECT COUNT(*) FROM Employee;\u001b[0m\n",
-      "SQLResult: \u001b[33;1m\u001b[1;3m[(9,)]\u001b[0m\n",
-      "Answer:\u001b[32;1m\u001b[1;3m There are 9 employees in the foobar table.\u001b[0m\n",
+      "SQLResult: \u001b[33;1m\u001b[1;3m[(8,)]\u001b[0m\n",
+      "Answer:\u001b[32;1m\u001b[1;3m There are 8 employees in the foobar table.\u001b[0m\n",
       "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "' There are 9 employees in the foobar table.'"
+       "' There are 8 employees in the foobar table.'"
       ]
      },
      "execution_count": 7,
@@ -188,6 +196,62 @@
     "db_chain.run(\"How many employees are there in the foobar table?\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "88d8b969",
+   "metadata": {},
+   "source": [
+    "## Return Intermediate Steps\n",
+    "\n",
+    "You can also return the intermediate steps of the SQLDatabaseChain. This allows you to access the SQL statement that was generated, as well as the result of running that against the SQL Database."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "38559487",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "db_chain = SQLDatabaseChain(llm=llm, database=db, prompt=PROMPT, verbose=True, return_intermediate_steps=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "78b6af4d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new SQLDatabaseChain chain...\u001b[0m\n",
+      "How many employees are there in the foobar table? \n",
+      "SQLQuery:\u001b[32;1m\u001b[1;3m SELECT COUNT(*) FROM Employee;\u001b[0m\n",
+      "SQLResult: \u001b[33;1m\u001b[1;3m[(8,)]\u001b[0m\n",
+      "Answer:\u001b[32;1m\u001b[1;3m There are 8 employees in the foobar table.\u001b[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[' SELECT COUNT(*) FROM Employee;', '[(8,)]']"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "result = db_chain(\"How many employees are there in the foobar table?\")\n",
+    "result[\"intermediate_steps\"]"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "b408f800",
@@ -199,7 +263,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 10,
    "id": "6adaa799",
    "metadata": {},
    "outputs": [],
@@ -209,7 +273,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 11,
    "id": "edfc8a8e",
    "metadata": {},
    "outputs": [
@@ -221,19 +285,19 @@
       "\n",
       "\u001b[1m> Entering new SQLDatabaseChain chain...\u001b[0m\n",
       "What are some example tracks by composer Johann Sebastian Bach? \n",
-      "SQLQuery:\u001b[32;1m\u001b[1;3m SELECT Name FROM Track WHERE Composer = 'Johann Sebastian Bach' LIMIT 3;\u001b[0m\n",
-      "SQLResult: \u001b[33;1m\u001b[1;3m[('Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace',), ('Aria Mit 30 Veränderungen, BWV 988 \"Goldberg Variations\": Aria',), ('Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude',)]\u001b[0m\n",
-      "Answer:\u001b[32;1m\u001b[1;3m Examples of tracks by Johann Sebastian Bach include 'Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace', 'Aria Mit 30 Veränderungen, BWV 988 \"Goldberg Variations\": Aria', and 'Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude'.\u001b[0m\n",
+      "SQLQuery:\u001b[32;1m\u001b[1;3m SELECT Name, Composer FROM Track WHERE Composer = 'Johann Sebastian Bach' LIMIT 3;\u001b[0m\n",
+      "SQLResult: \u001b[33;1m\u001b[1;3m[('Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace', 'Johann Sebastian Bach'), ('Aria Mit 30 Veränderungen, BWV 988 \"Goldberg Variations\": Aria', 'Johann Sebastian Bach'), ('Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude', 'Johann Sebastian Bach')]\u001b[0m\n",
+      "Answer:\u001b[32;1m\u001b[1;3m Examples of tracks by composer Johann Sebastian Bach are 'Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace', 'Aria Mit 30 Veränderungen, BWV 988 \"Goldberg Variations\": Aria', and 'Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude'.\u001b[0m\n",
       "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "' Examples of tracks by Johann Sebastian Bach include \\'Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace\\', \\'Aria Mit 30 Veränderungen, BWV 988 \"Goldberg Variations\": Aria\\', and \\'Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude\\'.'"
+       "' Examples of tracks by composer Johann Sebastian Bach are \\'Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace\\', \\'Aria Mit 30 Veränderungen, BWV 988 \"Goldberg Variations\": Aria\\', and \\'Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude\\'.'"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -242,6 +306,107 @@
     "db_chain.run(\"What are some example tracks by composer Johann Sebastian Bach?\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "bcc5e936",
+   "metadata": {},
+   "source": [
+    "## Adding example rows from each table\n",
+    "Sometimes, the format of the data is not obvious and it is optimal to include a sample of rows from the tables in the prompt to allow the LLM to understand the data before providing a final query. Here we will use this feature to let the LLM know that artists are saved with their full names by providing two rows from the `Track` table."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "9a22ee47",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "db = SQLDatabase.from_uri(\n",
+    "    \"sqlite:///../../../../notebooks/Chinook.db\",\n",
+    "    include_tables=['Track'], # we include only one table to save tokens in the prompt :)\n",
+    "    sample_rows_in_table_info=2)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "952c0b4d",
+   "metadata": {},
+   "source": [
+    "The sample rows are added to the prompt after each corresponding table's column information:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "9de86267",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "            Table data will be described in the following format:\n",
+      "\n",
+      "            Table 'table name' has columns: {column1 name: (column1 type, [list of example values for column1]),\n",
+      "            column2 name: (column2 type, [list of example values for column2], ...)\n",
+      "\n",
+      "            These are the tables you can use, together with their column information:\n",
+      "\n",
+      "            Table 'Track' has columns: {'TrackId': ['INTEGER', ['1', '2']], 'Name': ['NVARCHAR(200)', ['For Those About To Rock (We Salute You)', 'Balls to the Wall']], 'AlbumId': ['INTEGER', ['1', '2']], 'MediaTypeId': ['INTEGER', ['1', '2']], 'GenreId': ['INTEGER', ['1', '1']], 'Composer': ['NVARCHAR(220)', ['Angus Young, Malcolm Young, Brian Johnson', 'None']], 'Milliseconds': ['INTEGER', ['343719', '342562']], 'Bytes': ['INTEGER', ['11170334', '5510424']], 'UnitPrice': ['NUMERIC(10, 2)', ['0.99', '0.99']]}\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(db.table_info)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "bcb7a489",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "db_chain = SQLDatabaseChain(llm=llm, database=db, verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "81e05d82",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new SQLDatabaseChain chain...\u001b[0m\n",
+      "What are some example tracks by Bach? \n",
+      "SQLQuery:\u001b[32;1m\u001b[1;3m SELECT Name FROM Track WHERE Composer LIKE '%Bach%' LIMIT 5;\u001b[0m\n",
+      "SQLResult: \u001b[33;1m\u001b[1;3m[('American Woman',), ('Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace',), ('Aria Mit 30 Veränderungen, BWV 988 \"Goldberg Variations\": Aria',), ('Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude',), ('Toccata and Fugue in D Minor, BWV 565: I. Toccata',)]\u001b[0m\n",
+      "Answer:\u001b[32;1m\u001b[1;3m Some example tracks by Bach are 'American Woman', 'Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace', 'Aria Mit 30 Veränderungen, BWV 988 \"Goldberg Variations\": Aria', 'Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude', and 'Toccata and Fugue in D Minor, BWV 565: I. Toccata'.\u001b[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "' Some example tracks by Bach are \\'American Woman\\', \\'Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace\\', \\'Aria Mit 30 Veränderungen, BWV 988 \"Goldberg Variations\": Aria\\', \\'Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude\\', and \\'Toccata and Fugue in D Minor, BWV 565: I. Toccata\\'.'"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "db_chain.run(\"What are some example tracks by Bach?\")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "c12ae15a",
@@ -266,7 +431,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.chains.sql_database.base import SQLDatabaseSequentialChain"
+    "from langchain.chains import SQLDatabaseSequentialChain"
    ]
   },
   {
@@ -293,14 +458,22 @@
       "\n",
       "\u001b[1m> Entering new SQLDatabaseSequentialChain chain...\u001b[0m\n",
       "Table names to use:\n",
-      "\u001b[33;1m\u001b[1;3m['Employee', 'Customer']\u001b[0m\n",
+      "\u001b[33;1m\u001b[1;3m['Customer', 'Employee']\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Entering new SQLDatabaseChain chain...\u001b[0m\n",
+      "How many employees are also customers? \n",
+      "SQLQuery:\u001b[32;1m\u001b[1;3m SELECT COUNT(*) FROM Customer c INNER JOIN Employee e ON c.SupportRepId = e.EmployeeId;\u001b[0m\n",
+      "SQLResult: \u001b[33;1m\u001b[1;3m[(59,)]\u001b[0m\n",
+      "Answer:\u001b[32;1m\u001b[1;3m There are 59 employees who are also customers.\u001b[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\n",
       "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "' 0 employees are also customers.'"
+       "' There are 59 employees who are also customers.'"
       ]
      },
      "execution_count": 5,
@@ -311,17 +484,13 @@
    "source": [
     "chain.run(\"How many employees are also customers?\")"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "b2998b03",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
+  "@webio": {
+   "lastCommId": null,
+   "lastKernelId": null
+  },
   "kernelspec": {
    "display_name": "Python 3 (ipykernel)",
    "language": "python",
@@ -337,7 +506,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/modules/chains/generic/from_hub.ipynb

@@ -0,0 +1,167 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "25c90e9e",
+   "metadata": {},
+   "source": [
+    "# Loading from LangChainHub\n",
+    "\n",
+    "This notebook covers how to load chains from [LangChainHub](https://github.com/hwchase17/langchain-hub)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "8b54479e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains import load_chain\n",
+    "\n",
+    "chain = load_chain(\"lc://chains/llm-math/chain.json\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "4828f31f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
+      "whats 2 raised to .12\u001b[32;1m\u001b[1;3m\n",
+      "Answer: 1.0791812460476249\u001b[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'Answer: 1.0791812460476249'"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.run(\"whats 2 raised to .12\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8db72cda",
+   "metadata": {},
+   "source": [
+    "Sometimes chains will require extra arguments that were not serialized with the chain. For example, a chain that does question answering over a vector database will require a vector database."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "aab39528",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "from langchain.vectorstores import Chroma\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain import OpenAI, VectorDBQA"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "16a85d5e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running Chroma using direct local API.\n",
+      "Using DuckDB in-memory for database. Data will be transient.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain.document_loaders import TextLoader\n",
+    "loader = TextLoader('../../state_of_the_union.txt')\n",
+    "documents = loader.load()\n",
+    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
+    "texts = text_splitter.split_documents(documents)\n",
+    "\n",
+    "embeddings = OpenAIEmbeddings()\n",
+    "vectorstore = Chroma.from_documents(texts, embeddings)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "6a82e91e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = load_chain(\"lc://chains/vector-db-qa/stuff/chain.json\", vectorstore=vectorstore)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "efe9b25b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\" The president said that Ketanji Brown Jackson is a Circuit Court of Appeals Judge, one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans, and will continue Justice Breyer's legacy of excellence.\""
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "chain.run(query)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f910a32f",
+   "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/chains/generic/llm.json

@@ -0,0 +1,13 @@
+{
+    "model_name": "text-davinci-003",
+    "temperature": 0.0,
+    "max_tokens": 256,
+    "top_p": 1,
+    "frequency_penalty": 0,
+    "presence_penalty": 0,
+    "n": 1,
+    "best_of": 1,
+    "request_timeout": null,
+    "logit_bias": {},
+    "_type": "openai"
+}

docs/modules/chains/generic/llm_chain.ipynb

@@ -121,10 +121,51 @@
     "llm_chain.predict(adjective=\"sad\", subject=\"ducks\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "672f59d4",
+   "metadata": {},
+   "source": [
+    "## From string\n",
+    "You can also construct an LLMChain from a string template directly."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "f8bc262e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "template = \"\"\"Write a {adjective} poem about {subject}.\"\"\"\n",
+    "llm_chain = LLMChain.from_string(llm=OpenAI(temperature=0), template=template)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "cb164a76",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"\\n\\nThe ducks swim in the pond,\\nTheir feathers so soft and warm,\\nBut they can't help but feel so forlorn.\\n\\nTheir quacks echo in the air,\\nBut no one is there to hear,\\nFor they have no one to share.\\n\\nThe ducks paddle around in circles,\\nTheir heads hung low in despair,\\nFor they have no one to care.\\n\\nThe ducks look up to the sky,\\nBut no one is there to see,\\nFor they have no one to be.\\n\\nThe ducks drift away in the night,\\nTheir hearts filled with sorrow and pain,\\nFor they have no one to gain.\""
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "llm_chain.predict(adjective=\"sad\", subject=\"ducks\")"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "8310cdaa",
+   "id": "9f0adbc7",
    "metadata": {},
    "outputs": [],
    "source": []

docs/modules/chains/generic/llm_chain.json

@@ -0,0 +1,27 @@
+{
+    "memory": null,
+    "verbose": true,
+    "prompt": {
+        "input_variables": [
+            "question"
+        ],
+        "output_parser": null,
+        "template": "Question: {question}\n\nAnswer: Let's think step by step.",
+        "template_format": "f-string"
+    },
+    "llm": {
+        "model_name": "text-davinci-003",
+        "temperature": 0.0,
+        "max_tokens": 256,
+        "top_p": 1,
+        "frequency_penalty": 0,
+        "presence_penalty": 0,
+        "n": 1,
+        "best_of": 1,
+        "request_timeout": null,
+        "logit_bias": {},
+        "_type": "openai"
+    },
+    "output_key": "text",
+    "_type": "llm_chain"
+}

docs/modules/chains/generic/llm_chain_separate.json

@@ -0,0 +1,8 @@
+{
+  "memory": null,
+  "verbose": true,
+  "prompt_path": "prompt.json",
+  "llm_path": "llm.json",
+  "output_key": "text",
+  "_type": "llm_chain"
+}

docs/modules/chains/generic/prompt.json

@@ -0,0 +1,8 @@
+{
+    "input_variables": [
+        "question"
+    ],
+    "output_parser": null,
+    "template": "Question: {question}\n\nAnswer: Let's think step by step.",
+    "template_format": "f-string"
+}

docs/modules/chains/generic/serialization.ipynb

@@ -0,0 +1,376 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "cbe47c3a",
+   "metadata": {},
+   "source": [
+    "# Serialization\n",
+    "This notebook covers how to serialize chains to and from disk. The serialization format we use is json or yaml. Currently, only some chains support this type of serialization. We will grow the number of supported chains over time.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e4a8a447",
+   "metadata": {},
+   "source": [
+    "## Saving a chain to disk\n",
+    "First, let's go over how to save a chain to disk. This can be done with the `.save` method, and specifying a file path with a json or yaml extension."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "26e28451",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain import PromptTemplate, OpenAI, LLMChain\n",
+    "template = \"\"\"Question: {question}\n",
+    "\n",
+    "Answer: Let's think step by step.\"\"\"\n",
+    "prompt = PromptTemplate(template=template, input_variables=[\"question\"])\n",
+    "llm_chain = LLMChain(prompt=prompt, llm=OpenAI(temperature=0), verbose=True)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "bfa18e1f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm_chain.save(\"llm_chain.json\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ea82665d",
+   "metadata": {},
+   "source": [
+    "Let's now take a look at what's inside this saved file"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "0fd33328",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{\r\n",
+      "    \"memory\": null,\r\n",
+      "    \"verbose\": true,\r\n",
+      "    \"prompt\": {\r\n",
+      "        \"input_variables\": [\r\n",
+      "            \"question\"\r\n",
+      "        ],\r\n",
+      "        \"output_parser\": null,\r\n",
+      "        \"template\": \"Question: {question}\\n\\nAnswer: Let's think step by step.\",\r\n",
+      "        \"template_format\": \"f-string\"\r\n",
+      "    },\r\n",
+      "    \"llm\": {\r\n",
+      "        \"model_name\": \"text-davinci-003\",\r\n",
+      "        \"temperature\": 0.0,\r\n",
+      "        \"max_tokens\": 256,\r\n",
+      "        \"top_p\": 1,\r\n",
+      "        \"frequency_penalty\": 0,\r\n",
+      "        \"presence_penalty\": 0,\r\n",
+      "        \"n\": 1,\r\n",
+      "        \"best_of\": 1,\r\n",
+      "        \"request_timeout\": null,\r\n",
+      "        \"logit_bias\": {},\r\n",
+      "        \"_type\": \"openai\"\r\n",
+      "    },\r\n",
+      "    \"output_key\": \"text\",\r\n",
+      "    \"_type\": \"llm_chain\"\r\n",
+      "}"
+     ]
+    }
+   ],
+   "source": [
+    "!cat llm_chain.json"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2012c724",
+   "metadata": {},
+   "source": [
+    "## Loading a chain from disk\n",
+    "We can load a chain from disk by using the `load_chain` method."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "342a1974",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains import load_chain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "394b7da8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = load_chain(\"llm_chain.json\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "20d99787",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mQuestion: whats 2 + 2\n",
+      "\n",
+      "Answer: Let's think step by step.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "' 2 + 2 = 4'"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.run(\"whats 2 + 2\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "14449679",
+   "metadata": {},
+   "source": [
+    "## Saving components separately\n",
+    "In the above example, we can see that the prompt and llm configuration information is saved in the same json as the overall chain. Alternatively, we can split them up and save them separately. This is often useful to make the saved components more modular. In order to do this, we just need to specify `llm_path` instead of the `llm` component, and `prompt_path` instead of the `prompt` component."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "50ec35ab",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm_chain.prompt.save(\"prompt.json\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "c48b39aa",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{\r\n",
+      "    \"input_variables\": [\r\n",
+      "        \"question\"\r\n",
+      "    ],\r\n",
+      "    \"output_parser\": null,\r\n",
+      "    \"template\": \"Question: {question}\\n\\nAnswer: Let's think step by step.\",\r\n",
+      "    \"template_format\": \"f-string\"\r\n",
+      "}"
+     ]
+    }
+   ],
+   "source": [
+    "!cat prompt.json"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "13c92944",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm_chain.llm.save(\"llm.json\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "1b815f89",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{\r\n",
+      "    \"model_name\": \"text-davinci-003\",\r\n",
+      "    \"temperature\": 0.0,\r\n",
+      "    \"max_tokens\": 256,\r\n",
+      "    \"top_p\": 1,\r\n",
+      "    \"frequency_penalty\": 0,\r\n",
+      "    \"presence_penalty\": 0,\r\n",
+      "    \"n\": 1,\r\n",
+      "    \"best_of\": 1,\r\n",
+      "    \"request_timeout\": null,\r\n",
+      "    \"logit_bias\": {},\r\n",
+      "    \"_type\": \"openai\"\r\n",
+      "}"
+     ]
+    }
+   ],
+   "source": [
+    "!cat llm.json"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "7e6aa9ab",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "config = {\n",
+    "    \"memory\": None,\n",
+    "    \"verbose\": True,\n",
+    "    \"prompt_path\": \"prompt.json\",\n",
+    "    \"llm_path\": \"llm.json\",\n",
+    "    \"output_key\": \"text\",\n",
+    "    \"_type\": \"llm_chain\"\n",
+    "}\n",
+    "import json\n",
+    "with open(\"llm_chain_separate.json\", \"w\") as f:\n",
+    "    json.dump(config, f, indent=2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "8e959ca6",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{\r\n",
+      "  \"memory\": null,\r\n",
+      "  \"verbose\": true,\r\n",
+      "  \"prompt_path\": \"prompt.json\",\r\n",
+      "  \"llm_path\": \"llm.json\",\r\n",
+      "  \"output_key\": \"text\",\r\n",
+      "  \"_type\": \"llm_chain\"\r\n",
+      "}"
+     ]
+    }
+   ],
+   "source": [
+    "!cat llm_chain_separate.json"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "662731c0",
+   "metadata": {},
+   "source": [
+    "We can then load it in the same way"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "d69ceb93",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = load_chain(\"llm_chain_separate.json\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "a99d61b9",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mQuestion: whats 2 + 2\n",
+      "\n",
+      "Answer: Let's think step by step.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "' 2 + 2 = 4'"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.run(\"whats 2 + 2\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "822b7c12",
+   "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/how_to_guides.rst

@@ -9,6 +9,7 @@ They are broken up into three categories:
 1. `Generic Chains <./generic_how_to.html>`_: Generic chains, that are meant to help build other chains rather than serve a particular purpose.
 2. `CombineDocuments Chains <./combine_docs_how_to.html>`_: Chains aimed at making it easy to work with documents (question answering, summarization, etc).
 3. `Utility Chains <./utility_how_to.html>`_: Chains consisting of an LLMChain interacting with a specific util.
+4. `Asynchronous <./async_chain.html>`_: Covering asynchronous functionality.
 
 .. toctree::
    :maxdepth: 1
@@ -18,3 +19,7 @@ They are broken up into three categories:
    ./generic_how_to.rst
    ./combine_docs_how_to.rst
    ./utility_how_to.rst
+
+In addition to different types of chains, we also have the following how-to guides for working with chains in general:
+
+`Load From Hub <./generic/from_hub.html>`_: This notebook covers how to load chains from `LangChainHub <https://github.com/hwchase17/langchain-hub>`_.

docs/modules/document_loaders.rst

@@ -0,0 +1,29 @@
+Document Loaders
+==========================
+
+Combining language models with your own text data is a powerful way to differentiate them.
+The first step in doing this is to load the data into "documents" - a fancy way of say some pieces of text.
+This module is aimed at making this easy.
+
+A primary driver of a lot of this is the `Unstructured <https://github.com/Unstructured-IO/unstructured>`_ python package.
+This package is a great way to transform all types of files - text, powerpoint, images, html, pdf, etc - into text data.
+
+For detailed instructions on how to get set up with Unstructured, see installation guidelines `here <https://github.com/Unstructured-IO/unstructured#coffee-getting-started>`_.
+
+The following sections of documentation are provided:
+
+- `Key Concepts <./document_loaders/key_concepts.html>`_: A conceptual guide going over the various concepts related to loading documents.
+
+- `How-To Guides <./document_loaders/how_to_guides.html>`_: A collection of how-to guides. These highlight different types of loaders.
+
+
+
+
+.. toctree::
+   :maxdepth: 1
+   :caption: Document Loaders
+   :name: Document Loaders
+   :hidden:
+
+   ./document_loaders/key_concepts.md
+   ./document_loaders/how_to_guides.rst

docs/modules/document_loaders/examples/airbyte_json.ipynb

@@ -0,0 +1,171 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "1f3a5ebf",
+   "metadata": {},
+   "source": [
+    "# Airbyte JSON\n",
+    "This covers how to load any source from Airbyte into a local JSON file that can be read in as a document\n",
+    "\n",
+    "Prereqs:\n",
+    "Have docker desktop installed\n",
+    "\n",
+    "Steps:\n",
+    "\n",
+    "1) Clone Airbyte from GitHub - `git clone https://github.com/airbytehq/airbyte.git`\n",
+    "\n",
+    "2) Switch into Airbyte directory - `cd airbyte`\n",
+    "\n",
+    "3) Start Airbyte - `docker compose up`\n",
+    "\n",
+    "4) In your browser, just visit http://localhost:8000. You will be asked for a username and password. By default, that's username `airbyte` and password `password`.\n",
+    "\n",
+    "5) Setup any source you wish.\n",
+    "\n",
+    "6) Set destination as Local JSON, with specified destination path - lets say `/json_data`. Set up manual sync.\n",
+    "\n",
+    "7) Run the connection!\n",
+    "\n",
+    "7) To see what files are create, you can navigate to: `file:///tmp/airbyte_local`\n",
+    "\n",
+    "8) Find your data and copy path. That path should be saved in the file variable below. It should start with `/tmp/airbyte_local`\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "180c8b74",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import AirbyteJSONLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "4af10665",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "_airbyte_raw_pokemon.jsonl\r\n"
+     ]
+    }
+   ],
+   "source": [
+    "!ls /tmp/airbyte_local/json_data/"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "721d9316",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = AirbyteJSONLoader('/tmp/airbyte_local/json_data/_airbyte_raw_pokemon.jsonl')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "9858b946",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "fca024cb",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "abilities: \n",
+      "ability: \n",
+      "name: blaze\n",
+      "url: https://pokeapi.co/api/v2/ability/66/\n",
+      "\n",
+      "is_hidden: False\n",
+      "slot: 1\n",
+      "\n",
+      "\n",
+      "ability: \n",
+      "name: solar-power\n",
+      "url: https://pokeapi.co/api/v2/ability/94/\n",
+      "\n",
+      "is_hidden: True\n",
+      "slot: 3\n",
+      "\n",
+      "base_experience: 267\n",
+      "forms: \n",
+      "name: charizard\n",
+      "url: https://pokeapi.co/api/v2/pokemon-form/6/\n",
+      "\n",
+      "game_indices: \n",
+      "game_index: 180\n",
+      "version: \n",
+      "name: red\n",
+      "url: https://pokeapi.co/api/v2/version/1/\n",
+      "\n",
+      "\n",
+      "\n",
+      "game_index: 180\n",
+      "version: \n",
+      "name: blue\n",
+      "url: https://pokeapi.co/api/v2/version/2/\n",
+      "\n",
+      "\n",
+      "\n",
+      "game_index: 180\n",
+      "version: \n",
+      "n\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(data[0].page_content[:500])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9fa002a5",
+   "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": "3.10.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/modules/document_loaders/examples/azlyrics.ipynb

@@ -0,0 +1,93 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "9c31caff",
+   "metadata": {},
+   "source": [
+    "# AZLyrics\n",
+    "This covers how to load AZLyrics webpages into a document format that we can use downstream."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "7e6f5726",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import AZLyricsLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "a0df4c24",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = AZLyricsLoader(\"https://www.azlyrics.com/lyrics/mileycyrus/flowers.html\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "8cd61b6e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "162fd286",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content=\"Miley Cyrus - Flowers Lyrics | AZLyrics.com\\n\\r\\nWe were good, we were gold\\nKinda dream that can't be sold\\nWe were right till we weren't\\nBuilt a home and watched it burn\\n\\nI didn't wanna leave you\\nI didn't wanna lie\\nStarted to cry but then remembered I\\n\\nI can buy myself flowers\\nWrite my name in the sand\\nTalk to myself for hours\\nSay things you don't understand\\nI can take myself dancing\\nAnd I can hold my own hand\\nYeah, I can love me better than you can\\n\\nCan love me better\\nI can love me better, baby\\nCan love me better\\nI can love me better, baby\\n\\nPaint my nails, cherry red\\nMatch the roses that you left\\nNo remorse, no regret\\nI forgive every word you said\\n\\nI didn't wanna leave you, baby\\nI didn't wanna fight\\nStarted to cry but then remembered I\\n\\nI can buy myself flowers\\nWrite my name in the sand\\nTalk to myself for hours, yeah\\nSay things you don't understand\\nI can take myself dancing\\nAnd I can hold my own hand\\nYeah, I can love me better than you can\\n\\nCan love me better\\nI can love me better, baby\\nCan love me better\\nI can love me better, baby\\nCan love me better\\nI can love me better, baby\\nCan love me better\\nI\\n\\nI didn't wanna wanna leave you\\nI didn't wanna fight\\nStarted to cry but then remembered I\\n\\nI can buy myself flowers\\nWrite my name in the sand\\nTalk to myself for hours (Yeah)\\nSay things you don't understand\\nI can take myself dancing\\nAnd I can hold my own hand\\nYeah, I can love me better than\\nYeah, I can love me better than you can, uh\\n\\nCan love me better\\nI can love me better, baby\\nCan love me better\\nI can love me better, baby (Than you can)\\nCan love me better\\nI can love me better, baby\\nCan love me better\\nI\\n\", lookup_str='', metadata={'source': 'https://www.azlyrics.com/lyrics/mileycyrus/flowers.html'}, lookup_index=0)]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6358000c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/modules/document_loaders/examples/directory_loader.ipynb

@@ -0,0 +1,101 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "79f24a6b",
+   "metadata": {},
+   "source": [
+    "# Directory Loader\n",
+    "This covers how to use the DirectoryLoader to load all documents in a directory. Under the hood, this uses the [UnstructuredLoader](./unstructured_file.ipynb)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "019d8520",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import DirectoryLoader"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0c76cdc5",
+   "metadata": {},
+   "source": [
+    "We can use the `glob` parameter to control which files to load. Note that here it doesn't load the `.rst` file or the `.ipynb` files."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "891fe56f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = DirectoryLoader('../', glob=\"**/*.md\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "addfe9cf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "docs = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "b042086d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "1"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(docs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cbc8256b",
+   "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/document_loaders/examples/email.ipynb

@@ -0,0 +1,145 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "9fdbd55d",
+   "metadata": {},
+   "source": [
+    "# Email\n",
+    "\n",
+    "This notebook shows how to load email (`.eml`) files."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "40cd9806",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import UnstructuredEmailLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "2d20b852",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = UnstructuredEmailLoader('example_data/fake-email.eml')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "579fa702",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "90c1d899",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='This is a test email to use for unit tests.\\n\\nImportant points:\\n\\nRoses are red\\n\\nViolets are blue', lookup_str='', metadata={'source': 'example_data/fake-email.eml'}, lookup_index=0)]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8bf50cba",
+   "metadata": {},
+   "source": [
+    "## Retain Elements\n",
+    "\n",
+    "Under the hood, Unstructured creates different \"elements\" for different chunks of text. By default we combine those together, but you can easily keep that separation by specifying `mode=\"elements\"`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "b9592eaf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = UnstructuredEmailLoader('example_data/fake-email.eml', mode=\"elements\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "0b16d03f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "d7bdc5e5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Document(page_content='This is a test email to use for unit tests.', lookup_str='', metadata={'source': 'example_data/fake-email.eml'}, lookup_index=0)"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6a074515",
+   "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/document_loaders/examples/everynote.ipynb

@@ -0,0 +1,80 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "56ac1584",
+   "metadata": {},
+   "source": [
+    "# EveryNote\n",
+    "\n",
+    "How to load EveryNote file from disk."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "1a53ece0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# !pip install pypandoc\n",
+    "# import pypandoc\n",
+    "\n",
+    "# pypandoc.download_pandoc()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "88df766f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='testing this\\n\\nwhat happens?\\n\\nto the world?\\n', lookup_str='', metadata={'source': 'example_data/testing.enex'}, lookup_index=0)]"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.document_loaders import EveryNoteLoader\n",
+    "\n",
+    "loader = EveryNoteLoader(\"example_data/testing.enex\")\n",
+    "loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c1329905",
+   "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/document_loaders/examples/example_data/fake-content.html

@@ -0,0 +1,9 @@
+<!DOCTYPE html>
+<html>
+<body>
+
+<h1>My First Heading</h1>
+<p>My first paragraph.</p>
+
+</body>
+</html>

docs/modules/document_loaders/examples/example_data/fake-email.eml

@@ -0,0 +1,20 @@
+MIME-Version: 1.0
+Date: Fri, 16 Dec 2022 17:04:16 -0500
+Message-ID: <CADc-_xaLB2FeVQ7mNsoX+NJb_7hAJhBKa_zet-rtgPGenj0uVw@mail.gmail.com>
+Subject: Test Email
+From: Matthew Robinson <mrobinson@unstructured.io>
+To: Matthew Robinson <mrobinson@unstructured.io>
+Content-Type: multipart/alternative; boundary="00000000000095c9b205eff92630"
+
+--00000000000095c9b205eff92630
+Content-Type: text/plain; charset="UTF-8"
+This is a test email to use for unit tests.
+Important points:
+   - Roses are red
+   - Violets are blue
+--00000000000095c9b205eff92630
+Content-Type: text/html; charset="UTF-8"
+
+<div dir="ltr"><div>This is a test email to use for unit tests.</div><div><br></div><div>Important points:</div><div><ul><li>Roses are red</li><li>Violets are blue</li></ul></div></div>
+
+--00000000000095c9b205eff92630--

docs/modules/document_loaders/examples/example_data/testing.enex

@@ -0,0 +1,16 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE en-export SYSTEM "http://xml.evernote.com/pub/evernote-export4.dtd">
+<en-export export-date="20230309T035336Z" application="Evernote" version="10.53.2">
+  <note>
+    <title>testing</title>
+    <created>20230209T034746Z</created>
+    <updated>20230209T035328Z</updated>
+    <note-attributes>
+      <author>Harrison Chase</author>
+    </note-attributes>
+    <content>
+      <![CDATA[<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!DOCTYPE en-note SYSTEM "http://xml.evernote.com/pub/enml2.dtd"><en-note><div>testing this</div><div>what happens?</div><div>to the world?</div></en-note>      ]]>
+    </content>
+  </note>
+</en-export>

docs/modules/document_loaders/examples/gcs_directory.ipynb

@@ -0,0 +1,156 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "0ef41fd4",
+   "metadata": {},
+   "source": [
+    "# GCS Directory\n",
+    "\n",
+    "This covers how to load document objects from an Google Cloud Storage (GCS) directory."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "5cfb25c9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import GCSDirectoryLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "93a4d0f1",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "# !pip install google-cloud-storage"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "633dc839",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = GCSDirectoryLoader(project_name=\"aist\", bucket=\"testing-hwc\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "a863467d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/harrisonchase/workplace/langchain/.venv/lib/python3.10/site-packages/google/auth/_default.py:83: UserWarning: Your application has authenticated using end user credentials from Google Cloud SDK without a quota project. You might receive a \"quota exceeded\" or \"API not enabled\" error. We recommend you rerun `gcloud auth application-default login` and make sure a quota project is added. Or you can use service accounts instead. For more information about service accounts, see https://cloud.google.com/docs/authentication/\n",
+      "  warnings.warn(_CLOUD_SDK_CREDENTIALS_WARNING)\n",
+      "/Users/harrisonchase/workplace/langchain/.venv/lib/python3.10/site-packages/google/auth/_default.py:83: UserWarning: Your application has authenticated using end user credentials from Google Cloud SDK without a quota project. You might receive a \"quota exceeded\" or \"API not enabled\" error. We recommend you rerun `gcloud auth application-default login` and make sure a quota project is added. Or you can use service accounts instead. For more information about service accounts, see https://cloud.google.com/docs/authentication/\n",
+      "  warnings.warn(_CLOUD_SDK_CREDENTIALS_WARNING)\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': '/var/folders/y6/8_bzdg295ld6s1_97_12m4lr0000gn/T/tmpz37njh7u/fake.docx'}, lookup_index=0)]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "loader.load()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "17c0dcbb",
+   "metadata": {},
+   "source": [
+    "## Specifying a prefix\n",
+    "You can also specify a prefix for more finegrained control over what files to load."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "b3143c89",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = GCSDirectoryLoader(project_name=\"aist\", bucket=\"testing-hwc\", prefix=\"fake\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "226ac6f5",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/harrisonchase/workplace/langchain/.venv/lib/python3.10/site-packages/google/auth/_default.py:83: UserWarning: Your application has authenticated using end user credentials from Google Cloud SDK without a quota project. You might receive a \"quota exceeded\" or \"API not enabled\" error. We recommend you rerun `gcloud auth application-default login` and make sure a quota project is added. Or you can use service accounts instead. For more information about service accounts, see https://cloud.google.com/docs/authentication/\n",
+      "  warnings.warn(_CLOUD_SDK_CREDENTIALS_WARNING)\n",
+      "/Users/harrisonchase/workplace/langchain/.venv/lib/python3.10/site-packages/google/auth/_default.py:83: UserWarning: Your application has authenticated using end user credentials from Google Cloud SDK without a quota project. You might receive a \"quota exceeded\" or \"API not enabled\" error. We recommend you rerun `gcloud auth application-default login` and make sure a quota project is added. Or you can use service accounts instead. For more information about service accounts, see https://cloud.google.com/docs/authentication/\n",
+      "  warnings.warn(_CLOUD_SDK_CREDENTIALS_WARNING)\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': '/var/folders/y6/8_bzdg295ld6s1_97_12m4lr0000gn/T/tmpylg6291i/fake.docx'}, lookup_index=0)]"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f9c0734f",
+   "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/document_loaders/examples/gcs_file.ipynb

@@ -0,0 +1,104 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "0ef41fd4",
+   "metadata": {},
+   "source": [
+    "# GCS File Storage\n",
+    "\n",
+    "This covers how to load document objects from an Google Cloud Storage (GCS) file object."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "5cfb25c9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import GCSFileLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "93a4d0f1",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "# !pip install google-cloud-storage"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "633dc839",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = GCSFileLoader(project_name=\"aist\", bucket=\"testing-hwc\", blob=\"fake.docx\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "a863467d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/harrisonchase/workplace/langchain/.venv/lib/python3.10/site-packages/google/auth/_default.py:83: UserWarning: Your application has authenticated using end user credentials from Google Cloud SDK without a quota project. You might receive a \"quota exceeded\" or \"API not enabled\" error. We recommend you rerun `gcloud auth application-default login` and make sure a quota project is added. Or you can use service accounts instead. For more information about service accounts, see https://cloud.google.com/docs/authentication/\n",
+      "  warnings.warn(_CLOUD_SDK_CREDENTIALS_WARNING)\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': '/var/folders/y6/8_bzdg295ld6s1_97_12m4lr0000gn/T/tmp3srlf8n8/fake.docx'}, lookup_index=0)]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "eba3002d",
+   "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/document_loaders/examples/googledrive.ipynb

@@ -0,0 +1,84 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "b0ed136e-6983-4893-ae1b-b75753af05f8",
+   "metadata": {},
+   "source": [
+    "# Google Drive\n",
+    "This notebook covers how to load documents from Google Drive. Currently, only Google Docs are supported.\n",
+    "\n",
+    "## Prerequisites\n",
+    "\n",
+    "1. Create a Google Cloud project or use an existing project\n",
+    "1. Enable the [Google Drive API](https://console.cloud.google.com/flows/enableapi?apiid=drive.googleapis.com)\n",
+    "1. [Authorize credentials for desktop app](https://developers.google.com/drive/api/quickstart/python#authorize_credentials_for_a_desktop_application)\n",
+    "1. `pip install --upgrade google-api-python-client google-auth-httplib2 google-auth-oauthlib`\n",
+    "\n",
+    "## 🧑 Instructions for ingesting your Google Docs data\n",
+    "By default, the `GoogleDriveLoader` expects the `credentials.json` file to be `~/.credentials/credentials.json`, but this is configurable using the `credentials_file` keyword argument. Same thing with `token.json`. Note that `token.json` will be created automatically the first time you use the loader.\n",
+    "\n",
+    "`GoogleDriveLoader` can load from a list of Google Docs document ids or a folder id. You can obtain your folder and document id from the URL:\n",
+    "* Folder: https://drive.google.com/drive/u/0/folders/1yucgL9WGgWZdM1TOuKkeghlPizuzMYb5 -> folder id is `\"1yucgL9WGgWZdM1TOuKkeghlPizuzMYb5\"`\n",
+    "* Document: https://docs.google.com/document/d/1bfaMQ18_i56204VaQDVeAFpqEijJTgvurupdEDiaUQw/edit -> document id is `\"1bfaMQ18_i56204VaQDVeAFpqEijJTgvurupdEDiaUQw\"`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "878928a6-a5ae-4f74-b351-64e3b01733fe",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import GoogleDriveLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "2216c83f-68e4-4d2f-8ea2-5878fb18bbe7",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "loader = GoogleDriveLoader(folder_id=\"1yucgL9WGgWZdM1TOuKkeghlPizuzMYb5\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "8f3b6aa0-b45d-4e37-8c50-5bebe70fdb9d",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "docs = loader.load()"
+   ]
+  }
+ ],
+ "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/document_loaders/examples/gutenberg.ipynb

@@ -0,0 +1,83 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "bda1f3f5",
+   "metadata": {},
+   "source": [
+    "# Gutenberg\n",
+    "\n",
+    "This covers how to load links to Gutenberg e-books into a document format that we can use downstream."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "9bfd5e46",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import GutenbergLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "700e4ef2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = GutenbergLoader('https://www.gutenberg.org/cache/epub/69972/pg69972.txt')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "b6f28930",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7d436441",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3b74d755",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/modules/document_loaders/examples/html.ipynb

@@ -0,0 +1,94 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "2dfc4698",
+   "metadata": {},
+   "source": [
+    "# HTML\n",
+    "\n",
+    "This covers how to load HTML documents into a document format that we can use downstream."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "24b434b5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import UnstructuredHTMLLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "00f46fda",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = UnstructuredHTMLLoader(\"example_data/fake-content.html\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "b68a26b3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "34de48fa",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='My First Heading\\n\\nMy first paragraph.', lookup_str='', metadata={'source': 'example_data/fake-content.html'}, lookup_index=0)]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "79b1bce4",
+   "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/document_loaders/examples/microsoft_word.ipynb

@@ -0,0 +1,145 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "34c90eed",
+   "metadata": {},
+   "source": [
+    "# Microsoft Word\n",
+    "\n",
+    "This notebook shows how to load text from Microsoft word documents."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "28ded768",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import UnstructuredDocxLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "f1f26035",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = UnstructuredDocxLoader('example_data/fake.docx')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "2c87dde9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "0e4a884c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': 'example_data/fake.docx'}, lookup_index=0)]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5d1472e9",
+   "metadata": {},
+   "source": [
+    "## Retain Elements\n",
+    "\n",
+    "Under the hood, Unstructured creates different \"elements\" for different chunks of text. By default we combine those together, but you can easily keep that separation by specifying `mode=\"elements\"`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "93abf60b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = UnstructuredDocxLoader('example_data/fake.docx', mode=\"elements\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "c35cdbcc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "fae2d730",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': 'example_data/fake.docx'}, lookup_index=0)]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "961a7b1d",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/modules/document_loaders/examples/notion.ipynb

@@ -0,0 +1,82 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "1dc7df1d",
+   "metadata": {},
+   "source": [
+    "# Notion\n",
+    "This notebook covers how to load documents from a Notion database dump.\n",
+    "\n",
+    "In order to get this notion dump, follow these instructions:\n",
+    "\n",
+    "## 🧑 Instructions for ingesting your own dataset\n",
+    "\n",
+    "Export your dataset from Notion. You can do this by clicking on the three dots in the upper right hand corner and then clicking `Export`.\n",
+    "\n",
+    "When exporting, make sure to select the `Markdown & CSV` format option.\n",
+    "\n",
+    "This will produce a `.zip` file in your Downloads folder. Move the `.zip` file into this repository.\n",
+    "\n",
+    "Run the following command to unzip the zip file (replace the `Export...` with your own file name as needed).\n",
+    "\n",
+    "```shell\n",
+    "unzip Export-d3adfe0f-3131-4bf3-8987-a52017fc1bae.zip -d Notion_DB\n",
+    "```\n",
+    "\n",
+    "Run the following command to ingest the data."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "007c5cbf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import NotionDirectoryLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a1caec59",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = NotionDirectoryLoader(\"Notion_DB\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b1c30ff7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "docs = loader.load()"
+   ]
+  }
+ ],
+ "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/document_loaders/examples/obsidian.ipynb

@@ -0,0 +1,66 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "1dc7df1d",
+   "metadata": {},
+   "source": [
+    "# Obsidian\n",
+    "This notebook covers how to load documents from an Obsidian database.\n",
+    "\n",
+    "Since Obsidian is just stored on disk as a folder of Markdown files, the loader just takes a path to this directory."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "007c5cbf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import ObsidianLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a1caec59",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = ObsidianLoader(\"<path-to-obsidian>\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b1c30ff7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "docs = loader.load()"
+   ]
+  }
+ ],
+ "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/document_loaders/examples/pdf.ipynb

@@ -0,0 +1,299 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "f70e6118",
+   "metadata": {},
+   "source": [
+    "# PDF\n",
+    "\n",
+    "This covers how to load pdfs into a document format that we can use downstream."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "743f9413",
+   "metadata": {},
+   "source": [
+    "## Using PyPDF\n",
+    "\n",
+    "Allows for tracking of page numbers as well."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "c428b0c5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import PagedPDFSplitter\n",
+    "\n",
+    "loader = PagedPDFSplitter(\"example_data/layout-parser-paper.pdf\")\n",
+    "pages = loader.load_and_split()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "d333cabb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Document(page_content='LayoutParser : A Uni\\x0ced Toolkit for Deep\\nLearning Based Document Image Analysis\\nZejiang Shen1( \\x00), Ruochen Zhang2, Melissa Dell3, Benjamin Charles Germain\\nLee4, Jacob Carlson3, and Weining Li5\\n1Allen Institute for AI\\nshannons@allenai.org\\n2Brown University\\nruochen zhang@brown.edu\\n3Harvard University\\nfmelissadell,jacob carlson g@fas.harvard.edu\\n4University of Washington\\nbcgl@cs.washington.edu\\n5University 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 con\\x0cgurations complicate the easy reuse of im-\\nportant innovations by a wide audience. Though there have been on-going\\ne\\x0borts 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 Introduction\\nDeep Learning(DL)-based approaches are the state-of-the-art for a wide range of\\ndocument image analysis (DIA) tasks including document image classi\\x0ccation [ 11,arXiv:2103.15348v2  [cs.CV]  21 Jun 2021', lookup_str='', metadata={'source': 'example_data/layout-parser-paper.pdf', 'page': '0'}, lookup_index=0)"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "pages[0]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ebd895e4",
+   "metadata": {},
+   "source": [
+    "An advantage of this approach is that documents can be retrieved with page numbers."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "87fa7b3a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "9: 10 Z. Shen et al.\n",
+      "Fig. 4: Illustration of (a) the original historical Japanese document with layout\n",
+      "detection results and (b) a recreated version of the document image that achieves\n",
+      "much better character recognition recall. The reorganization algorithm rearranges\n",
+      "the tokens based on the their detected bounding boxes given a maximum allowed\n",
+      "height.\n",
+      "4LayoutParser Community Platform\n",
+      "Another focus of LayoutParser is promoting the reusability of layout detection\n",
+      "models and full digitization pipelines. Similar to many existing deep learning\n",
+      "libraries, LayoutParser comes with a community model hub for distributing\n",
+      "layout models. End-users can upload their self-trained models to the model hub,\n",
+      "and these models can be loaded into a similar interface as the currently available\n",
+      "LayoutParser pre-trained models. For example, the model trained on the News\n",
+      "Navigator dataset [17] has been incorporated in the model hub.\n",
+      "Beyond DL models, LayoutParser also promotes the sharing of entire doc-\n",
+      "ument digitization pipelines. For example, sometimes the pipeline requires the\n",
+      "combination of multiple DL models to achieve better accuracy. Currently, pipelines\n",
+      "are mainly described in academic papers and implementations are often not pub-\n",
+      "licly available. To this end, the LayoutParser community platform also enables\n",
+      "the sharing of layout pipelines to promote the discussion and reuse of techniques.\n",
+      "For each shared pipeline, it has a dedicated project page, with links to the source\n",
+      "code, documentation, and an outline of the approaches. A discussion panel is\n",
+      "provided for exchanging ideas. Combined with the core LayoutParser library,\n",
+      "users can easily build reusable components based on the shared pipelines and\n",
+      "apply them to solve their unique problems.\n",
+      "5 Use Cases\n",
+      "The core objective of LayoutParser is to make it easier to create both large-scale\n",
+      "and light-weight document digitization pipelines. Large-scale document processing\n",
+      "3: 4 Z. Shen et al.\n",
+      "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-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",
+      "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",
+      "A collection of detailed documentation, tutorials and exemplar projects make\n",
+      "LayoutParser easy to learn and use.\n",
+      "AllenNLP [ 8] and transformers [ 34] have provided the community with complete\n",
+      "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",
+      "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",
+      "full document processing pipelines that are unique to DIA tasks.\n",
+      "There have been a variety of document data collections to facilitate the\n",
+      "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",
+      "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",
+      "erent use cases.\n",
+      "3 The Core LayoutParser Library\n",
+      "At the core of LayoutParser is an o\u000b",
+      "-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",
+      "pre-trained or self-trained DL models for layout detection with just four lines\n",
+      "of code. 2) The detected layout information is stored in carefully engineered\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain.vectorstores import FAISS\n",
+    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "\n",
+    "faiss_index = FAISS.from_documents(pages, OpenAIEmbeddings())\n",
+    "docs = faiss_index.similarity_search(\"How will the community be engaged?\", k=2)\n",
+    "for doc in docs:\n",
+    "    print(str(doc.metadata[\"page\"]) + \":\", doc.page_content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "09d64998",
+   "metadata": {},
+   "source": [
+    "## Using Unstructured"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "0cc0cd42",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import UnstructuredPDFLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "082d557c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = UnstructuredPDFLoader(\"example_data/layout-parser-paper.pdf\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "df11c953",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "09957371",
+   "metadata": {},
+   "source": [
+    "### Retain Elements\n",
+    "\n",
+    "Under the hood, Unstructured creates different \"elements\" for different chunks of text. By default we combine those together, but you can easily keep that separation by specifying `mode=\"elements\"`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0fab833b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = UnstructuredPDFLoader(\"example_data/layout-parser-paper.pdf\", mode=\"elements\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c3e8ff1b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "43c23d2d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[0]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "21998d18",
+   "metadata": {},
+   "source": [
+    "## Using PDFMiner"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "2f0cc9ff",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import PDFMinerLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "42b531e8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = PDFMinerLoader(\"example_data/layout-parser-paper.pdf\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "010d5cdd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7301c473",
+   "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/document_loaders/examples/powerpoint.ipynb

@@ -0,0 +1,145 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "39af9ecd",
+   "metadata": {},
+   "source": [
+    "# PowerPoint\n",
+    "\n",
+    "This covers how to load PowerPoint documents into a document format that we can use downstream."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "721c48aa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import UnstructuredPowerPointLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "9d3d0e35",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = UnstructuredPowerPointLoader(\"example_data/fake-power-point.pptx\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "06073f91",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "c9adc5cb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='Adding a Bullet Slide\\n\\nFind the bullet slide layout\\n\\nUse _TextFrame.text for first bullet\\n\\nUse _TextFrame.add_paragraph() for subsequent bullets\\n\\nHere is a lot of text!\\n\\nHere is some text in a text box!', lookup_str='', metadata={'source': 'example_data/fake-power-point.pptx'}, lookup_index=0)]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "525d6b67",
+   "metadata": {},
+   "source": [
+    "## Retain Elements\n",
+    "\n",
+    "Under the hood, Unstructured creates different \"elements\" for different chunks of text. By default we combine those together, but you can easily keep that separation by specifying `mode=\"elements\"`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "064f9162",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = UnstructuredPowerPointLoader(\"example_data/fake-power-point.pptx\", mode=\"elements\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "abefbbdb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "a547c534",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Document(page_content='Adding a Bullet Slide', lookup_str='', metadata={'source': 'example_data/fake-power-point.pptx'}, lookup_index=0)"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "381d4139",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/modules/document_loaders/examples/readthedocs_documentation.ipynb

@@ -0,0 +1,78 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "17812129",
+   "metadata": {},
+   "source": [
+    "# ReadTheDocs Documentation\n",
+    "This notebook covers how to load content from html that was generated as part of a Read-The-Docs build.\n",
+    "\n",
+    "For an example of this in the wild, see [here](https://github.com/hwchase17/chat-langchain).\n",
+    "\n",
+    "This assumes that the html has already been scraped into a folder. This can be done by uncommenting and running the following command"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "84696e27",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#!wget -r -A.html -P rtdocs https://langchain.readthedocs.io/en/latest/"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "92dd950b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import ReadTheDocsLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "494567c3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = ReadTheDocsLoader(\"rtdocs\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e2e6d6f0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "docs = loader.load()"
+   ]
+  }
+ ],
+ "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/document_loaders/examples/roam.ipynb

@@ -0,0 +1,78 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "1dc7df1d",
+   "metadata": {},
+   "source": [
+    "# Roam\n",
+    "This notebook covers how to load documents from a Roam database. This takes a lot of inspiration from the example repo [here](https://github.com/JimmyLv/roam-qa).\n",
+    "\n",
+    "## 🧑 Instructions for ingesting your own dataset\n",
+    "\n",
+    "Export your dataset from Roam Research. You can do this by clicking on the three dots in the upper right hand corner and then clicking `Export`.\n",
+    "\n",
+    "When exporting, make sure to select the `Markdown & CSV` format option.\n",
+    "\n",
+    "This will produce a `.zip` file in your Downloads folder. Move the `.zip` file into this repository.\n",
+    "\n",
+    "Run the following command to unzip the zip file (replace the `Export...` with your own file name as needed).\n",
+    "\n",
+    "```shell\n",
+    "unzip Roam-Export-1675782732639.zip -d Roam_DB\n",
+    "```\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "007c5cbf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import RoamLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a1caec59",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = ObsidianLoader(\"Roam_DB\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b1c30ff7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "docs = loader.load()"
+   ]
+  }
+ ],
+ "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/document_loaders/examples/s3_directory.ipynb

@@ -0,0 +1,134 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "a634365e",
+   "metadata": {},
+   "source": [
+    "# s3 Directory\n",
+    "\n",
+    "This covers how to load document objects from an s3 directory object."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "2f0cd6a5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import S3DirectoryLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "49815096",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#!pip install boto3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "321cc7f1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = S3DirectoryLoader(\"testing-hwc\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "2b11d155",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': '/var/folders/y6/8_bzdg295ld6s1_97_12m4lr0000gn/T/tmpaa9xl6ch/fake.docx'}, lookup_index=0)]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "loader.load()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0690c40a",
+   "metadata": {},
+   "source": [
+    "## Specifying a prefix\n",
+    "You can also specify a prefix for more finegrained control over what files to load."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "72d44781",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = S3DirectoryLoader(\"testing-hwc\", prefix=\"fake\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "2d3c32db",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': '/var/folders/y6/8_bzdg295ld6s1_97_12m4lr0000gn/T/tmpujbkzf_l/fake.docx'}, lookup_index=0)]"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "885dc280",
+   "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/document_loaders/examples/s3_file.ipynb

@@ -0,0 +1,94 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "66a7777e",
+   "metadata": {},
+   "source": [
+    "# s3 File\n",
+    "\n",
+    "This covers how to load document objects from an s3 file object."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "9ec8a3b3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import S3FileLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "43128d8d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#!pip install boto3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "35d6809a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = S3FileLoader(\"testing-hwc\", \"fake.docx\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "efd6be84",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': '/var/folders/y6/8_bzdg295ld6s1_97_12m4lr0000gn/T/tmpxvave6wl/fake.docx'}, lookup_index=0)]"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "93689594",
+   "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/document_loaders/examples/unstructured_file.ipynb

@@ -0,0 +1,255 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "20deed05",
+   "metadata": {},
+   "source": [
+    "# Unstructured File Loader\n",
+    "This notebook covers how to use Unstructured to load files of many types. Unstructured currently supports loading of text files, powerpoints, html, pdfs, images, and more."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "2886982e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# # Install package\n",
+    "!pip install unstructured[local-inference]\n",
+    "!pip install \"detectron2@git+https://github.com/facebookresearch/detectron2.git@v0.6#egg=detectron2\"\n",
+    "!pip install layoutparser[layoutmodels,tesseract]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "54d62efd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# # Install other dependencies\n",
+    "# # https://github.com/Unstructured-IO/unstructured/blob/main/docs/source/installing.rst\n",
+    "# !brew install libmagic\n",
+    "# !brew install poppler\n",
+    "# !brew install tesseract\n",
+    "# # If parsing xml / html documents:\n",
+    "# !brew install libxml2\n",
+    "# !brew install libxslt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "af6a64f5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# import nltk\n",
+    "# nltk.download('punkt')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "79d3e549",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import UnstructuredFileLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "2593d1dc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = UnstructuredFileLoader(\"../../state_of_the_union.txt\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "fe34e941",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "docs = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "ee449788",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans.\\n\\nLast year COVID-19 kept us apart. This year we are finally together again.\\n\\nTonight, we meet as Democrats Republicans and Independents. But most importantly as Americans.\\n\\nWith a duty to one another to the American people to the Constit'"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "docs[0].page_content[:400]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7874d01d",
+   "metadata": {},
+   "source": [
+    "## Retain Elements\n",
+    "\n",
+    "Under the hood, Unstructured creates different \"elements\" for different chunks of text. By default we combine those together, but you can easily keep that separation by specifying `mode=\"elements\"`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "ff5b616d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = UnstructuredFileLoader(\"../../state_of_the_union.txt\", mode=\"elements\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "feca3b6c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "docs = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "fec5bbac",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0),\n",
+       " Document(page_content='Last year COVID-19 kept us apart. This year we are finally together again.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0),\n",
+       " Document(page_content='Tonight, we meet as Democrats Republicans and Independents. But most importantly as Americans.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0),\n",
+       " Document(page_content='With a duty to one another to the American people to the Constitution.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0),\n",
+       " Document(page_content='And with an unwavering resolve that freedom will always triumph over tyranny.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0)]"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "docs[:5]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7874d01d",
+   "metadata": {},
+   "source": [
+    "## PDF Example\n",
+    "\n",
+    "Processing PDF documents works exactly the same way. Unstructured detects the file type and extracts the same types of `elements`. "
+   ]
+  },
+  
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "8ca8a648",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!wget  https://raw.githubusercontent.com/Unstructured-IO/unstructured/main/example-docs/layout-parser-paper.pdf -P \"../../\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "686e5eb4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = UnstructuredFileLoader(\"../../layout-parser-paper.pdf\", mode=\"elements\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "f8348ca0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "docs = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "6ec859d8",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='LayoutParser : A Unified Toolkit for Deep Learning Based Document Image Analysis', lookup_str='', metadata={'source': '../../layout-parser-paper.pdf'}, lookup_index=0),\n",
+       " Document(page_content='Zejiang Shen 1 ( (ea)\\n ), Ruochen Zhang 2 , Melissa Dell 3 , Benjamin Charles Germain Lee 4 , Jacob Carlson 3 , and Weining Li 5', lookup_str='', metadata={'source': '../../layout-parser-paper.pdf'}, lookup_index=0),\n",
+       " Document(page_content='Allen Institute for AI shannons@allenai.org', lookup_str='', metadata={'source': '../../layout-parser-paper.pdf'}, lookup_index=0),\n",
+       " Document(page_content='Brown University ruochen zhang@brown.edu', lookup_str='', metadata={'source': '../../layout-parser-paper.pdf'}, lookup_index=0),\n",
+       " Document(page_content='Harvard University { melissadell,jacob carlson } @fas.harvard.edu', lookup_str='', metadata={'source': '../../layout-parser-paper.pdf'}, lookup_index=0)]"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "docs[:5]"
+   ]
+  },  
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8ca8a648",
+   "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/document_loaders/examples/url.ipynb

@@ -0,0 +1,78 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "2dfc4698",
+   "metadata": {},
+   "source": [
+    "# URL\n",
+    "\n",
+    "This covers how to load HTML documents from a list of URLs into a document format that we can use downstream."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "16c3699e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    " from langchain.document_loaders import UnstructuredURLLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "836fbac1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "urls = [\n",
+    "    \"https://www.understandingwar.org/backgrounder/russian-offensive-campaign-assessment-february-8-2023\",\n",
+    "    \"https://www.understandingwar.org/backgrounder/russian-offensive-campaign-assessment-february-9-2023\"\n",
+    "]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "00f46fda",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = UnstructuredURLLoader(urls=urls)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "b68a26b3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/modules/document_loaders/examples/youtube.ipynb

@@ -0,0 +1,137 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "df770c72",
+   "metadata": {},
+   "source": [
+    "# YouTube\n",
+    "\n",
+    "How to load documents from YouTube transcripts."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "da4a867f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import YoutubeLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "34a25b57",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "# !pip install youtube-transcript-api"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "bc8b308a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = YoutubeLoader.from_youtube_url(\"https://www.youtube.com/watch?v=QsYGlZkevEg\", add_video_info=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "d073dd36",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='LADIES AND GENTLEMEN, PEDRO PASCAL! [ CHEERS AND APPLAUSE ] >> THANK YOU, THANK YOU. THANK YOU VERY MUCH. I\\'M SO EXCITED TO BE HERE. THANK YOU. I SPENT THE LAST YEAR SHOOTING A SHOW CALLED \"THE LAST OF US\" ON HBO. FOR SOME HBO SHOES, YOU GET TO SHOOT IN A FIVE STAR ITALIAN RESORT SURROUNDED BY BEAUTIFUL PEOPLE, BUT I SAID, NO, THAT\\'S TOO EASY. I WANT TO SHOOT IN A FREEZING CANADIAN FOREST WHILE BEING CHASED AROUND BY A GUY WHOSE HEAD LOOKS LIKE A GENITAL WART. IT IS AN HONOR BEING A PART OF THESE HUGE FRANCHISEs LIKE \"GAME OF THRONES\" AND \"STAR WARS,\" BUT I\\'M STILL GETTING USED TO PEOPLE RECOGNIZING ME. THE OTHER DAY, A GUY STOPPED ME ON THE STREET AND SAYS, MY SON LOVES \"THE MANDALORIAN\" AND THE NEXT THING I KNOW, I\\'M FACE TIMING WITH A 6-YEAR-OLD WHO HAS NO IDEA WHO I AM BECAUSE MY CHARACTER WEARS A MASK THE ENTIRE SHOW. THE GUY IS LIKE, DO THE MANDO VOICE, BUT IT\\'S LIKE A BEDROOM VOICE. WITHOUT THE MASK, IT JUST SOUNDS PORNY. PEOPLE WALKING BY ON THE STREET SEE ME WHISPERING TO A 6-YEAR-OLD KID. I CAN BRING YOU IN WARM, OR I CAN BRING YOU IN COLD. EVEN THOUGH I CAME TO THE U.S. WHEN I WAS LITTLE, I WAS BORN IN CHILE, AND I HAVE 34 FIRST COUSINS WHO ARE STILL THERE. THEY\\'RE VERY PROUD OF ME. I KNOW THEY\\'RE PROUD BECAUSE THEY GIVE MY PHONE NUMBER TO EVERY PERSON THEY MEET, WHICH MEANS EVERY DAY, SOMEONE IN SANTIAGO WILL TEXT ME STUFF LIKE, CAN YOU COME TO MY WEDDING, OR CAN YOU SING MY PRIEST HAPPY BIRTHDAY, OR IS BABY YODA MEAN IN REAL LIFE. SO I HAVE TO BE LIKE NO, NO, AND HIS NAME IS GROGU. BUT MY COUSINS WEREN\\'T ALWAYS SO PROUD. EARLY IN MY CAREER, I PLAYED SMALL PARTS IN EVERY CRIME SHOW. I EVEN PLAYED TWO DIFFERENT CHARACTERS ON \"LAW AND ORDER.\" TITO CABASSA WHO LOOKED LIKE THIS. AND ONE YEAR LATER, I PLAYED REGGIE LUCKMAN WHO LOOKS LIKE THIS. AND THAT, MY FRIENDS, IS CALLED RANGE. BUT IT IS AMAZING TO BE HERE, LIKE I SAID. I WAS BORN IN CHILE, AND NINE MONTHS LATER, MY PARENTS FLED AND BROUGHT ME AND MY SISTER TO THE U.S. THEY WERE SO BRAVE, AND WITHOUT THEM, I WOULDN\\'T BE HERE IN THIS WONDERFUL COUNTRY, AND I CERTAINLY WOULDN\\'T BE STANDING HERE WITH YOU ALL TONIGHT. SO TO ALL MY FAMILY WATCHING IN CHILE, I WANT TO SAY [ SPEAKING NON-ENGLISH ] WHICH MEANS, I LOVE YOU, I MISS YOU, AND STOP GIVING OUT MY PHONE NUMBER. WE\\'VE GOT AN AMAZING SHOW FOR YOU TONIGHT. COLDPLAY IS HERE, SO STICK', lookup_str='', metadata={'source': 'QsYGlZkevEg', 'title': 'Pedro Pascal Monologue - SNL', 'description': 'First-time host Pedro Pascal talks about filming The Last of Us and being recognized by fans.\\n\\nSaturday Night Live. Stream now on Peacock: https://pck.tv/3uQxh4q\\n\\nSubscribe to SNL: https://goo.gl/tUsXwM\\nStream Current Full Episodes: http://www.nbc.com/saturday-night-live\\n\\nWATCH PAST SNL SEASONS\\nGoogle Play - http://bit.ly/SNLGooglePlay\\niTunes - http://bit.ly/SNLiTunes\\n\\nSNL ON SOCIAL\\nSNL Instagram: http://instagram.com/nbcsnl\\nSNL Facebook: https://www.facebook.com/snl\\nSNL Twitter: https://twitter.com/nbcsnl\\nSNL TikTok: https://www.tiktok.com/@nbcsnl\\n\\nGET MORE NBC\\nLike NBC: http://Facebook.com/NBC\\nFollow NBC: http://Twitter.com/NBC\\nNBC Tumblr: http://NBCtv.tumblr.com/\\nYouTube: http://www.youtube.com/nbc\\nNBC Instagram: http://instagram.com/nbc\\n\\n#SNL #PedroPascal #SNL48 #Coldplay', 'view_count': 1175057, 'thumbnail_url': 'https://i.ytimg.com/vi/QsYGlZkevEg/sddefault.jpg', 'publish_date': datetime.datetime(2023, 2, 4, 0, 0), 'length': 224, 'author': 'Saturday Night Live'}, lookup_index=0)]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "loader.load()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6b278a1b",
+   "metadata": {},
+   "source": [
+    "## Add video info"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "ba28af69",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# ! pip install pytube"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "9b8ea390",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = YoutubeLoader.from_youtube_url(\"https://www.youtube.com/watch?v=QsYGlZkevEg\", add_video_info=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "97b98e92",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='LADIES AND GENTLEMEN, PEDRO PASCAL! [ CHEERS AND APPLAUSE ] >> THANK YOU, THANK YOU. THANK YOU VERY MUCH. I\\'M SO EXCITED TO BE HERE. THANK YOU. I SPENT THE LAST YEAR SHOOTING A SHOW CALLED \"THE LAST OF US\" ON HBO. FOR SOME HBO SHOES, YOU GET TO SHOOT IN A FIVE STAR ITALIAN RESORT SURROUNDED BY BEAUTIFUL PEOPLE, BUT I SAID, NO, THAT\\'S TOO EASY. I WANT TO SHOOT IN A FREEZING CANADIAN FOREST WHILE BEING CHASED AROUND BY A GUY WHOSE HEAD LOOKS LIKE A GENITAL WART. IT IS AN HONOR BEING A PART OF THESE HUGE FRANCHISEs LIKE \"GAME OF THRONES\" AND \"STAR WARS,\" BUT I\\'M STILL GETTING USED TO PEOPLE RECOGNIZING ME. THE OTHER DAY, A GUY STOPPED ME ON THE STREET AND SAYS, MY SON LOVES \"THE MANDALORIAN\" AND THE NEXT THING I KNOW, I\\'M FACE TIMING WITH A 6-YEAR-OLD WHO HAS NO IDEA WHO I AM BECAUSE MY CHARACTER WEARS A MASK THE ENTIRE SHOW. THE GUY IS LIKE, DO THE MANDO VOICE, BUT IT\\'S LIKE A BEDROOM VOICE. WITHOUT THE MASK, IT JUST SOUNDS PORNY. PEOPLE WALKING BY ON THE STREET SEE ME WHISPERING TO A 6-YEAR-OLD KID. I CAN BRING YOU IN WARM, OR I CAN BRING YOU IN COLD. EVEN THOUGH I CAME TO THE U.S. WHEN I WAS LITTLE, I WAS BORN IN CHILE, AND I HAVE 34 FIRST COUSINS WHO ARE STILL THERE. THEY\\'RE VERY PROUD OF ME. I KNOW THEY\\'RE PROUD BECAUSE THEY GIVE MY PHONE NUMBER TO EVERY PERSON THEY MEET, WHICH MEANS EVERY DAY, SOMEONE IN SANTIAGO WILL TEXT ME STUFF LIKE, CAN YOU COME TO MY WEDDING, OR CAN YOU SING MY PRIEST HAPPY BIRTHDAY, OR IS BABY YODA MEAN IN REAL LIFE. SO I HAVE TO BE LIKE NO, NO, AND HIS NAME IS GROGU. BUT MY COUSINS WEREN\\'T ALWAYS SO PROUD. EARLY IN MY CAREER, I PLAYED SMALL PARTS IN EVERY CRIME SHOW. I EVEN PLAYED TWO DIFFERENT CHARACTERS ON \"LAW AND ORDER.\" TITO CABASSA WHO LOOKED LIKE THIS. AND ONE YEAR LATER, I PLAYED REGGIE LUCKMAN WHO LOOKS LIKE THIS. AND THAT, MY FRIENDS, IS CALLED RANGE. BUT IT IS AMAZING TO BE HERE, LIKE I SAID. I WAS BORN IN CHILE, AND NINE MONTHS LATER, MY PARENTS FLED AND BROUGHT ME AND MY SISTER TO THE U.S. THEY WERE SO BRAVE, AND WITHOUT THEM, I WOULDN\\'T BE HERE IN THIS WONDERFUL COUNTRY, AND I CERTAINLY WOULDN\\'T BE STANDING HERE WITH YOU ALL TONIGHT. SO TO ALL MY FAMILY WATCHING IN CHILE, I WANT TO SAY [ SPEAKING NON-ENGLISH ] WHICH MEANS, I LOVE YOU, I MISS YOU, AND STOP GIVING OUT MY PHONE NUMBER. WE\\'VE GOT AN AMAZING SHOW FOR YOU TONIGHT. COLDPLAY IS HERE, SO STICK', lookup_str='', metadata={'source': 'QsYGlZkevEg', 'title': 'Pedro Pascal Monologue - SNL', 'description': 'First-time host Pedro Pascal talks about filming The Last of Us and being recognized by fans.\\n\\nSaturday Night Live. Stream now on Peacock: https://pck.tv/3uQxh4q\\n\\nSubscribe to SNL: https://goo.gl/tUsXwM\\nStream Current Full Episodes: http://www.nbc.com/saturday-night-live\\n\\nWATCH PAST SNL SEASONS\\nGoogle Play - http://bit.ly/SNLGooglePlay\\niTunes - http://bit.ly/SNLiTunes\\n\\nSNL ON SOCIAL\\nSNL Instagram: http://instagram.com/nbcsnl\\nSNL Facebook: https://www.facebook.com/snl\\nSNL Twitter: https://twitter.com/nbcsnl\\nSNL TikTok: https://www.tiktok.com/@nbcsnl\\n\\nGET MORE NBC\\nLike NBC: http://Facebook.com/NBC\\nFollow NBC: http://Twitter.com/NBC\\nNBC Tumblr: http://NBCtv.tumblr.com/\\nYouTube: http://www.youtube.com/nbc\\nNBC Instagram: http://instagram.com/nbc\\n\\n#SNL #PedroPascal #SNL48 #Coldplay', 'view_count': 1175057, 'thumbnail_url': 'https://i.ytimg.com/vi/QsYGlZkevEg/sddefault.jpg', 'publish_date': datetime.datetime(2023, 2, 4, 0, 0), 'length': 224, 'author': 'Saturday Night Live'}, lookup_index=0)]"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "loader.load()"
+   ]
+  }
+ ],
+ "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/document_loaders/how_to_guides.rst

@@ -0,0 +1,61 @@
+How To Guides
+====================================
+
+There are a lot of different document loaders that LangChain supports. Below are how-to guides for working with them
+
+`File Loader <./examples/unstructured_file.html>`_: A walkthrough of how to use Unstructured to load files of arbitrary types (pdfs, txt, html, etc).
+
+`Directory Loader <./examples/directory_loader.html>`_: A walkthrough of how to use Unstructured load files from a given directory.
+
+`Notion <./examples/notion.html>`_: A walkthrough of how to load data for an arbitrary Notion DB.
+
+`ReadTheDocs <./examples/readthedocs_documentation.html>`_: A walkthrough of how to load data for documentation generated by ReadTheDocs.
+
+`HTML <./examples/html.html>`_: A walkthrough of how to load data from an html file.
+
+`PDF <./examples/pdf.html>`_: A walkthrough of how to load data from a PDF file.
+
+`PowerPoint <./examples/powerpoint.html>`_: A walkthrough of how to load data from a powerpoint file.
+
+`Email <./examples/email.html>`_: A walkthrough of how to load data from an email (`.eml`) file.
+
+`GoogleDrive <./examples/googledrive.html>`_: A walkthrough of how to load data from Google drive.
+
+`Microsoft Word <./examples/microsoft_word.html>`_: A walkthrough of how to load data from Microsoft Word files.
+
+`Obsidian <./examples/obsidian.html>`_: A walkthrough of how to load data from an Obsidian file dump.
+
+`Roam <./examples/roam.html>`_: A walkthrough of how to load data from a Roam file export.
+
+`EveryNote <./examples/everynote.html>`_: A walkthrough of how to load data from a EveryNote (`.enex`) file.
+
+`YouTube <./examples/youtube.html>`_: A walkthrough of how to load the transcript from a YouTube video.
+
+`s3 File <./examples/s3_file.html>`_: A walkthrough of how to load a file from s3.
+
+`s3 Directory <./examples/s3_directory.html>`_: A walkthrough of how to load all files in a directory from s3.
+
+`GCS File <./examples/gcs_file.html>`_: A walkthrough of how to load a file from Google Cloud Storage (GCS).
+
+`GCS Directory <./examples/gcs_directory.html>`_: A walkthrough of how to load all files in a directory from Google Cloud Storage (GCS).
+
+`Web Base <./examples/web_base.html>`_: A walkthrough of how to load all text data from webpages.
+
+`IMSDb <./examples/imsdb.html>`_: A walkthrough of how to load all text data from IMSDb webpage.
+
+`AZLyrics <./examples/azlyrics.html>`_: A walkthrough of how to load all text data from AZLyrics webpage.
+
+`College Confidential <./examples/college_confidential.html>`_: A walkthrough of how to load all text data from College Confidential webpage.
+
+`Gutenberg <./examples/gutenberg.html>`_: A walkthrough of how to load data from a Gutenberg ebook text.
+
+`Airbyte Json <./examples/airbyte_json.html>`_: A walkthrough of how to load data from a local Airbyte JSON file.
+
+`Online PDF <./examples/online_pdf.html>`_: A walkthrough of how to load data from an online PDF.
+
+.. toctree::
+   :maxdepth: 1
+   :glob:
+   :hidden:
+
+   examples/*

docs/modules/document_loaders/key_concepts.md

@@ -0,0 +1,12 @@
+# Key Concepts
+
+## Document
+This class is a container for document information. This contains two parts:
+- `page_content`: The content of the actual page itself.
+- `metadata`: The metadata associated with the document. This can be things like the file path, the url, etc.
+
+## Loader
+This base class is a way to load documents. It exposes a `load` method that returns `Document` objects.
+
+## [Unstructured](https://github.com/Unstructured-IO/unstructured)
+Unstructured is a python package specifically focused on transformations from raw documents to text.

docs/modules/llms/async_llm.ipynb

@@ -0,0 +1,150 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "f6574496-b360-4ffa-9523-7fd34a590164",
+   "metadata": {},
+   "source": [
+    "# Async API for LLM\n",
+    "\n",
+    "LangChain provides async support for LLMs by leveraging the [asyncio](https://docs.python.org/3/library/asyncio.html) library.\n",
+    "\n",
+    "Async support is particularly useful for calling multiple LLMs concurrently, as these calls are network-bound. Currently, only `OpenAI` is supported, but async support for other LLMs is on the roadmap.\n",
+    "\n",
+    "You can use the `agenerate` method to call an OpenAI LLM asynchronously."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "5e49e96c-0f88-466d-b3d3-ea0966bdf19e",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "I'm doing well. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "I am doing quite well. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing great, thank you! How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thanks for asking. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\u001b[1mConcurrent executed in 1.93 seconds.\u001b[0m\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing great, thank you. How about you?\n",
+      "\u001b[1mSerial executed in 10.54 seconds.\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "import time\n",
+    "import asyncio\n",
+    "\n",
+    "from langchain.llms import OpenAI\n",
+    "\n",
+    "def generate_serially():\n",
+    "    llm = OpenAI(temperature=0.9)\n",
+    "    for _ in range(10):\n",
+    "        resp = llm.generate([\"Hello, how are you?\"])\n",
+    "        print(resp.generations[0][0].text)\n",
+    "\n",
+    "\n",
+    "async def async_generate(llm):\n",
+    "    resp = await llm.agenerate([\"Hello, how are you?\"])\n",
+    "    print(resp.generations[0][0].text)\n",
+    "\n",
+    "\n",
+    "async def generate_concurrently():\n",
+    "    llm = OpenAI(temperature=0.9)\n",
+    "    tasks = [async_generate(llm) for _ in range(10)]\n",
+    "    await asyncio.gather(*tasks)\n",
+    "\n",
+    "\n",
+    "s = time.perf_counter()\n",
+    "# If running this outside of Jupyter, use asyncio.run(generate_concurrently())\n",
+    "await generate_concurrently() \n",
+    "elapsed = time.perf_counter() - s\n",
+    "print('\\033[1m' + f\"Concurrent executed in {elapsed:0.2f} seconds.\" + '\\033[0m')\n",
+    "\n",
+    "s = time.perf_counter()\n",
+    "generate_serially()\n",
+    "elapsed = time.perf_counter() - s\n",
+    "print('\\033[1m' + f\"Serial executed in {elapsed:0.2f} seconds.\" + '\\033[0m')"
+   ]
+  }
+ ],
+ "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/llms/examples/fake_llm.ipynb

@@ -0,0 +1,138 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "052dfe58",
+   "metadata": {},
+   "source": [
+    "# Fake LLM\n",
+    "We expose a fake LLM class that can be used for testing. This allows you to mock out calls to the LLM and simulate what would happen if the LLM responded in a certain way.\n",
+    "\n",
+    "In this notebook we go over how to use this.\n",
+    "\n",
+    "We start this with using the FakeLLM in an agent."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "ef97ac4d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.llms.fake import FakeListLLM"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "9a0a160f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.agents import load_tools\n",
+    "from langchain.agents import initialize_agent"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "b272258c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tools = load_tools([\"python_repl\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "94096c4c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "responses=[\n",
+    "    \"Action: Python REPL\\nAction Input: print(2 + 2)\",\n",
+    "    \"Final Answer: 4\"\n",
+    "]\n",
+    "llm = FakeListLLM(responses=responses)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "da226d02",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "44c13426",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mAction: Python REPL\n",
+      "Action Input: print(2 + 2)\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3m4\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3mFinal Answer: 4\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'4'"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent.run(\"whats 2 + 2\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "814c2858",
+   "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/llms/examples/token_usage_tracking.ipynb

@@ -0,0 +1,179 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "e5715368",
+   "metadata": {},
+   "source": [
+    "# Token Usage Tracking\n",
+    "\n",
+    "This notebook goes over how to track your token usage for specific calls. It is currently only implemented for the OpenAI API.\n",
+    "\n",
+    "Let's first look at an extremely simple example of tracking token usage for a single LLM call."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "9455db35",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.llms import OpenAI\n",
+    "from langchain.callbacks import get_openai_callback"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "d1c55cc9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(model_name=\"text-davinci-002\", n=2, best_of=2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "31667d54",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "42\n"
+     ]
+    }
+   ],
+   "source": [
+    "with get_openai_callback() as cb:\n",
+    "    result = llm(\"Tell me a joke\")\n",
+    "    print(cb.total_tokens)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c0ab6d27",
+   "metadata": {},
+   "source": [
+    "Anything inside the context manager will get tracked. Here's an example of using it to track multiple calls in sequence."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "e09420f4",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "83\n"
+     ]
+    }
+   ],
+   "source": [
+    "with get_openai_callback() as cb:\n",
+    "    result = llm(\"Tell me a joke\")\n",
+    "    result2 = llm(\"Tell me a joke\")\n",
+    "    print(cb.total_tokens)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d8186e7b",
+   "metadata": {},
+   "source": [
+    "If a chain or agent with multiple steps in it is used, it will track all those steps."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "5d1125c6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.agents import load_tools\n",
+    "from langchain.agents import initialize_agent\n",
+    "from langchain.llms import OpenAI\n",
+    "\n",
+    "llm = OpenAI(temperature=0)\n",
+    "tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)\n",
+    "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "2f98c536",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I need to find out who Olivia Wilde's boyfriend is and then calculate his age raised to the 0.23 power.\n",
+      "Action: Search\n",
+      "Action Input: \"Olivia Wilde boyfriend\"\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mJason Sudeikis\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to find out Jason Sudeikis' age\n",
+      "Action: Search\n",
+      "Action Input: \"Jason Sudeikis age\"\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3m47 years\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to calculate 47 raised to the 0.23 power\n",
+      "Action: Calculator\n",
+      "Action Input: 47^0.23\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mAnswer: 2.4242784855673896\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: Jason Sudeikis, Olivia Wilde's boyfriend, is 47 years old and his age raised to the 0.23 power is 2.4242784855673896.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "1465\n"
+     ]
+    }
+   ],
+   "source": [
+    "with get_openai_callback() as cb:\n",
+    "    response = agent.run(\"Who is Olivia Wilde's boyfriend? What is his current age raised to the 0.23 power?\")\n",
+    "    print(cb.total_tokens)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "80ca77a3",
+   "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/llms/generic_how_to.rst

@@ -9,6 +9,10 @@ The examples here all address certain "how-to" guides for working with LLMs.
 
 `Custom LLM <./examples/custom_llm.html>`_: How to create and use a custom LLM class, in case you have an LLM not from one of the standard providers (including one that you host yourself).
 
+`Token Usage Tracking <./examples/token_usage_tracking.html>`_: How to track the token usage of various chains/agents/LLM calls.
+
+`Fake LLM <./examples/fake_llm.html>`_: How to create and use a fake LLM for testing and debugging purposes.
+
 
 .. toctree::
    :maxdepth: 1

docs/modules/llms/getting_started.ipynb

@@ -18,7 +18,9 @@
    "cell_type": "code",
    "execution_count": 1,
    "id": "df924055",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "from langchain.llms import OpenAI"
@@ -207,14 +209,6 @@
    "source": [
     "llm.get_num_tokens(\"what a joke\")"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "b004ffdd",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {

docs/modules/llms/how_to_guides.rst

@@ -7,6 +7,8 @@ They are split into two categories:
 
 1. `Generic Functionality <./generic_how_to.html>`_: Covering generic functionality all LLMs should have.
 2. `Integrations <./integrations.html>`_: Covering integrations with various LLM providers.
+3. `Asynchronous <./async_llm.html>`_: Covering asynchronous functionality.
+4. `Streaming <./streaming_llm.html>`_: Covering streaming functionality.
 
 .. toctree::
    :maxdepth: 1

docs/modules/llms/integrations.rst

@@ -9,6 +9,16 @@ The examples here are all "how-to" guides for how to integrate with various LLM
 
 `Manifest <./integrations/manifest.html>`_: Covers how to utilize the Manifest wrapper.
 
+`Goose AI <./integrations/gooseai_example.html>`_: Covers how to utilize the Goose AI wrapper.
+
+`Cerebrium <./integrations/cerebriumai_example.html>`_: Covers how to utilize the Cerebrium AI wrapper.
+
+`Petals <./integrations/petals_example.html>`_: Covers how to utilize the Petals wrapper.
+
+`Forefront AI <./integrations/forefrontai_example.html>`_: Covers how to utilize the Forefront AI wrapper.
+
+`PromptLayer OpenAI <./integrations/promptlayer_openai.html>`_: Covers how to use `PromptLayer <https://promptlayer.com>`_ with Langchain.
+
 
 .. toctree::
    :maxdepth: 1

docs/modules/llms/integrations/azure_openai_example.ipynb

@@ -20,7 +20,7 @@
     "# The API version you want to use: set this to `2022-12-01` for the released version.\n",
     "export OPENAI_API_VERSION=2022-12-01\n",
     "# The base URL for your Azure OpenAI resource.  You can find this in the Azure portal under your Azure OpenAI resource.\n",
-    "export OPENAI_API_BASE_URL=https://your-resource-name.openai.azure.com\n",
+    "export OPENAI_API_BASE=https://your-resource-name.openai.azure.com\n",
     "# The API key for your Azure OpenAI resource.  You can find this in the Azure portal under your Azure OpenAI resource.\n",
     "export OPENAI_API_KEY=<your Azure OpenAI API key>\n",
     "```\n",

docs/modules/llms/integrations/cerebriumai_example.ipynb

@@ -0,0 +1,156 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# CerebriumAI LLM Example\n",
+    "This notebook goes over how to use Langchain with [CerebriumAI](https://docs.cerebrium.ai/introduction)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Install cerebrium\n",
+    "The `cerebrium` package is required to use the CerebriumAI API. Install `cerebrium` using `pip3 install cerebrium`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "$ pip3 install cerebrium"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from langchain.llms import CerebriumAI\n",
+    "from langchain import PromptTemplate, LLMChain"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Set the Environment API Key\n",
+    "Make sure to get your API key from CerebriumAI. You are given a 1 hour free of serverless GPU compute to test different models."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "os.environ[\"CEREBRIUMAI_API_KEY\"] = \"YOUR_KEY_HERE\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create the CerebriumAI instance\n",
+    "You can specify different parameters such as the model endpoint url, max length, temperature, etc. You must provide an endpoint url."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = CerebriumAI(endpoint_url=\"YOUR ENDPOINT URL HERE\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create a Prompt Template\n",
+    "We will create a prompt template for Question and Answer."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "template = \"\"\"Question: {question}\n",
+    "\n",
+    "Answer: Let's think step by step.\"\"\"\n",
+    "\n",
+    "prompt = PromptTemplate(template=template, input_variables=[\"question\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Initiate the LLMChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm_chain = LLMChain(prompt=prompt, llm=llm)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Run the LLMChain\n",
+    "Provide a question and run the LLMChain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "question = \"What NFL team won the Super Bowl in the year Justin Beiber was born?\"\n",
+    "\n",
+    "llm_chain.run(question)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.9.12 ('palm')",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.9.12"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "a0a0263b650d907a3bfe41c0f8d6a63a071b884df3cfdc1579f00cdc1aed6b03"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/modules/llms/integrations/forefrontai_example.ipynb

@@ -0,0 +1,139 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# ForefrontAI LLM Example\n",
+    "This notebook goes over how to use Langchain with [ForefrontAI](https://www.forefront.ai/)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from langchain.llms import ForefrontAI\n",
+    "from langchain import PromptTemplate, LLMChain"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Set the Environment API Key\n",
+    "Make sure to get your API key from ForefrontAI. You are given a 5 day free trial to test different models."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "os.environ[\"FOREFRONTAI_API_KEY\"] = \"YOUR_KEY_HERE\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create the ForefrontAI instance\n",
+    "You can specify different parameters such as the model endpoint url, length, temperature, etc. You must provide an endpoint url."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = ForefrontAI(endpoint_url=\"YOUR ENDPOINT URL HERE\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create a Prompt Template\n",
+    "We will create a prompt template for Question and Answer."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "template = \"\"\"Question: {question}\n",
+    "\n",
+    "Answer: Let's think step by step.\"\"\"\n",
+    "\n",
+    "prompt = PromptTemplate(template=template, input_variables=[\"question\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Initiate the LLMChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm_chain = LLMChain(prompt=prompt, llm=llm)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Run the LLMChain\n",
+    "Provide a question and run the LLMChain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "question = \"What NFL team won the Super Bowl in the year Justin Beiber was born?\"\n",
+    "\n",
+    "llm_chain.run(question)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.9.12 ('palm')",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.9.12"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "a0a0263b650d907a3bfe41c0f8d6a63a071b884df3cfdc1579f00cdc1aed6b03"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/modules/llms/integrations/gooseai_example.ipynb

@@ -0,0 +1,156 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# GooseAI LLM Example\n",
+    "This notebook goes over how to use Langchain with [GooseAI](https://goose.ai/)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Install openai\n",
+    "The `openai` package is required to use the GooseAI API. Install `openai` using `pip3 install openai`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "$ pip3 install openai"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from langchain.llms import GooseAI\n",
+    "from langchain import PromptTemplate, LLMChain"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Set the Environment API Key\n",
+    "Make sure to get your API key from GooseAI. You are given $10 in free credits to test different models."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "os.environ[\"GOOSEAI_API_KEY\"] = \"YOUR_KEY_HERE\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create the GooseAI instance\n",
+    "You can specify different parameters such as the model name, max tokens generated, temperature, etc."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = GooseAI()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create a Prompt Template\n",
+    "We will create a prompt template for Question and Answer."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "template = \"\"\"Question: {question}\n",
+    "\n",
+    "Answer: Let's think step by step.\"\"\"\n",
+    "\n",
+    "prompt = PromptTemplate(template=template, input_variables=[\"question\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Initiate the LLMChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm_chain = LLMChain(prompt=prompt, llm=llm)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Run the LLMChain\n",
+    "Provide a question and run the LLMChain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "question = \"What NFL team won the Super Bowl in the year Justin Beiber was born?\"\n",
+    "\n",
+    "llm_chain.run(question)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.9.12 ('palm')",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.9.12"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "a0a0263b650d907a3bfe41c0f8d6a63a071b884df3cfdc1579f00cdc1aed6b03"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/modules/llms/integrations/huggingface_hub.ipynb

@@ -5,9 +5,9 @@
    "id": "959300d4",
    "metadata": {},
    "source": [
-    "# HuggingFace Hub\n",
+    "# Hugging Face Hub\n",
     "\n",
-    "This example showcases how to connect to the HuggingFace Hub."
+    "This example showcases how to connect to the Hugging Face Hub."
    ]
   },
   {
@@ -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\n"
+      "The Seattle Seahawks won the Super Bowl in 2010. Justin Beiber was born in 2010. The final answer: Seattle Seahawks.\n"
      ]
     }
    ],
@@ -31,7 +31,7 @@
     "\n",
     "Answer: Let's think step by step.\"\"\"\n",
     "prompt = PromptTemplate(template=template, input_variables=[\"question\"])\n",
-    "llm_chain = LLMChain(prompt=prompt, llm=HuggingFaceHub(repo_id=\"google/flan-t5-xl\", model_kwargs={\"temperature\":1e-10}))\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",
     "\n",

docs/modules/llms/integrations/petals_example.ipynb

@@ -0,0 +1,156 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Petals LLM Example\n",
+    "This notebook goes over how to use Langchain with [Petals](https://github.com/bigscience-workshop/petals)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Install petals\n",
+    "The `petals` package is required to use the Petals API. Install `petals` using `pip3 install petals`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "$ pip3 install petals"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from langchain.llms import Petals\n",
+    "from langchain import PromptTemplate, LLMChain"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Set the Environment API Key\n",
+    "Make sure to get your API key from Huggingface."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "os.environ[\"HUGGINGFACE_API_KEY\"] = \"YOUR_KEY_HERE\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create the Petals instance\n",
+    "You can specify different parameters such as the model name, max new tokens, temperature, etc."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = Petals(model_name=\"bigscience/bloom-petals\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create a Prompt Template\n",
+    "We will create a prompt template for Question and Answer."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "template = \"\"\"Question: {question}\n",
+    "\n",
+    "Answer: Let's think step by step.\"\"\"\n",
+    "\n",
+    "prompt = PromptTemplate(template=template, input_variables=[\"question\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Initiate the LLMChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm_chain = LLMChain(prompt=prompt, llm=llm)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Run the LLMChain\n",
+    "Provide a question and run the LLMChain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "question = \"What NFL team won the Super Bowl in the year Justin Beiber was born?\"\n",
+    "\n",
+    "llm_chain.run(question)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.9.12 ('palm')",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.9.12"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "a0a0263b650d907a3bfe41c0f8d6a63a071b884df3cfdc1579f00cdc1aed6b03"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/modules/llms/integrations/promptlayer_openai.ipynb

@@ -0,0 +1,81 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "959300d4",
+   "metadata": {},
+   "source": [
+    "# PromptLayer OpenAI\n",
+    "\n",
+    "This example showcases how to connect to [PromptLayer](https://www.promptlayer.com) to start recording your OpenAI requests."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "3acf0069",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "' to go outside\\n\\nUnfortunately, cats cannot go outside without being supervised by a human. Going outside can be dangerous for cats, as they may come into contact with cars, other animals, or other dangers. If you want to go outside, ask your human to take you on a supervised walk or to a safe, enclosed outdoor space.'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.llms import PromptLayerOpenAI\n",
+    "import promptlayer\n",
+    "import os\n",
+    "\n",
+    "# Set up API keys, you can get a promptlayer api key here: https://promptlayer.com/\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"YOUR_OPENAI_API_KEY\"\n",
+    "promptlayer.api_key = \"YOUR_PROMPTLAYER_API_KEY\"\n",
+    "\n",
+    "# Optionally pass in pl_tags to track your requests\n",
+    "llm = PromptLayerOpenAI(pl_tags=[\"langchain\"])\n",
+    "\n",
+    "llm(\"I am a cat and I want\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ae4559c7",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.8"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "c4fe2cd85a8d9e8baaec5340ce66faff1c77581a9f43e6c45e85e09b6fced008"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/modules/llms/streaming_llm.ipynb

@@ -0,0 +1,140 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "6eaf7e66-f49c-42da-8d11-22ea13bef718",
+   "metadata": {},
+   "source": [
+    "# Streaming with LLMs\n",
+    "\n",
+    "LangChain provides streaming support for LLMs. Currently, we only support streaming for the `OpenAI` LLM implementation, but streaming support for other LLM implementations is on the roadmap. To utilize streaming, use a [`CallbackHandler`](https://github.com/hwchase17/langchain/blob/master/langchain/callbacks/base.py) that implements `on_llm_new_token`. In this example, we are using [`StreamingStdOutCallbackHandler`]()."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "4ac0ff54-540a-4f2b-8d9a-b590fec7fe07",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "Verse 1\n",
+      "I'm sippin' on sparkling water,\n",
+      "It's so refreshing and light,\n",
+      "It's the perfect way to quench my thirst,\n",
+      "On a hot summer night.\n",
+      "\n",
+      "Chorus\n",
+      "Sparkling water, sparkling water,\n",
+      "It's the best way to stay hydrated,\n",
+      "It's so refreshing and light,\n",
+      "It's the perfect way to stay alive.\n",
+      "\n",
+      "Verse 2\n",
+      "I'm sippin' on sparkling water,\n",
+      "It's so bubbly and bright,\n",
+      "It's the perfect way to cool me down,\n",
+      "On a hot summer night.\n",
+      "\n",
+      "Chorus\n",
+      "Sparkling water, sparkling water,\n",
+      "It's the best way to stay hydrated,\n",
+      "It's so refreshing and light,\n",
+      "It's the perfect way to stay alive.\n",
+      "\n",
+      "Verse 3\n",
+      "I'm sippin' on sparkling water,\n",
+      "It's so crisp and clean,\n",
+      "It's the perfect way to keep me going,\n",
+      "On a hot summer day.\n",
+      "\n",
+      "Chorus\n",
+      "Sparkling water, sparkling water,\n",
+      "It's the best way to stay hydrated,\n",
+      "It's so refreshing and light,\n",
+      "It's the perfect way to stay alive."
+     ]
+    }
+   ],
+   "source": [
+    "from langchain.llms import OpenAI\n",
+    "from langchain.callbacks.base import CallbackManager\n",
+    "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
+    "\n",
+    "\n",
+    "llm = OpenAI(streaming=True, callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), verbose=True, temperature=0)\n",
+    "resp = llm(\"Write me a song about sparkling water.\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "61fb6de7-c6c8-48d0-a48e-1204c027a23c",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "We still have access to the end `LLMResult` if using `generate`. However, `token_usage` is not currently supported for streaming."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "a35373f1-9ee6-4753-a343-5aee749b8527",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "Q: What did the fish say when it hit the wall?\n",
+      "A: Dam!"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "LLMResult(generations=[[Generation(text='\\n\\nQ: What did the fish say when it hit the wall?\\nA: Dam!', generation_info={'finish_reason': 'stop', 'logprobs': None})]], llm_output={'token_usage': {}})"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "llm.generate([\"Tell me a joke.\"])"
+   ]
+  }
+ ],
+ "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
+}