bump version to 136 (#2634)

Minor typo in the docs ("reccomended" -> "recommended")

Co-authored-by: Nick Gibb <nick.gibb@bluedot.global>

.coveragerc

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

.dockerignore

@@ -0,0 +1,6 @@
+.venv
+.github
+.git
+.mypy_cache
+.pytest_cache
+Dockerfile

.flake8

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

.github/CONTRIBUTING.md

@@ -46,8 +46,8 @@ 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/).
+As of now, LangChain has an ad hoc release process: releases are cut with high frequency by
+a developer and published to [PyPI](https://pypi.org/project/langchain/).
 
 LangChain follows the [semver](https://semver.org/) versioning standard. However, as pre-1.0 software,
 even patch releases may contain [non-backwards-compatible changes](https://semver.org/#spec-item-4).
@@ -55,12 +55,16 @@ even patch releases may contain [non-backwards-compatible changes](https://semve
 If your contribution has made its way into a release, we will want to give you credit on Twitter (only if you want though)!
 If you have a Twitter account you would like us to mention, please let us know in the PR or in another manner.
 
-## 🤖Developer Setup
-
-### 🚀Quick Start
+## 🚀Quick Start
 
 This project uses [Poetry](https://python-poetry.org/) as a dependency manager. Check out Poetry's [documentation on how to install it](https://python-poetry.org/docs/#installation) on your system before proceeding.
 
+❗Note: If you use `Conda` or `Pyenv` as your environment / package manager, avoid dependency conflicts by doing the following first:
+1. *Before installing Poetry*, create and activate a new Conda env (e.g. `conda create -n langchain python=3.9`)
+2. Install Poetry (see above)
+3. Tell Poetry to use the virtualenv python environment (`poetry config virtualenvs.prefer-active-python true`)
+4. Continue with the following steps.
+
 To install requirements:
 
 ```bash
@@ -69,11 +73,15 @@ poetry install -E all
 
 This will install all requirements for running the package, examples, linting, formatting, tests, and coverage. Note the `-E all` flag will install all optional dependencies necessary for integration testing.
 
+❗Note: If you're running Poetry 1.4.1 and receive a `WheelFileValidationError` for `debugpy` during installation, you can try either downgrading to Poetry 1.4.0 or disabling "modern installation" (`poetry config installer.modern-installation false`) and re-install requirements. See [this `debugpy` issue](https://github.com/microsoft/debugpy/issues/1246) for more details.
+
 Now, you should be able to run the common tasks in the following section.
 
-### ✅Common Tasks
+## ✅Common Tasks
 
-#### Code Formatting
+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/).
 
@@ -83,7 +91,7 @@ To run formatting for this project:
 make format
 ```
 
-#### Linting
+### Linting
 
 Linting for this project is done via a combination of [Black](https://black.readthedocs.io/en/stable/), [isort](https://pycqa.github.io/isort/), [flake8](https://flake8.pycqa.org/en/latest/), and [mypy](http://mypy-lang.org/).
 
@@ -95,7 +103,7 @@ make lint
 
 We recognize linting can be annoying - if you do not want to do it, please contact a project maintainer, and they can help you with it. We do not want this to be a blocker for good code getting contributed.
 
-#### Coverage
+### Coverage
 
 Code coverage (i.e. the amount of code that is covered by unit tests) helps identify areas of the code that are potentially more or less brittle.
 
@@ -105,14 +113,20 @@ To get a report of current coverage, run the following:
 make coverage
 ```
 
-#### Testing
+### Testing
 
 Unit tests cover modular logic that does not require calls to outside APIs.
 
 To run unit tests:
 
 ```bash
-make tests
+make test
+```
+
+To run unit tests in Docker:
+
+```bash
+make docker_tests
 ```
 
 If you add new logic, please add a unit test.
@@ -127,7 +141,7 @@ make integration_tests
 
 If you add support for a new external API, please add a new integration test.
 
-#### Adding a Jupyter Notebook
+### Adding a Jupyter Notebook
 
 If you are adding a Jupyter notebook example, you'll want to install the optional `dev` dependencies.
 
@@ -145,10 +159,32 @@ poetry run jupyter notebook
 
 When you run `poetry install`, the `langchain` package is installed as editable in the virtualenv, so your new logic can be imported into the notebook.
 
-#### Contribute Documentation
+## Documentation
+
+### Contribute Documentation
 
 Docs are largely autogenerated by [sphinx](https://www.sphinx-doc.org/en/master/) from the code.
 
 For that reason, we ask that you add good documentation to all classes and methods.
 
 Similar to linting, we recognize documentation can be annoying. If you do not want to do it, please contact a project maintainer, and they can help you with it. We do not want this to be a blocker for good code getting contributed.
+
+### Build Documentation Locally
+
+Before building the documentation, it is always a good idea to clean the build directory:
+
+```bash
+make docs_clean
+```
+
+Next, you can run the linkchecker to make sure all links are valid:
+
+```bash
+make docs_linkcheck
+```
+
+Finally, you can build the documentation as outlined below:
+
+```bash
+make docs_build
+```

.github/workflows/linkcheck.yml

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

.github/workflows/release.yml

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

.github/workflows/test.yml

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

.gitignore

@@ -106,7 +106,9 @@ celerybeat.pid
 
 # Environments
 .env
+.envrc
 .venv
+.venvs
 env/
 venv/
 ENV/
@@ -130,3 +132,13 @@ dmypy.json
 
 # Pyre type checker
 .pyre/
+
+# macOS display setting files
+.DS_Store
+
+# Wandb directory
+wandb/
+
+# asdf tool versions
+.tool-versions
+/.ruff_cache/

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"

Dockerfile

@@ -0,0 +1,44 @@
+# This is a Dockerfile for running unit tests
+
+# Use the Python base image
+FROM python:3.11.2-bullseye AS builder
+
+# Define the version of Poetry to install (default is 1.4.2)
+ARG POETRY_VERSION=1.4.2
+
+# Define the directory to install Poetry to (default is /opt/poetry)
+ARG POETRY_HOME=/opt/poetry
+
+# Create a Python virtual environment for Poetry and install it
+RUN python3 -m venv ${POETRY_HOME} && \
+    $POETRY_HOME/bin/pip install --upgrade pip && \
+    $POETRY_HOME/bin/pip install poetry==${POETRY_VERSION}
+
+# Test if Poetry is installed in the expected path
+RUN echo "Poetry version:" && $POETRY_HOME/bin/poetry --version
+
+# Set the working directory for the app
+WORKDIR /app
+
+# Use a multi-stage build to install dependencies
+FROM builder AS dependencies
+
+# Copy only the dependency files for installation
+COPY pyproject.toml poetry.lock poetry.toml ./
+
+# Install the Poetry dependencies (this layer will be cached as long as the dependencies don't change)
+RUN $POETRY_HOME/bin/poetry install --no-interaction --no-ansi --with test
+
+# Use a multi-stage build to run tests
+FROM dependencies AS tests
+
+# Copy the rest of the app source code (this layer will be invalidated and rebuilt whenever the source code changes)
+COPY . .
+
+RUN /opt/poetry/bin/poetry install --no-interaction --no-ansi --with test
+
+# Set the entrypoint to run tests using Poetry
+ENTRYPOINT ["/opt/poetry/bin/poetry", "run", "pytest"]
+
+# Set the default command to run all unit tests
+CMD ["tests/unit_tests"]

Makefile

@@ -1,4 +1,6 @@
-.PHONY: format lint tests integration_tests
+.PHONY: all clean format lint test tests test_watch integration_tests docker_tests help
+
+all: help
 
 coverage:
 	poetry run pytest --cov \
@@ -6,18 +8,55 @@ coverage:
 		--cov-report xml \
 		--cov-report term-missing:skip-covered
 
+clean: docs_clean
+
+docs_build:
+	cd docs && poetry run make html
+
+docs_clean:
+	cd docs && poetry run make clean
+
+docs_linkcheck:
+	poetry run linkchecker docs/_build/html/index.html
+
 format:
 	poetry run black .
-	poetry run isort .
+	poetry run ruff --select I --fix .
 
-lint:
-	poetry run mypy .
-	poetry run black . --check
-	poetry run isort . --check
-	poetry run flake8 .
+PYTHON_FILES=.
+lint: PYTHON_FILES=.
+lint_diff: PYTHON_FILES=$(shell git diff --name-only --diff-filter=d master | grep -E '\.py$$')
+
+lint lint_diff:
+	poetry run mypy $(PYTHON_FILES)
+	poetry run black $(PYTHON_FILES) --check
+	poetry run ruff .
+
+test:
+	poetry run pytest tests/unit_tests
 
 tests:
 	poetry run pytest tests/unit_tests
 
+test_watch:
+	poetry run ptw --now . -- tests/unit_tests
+
 integration_tests:
 	poetry run pytest tests/integration_tests
+
+docker_tests:
+	docker build -t my-langchain-image:test .
+	docker run --rm my-langchain-image:test
+
+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'
+	@echo 'docker_tests        - run unit tests in docker'

README.md

@@ -2,7 +2,10 @@
 
 ⚡ Building applications with LLMs through composability ⚡
 
-[![lint](https://github.com/hwchase17/langchain/actions/workflows/lint.yml/badge.svg)](https://github.com/hwchase17/langchain/actions/workflows/lint.yml) [![test](https://github.com/hwchase17/langchain/actions/workflows/test.yml/badge.svg)](https://github.com/hwchase17/langchain/actions/workflows/test.yml) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai) [![](https://dcbadge.vercel.app/api/server/6adMQxSpJS?compact=true&style=flat)](https://discord.gg/6adMQxSpJS)
+[![lint](https://github.com/hwchase17/langchain/actions/workflows/lint.yml/badge.svg)](https://github.com/hwchase17/langchain/actions/workflows/lint.yml) [![test](https://github.com/hwchase17/langchain/actions/workflows/test.yml/badge.svg)](https://github.com/hwchase17/langchain/actions/workflows/test.yml) [![linkcheck](https://github.com/hwchase17/langchain/actions/workflows/linkcheck.yml/badge.svg)](https://github.com/hwchase17/langchain/actions/workflows/linkcheck.yml) [![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
 
@@ -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/modules/agents.html)
+- End-to-end Example: [GPT+WolframAlpha](https://huggingface.co/spaces/JavaFXpert/Chat-GPT-LangChain)
 
 ## 📖 Documentation
 
@@ -24,11 +42,11 @@ Please see [here](https://langchain.readthedocs.io/en/latest/?) for full documen
 - Getting started (installation, setting up the environment, simple examples)
 - How-To examples (demos, integrations, helper functions)
 - Reference (full API docs)
-  Resources (high-level explanation of core concepts)
+- Resources (high-level explanation of core concepts)
 
 ## 🚀 What can this help with?
 
-There are four main areas that LangChain is designed to help with.
+There are six main areas that LangChain is designed to help with.
 These are, in increasing order of complexity:
 
 **📃 LLMs and Prompts:**
@@ -39,6 +57,10 @@ This includes prompt management, prompt optimization, generic interface for all
 
 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.
 
+**📚 Data Augmented Generation:**
+
+Data Augmented Generation involves specific types of chains that first interact with an external datasource to fetch data to use in the generation step. Examples of this include summarization of long pieces of text and question/answering over specific data sources.
+
 **🤖 Agents:**
 
 Agents involve an LLM making decisions about which Actions to take, taking that Action, seeing an Observation, and repeating that until done. LangChain provides a standard interface for agents, a selection of agents to choose from, and examples of end to end agents.
@@ -47,11 +69,14 @@ Agents involve an LLM making decisions about which Actions to take, taking that
 
 Memory is the concept of persisting state between calls of a chain/agent. LangChain provides a standard interface for memory, a collection of memory implementations, and examples of chains/agents that use memory.
 
-For more information on these concepts, please see our [full documentation](https://langchain.readthedocs.io/en/latest/?).
+**🧐 Evaluation:**
+
+[BETA] Generative models are notoriously hard to evaluate with traditional metrics. One new way of evaluating them is using language models themselves to do the evaluation. LangChain provides some prompts/chains for assisting in this.
+
+For more information on these concepts, please see our [full documentation](https://langchain.readthedocs.io/en/latest/).
 
 ## 💁 Contributing
 
-As an open source project in a rapidly developing field, we are extremely open
-to contributions, whether it be in the form of a new feature, improved infra, or better documentation.
+As an open source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infra, or better documentation.
 
-For detailed information on how to contribute, see [here](CONTRIBUTING.md).
+For detailed information on how to contribute, see [here](.github/CONTRIBUTING.md).

docs/Makefile

@@ -3,7 +3,7 @@
 
 # You can set these variables from the command line, and also
 # from the environment for the first two.
-SPHINXOPTS    ?=
+SPHINXOPTS    ?= 
 SPHINXBUILD   ?= sphinx-build
 SPHINXAUTOBUILD   ?= sphinx-autobuild
 SOURCEDIR     = .

docs/_static/css/custom.css

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

docs/conf.py

@@ -22,13 +22,16 @@ with open("../pyproject.toml") as f:
 
 # -- Project information -----------------------------------------------------
 
-project = "LangChain"
-copyright = "2022, Harrison Chase"
+project = "🦜🔗 LangChain"
+copyright = "2023, Harrison Chase"
 author = "Harrison Chase"
 
 version = data["tool"]["poetry"]["version"]
 release = version
 
+html_title = project + " " + version
+html_last_updated_fmt = "%b %d, %Y"
+
 
 # -- General configuration ---------------------------------------------------
 
@@ -42,11 +45,12 @@ extensions = [
     "sphinx.ext.napoleon",
     "sphinx.ext.viewcode",
     "sphinxcontrib.autodoc_pydantic",
-    "myst_parser",
-    "nbsphinx",
+    "myst_nb",
+    "sphinx_copybutton",
     "sphinx_panels",
+    "IPython.sphinxext.ipython_console_highlighting",
 ]
-
+source_suffix = [".ipynb", ".html", ".md", ".rst"]
 
 autodoc_pydantic_model_show_json = False
 autodoc_pydantic_field_list_validators = False
@@ -73,8 +77,13 @@ exclude_patterns = ["_build", "Thumbs.db", ".DS_Store"]
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
-html_theme = "sphinx_rtd_theme"
-# html_theme = "sphinx_typlog_theme"
+html_theme = "sphinx_book_theme"
+
+html_theme_options = {
+    "path_to_docs": "docs",
+    "repository_url": "https://github.com/hwchase17/langchain",
+    "use_repository_button": True,
+}
 
 html_context = {
     "display_github": True,  # Integrate GitHub
@@ -87,4 +96,12 @@ html_context = {
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path: list = []
+html_static_path = ["_static"]
+
+# These paths are either relative to html_static_path
+# or fully qualified paths (eg. https://...)
+html_css_files = [
+    "css/custom.css",
+]
+nb_execution_mode = "off"
+myst_enable_extensions = ["colon_fence"]

docs/deployments.md

@@ -0,0 +1,42 @@
+# Deployments
+
+So you've made a really cool chain - now what? How do you deploy it and make it easily sharable with the world?
+
+This section covers several options for that.
+Note that these are meant as quick deployment options for prototypes and demos, and not for production systems.
+If you are looking for help with deployment of a production system, please contact us directly.
+
+What follows is a list of template GitHub repositories aimed that are intended to be
+very easy to fork and modify to use your chain.
+This is far from an exhaustive list of options, and we are EXTREMELY open to contributions here.
+
+## [Streamlit](https://github.com/hwchase17/langchain-streamlit-template)
+
+This repo serves as a template for how to deploy a LangChain with Streamlit.
+It implements a chatbot interface.
+It also contains instructions for how to deploy this app on the Streamlit platform.
+
+## [Gradio (on Hugging Face)](https://github.com/hwchase17/langchain-gradio-template)
+
+This repo serves as a template for how deploy a LangChain with Gradio.
+It implements a chatbot interface, with a "Bring-Your-Own-Token" approach (nice for not wracking up big bills).
+It also contains instructions for how to deploy this app on the Hugging Face platform.
+This is heavily influenced by James Weaver's [excellent examples](https://huggingface.co/JavaFXpert).
+
+## [Beam](https://github.com/slai-labs/get-beam/tree/main/examples/langchain-question-answering)
+
+This repo serves as a template for how deploy a LangChain with [Beam](https://beam.cloud).
+
+It implements a Question Answering app and contains instructions for deploying the app as a serverless REST API.
+
+## [Vercel](https://github.com/homanp/vercel-langchain)
+
+A minimal example on how to run LangChain on Vercel using Flask.
+
+
+## [SteamShip](https://github.com/steamship-core/steamship-langchain/)
+This repository contains LangChain adapters for Steamship, enabling LangChain developers to rapidly deploy their apps on Steamship.
+This includes: production ready endpoints, horizontal scaling across dependencies, persistant storage of app state, multi-tenancy support, etc.
+
+## [Langchain-serve](https://github.com/jina-ai/langchain-serve)
+This repository allows users to serve local chains and agents as RESTful, gRPC, or Websocket APIs thanks to [Jina](https://docs.jina.ai/). Deploy your chains & agents with ease and enjoy independent scaling, serverless and autoscaling APIs, as well as a Streamlit playground on Jina AI Cloud.

docs/ecosystem.rst

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

docs/ecosystem/ai21.md

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

docs/ecosystem/aim_tracking.ipynb

@@ -0,0 +1,293 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Aim\n",
+    "\n",
+    "Aim makes it super easy to visualize and debug LangChain executions. Aim tracks inputs and outputs of LLMs and tools, as well as actions of agents. \n",
+    "\n",
+    "With Aim, you can easily debug and examine an individual execution:\n",
+    "\n",
+    "![](https://user-images.githubusercontent.com/13848158/227784778-06b806c7-74a1-4d15-ab85-9ece09b458aa.png)\n",
+    "\n",
+    "Additionally, you have the option to compare multiple executions side by side:\n",
+    "\n",
+    "![](https://user-images.githubusercontent.com/13848158/227784994-699b24b7-e69b-48f9-9ffa-e6a6142fd719.png)\n",
+    "\n",
+    "Aim is fully open source, [learn more](https://github.com/aimhubio/aim) about Aim on GitHub.\n",
+    "\n",
+    "Let's move forward and see how to enable and configure Aim callback."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<h3>Tracking LangChain Executions with Aim</h3>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "In this notebook we will explore three usage scenarios. To start off, we will install the necessary packages and import certain modules. Subsequently, we will configure two environment variables that can be established either within the Python script or through the terminal."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "mf88kuCJhbVu"
+   },
+   "outputs": [],
+   "source": [
+    "!pip install aim\n",
+    "!pip install langchain\n",
+    "!pip install openai\n",
+    "!pip install google-search-results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "g4eTuajwfl6L"
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from datetime import datetime\n",
+    "\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.callbacks.base import CallbackManager\n",
+    "from langchain.callbacks import AimCallbackHandler, StdOutCallbackHandler"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Our examples use a GPT model as the LLM, and OpenAI offers an API for this purpose. You can obtain the key from the following link: https://platform.openai.com/account/api-keys .\n",
+    "\n",
+    "We will use the SerpApi to retrieve search results from Google. To acquire the SerpApi key, please go to https://serpapi.com/manage-api-key ."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "T1bSmKd6V2If"
+   },
+   "outputs": [],
+   "source": [
+    "os.environ[\"OPENAI_API_KEY\"] = \"...\"\n",
+    "os.environ[\"SERPAPI_API_KEY\"] = \"...\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "QenUYuBZjIzc"
+   },
+   "source": [
+    "The event methods of `AimCallbackHandler` accept the LangChain module or agent as input and log at least the prompts and generated results, as well as the serialized version of the LangChain module, to the designated Aim run."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "KAz8weWuUeXF"
+   },
+   "outputs": [],
+   "source": [
+    "session_group = datetime.now().strftime(\"%m.%d.%Y_%H.%M.%S\")\n",
+    "aim_callback = AimCallbackHandler(\n",
+    "    repo=\".\",\n",
+    "    experiment_name=\"scenario 1: OpenAI LLM\",\n",
+    ")\n",
+    "\n",
+    "manager = CallbackManager([StdOutCallbackHandler(), aim_callback])\n",
+    "llm = OpenAI(temperature=0, callback_manager=manager, verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "b8WfByB4fl6N"
+   },
+   "source": [
+    "The `flush_tracker` function is used to record LangChain assets on Aim. By default, the session is reset rather than being terminated outright."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<h3>Scenario 1</h3> In the first scenario, we will use OpenAI LLM."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "o_VmneyIUyx8"
+   },
+   "outputs": [],
+   "source": [
+    "# scenario 1 - LLM\n",
+    "llm_result = llm.generate([\"Tell me a joke\", \"Tell me a poem\"] * 3)\n",
+    "aim_callback.flush_tracker(\n",
+    "    langchain_asset=llm,\n",
+    "    experiment_name=\"scenario 2: Chain with multiple SubChains on multiple generations\",\n",
+    ")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<h3>Scenario 2</h3> Scenario two involves chaining with multiple SubChains across multiple generations."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "trxslyb1U28Y"
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.prompts import PromptTemplate\n",
+    "from langchain.chains import LLMChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "uauQk10SUzF6"
+   },
+   "outputs": [],
+   "source": [
+    "# scenario 2 - Chain\n",
+    "template = \"\"\"You are a playwright. Given the title of play, it is your job to write a synopsis for that title.\n",
+    "Title: {title}\n",
+    "Playwright: This is a synopsis for the above play:\"\"\"\n",
+    "prompt_template = PromptTemplate(input_variables=[\"title\"], template=template)\n",
+    "synopsis_chain = LLMChain(llm=llm, prompt=prompt_template, callback_manager=manager)\n",
+    "\n",
+    "test_prompts = [\n",
+    "    {\"title\": \"documentary about good video games that push the boundary of game design\"},\n",
+    "    {\"title\": \"the phenomenon behind the remarkable speed of cheetahs\"},\n",
+    "    {\"title\": \"the best in class mlops tooling\"},\n",
+    "]\n",
+    "synopsis_chain.apply(test_prompts)\n",
+    "aim_callback.flush_tracker(\n",
+    "    langchain_asset=synopsis_chain, experiment_name=\"scenario 3: Agent with Tools\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<h3>Scenario 3</h3> The third scenario involves an agent with tools."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "_jN73xcPVEpI"
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.agents import initialize_agent, load_tools\n",
+    "from langchain.agents import AgentType"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "Gpq4rk6VT9cu",
+    "outputId": "68ae261e-d0a2-4229-83c4-762562263b66"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I need to find out who Leo DiCaprio's girlfriend is and then calculate her age raised to the 0.43 power.\n",
+      "Action: Search\n",
+      "Action Input: \"Leo DiCaprio girlfriend\"\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mLeonardo DiCaprio seemed to prove a long-held theory about his love life right after splitting from girlfriend Camila Morrone just months ...\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to find out Camila Morrone's age\n",
+      "Action: Search\n",
+      "Action Input: \"Camila Morrone age\"\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3m25 years\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to calculate 25 raised to the 0.43 power\n",
+      "Action: Calculator\n",
+      "Action Input: 25^0.43\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mAnswer: 3.991298452658078\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: Camila Morrone is Leo DiCaprio's girlfriend and her current age raised to the 0.43 power is 3.991298452658078.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "# scenario 3 - Agent with Tools\n",
+    "tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm, callback_manager=manager)\n",
+    "agent = initialize_agent(\n",
+    "    tools,\n",
+    "    llm,\n",
+    "    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,\n",
+    "    callback_manager=manager,\n",
+    "    verbose=True,\n",
+    ")\n",
+    "agent.run(\n",
+    "    \"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\"\n",
+    ")\n",
+    "aim_callback.flush_tracker(langchain_asset=agent, reset=False, finish=True)"
+   ]
+  }
+ ],
+ "metadata": {
+  "accelerator": "GPU",
+  "colab": {
+   "provenance": []
+  },
+  "gpuClass": "standard",
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}

docs/ecosystem/apify.md

@@ -0,0 +1,46 @@
+# Apify
+
+This page covers how to use [Apify](https://apify.com) within LangChain.
+
+## Overview
+
+Apify is a cloud platform for web scraping and data extraction,
+which provides an [ecosystem](https://apify.com/store) of more than a thousand
+ready-made apps called *Actors* for various scraping, crawling, and extraction use cases.
+
+[![Apify Actors](../_static/ApifyActors.png)](https://apify.com/store)
+
+This integration enables you run Actors on the Apify platform and load their results into LangChain to feed your vector
+indexes with documents and data from the web, e.g. to generate answers from websites with documentation,
+blogs, or knowledge bases.
+
+
+## Installation and Setup
+
+- Install the Apify API client for Python with `pip install apify-client`
+- Get your [Apify API token](https://console.apify.com/account/integrations) and either set it as
+  an environment variable (`APIFY_API_TOKEN`) or pass it to the `ApifyWrapper` as `apify_api_token` in the constructor.
+
+
+## Wrappers
+
+### Utility
+
+You can use the `ApifyWrapper` to run Actors on the Apify platform.
+
+```python
+from langchain.utilities import ApifyWrapper
+```
+
+For a more detailed walkthrough of this wrapper, see [this notebook](../modules/agents/tools/examples/apify.ipynb).
+
+
+### Loader
+
+You can also use our `ApifyDatasetLoader` to get data from Apify dataset.
+
+```python
+from langchain.document_loaders import ApifyDatasetLoader
+```
+
+For a more detailed walkthrough of this loader, see [this notebook](../modules/indexes/document_loaders/examples/apify_dataset.ipynb).

docs/ecosystem/atlas.md

@@ -0,0 +1,27 @@
+# AtlasDB
+
+This page covers how to use Nomic's Atlas ecosystem within LangChain.
+It is broken into two parts: installation and setup, and then references to specific Atlas wrappers.
+
+## Installation and Setup
+- Install the Python package with `pip install nomic`
+- Nomic is also included in langchains poetry extras `poetry install -E all`
+
+## Wrappers
+
+### VectorStore
+
+There exists a wrapper around the Atlas neural database, allowing you to use it as a vectorstore.
+This vectorstore also gives you full access to the underlying AtlasProject object, which will allow you to use the full range of Atlas map interactions, such as bulk tagging and automatic topic modeling.
+Please see [the Atlas docs](https://docs.nomic.ai/atlas_api.html) for more detailed information.
+
+
+
+
+
+To import this vectorstore:
+```python
+from langchain.vectorstores import AtlasDB
+```
+
+For a more detailed walkthrough of the AtlasDB wrapper, see [this notebook](../modules/indexes/vectorstores/examples/atlas.ipynb)

docs/ecosystem/bananadev.md

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

docs/ecosystem/cerebriumai.md

@@ -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/indexes/vectorstores/getting_started.ipynb)

docs/ecosystem/clearml_tracking.ipynb

@@ -0,0 +1,589 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# ClearML Integration\n",
+    "\n",
+    "In order to properly keep track of your langchain experiments and their results, you can enable the ClearML integration. ClearML is an experiment manager that neatly tracks and organizes all your experiment runs.\n",
+    "\n",
+    "<a target=\"_blank\" href=\"https://colab.research.google.com/github/hwchase17/langchain/blob/master/docs/ecosystem/clearml_tracking.ipynb\">\n",
+    "  <img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/>\n",
+    "</a>"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Getting API Credentials\n",
+    "\n",
+    "We'll be using quite some APIs in this notebook, here is a list and where to get them:\n",
+    "\n",
+    "- ClearML: https://app.clear.ml/settings/workspace-configuration\n",
+    "- OpenAI: https://platform.openai.com/account/api-keys\n",
+    "- SerpAPI (google search): https://serpapi.com/dashboard"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "os.environ[\"CLEARML_API_ACCESS_KEY\"] = \"\"\n",
+    "os.environ[\"CLEARML_API_SECRET_KEY\"] = \"\"\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"\"\n",
+    "os.environ[\"SERPAPI_API_KEY\"] = \"\""
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Setting Up"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install clearml\n",
+    "!pip install pandas\n",
+    "!pip install textstat\n",
+    "!pip install spacy\n",
+    "!python -m spacy download en_core_web_sm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The clearml callback is currently in beta and is subject to change based on updates to `langchain`. Please report any issues to https://github.com/allegroai/clearml/issues with the tag `langchain`.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from datetime import datetime\n",
+    "from langchain.callbacks import ClearMLCallbackHandler, StdOutCallbackHandler\n",
+    "from langchain.callbacks.base import CallbackManager\n",
+    "from langchain.llms import OpenAI\n",
+    "\n",
+    "# Setup and use the ClearML Callback\n",
+    "clearml_callback = ClearMLCallbackHandler(\n",
+    "    task_type=\"inference\",\n",
+    "    project_name=\"langchain_callback_demo\",\n",
+    "    task_name=\"llm\",\n",
+    "    tags=[\"test\"],\n",
+    "    # Change the following parameters based on the amount of detail you want tracked\n",
+    "    visualize=True,\n",
+    "    complexity_metrics=True,\n",
+    "    stream_logs=True\n",
+    ")\n",
+    "manager = CallbackManager([StdOutCallbackHandler(), clearml_callback])\n",
+    "# Get the OpenAI model ready to go\n",
+    "llm = OpenAI(temperature=0, callback_manager=manager, verbose=True)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Scenario 1: Just an LLM\n",
+    "\n",
+    "First, let's just run a single LLM a few times and capture the resulting prompt-answer conversation in ClearML"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'prompts': 'Tell me a joke'}\n",
+      "{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'prompts': 'Tell me a poem'}\n",
+      "{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'prompts': 'Tell me a joke'}\n",
+      "{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'prompts': 'Tell me a poem'}\n",
+      "{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'prompts': 'Tell me a joke'}\n",
+      "{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'prompts': 'Tell me a poem'}\n",
+      "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'text-davinci-003', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nQ: What did the fish say when it hit the wall?\\nA: Dam!', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 109.04, 'flesch_kincaid_grade': 1.3, 'smog_index': 0.0, 'coleman_liau_index': -1.24, 'automated_readability_index': 0.3, 'dale_chall_readability_score': 5.5, 'difficult_words': 0, 'linsear_write_formula': 5.5, 'gunning_fog': 5.2, 'text_standard': '5th and 6th grade', 'fernandez_huerta': 133.58, 'szigriszt_pazos': 131.54, 'gutierrez_polini': 62.3, 'crawford': -0.2, 'gulpease_index': 79.8, 'osman': 116.91}\n",
+      "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'text-davinci-003', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nRoses are red,\\nViolets are blue,\\nSugar is sweet,\\nAnd so are you.', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 83.66, 'flesch_kincaid_grade': 4.8, 'smog_index': 0.0, 'coleman_liau_index': 3.23, 'automated_readability_index': 3.9, 'dale_chall_readability_score': 6.71, 'difficult_words': 2, 'linsear_write_formula': 6.5, 'gunning_fog': 8.28, 'text_standard': '6th and 7th grade', 'fernandez_huerta': 115.58, 'szigriszt_pazos': 112.37, 'gutierrez_polini': 54.83, 'crawford': 1.4, 'gulpease_index': 72.1, 'osman': 100.17}\n",
+      "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'text-davinci-003', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nQ: What did the fish say when it hit the wall?\\nA: Dam!', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 109.04, 'flesch_kincaid_grade': 1.3, 'smog_index': 0.0, 'coleman_liau_index': -1.24, 'automated_readability_index': 0.3, 'dale_chall_readability_score': 5.5, 'difficult_words': 0, 'linsear_write_formula': 5.5, 'gunning_fog': 5.2, 'text_standard': '5th and 6th grade', 'fernandez_huerta': 133.58, 'szigriszt_pazos': 131.54, 'gutierrez_polini': 62.3, 'crawford': -0.2, 'gulpease_index': 79.8, 'osman': 116.91}\n",
+      "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'text-davinci-003', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nRoses are red,\\nViolets are blue,\\nSugar is sweet,\\nAnd so are you.', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 83.66, 'flesch_kincaid_grade': 4.8, 'smog_index': 0.0, 'coleman_liau_index': 3.23, 'automated_readability_index': 3.9, 'dale_chall_readability_score': 6.71, 'difficult_words': 2, 'linsear_write_formula': 6.5, 'gunning_fog': 8.28, 'text_standard': '6th and 7th grade', 'fernandez_huerta': 115.58, 'szigriszt_pazos': 112.37, 'gutierrez_polini': 54.83, 'crawford': 1.4, 'gulpease_index': 72.1, 'osman': 100.17}\n",
+      "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'text-davinci-003', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nQ: What did the fish say when it hit the wall?\\nA: Dam!', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 109.04, 'flesch_kincaid_grade': 1.3, 'smog_index': 0.0, 'coleman_liau_index': -1.24, 'automated_readability_index': 0.3, 'dale_chall_readability_score': 5.5, 'difficult_words': 0, 'linsear_write_formula': 5.5, 'gunning_fog': 5.2, 'text_standard': '5th and 6th grade', 'fernandez_huerta': 133.58, 'szigriszt_pazos': 131.54, 'gutierrez_polini': 62.3, 'crawford': -0.2, 'gulpease_index': 79.8, 'osman': 116.91}\n",
+      "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'text-davinci-003', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nRoses are red,\\nViolets are blue,\\nSugar is sweet,\\nAnd so are you.', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 83.66, 'flesch_kincaid_grade': 4.8, 'smog_index': 0.0, 'coleman_liau_index': 3.23, 'automated_readability_index': 3.9, 'dale_chall_readability_score': 6.71, 'difficult_words': 2, 'linsear_write_formula': 6.5, 'gunning_fog': 8.28, 'text_standard': '6th and 7th grade', 'fernandez_huerta': 115.58, 'szigriszt_pazos': 112.37, 'gutierrez_polini': 54.83, 'crawford': 1.4, 'gulpease_index': 72.1, 'osman': 100.17}\n",
+      "{'action_records':           action    name  step  starts  ends  errors  text_ctr  chain_starts  \\\n",
+      "0   on_llm_start  OpenAI     1       1     0       0         0             0   \n",
+      "1   on_llm_start  OpenAI     1       1     0       0         0             0   \n",
+      "2   on_llm_start  OpenAI     1       1     0       0         0             0   \n",
+      "3   on_llm_start  OpenAI     1       1     0       0         0             0   \n",
+      "4   on_llm_start  OpenAI     1       1     0       0         0             0   \n",
+      "5   on_llm_start  OpenAI     1       1     0       0         0             0   \n",
+      "6     on_llm_end     NaN     2       1     1       0         0             0   \n",
+      "7     on_llm_end     NaN     2       1     1       0         0             0   \n",
+      "8     on_llm_end     NaN     2       1     1       0         0             0   \n",
+      "9     on_llm_end     NaN     2       1     1       0         0             0   \n",
+      "10    on_llm_end     NaN     2       1     1       0         0             0   \n",
+      "11    on_llm_end     NaN     2       1     1       0         0             0   \n",
+      "12  on_llm_start  OpenAI     3       2     1       0         0             0   \n",
+      "13  on_llm_start  OpenAI     3       2     1       0         0             0   \n",
+      "14  on_llm_start  OpenAI     3       2     1       0         0             0   \n",
+      "15  on_llm_start  OpenAI     3       2     1       0         0             0   \n",
+      "16  on_llm_start  OpenAI     3       2     1       0         0             0   \n",
+      "17  on_llm_start  OpenAI     3       2     1       0         0             0   \n",
+      "18    on_llm_end     NaN     4       2     2       0         0             0   \n",
+      "19    on_llm_end     NaN     4       2     2       0         0             0   \n",
+      "20    on_llm_end     NaN     4       2     2       0         0             0   \n",
+      "21    on_llm_end     NaN     4       2     2       0         0             0   \n",
+      "22    on_llm_end     NaN     4       2     2       0         0             0   \n",
+      "23    on_llm_end     NaN     4       2     2       0         0             0   \n",
+      "\n",
+      "    chain_ends  llm_starts  ...  difficult_words  linsear_write_formula  \\\n",
+      "0            0           1  ...              NaN                    NaN   \n",
+      "1            0           1  ...              NaN                    NaN   \n",
+      "2            0           1  ...              NaN                    NaN   \n",
+      "3            0           1  ...              NaN                    NaN   \n",
+      "4            0           1  ...              NaN                    NaN   \n",
+      "5            0           1  ...              NaN                    NaN   \n",
+      "6            0           1  ...              0.0                    5.5   \n",
+      "7            0           1  ...              2.0                    6.5   \n",
+      "8            0           1  ...              0.0                    5.5   \n",
+      "9            0           1  ...              2.0                    6.5   \n",
+      "10           0           1  ...              0.0                    5.5   \n",
+      "11           0           1  ...              2.0                    6.5   \n",
+      "12           0           2  ...              NaN                    NaN   \n",
+      "13           0           2  ...              NaN                    NaN   \n",
+      "14           0           2  ...              NaN                    NaN   \n",
+      "15           0           2  ...              NaN                    NaN   \n",
+      "16           0           2  ...              NaN                    NaN   \n",
+      "17           0           2  ...              NaN                    NaN   \n",
+      "18           0           2  ...              0.0                    5.5   \n",
+      "19           0           2  ...              2.0                    6.5   \n",
+      "20           0           2  ...              0.0                    5.5   \n",
+      "21           0           2  ...              2.0                    6.5   \n",
+      "22           0           2  ...              0.0                    5.5   \n",
+      "23           0           2  ...              2.0                    6.5   \n",
+      "\n",
+      "    gunning_fog      text_standard  fernandez_huerta szigriszt_pazos  \\\n",
+      "0           NaN                NaN               NaN             NaN   \n",
+      "1           NaN                NaN               NaN             NaN   \n",
+      "2           NaN                NaN               NaN             NaN   \n",
+      "3           NaN                NaN               NaN             NaN   \n",
+      "4           NaN                NaN               NaN             NaN   \n",
+      "5           NaN                NaN               NaN             NaN   \n",
+      "6          5.20  5th and 6th grade            133.58          131.54   \n",
+      "7          8.28  6th and 7th grade            115.58          112.37   \n",
+      "8          5.20  5th and 6th grade            133.58          131.54   \n",
+      "9          8.28  6th and 7th grade            115.58          112.37   \n",
+      "10         5.20  5th and 6th grade            133.58          131.54   \n",
+      "11         8.28  6th and 7th grade            115.58          112.37   \n",
+      "12          NaN                NaN               NaN             NaN   \n",
+      "13          NaN                NaN               NaN             NaN   \n",
+      "14          NaN                NaN               NaN             NaN   \n",
+      "15          NaN                NaN               NaN             NaN   \n",
+      "16          NaN                NaN               NaN             NaN   \n",
+      "17          NaN                NaN               NaN             NaN   \n",
+      "18         5.20  5th and 6th grade            133.58          131.54   \n",
+      "19         8.28  6th and 7th grade            115.58          112.37   \n",
+      "20         5.20  5th and 6th grade            133.58          131.54   \n",
+      "21         8.28  6th and 7th grade            115.58          112.37   \n",
+      "22         5.20  5th and 6th grade            133.58          131.54   \n",
+      "23         8.28  6th and 7th grade            115.58          112.37   \n",
+      "\n",
+      "    gutierrez_polini  crawford  gulpease_index   osman  \n",
+      "0                NaN       NaN             NaN     NaN  \n",
+      "1                NaN       NaN             NaN     NaN  \n",
+      "2                NaN       NaN             NaN     NaN  \n",
+      "3                NaN       NaN             NaN     NaN  \n",
+      "4                NaN       NaN             NaN     NaN  \n",
+      "5                NaN       NaN             NaN     NaN  \n",
+      "6              62.30      -0.2            79.8  116.91  \n",
+      "7              54.83       1.4            72.1  100.17  \n",
+      "8              62.30      -0.2            79.8  116.91  \n",
+      "9              54.83       1.4            72.1  100.17  \n",
+      "10             62.30      -0.2            79.8  116.91  \n",
+      "11             54.83       1.4            72.1  100.17  \n",
+      "12               NaN       NaN             NaN     NaN  \n",
+      "13               NaN       NaN             NaN     NaN  \n",
+      "14               NaN       NaN             NaN     NaN  \n",
+      "15               NaN       NaN             NaN     NaN  \n",
+      "16               NaN       NaN             NaN     NaN  \n",
+      "17               NaN       NaN             NaN     NaN  \n",
+      "18             62.30      -0.2            79.8  116.91  \n",
+      "19             54.83       1.4            72.1  100.17  \n",
+      "20             62.30      -0.2            79.8  116.91  \n",
+      "21             54.83       1.4            72.1  100.17  \n",
+      "22             62.30      -0.2            79.8  116.91  \n",
+      "23             54.83       1.4            72.1  100.17  \n",
+      "\n",
+      "[24 rows x 39 columns], 'session_analysis':     prompt_step         prompts    name  output_step  \\\n",
+      "0             1  Tell me a joke  OpenAI            2   \n",
+      "1             1  Tell me a poem  OpenAI            2   \n",
+      "2             1  Tell me a joke  OpenAI            2   \n",
+      "3             1  Tell me a poem  OpenAI            2   \n",
+      "4             1  Tell me a joke  OpenAI            2   \n",
+      "5             1  Tell me a poem  OpenAI            2   \n",
+      "6             3  Tell me a joke  OpenAI            4   \n",
+      "7             3  Tell me a poem  OpenAI            4   \n",
+      "8             3  Tell me a joke  OpenAI            4   \n",
+      "9             3  Tell me a poem  OpenAI            4   \n",
+      "10            3  Tell me a joke  OpenAI            4   \n",
+      "11            3  Tell me a poem  OpenAI            4   \n",
+      "\n",
+      "                                               output  \\\n",
+      "0   \\n\\nQ: What did the fish say when it hit the w...   \n",
+      "1   \\n\\nRoses are red,\\nViolets are blue,\\nSugar i...   \n",
+      "2   \\n\\nQ: What did the fish say when it hit the w...   \n",
+      "3   \\n\\nRoses are red,\\nViolets are blue,\\nSugar i...   \n",
+      "4   \\n\\nQ: What did the fish say when it hit the w...   \n",
+      "5   \\n\\nRoses are red,\\nViolets are blue,\\nSugar i...   \n",
+      "6   \\n\\nQ: What did the fish say when it hit the w...   \n",
+      "7   \\n\\nRoses are red,\\nViolets are blue,\\nSugar i...   \n",
+      "8   \\n\\nQ: What did the fish say when it hit the w...   \n",
+      "9   \\n\\nRoses are red,\\nViolets are blue,\\nSugar i...   \n",
+      "10  \\n\\nQ: What did the fish say when it hit the w...   \n",
+      "11  \\n\\nRoses are red,\\nViolets are blue,\\nSugar i...   \n",
+      "\n",
+      "    token_usage_total_tokens  token_usage_prompt_tokens  \\\n",
+      "0                        162                         24   \n",
+      "1                        162                         24   \n",
+      "2                        162                         24   \n",
+      "3                        162                         24   \n",
+      "4                        162                         24   \n",
+      "5                        162                         24   \n",
+      "6                        162                         24   \n",
+      "7                        162                         24   \n",
+      "8                        162                         24   \n",
+      "9                        162                         24   \n",
+      "10                       162                         24   \n",
+      "11                       162                         24   \n",
+      "\n",
+      "    token_usage_completion_tokens  flesch_reading_ease  flesch_kincaid_grade  \\\n",
+      "0                             138               109.04                   1.3   \n",
+      "1                             138                83.66                   4.8   \n",
+      "2                             138               109.04                   1.3   \n",
+      "3                             138                83.66                   4.8   \n",
+      "4                             138               109.04                   1.3   \n",
+      "5                             138                83.66                   4.8   \n",
+      "6                             138               109.04                   1.3   \n",
+      "7                             138                83.66                   4.8   \n",
+      "8                             138               109.04                   1.3   \n",
+      "9                             138                83.66                   4.8   \n",
+      "10                            138               109.04                   1.3   \n",
+      "11                            138                83.66                   4.8   \n",
+      "\n",
+      "    ...  difficult_words  linsear_write_formula  gunning_fog  \\\n",
+      "0   ...                0                    5.5         5.20   \n",
+      "1   ...                2                    6.5         8.28   \n",
+      "2   ...                0                    5.5         5.20   \n",
+      "3   ...                2                    6.5         8.28   \n",
+      "4   ...                0                    5.5         5.20   \n",
+      "5   ...                2                    6.5         8.28   \n",
+      "6   ...                0                    5.5         5.20   \n",
+      "7   ...                2                    6.5         8.28   \n",
+      "8   ...                0                    5.5         5.20   \n",
+      "9   ...                2                    6.5         8.28   \n",
+      "10  ...                0                    5.5         5.20   \n",
+      "11  ...                2                    6.5         8.28   \n",
+      "\n",
+      "        text_standard  fernandez_huerta  szigriszt_pazos  gutierrez_polini  \\\n",
+      "0   5th and 6th grade            133.58           131.54             62.30   \n",
+      "1   6th and 7th grade            115.58           112.37             54.83   \n",
+      "2   5th and 6th grade            133.58           131.54             62.30   \n",
+      "3   6th and 7th grade            115.58           112.37             54.83   \n",
+      "4   5th and 6th grade            133.58           131.54             62.30   \n",
+      "5   6th and 7th grade            115.58           112.37             54.83   \n",
+      "6   5th and 6th grade            133.58           131.54             62.30   \n",
+      "7   6th and 7th grade            115.58           112.37             54.83   \n",
+      "8   5th and 6th grade            133.58           131.54             62.30   \n",
+      "9   6th and 7th grade            115.58           112.37             54.83   \n",
+      "10  5th and 6th grade            133.58           131.54             62.30   \n",
+      "11  6th and 7th grade            115.58           112.37             54.83   \n",
+      "\n",
+      "   crawford  gulpease_index   osman  \n",
+      "0      -0.2            79.8  116.91  \n",
+      "1       1.4            72.1  100.17  \n",
+      "2      -0.2            79.8  116.91  \n",
+      "3       1.4            72.1  100.17  \n",
+      "4      -0.2            79.8  116.91  \n",
+      "5       1.4            72.1  100.17  \n",
+      "6      -0.2            79.8  116.91  \n",
+      "7       1.4            72.1  100.17  \n",
+      "8      -0.2            79.8  116.91  \n",
+      "9       1.4            72.1  100.17  \n",
+      "10     -0.2            79.8  116.91  \n",
+      "11      1.4            72.1  100.17  \n",
+      "\n",
+      "[12 rows x 24 columns]}\n",
+      "2023-03-29 14:00:25,948 - clearml.Task - INFO - Completed model upload to https://files.clear.ml/langchain_callback_demo/llm.988bd727b0e94a29a3ac0ee526813545/models/simple_sequential\n"
+     ]
+    }
+   ],
+   "source": [
+    "# SCENARIO 1 - LLM\n",
+    "llm_result = llm.generate([\"Tell me a joke\", \"Tell me a poem\"] * 3)\n",
+    "# After every generation run, use flush to make sure all the metrics\n",
+    "# prompts and other output are properly saved separately\n",
+    "clearml_callback.flush_tracker(langchain_asset=llm, name=\"simple_sequential\")"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "At this point you can already go to https://app.clear.ml and take a look at the resulting ClearML Task that was created.\n",
+    "\n",
+    "Among others, you should see that this notebook is saved along with any git information. The model JSON that contains the used parameters is saved as an artifact, there are also console logs and under the plots section, you'll find tables that represent the flow of the chain.\n",
+    "\n",
+    "Finally, if you enabled visualizations, these are stored as HTML files under debug samples."
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Scenario 2: Creating a agent with tools\n",
+    "\n",
+    "To show a more advanced workflow, let's create an agent with access to tools. The way ClearML tracks the results is not different though, only the table will look slightly different as there are other types of actions taken when compared to the earlier, simpler example.\n",
+    "\n",
+    "You can now also see the use of the `finish=True` keyword, which will fully close the ClearML Task, instead of just resetting the parameters and prompts for a new conversation."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "{'action': 'on_chain_start', 'name': 'AgentExecutor', 'step': 1, 'starts': 1, 'ends': 0, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 0, 'llm_ends': 0, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'input': 'Who is the wife of the person who sang summer of 69?'}\n",
+      "{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 2, 'starts': 2, 'ends': 0, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 1, 'llm_ends': 0, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'prompts': '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: Who is the wife of the person who sang summer of 69?\\nThought:'}\n",
+      "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 189, 'token_usage_completion_tokens': 34, 'token_usage_total_tokens': 223, 'model_name': 'text-davinci-003', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 1, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': ' I need to find out who sang summer of 69 and then find out who their wife is.\\nAction: Search\\nAction Input: \"Who sang summer of 69\"', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 91.61, 'flesch_kincaid_grade': 3.8, 'smog_index': 0.0, 'coleman_liau_index': 3.41, 'automated_readability_index': 3.5, 'dale_chall_readability_score': 6.06, 'difficult_words': 2, 'linsear_write_formula': 5.75, 'gunning_fog': 5.4, 'text_standard': '3rd and 4th grade', 'fernandez_huerta': 121.07, 'szigriszt_pazos': 119.5, 'gutierrez_polini': 54.91, 'crawford': 0.9, 'gulpease_index': 72.7, 'osman': 92.16}\n",
+      "\u001b[32;1m\u001b[1;3m I need to find out who sang summer of 69 and then find out who their wife is.\n",
+      "Action: Search\n",
+      "Action Input: \"Who sang summer of 69\"\u001b[0m{'action': 'on_agent_action', 'tool': 'Search', 'tool_input': 'Who sang summer of 69', 'log': ' I need to find out who sang summer of 69 and then find out who their wife is.\\nAction: Search\\nAction Input: \"Who sang summer of 69\"', 'step': 4, 'starts': 3, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 1, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 1, 'tool_ends': 0, 'agent_ends': 0}\n",
+      "{'action': 'on_tool_start', 'input_str': 'Who sang summer of 69', 'name': 'Search', 'description': 'A search engine. Useful for when you need to answer questions about current events. Input should be a search query.', 'step': 5, 'starts': 4, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 1, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 2, 'tool_ends': 0, 'agent_ends': 0}\n",
+      "\n",
+      "Observation: \u001b[36;1m\u001b[1;3mBryan Adams - Summer Of 69 (Official Music Video).\u001b[0m\n",
+      "Thought:{'action': 'on_tool_end', 'output': 'Bryan Adams - Summer Of 69 (Official Music Video).', 'step': 6, 'starts': 4, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 1, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 2, 'tool_ends': 1, 'agent_ends': 0}\n",
+      "{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 7, 'starts': 5, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 2, 'tool_ends': 1, 'agent_ends': 0, 'prompts': '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: Who is the wife of the person who sang summer of 69?\\nThought: I need to find out who sang summer of 69 and then find out who their wife is.\\nAction: Search\\nAction Input: \"Who sang summer of 69\"\\nObservation: Bryan Adams - Summer Of 69 (Official Music Video).\\nThought:'}\n",
+      "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 242, 'token_usage_completion_tokens': 28, 'token_usage_total_tokens': 270, 'model_name': 'text-davinci-003', 'step': 8, 'starts': 5, 'ends': 3, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 2, 'tool_ends': 1, 'agent_ends': 0, 'text': ' I need to find out who Bryan Adams is married to.\\nAction: Search\\nAction Input: \"Who is Bryan Adams married to\"', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 94.66, 'flesch_kincaid_grade': 2.7, 'smog_index': 0.0, 'coleman_liau_index': 4.73, 'automated_readability_index': 4.0, 'dale_chall_readability_score': 7.16, 'difficult_words': 2, 'linsear_write_formula': 4.25, 'gunning_fog': 4.2, 'text_standard': '4th and 5th grade', 'fernandez_huerta': 124.13, 'szigriszt_pazos': 119.2, 'gutierrez_polini': 52.26, 'crawford': 0.7, 'gulpease_index': 74.7, 'osman': 84.2}\n",
+      "\u001b[32;1m\u001b[1;3m I need to find out who Bryan Adams is married to.\n",
+      "Action: Search\n",
+      "Action Input: \"Who is Bryan Adams married to\"\u001b[0m{'action': 'on_agent_action', 'tool': 'Search', 'tool_input': 'Who is Bryan Adams married to', 'log': ' I need to find out who Bryan Adams is married to.\\nAction: Search\\nAction Input: \"Who is Bryan Adams married to\"', 'step': 9, 'starts': 6, 'ends': 3, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 3, 'tool_ends': 1, 'agent_ends': 0}\n",
+      "{'action': 'on_tool_start', 'input_str': 'Who is Bryan Adams married to', 'name': 'Search', 'description': 'A search engine. Useful for when you need to answer questions about current events. Input should be a search query.', 'step': 10, 'starts': 7, 'ends': 3, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 4, 'tool_ends': 1, 'agent_ends': 0}\n",
+      "\n",
+      "Observation: \u001b[36;1m\u001b[1;3mBryan Adams has never married. In the 1990s, he was in a relationship with Danish model Cecilie Thomsen. In 2011, Bryan and Alicia Grimaldi, his ...\u001b[0m\n",
+      "Thought:{'action': 'on_tool_end', 'output': 'Bryan Adams has never married. In the 1990s, he was in a relationship with Danish model Cecilie Thomsen. In 2011, Bryan and Alicia Grimaldi, his ...', 'step': 11, 'starts': 7, 'ends': 4, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 4, 'tool_ends': 2, 'agent_ends': 0}\n",
+      "{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 12, 'starts': 8, 'ends': 4, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 3, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 4, 'tool_ends': 2, 'agent_ends': 0, 'prompts': '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: Who is the wife of the person who sang summer of 69?\\nThought: I need to find out who sang summer of 69 and then find out who their wife is.\\nAction: Search\\nAction Input: \"Who sang summer of 69\"\\nObservation: Bryan Adams - Summer Of 69 (Official Music Video).\\nThought: I need to find out who Bryan Adams is married to.\\nAction: Search\\nAction Input: \"Who is Bryan Adams married to\"\\nObservation: Bryan Adams has never married. In the 1990s, he was in a relationship with Danish model Cecilie Thomsen. In 2011, Bryan and Alicia Grimaldi, his ...\\nThought:'}\n",
+      "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 314, 'token_usage_completion_tokens': 18, 'token_usage_total_tokens': 332, 'model_name': 'text-davinci-003', 'step': 13, 'starts': 8, 'ends': 5, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 3, 'llm_ends': 3, 'llm_streams': 0, 'tool_starts': 4, 'tool_ends': 2, 'agent_ends': 0, 'text': ' I now know the final answer.\\nFinal Answer: Bryan Adams has never been married.', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 81.29, 'flesch_kincaid_grade': 3.7, 'smog_index': 0.0, 'coleman_liau_index': 5.75, 'automated_readability_index': 3.9, 'dale_chall_readability_score': 7.37, 'difficult_words': 1, 'linsear_write_formula': 2.5, 'gunning_fog': 2.8, 'text_standard': '3rd and 4th grade', 'fernandez_huerta': 115.7, 'szigriszt_pazos': 110.84, 'gutierrez_polini': 49.79, 'crawford': 0.7, 'gulpease_index': 85.4, 'osman': 83.14}\n",
+      "\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: Bryan Adams has never been married.\u001b[0m\n",
+      "{'action': 'on_agent_finish', 'output': 'Bryan Adams has never been married.', 'log': ' I now know the final answer.\\nFinal Answer: Bryan Adams has never been married.', 'step': 14, 'starts': 8, 'ends': 6, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 3, 'llm_ends': 3, 'llm_streams': 0, 'tool_starts': 4, 'tool_ends': 2, 'agent_ends': 1}\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "{'action': 'on_chain_end', 'outputs': 'Bryan Adams has never been married.', 'step': 15, 'starts': 8, 'ends': 7, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 1, 'llm_starts': 3, 'llm_ends': 3, 'llm_streams': 0, 'tool_starts': 4, 'tool_ends': 2, 'agent_ends': 1}\n",
+      "{'action_records':              action    name  step  starts  ends  errors  text_ctr  \\\n",
+      "0      on_llm_start  OpenAI     1       1     0       0         0   \n",
+      "1      on_llm_start  OpenAI     1       1     0       0         0   \n",
+      "2      on_llm_start  OpenAI     1       1     0       0         0   \n",
+      "3      on_llm_start  OpenAI     1       1     0       0         0   \n",
+      "4      on_llm_start  OpenAI     1       1     0       0         0   \n",
+      "..              ...     ...   ...     ...   ...     ...       ...   \n",
+      "66      on_tool_end     NaN    11       7     4       0         0   \n",
+      "67     on_llm_start  OpenAI    12       8     4       0         0   \n",
+      "68       on_llm_end     NaN    13       8     5       0         0   \n",
+      "69  on_agent_finish     NaN    14       8     6       0         0   \n",
+      "70     on_chain_end     NaN    15       8     7       0         0   \n",
+      "\n",
+      "    chain_starts  chain_ends  llm_starts  ...  gulpease_index  osman  input  \\\n",
+      "0              0           0           1  ...             NaN    NaN    NaN   \n",
+      "1              0           0           1  ...             NaN    NaN    NaN   \n",
+      "2              0           0           1  ...             NaN    NaN    NaN   \n",
+      "3              0           0           1  ...             NaN    NaN    NaN   \n",
+      "4              0           0           1  ...             NaN    NaN    NaN   \n",
+      "..           ...         ...         ...  ...             ...    ...    ...   \n",
+      "66             1           0           2  ...             NaN    NaN    NaN   \n",
+      "67             1           0           3  ...             NaN    NaN    NaN   \n",
+      "68             1           0           3  ...            85.4  83.14    NaN   \n",
+      "69             1           0           3  ...             NaN    NaN    NaN   \n",
+      "70             1           1           3  ...             NaN    NaN    NaN   \n",
+      "\n",
+      "    tool  tool_input                                                log  \\\n",
+      "0    NaN         NaN                                                NaN   \n",
+      "1    NaN         NaN                                                NaN   \n",
+      "2    NaN         NaN                                                NaN   \n",
+      "3    NaN         NaN                                                NaN   \n",
+      "4    NaN         NaN                                                NaN   \n",
+      "..   ...         ...                                                ...   \n",
+      "66   NaN         NaN                                                NaN   \n",
+      "67   NaN         NaN                                                NaN   \n",
+      "68   NaN         NaN                                                NaN   \n",
+      "69   NaN         NaN   I now know the final answer.\\nFinal Answer: B...   \n",
+      "70   NaN         NaN                                                NaN   \n",
+      "\n",
+      "    input_str  description                                             output  \\\n",
+      "0         NaN          NaN                                                NaN   \n",
+      "1         NaN          NaN                                                NaN   \n",
+      "2         NaN          NaN                                                NaN   \n",
+      "3         NaN          NaN                                                NaN   \n",
+      "4         NaN          NaN                                                NaN   \n",
+      "..        ...          ...                                                ...   \n",
+      "66        NaN          NaN  Bryan Adams has never married. In the 1990s, h...   \n",
+      "67        NaN          NaN                                                NaN   \n",
+      "68        NaN          NaN                                                NaN   \n",
+      "69        NaN          NaN                Bryan Adams has never been married.   \n",
+      "70        NaN          NaN                                                NaN   \n",
+      "\n",
+      "                                outputs  \n",
+      "0                                   NaN  \n",
+      "1                                   NaN  \n",
+      "2                                   NaN  \n",
+      "3                                   NaN  \n",
+      "4                                   NaN  \n",
+      "..                                  ...  \n",
+      "66                                  NaN  \n",
+      "67                                  NaN  \n",
+      "68                                  NaN  \n",
+      "69                                  NaN  \n",
+      "70  Bryan Adams has never been married.  \n",
+      "\n",
+      "[71 rows x 47 columns], 'session_analysis':    prompt_step                                            prompts    name  \\\n",
+      "0            2  Answer the following questions as best you can...  OpenAI   \n",
+      "1            7  Answer the following questions as best you can...  OpenAI   \n",
+      "2           12  Answer the following questions as best you can...  OpenAI   \n",
+      "\n",
+      "   output_step                                             output  \\\n",
+      "0            3   I need to find out who sang summer of 69 and ...   \n",
+      "1            8   I need to find out who Bryan Adams is married...   \n",
+      "2           13   I now know the final answer.\\nFinal Answer: B...   \n",
+      "\n",
+      "   token_usage_total_tokens  token_usage_prompt_tokens  \\\n",
+      "0                       223                        189   \n",
+      "1                       270                        242   \n",
+      "2                       332                        314   \n",
+      "\n",
+      "   token_usage_completion_tokens  flesch_reading_ease  flesch_kincaid_grade  \\\n",
+      "0                             34                91.61                   3.8   \n",
+      "1                             28                94.66                   2.7   \n",
+      "2                             18                81.29                   3.7   \n",
+      "\n",
+      "   ...  difficult_words  linsear_write_formula  gunning_fog  \\\n",
+      "0  ...                2                   5.75          5.4   \n",
+      "1  ...                2                   4.25          4.2   \n",
+      "2  ...                1                   2.50          2.8   \n",
+      "\n",
+      "       text_standard  fernandez_huerta  szigriszt_pazos  gutierrez_polini  \\\n",
+      "0  3rd and 4th grade            121.07           119.50             54.91   \n",
+      "1  4th and 5th grade            124.13           119.20             52.26   \n",
+      "2  3rd and 4th grade            115.70           110.84             49.79   \n",
+      "\n",
+      "  crawford  gulpease_index  osman  \n",
+      "0      0.9            72.7  92.16  \n",
+      "1      0.7            74.7  84.20  \n",
+      "2      0.7            85.4  83.14  \n",
+      "\n",
+      "[3 rows x 24 columns]}\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Could not update last created model in Task 988bd727b0e94a29a3ac0ee526813545, Task status 'completed' cannot be updated\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain.agents import initialize_agent, load_tools\n",
+    "from langchain.agents import AgentType\n",
+    "\n",
+    "# SCENARIO 2 - Agent with Tools\n",
+    "tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm, callback_manager=manager)\n",
+    "agent = initialize_agent(\n",
+    "    tools,\n",
+    "    llm,\n",
+    "    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,\n",
+    "    callback_manager=manager,\n",
+    "    verbose=True,\n",
+    ")\n",
+    "agent.run(\n",
+    "    \"Who is the wife of the person who sang summer of 69?\"\n",
+    ")\n",
+    "clearml_callback.flush_tracker(langchain_asset=agent, name=\"Agent with Tools\", finish=True)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Tips and Next Steps\n",
+    "\n",
+    "- Make sure you always use a unique `name` argument for the `clearml_callback.flush_tracker` function. If not, the model parameters used for a run will override the previous run!\n",
+    "\n",
+    "- If you close the ClearML Callback using `clearml_callback.flush_tracker(..., finish=True)` the Callback cannot be used anymore. Make a new one if you want to keep logging.\n",
+    "\n",
+    "- Check out the rest of the open source ClearML ecosystem, there is a data version manager, a remote execution agent, automated pipelines and much more!\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.9"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "a53ebf4a859167383b364e7e7521d0add3c2dbbdecce4edf676e8c4634ff3fbb"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/ecosystem/cohere.md

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

docs/ecosystem/deepinfra.md

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

docs/ecosystem/deeplake.md

@@ -0,0 +1,30 @@
+# Deep Lake
+This page covers how to use the Deep Lake ecosystem within LangChain.
+
+## Why Deep Lake?
+- More than just a (multi-modal) vector store. You can later use the dataset to fine-tune your own LLM models.
+- Not only stores embeddings, but also the original data with automatic version control.
+- Truly serverless. Doesn't require another service and can be used with major cloud providers (AWS S3, GCS, etc.)
+
+## More Resources
+1. [Ultimate Guide to LangChain & Deep Lake: Build ChatGPT to Answer Questions on Your Financial Data](https://www.activeloop.ai/resources/ultimate-guide-to-lang-chain-deep-lake-build-chat-gpt-to-answer-questions-on-your-financial-data/)
+2. [Twitter the-algorithm codebase analysis with Deep Lake](../use_cases/code/twitter-the-algorithm-analysis-deeplake.ipynb)
+3. Here is [whitepaper](https://www.deeplake.ai/whitepaper) and [academic paper](https://arxiv.org/pdf/2209.10785.pdf) for Deep Lake
+4. Here is a set of additional resources available for review: [Deep Lake](https://github.com/activeloopai/deeplake), [Getting Started](https://docs.activeloop.ai/getting-started) and [Tutorials](https://docs.activeloop.ai/hub-tutorials)
+
+## Installation and Setup
+- Install the Python package with `pip install deeplake`
+
+## Wrappers
+
+### VectorStore
+
+There exists a wrapper around Deep Lake, a data lake for Deep Learning applications, allowing you to use it as a vector store (for now), whether for semantic search or example selection.
+
+To import this vectorstore:
+```python
+from langchain.vectorstores import DeepLake
+```
+
+
+For a more detailed walkthrough of the Deep Lake wrapper, see [this notebook](../modules/indexes/vectorstores/examples/deeplake.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

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

docs/ecosystem/google_serper.md

@@ -0,0 +1,73 @@
+# Google Serper Wrapper
+
+This page covers how to use the [Serper](https://serper.dev) Google Search API within LangChain. Serper is a low-cost Google Search API that can be used to add answer box, knowledge graph, and organic results data from Google Search. 
+It is broken into two parts: setup, and then references to the specific Google Serper wrapper.
+
+## Setup
+- Go to [serper.dev](https://serper.dev) to sign up for a free account
+- Get the api key and set it as an environment variable (`SERPER_API_KEY`)
+
+## Wrappers
+
+### Utility
+
+There exists a GoogleSerperAPIWrapper utility which wraps this API. To import this utility:
+
+```python
+from langchain.utilities import GoogleSerperAPIWrapper
+```
+
+You can use it as part of a Self Ask chain:
+
+```python
+from langchain.utilities import GoogleSerperAPIWrapper
+from langchain.llms.openai import OpenAI
+from langchain.agents import initialize_agent, Tool
+from langchain.agents import AgentType
+
+import os
+
+os.environ["SERPER_API_KEY"] = ""
+os.environ['OPENAI_API_KEY'] = ""
+
+llm = OpenAI(temperature=0)
+search = GoogleSerperAPIWrapper()
+tools = [
+    Tool(
+        name="Intermediate Answer",
+        func=search.run,
+        description="useful for when you need to ask with search"
+    )
+]
+
+self_ask_with_search = initialize_agent(tools, llm, agent=AgentType.SELF_ASK_WITH_SEARCH, verbose=True)
+self_ask_with_search.run("What is the hometown of the reigning men's U.S. Open champion?")
+```
+
+#### Output
+```
+Entering new AgentExecutor chain...
+ Yes.
+Follow up: Who is the reigning men's U.S. Open champion?
+Intermediate answer: Current champions Carlos Alcaraz, 2022 men's singles champion.
+Follow up: Where is Carlos Alcaraz from?
+Intermediate answer: El Palmar, Spain
+So the final answer is: El Palmar, Spain
+
+> Finished chain.
+
+'El Palmar, Spain'
+```
+
+For a more detailed walkthrough of this wrapper, see [this notebook](../modules/agents/tools/examples/google_serper.ipynb).
+
+### Tool
+
+You can also easily load this wrapper as a Tool (to use with an Agent).
+You can do this with:
+```python
+from langchain.agents import load_tools
+tools = load_tools(["google-serper"])
+```
+
+For more information on this, see [this page](../modules/agents/tools/getting_started.md)

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/gpt4all.md

@@ -0,0 +1,37 @@
+# GPT4All
+
+This page covers how to use the `GPT4All` wrapper within LangChain.
+It is broken into two parts: installation and setup, and then usage with an example.
+
+## Installation and Setup
+- Install the Python package with `pip install pyllamacpp`
+- Download a [GPT4All model](https://github.com/nomic-ai/gpt4all) and place it in your desired directory
+
+## Usage
+
+### GPT4All
+
+To use the GPT4All wrapper, you need to provide the path to the pre-trained model file and the model's configuration.
+```python
+from langchain.llms import GPT4All
+
+# Instantiate the model
+model = GPT4All(model="./models/gpt4all-model.bin", n_ctx=512, n_threads=8)
+
+# Generate text
+response = model("Once upon a time, ")
+```
+
+You can also customize the generation parameters, such as n_predict, temp, top_p, top_k, and others.
+
+Example:
+
+```python
+model = GPT4All(model="./models/gpt4all-model.bin", n_predict=55, temp=0)
+response = model("Once upon a time, ")
+```
+## Model File
+
+You can find links to model file downloads at the [GPT4all](https://github.com/nomic-ai/gpt4all) repository. They will need to be converted to `ggml` format to work, as specified in the [pyllamacpp](https://github.com/nomic-ai/pyllamacpp) repository.
+
+For a more detailed walkthrough of this, see [this notebook](../modules/models/llms/integrations/gpt4all.ipynb)

docs/ecosystem/graphsignal.md

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

docs/ecosystem/hazy_research.md

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

docs/ecosystem/helicone.md

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

docs/ecosystem/huggingface.md

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

docs/ecosystem/jina.md

@@ -0,0 +1,18 @@
+# Jina
+
+This page covers how to use the Jina ecosystem within LangChain.
+It is broken into two parts: installation and setup, and then references to specific Jina wrappers.
+
+## Installation and Setup
+- Install the Python SDK with `pip install jina`
+- Get a Jina AI Cloud auth token from [here](https://cloud.jina.ai/settings/tokens) and set it as an environment variable (`JINA_AUTH_TOKEN`)
+
+## Wrappers
+
+### Embeddings
+
+There exists a Jina Embeddings wrapper, which you can access with 
+```python
+from langchain.embeddings import JinaEmbeddings
+```
+For a more detailed walkthrough of this, see [this notebook](../modules/models/text_embedding/examples/jina.ipynb)

docs/ecosystem/llamacpp.md

@@ -0,0 +1,26 @@
+# Llama.cpp
+
+This page covers how to use [llama.cpp](https://github.com/ggerganov/llama.cpp) within LangChain.
+It is broken into two parts: installation and setup, and then references to specific Llama-cpp wrappers.
+
+## Installation and Setup
+- Install the Python package with `pip install llama-cpp-python`
+- Download one of the [supported models](https://github.com/ggerganov/llama.cpp#description) and convert them to the llama.cpp format per the [instructions](https://github.com/ggerganov/llama.cpp)
+
+## Wrappers
+
+### LLM
+
+There exists a LlamaCpp LLM wrapper, which you can access with 
+```python
+from langchain.llms import LlamaCpp
+```
+For a more detailed walkthrough of this, see [this notebook](../modules/models/llms/integrations/llamacpp.ipynb)
+
+### Embeddings
+
+There exists a LlamaCpp Embeddings wrapper, which you can access with 
+```python
+from langchain.embeddings import LlamaCppEmbeddings
+```
+For a more detailed walkthrough of this, see [this notebook](../modules/models/text_embedding/examples/llamacpp.ipynb)

docs/ecosystem/milvus.md

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

docs/ecosystem/modal.md

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

docs/ecosystem/nlpcloud.md

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

docs/ecosystem/openai.md

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

docs/ecosystem/opensearch.md

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

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 a Hugging Face api key and set it as an environment variable (`HUGGINGFACE_API_KEY`)
+
+## Wrappers
+
+### LLM
+
+There exists an Petals LLM wrapper, which you can access with 
+```python
+from langchain.llms import Petals
+```

docs/ecosystem/pgvector.md

@@ -0,0 +1,29 @@
+# PGVector
+
+This page covers how to use the Postgres [PGVector](https://github.com/pgvector/pgvector) ecosystem within LangChain
+It is broken into two parts: installation and setup, and then references to specific PGVector wrappers.
+
+## Installation
+- Install the Python package with `pip install pgvector`
+
+
+## Setup
+1. The first step is to create a database with the `pgvector` extension installed.
+
+    Follow the steps at [PGVector Installation Steps](https://github.com/pgvector/pgvector#installation) to install the database and the extension. The docker image is the easiest way to get started.
+
+## Wrappers
+
+### VectorStore
+
+There exists a wrapper around Postgres vector databases, allowing you to use it as a vectorstore,
+whether for semantic search or example selection.
+
+To import this vectorstore:
+```python
+from langchain.vectorstores.pgvector import PGVector
+```
+
+### Usage
+
+For a more detailed walkthrough of the PGVector Wrapper, see [this notebook](../modules/indexes/vectorstores/examples/pgvector.ipynb)

docs/ecosystem/pinecone.md

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

docs/ecosystem/promptlayer.md

@@ -0,0 +1,49 @@
+# 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"])
+```
+
+To get the PromptLayer request id, use the argument `return_pl_id` when instanializing the LLM
+```python
+from langchain.llms import PromptLayerOpenAI
+llm = PromptLayerOpenAI(return_pl_id=True)
+```
+This will add the PromptLayer request ID in the `generation_info` field of the `Generation` returned when using `.generate` or `.agenerate`
+
+For example:
+```python
+llm_results = llm.generate(["hello world"])
+for res in llm_results.generations:
+    print("pl request id: ", res[0].generation_info["pl_request_id"])
+```
+You can use the PromptLayer request ID to add a prompt, score, or other metadata to your request. [Read more about it here](https://magniv.notion.site/Track-4deee1b1f7a34c1680d085f82567dab9).
+
+This LLM is identical to the [OpenAI LLM](./openai.md), except that
+- all your requests will be logged to your PromptLayer account
+- you can add `pl_tags` when instantializing to tag your requests on PromptLayer
+- you can add `return_pl_id` when instantializing to return a PromptLayer request id to use [while tracking requests](https://magniv.notion.site/Track-4deee1b1f7a34c1680d085f82567dab9).
+
+
+PromptLayer also provides native wrappers for [`PromptLayerChatOpenAI`](../modules/models/chat/integrations/promptlayer_chatopenai.ipynb) and `PromptLayerOpenAIChat`

docs/ecosystem/qdrant.md

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

docs/ecosystem/replicate.md

@@ -0,0 +1,47 @@
+# Replicate
+This page covers how to run models on Replicate within LangChain.
+
+## Installation and Setup
+- Create a [Replicate](https://replicate.com) account. Get your API key and set it as an environment variable (`REPLICATE_API_TOKEN`)
+- Install the [Replicate python client](https://github.com/replicate/replicate-python) with `pip install replicate`
+
+## Calling a model
+
+Find a model on the [Replicate explore page](https://replicate.com/explore), and then paste in the model name and version in this format: `owner-name/model-name:version`
+
+For example, for this [flan-t5 model](https://replicate.com/daanelson/flan-t5), click on the API tab. The model name/version would be: `daanelson/flan-t5:04e422a9b85baed86a4f24981d7f9953e20c5fd82f6103b74ebc431588e1cec8`
+
+Only the `model` param is required, but any other model parameters can also be passed in with the format `input={model_param: value, ...}`
+
+
+For example, if we were running stable diffusion and wanted to change the image dimensions:
+
+```
+Replicate(model="stability-ai/stable-diffusion:db21e45d3f7023abc2a46ee38a23973f6dce16bb082a930b0c49861f96d1e5bf", input={'image_dimensions': '512x512'})
+```
+
+*Note that only the first output of a model will be returned.*
+From here, we can initialize our model:
+
+```python
+llm = Replicate(model="daanelson/flan-t5:04e422a9b85baed86a4f24981d7f9953e20c5fd82f6103b74ebc431588e1cec8")
+```
+
+And run it:
+
+```python
+prompt = """
+Answer the following yes/no question by reasoning step by step.
+Can a dog drive a car?
+"""
+llm(prompt)
+```
+
+We can call any Replicate model (not just LLMs) using this syntax. For example, we can call [Stable Diffusion](https://replicate.com/stability-ai/stable-diffusion):
+
+```python
+text2image = Replicate(model="stability-ai/stable-diffusion:db21e45d3f7023abc2a46ee38a23973f6dce16bb082a930b0c49861f96d1e5bf",
+                       input={'image_dimensions'='512x512'}
+
+image_output = text2image("A cat riding a motorcycle by Picasso")
+```

docs/ecosystem/runhouse.md

@@ -0,0 +1,29 @@
+# Runhouse
+
+This page covers how to use the [Runhouse](https://github.com/run-house/runhouse) ecosystem within LangChain.
+It is broken into three parts: installation and setup, LLMs, and Embeddings.
+
+## Installation and Setup
+- Install the Python SDK with `pip install runhouse`
+- If you'd like to use on-demand cluster, check your cloud credentials with `sky check`
+
+## Self-hosted LLMs
+For a basic self-hosted LLM, you can use the `SelfHostedHuggingFaceLLM` class. For more
+custom LLMs, you can use the `SelfHostedPipeline` parent class.
+
+```python
+from langchain.llms import SelfHostedPipeline, SelfHostedHuggingFaceLLM
+```
+
+For a more detailed walkthrough of the Self-hosted LLMs, see [this notebook](../modules/models/llms/integrations/self_hosted_examples.ipynb)
+
+## Self-hosted Embeddings
+There are several ways to use self-hosted embeddings with LangChain via Runhouse.
+
+For a basic self-hosted embedding from a Hugging Face Transformers model, you can use 
+the `SelfHostedEmbedding` class.
+```python
+from langchain.llms import SelfHostedPipeline, SelfHostedHuggingFaceLLM
+```
+
+For a more detailed walkthrough of the Self-hosted Embeddings, see [this notebook](../modules/models/text_embedding/examples/self-hosted.ipynb)

docs/ecosystem/rwkv.md

@@ -0,0 +1,65 @@
+# RWKV-4
+
+This page covers how to use the `RWKV-4` wrapper within LangChain.
+It is broken into two parts: installation and setup, and then usage with an example.
+
+## Installation and Setup
+- Install the Python package with `pip install rwkv`
+- Install the tokenizer Python package with `pip install tokenizer`
+- Download a [RWKV model](https://huggingface.co/BlinkDL/rwkv-4-raven/tree/main) and place it in your desired directory
+- Download the [tokens file](https://raw.githubusercontent.com/BlinkDL/ChatRWKV/main/20B_tokenizer.json)
+
+## Usage
+
+### RWKV
+
+To use the RWKV wrapper, you need to provide the path to the pre-trained model file and the tokenizer's configuration.
+```python
+from langchain.llms import RWKV
+
+# Test the model
+
+```python
+
+def generate_prompt(instruction, input=None):
+    if input:
+        return f"""Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
+
+# Instruction:
+{instruction}
+
+# Input:
+{input}
+
+# Response:
+"""
+    else:
+        return f"""Below is an instruction that describes a task. Write a response that appropriately completes the request.
+
+# Instruction:
+{instruction}
+
+# Response:
+"""
+
+
+model = RWKV(model="./models/RWKV-4-Raven-3B-v7-Eng-20230404-ctx4096.pth", strategy="cpu fp32", tokens_path="./rwkv/20B_tokenizer.json")
+response = model(generate_prompt("Once upon a time, "))
+```
+## Model File
+
+You can find links to model file downloads at the [RWKV-4-Raven](https://huggingface.co/BlinkDL/rwkv-4-raven/tree/main) repository.
+
+### Rwkv-4 models -> recommended VRAM
+
+
+```
+RWKV VRAM
+Model | 8bit | bf16/fp16 | fp32
+14B   | 16GB | 28GB      | >50GB
+7B    | 8GB  | 14GB      | 28GB
+3B    | 2.8GB| 6GB       | 12GB
+1b5   | 1.3GB| 3GB       | 6GB
+```
+
+See the [rwkv pip](https://pypi.org/project/rwkv/) page for more information about strategies, including streaming and cuda support.

docs/ecosystem/searx.md

@@ -0,0 +1,70 @@
+# SearxNG Search API
+
+This page covers how to use the SearxNG search API within LangChain.
+It is broken into two parts: installation and setup, and then references to the specific SearxNG API wrapper.
+
+## Installation and Setup
+
+While it is possible to utilize the wrapper in conjunction with  [public searx
+instances](https://searx.space/) these instances frequently do not permit API
+access (see note on output format below) and have limitations on the frequency
+of requests. It is recommended to opt for a self-hosted instance instead.
+
+### Self Hosted Instance:
+
+See [this page](https://searxng.github.io/searxng/admin/installation.html) for installation instructions.
+
+When you install SearxNG, the only active output format by default is the HTML format.
+You need to activate the `json` format to use the API. This can be done by adding the following line to the `settings.yml` file:
+```yaml
+search:
+    formats:
+        - html
+        - json
+```
+You can make sure that the API is working by issuing a curl request to the API endpoint:
+
+`curl -kLX GET --data-urlencode q='langchain' -d format=json http://localhost:8888`
+
+This should return a JSON object with the results.
+
+
+## Wrappers
+
+### Utility
+
+To use the wrapper we need to pass the host of the SearxNG instance to the wrapper with:
+    1. the named parameter `searx_host` when creating the instance.
+    2. exporting the environment variable `SEARXNG_HOST`.
+
+You can use the wrapper to get results from a SearxNG instance. 
+
+```python
+from langchain.utilities import SearxSearchWrapper
+s = SearxSearchWrapper(searx_host="http://localhost:8888")
+s.run("what is a large language model?")
+```
+
+### Tool
+
+You can also load this wrapper as a Tool (to use with an Agent).
+
+You can do this with:
+
+```python
+from langchain.agents import load_tools
+tools = load_tools(["searx-search"],
+                    searx_host="http://localhost:8888",
+                    engines=["github"])
+```
+
+Note that we could _optionally_ pass custom engines to use.
+
+If you want to obtain results with metadata as *json* you can use:
+```python
+tools = load_tools(["searx-search-results-json"],
+                    searx_host="http://localhost:8888",
+                    num_results=5)
+```
+
+For more information on tools, see [this page](../modules/agents/tools/getting_started.md)

docs/ecosystem/serpapi.md

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

docs/ecosystem/stochasticai.md

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

docs/ecosystem/unstructured.md

@@ -0,0 +1,45 @@
+# Unstructured
+
+This page covers how to use the [`unstructured`](https://github.com/Unstructured-IO/unstructured)
+ecosystem within LangChain. The `unstructured` package from
+[Unstructured.IO](https://www.unstructured.io/) extracts clean text from raw source documents like
+PDFs and Word documents.
+
+
+This page is broken into two parts: installation and setup, and then references to specific
+`unstructured` wrappers.
+
+## Installation and Setup
+- Install the Python SDK with `pip install "unstructured[local-inference]"`
+- Install the following system dependencies if they are not already available on your system.
+  Depending on what document types you're parsing, you may not need all of these.
+    - `libmagic-dev` (filetype detection)
+    - `poppler-utils` (images and PDFs)
+    - `tesseract-ocr`(images and PDFs)
+    - `libreoffice` (MS Office docs)
+    - `pandoc` (EPUBs)
+- If you are parsing PDFs using the `"hi_res"` strategy, run the following to install the `detectron2` model, which
+  `unstructured` uses for layout detection:
+    - `pip install "detectron2@git+https://github.com/facebookresearch/detectron2.git@e2ce8dc#egg=detectron2"`
+    - If `detectron2` is not installed, `unstructured` will fallback to processing PDFs
+      using the `"fast"` strategy, which uses `pdfminer` directly and doesn't require
+      `detectron2`.
+
+## Wrappers
+
+### Data Loaders
+
+The primary `unstructured` wrappers within `langchain` are data loaders. The following
+shows how to use the most basic unstructured data loader. There are other file-specific
+data loaders available in the `langchain.document_loaders` module.
+
+```python
+from langchain.document_loaders import UnstructuredFileLoader
+
+loader = UnstructuredFileLoader("state_of_the_union.txt")
+loader.load()
+```
+
+If you instantiate the loader with `UnstructuredFileLoader(mode="elements")`, the loader
+will track additional metadata like the page number and text type (i.e. title, narrative text)
+when that information is available.

docs/ecosystem/wandb_tracking.ipynb

@@ -0,0 +1,626 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Weights & Biases\n",
+    "\n",
+    "This notebook goes over how to track your LangChain experiments into one centralized Weights and Biases dashboard. To learn more about prompt engineering and the callback please refer to this Report which explains both alongside the resultant dashboards you can expect to see.\n",
+    "\n",
+    "Run in Colab: https://colab.research.google.com/drive/1DXH4beT4HFaRKy_Vm4PoxhXVDRf7Ym8L?usp=sharing\n",
+    "\n",
+    "View Report: https://wandb.ai/a-sh0ts/langchain_callback_demo/reports/Prompt-Engineering-LLMs-with-LangChain-and-W-B--VmlldzozNjk1NTUw#👋-how-to-build-a-callback-in-langchain-for-better-prompt-engineering"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install wandb\n",
+    "!pip install pandas\n",
+    "!pip install textstat\n",
+    "!pip install spacy\n",
+    "!python -m spacy download en_core_web_sm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "id": "T1bSmKd6V2If"
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "os.environ[\"WANDB_API_KEY\"] = \"\"\n",
+    "# os.environ[\"OPENAI_API_KEY\"] = \"\"\n",
+    "# os.environ[\"SERPAPI_API_KEY\"] = \"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "id": "8WAGnTWpUUnD"
+   },
+   "outputs": [],
+   "source": [
+    "from datetime import datetime\n",
+    "from langchain.callbacks import WandbCallbackHandler, StdOutCallbackHandler\n",
+    "from langchain.callbacks.base import CallbackManager\n",
+    "from langchain.llms import OpenAI"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "```\n",
+    "Callback Handler that logs to Weights and Biases.\n",
+    "\n",
+    "Parameters:\n",
+    "    job_type (str): The type of job.\n",
+    "    project (str): The project to log to.\n",
+    "    entity (str): The entity to log to.\n",
+    "    tags (list): The tags to log.\n",
+    "    group (str): The group to log to.\n",
+    "    name (str): The name of the run.\n",
+    "    notes (str): The notes to log.\n",
+    "    visualize (bool): Whether to visualize the run.\n",
+    "    complexity_metrics (bool): Whether to log complexity metrics.\n",
+    "    stream_logs (bool): Whether to stream callback actions to W&B\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "cxBFfZR8d9FC"
+   },
+   "source": [
+    "```\n",
+    "Default values for WandbCallbackHandler(...)\n",
+    "\n",
+    "visualize: bool = False,\n",
+    "complexity_metrics: bool = False,\n",
+    "stream_logs: bool = False,\n",
+    "```\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "NOTE: For beta workflows we have made the default analysis based on textstat and the visualizations based on spacy"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "id": "KAz8weWuUeXF"
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Currently logged in as: \u001b[33mharrison-chase\u001b[0m. Use \u001b[1m`wandb login --relogin`\u001b[0m to force relogin\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "Tracking run with wandb version 0.14.0"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Run data is saved locally in <code>/Users/harrisonchase/workplace/langchain/docs/ecosystem/wandb/run-20230318_150408-e47j1914</code>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Syncing run <strong><a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/e47j1914' target=\"_blank\">llm</a></strong> to <a href='https://wandb.ai/harrison-chase/langchain_callback_demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/run' target=\"_blank\">docs</a>)<br/>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       " View project at <a href='https://wandb.ai/harrison-chase/langchain_callback_demo' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo</a>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       " View run at <a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/e47j1914' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo/runs/e47j1914</a>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m The wandb callback is currently in beta and is subject to change based on updates to `langchain`. Please report any issues to https://github.com/wandb/wandb/issues with the tag `langchain`.\n"
+     ]
+    }
+   ],
+   "source": [
+    "\"\"\"Main function.\n",
+    "\n",
+    "This function is used to try the callback handler.\n",
+    "Scenarios:\n",
+    "1. OpenAI LLM\n",
+    "2. Chain with multiple SubChains on multiple generations\n",
+    "3. Agent with Tools\n",
+    "\"\"\"\n",
+    "session_group = datetime.now().strftime(\"%m.%d.%Y_%H.%M.%S\")\n",
+    "wandb_callback = WandbCallbackHandler(\n",
+    "    job_type=\"inference\",\n",
+    "    project=\"langchain_callback_demo\",\n",
+    "    group=f\"minimal_{session_group}\",\n",
+    "    name=\"llm\",\n",
+    "    tags=[\"test\"],\n",
+    ")\n",
+    "manager = CallbackManager([StdOutCallbackHandler(), wandb_callback])\n",
+    "llm = OpenAI(temperature=0, callback_manager=manager, verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "Q-65jwrDeK6w"
+   },
+   "source": [
+    "\n",
+    "\n",
+    "```\n",
+    "# Defaults for WandbCallbackHandler.flush_tracker(...)\n",
+    "\n",
+    "reset: bool = True,\n",
+    "finish: bool = False,\n",
+    "```\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The `flush_tracker` function is used to log LangChain sessions to Weights & Biases. It takes in the LangChain module or agent, and logs at minimum the prompts and generations alongside the serialized form of the LangChain module to the specified Weights & Biases project. By default we reset the session as opposed to concluding the session outright."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "id": "o_VmneyIUyx8"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "Waiting for W&B process to finish... <strong style=\"color:green\">(success).</strong>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       " View run <strong style=\"color:#cdcd00\">llm</strong> at: <a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/e47j1914' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo/runs/e47j1914</a><br/>Synced 5 W&B file(s), 2 media file(s), 5 artifact file(s) and 0 other file(s)"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Find logs at: <code>./wandb/run-20230318_150408-e47j1914/logs</code>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "0d7b4307ccdb450ea631497174fca2d1",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.016745895149999985, max=1.0…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Tracking run with wandb version 0.14.0"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Run data is saved locally in <code>/Users/harrisonchase/workplace/langchain/docs/ecosystem/wandb/run-20230318_150534-jyxma7hu</code>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Syncing run <strong><a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/jyxma7hu' target=\"_blank\">simple_sequential</a></strong> to <a href='https://wandb.ai/harrison-chase/langchain_callback_demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/run' target=\"_blank\">docs</a>)<br/>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       " View project at <a href='https://wandb.ai/harrison-chase/langchain_callback_demo' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo</a>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       " View run at <a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/jyxma7hu' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo/runs/jyxma7hu</a>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# SCENARIO 1 - LLM\n",
+    "llm_result = llm.generate([\"Tell me a joke\", \"Tell me a poem\"] * 3)\n",
+    "wandb_callback.flush_tracker(llm, name=\"simple_sequential\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "id": "trxslyb1U28Y"
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.prompts import PromptTemplate\n",
+    "from langchain.chains import LLMChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "id": "uauQk10SUzF6"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "Waiting for W&B process to finish... <strong style=\"color:green\">(success).</strong>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       " View run <strong style=\"color:#cdcd00\">simple_sequential</strong> at: <a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/jyxma7hu' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo/runs/jyxma7hu</a><br/>Synced 4 W&B file(s), 2 media file(s), 6 artifact file(s) and 0 other file(s)"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Find logs at: <code>./wandb/run-20230318_150534-jyxma7hu/logs</code>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "dbdbf28fb8ed40a3a60218d2e6d1a987",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.016736786816666675, max=1.0…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Tracking run with wandb version 0.14.0"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Run data is saved locally in <code>/Users/harrisonchase/workplace/langchain/docs/ecosystem/wandb/run-20230318_150550-wzy59zjq</code>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Syncing run <strong><a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/wzy59zjq' target=\"_blank\">agent</a></strong> to <a href='https://wandb.ai/harrison-chase/langchain_callback_demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/run' target=\"_blank\">docs</a>)<br/>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       " View project at <a href='https://wandb.ai/harrison-chase/langchain_callback_demo' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo</a>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       " View run at <a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/wzy59zjq' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo/runs/wzy59zjq</a>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# SCENARIO 2 - Chain\n",
+    "template = \"\"\"You are a playwright. Given the title of play, it is your job to write a synopsis for that title.\n",
+    "Title: {title}\n",
+    "Playwright: This is a synopsis for the above play:\"\"\"\n",
+    "prompt_template = PromptTemplate(input_variables=[\"title\"], template=template)\n",
+    "synopsis_chain = LLMChain(llm=llm, prompt=prompt_template, callback_manager=manager)\n",
+    "\n",
+    "test_prompts = [\n",
+    "    {\n",
+    "        \"title\": \"documentary about good video games that push the boundary of game design\"\n",
+    "    },\n",
+    "    {\"title\": \"cocaine bear vs heroin wolf\"},\n",
+    "    {\"title\": \"the best in class mlops tooling\"},\n",
+    "]\n",
+    "synopsis_chain.apply(test_prompts)\n",
+    "wandb_callback.flush_tracker(synopsis_chain, name=\"agent\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "id": "_jN73xcPVEpI"
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.agents import initialize_agent, load_tools\n",
+    "from langchain.agents import AgentType"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "id": "Gpq4rk6VT9cu"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I need to find out who Leo DiCaprio's girlfriend is and then calculate her age raised to the 0.43 power.\n",
+      "Action: Search\n",
+      "Action Input: \"Leo DiCaprio girlfriend\"\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mDiCaprio had a steady girlfriend in Camila Morrone. He had been with the model turned actress for nearly five years, as they were first said to be dating at the end of 2017. And the now 26-year-old Morrone is no stranger to Hollywood.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to calculate her age raised to the 0.43 power.\n",
+      "Action: Calculator\n",
+      "Action Input: 26^0.43\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mAnswer: 4.059182145592686\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: Leo DiCaprio's girlfriend is Camila Morrone and her current age raised to the 0.43 power is 4.059182145592686.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "Waiting for W&B process to finish... <strong style=\"color:green\">(success).</strong>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       " View run <strong style=\"color:#cdcd00\">agent</strong> at: <a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/wzy59zjq' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo/runs/wzy59zjq</a><br/>Synced 5 W&B file(s), 2 media file(s), 7 artifact file(s) and 0 other file(s)"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Find logs at: <code>./wandb/run-20230318_150550-wzy59zjq/logs</code>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# SCENARIO 3 - Agent with Tools\n",
+    "tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm, callback_manager=manager)\n",
+    "agent = initialize_agent(\n",
+    "    tools,\n",
+    "    llm,\n",
+    "    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,\n",
+    "    callback_manager=manager,\n",
+    "    verbose=True,\n",
+    ")\n",
+    "agent.run(\n",
+    "    \"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\"\n",
+    ")\n",
+    "wandb_callback.flush_tracker(agent, reset=False, finish=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}

docs/ecosystem/weaviate.md

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

docs/ecosystem/wolfram_alpha.md

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

docs/ecosystem/writer.md

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

docs/examples/agents.rst

@@ -1,47 +0,0 @@
-Agents
-======
-
-The examples here are all end-to-end agents for specific applications.
-In all examples there is an Agent with a particular set of tools.
-
-- Tools: A tool can be anything that takes in a string and returns a string. This means that you can use both the primitives AND the chains found in `this <chains.rst>`_ documentation.
-- Agents: An agent uses an LLMChain to determine which tools to use. For a list of all available agent types, see `here <../explanation/agents.md>`_.
-
-**MRKL**
-
-- **Tools used**: Search, SQLDatabaseChain, LLMMathChain
-- **Agent used**: `zero-shot-react-description`
-- `Paper <https://arxiv.org/pdf/2205.00445.pdf>`_
-- **Note**: This is the most general purpose example, so if you are looking to use an agent with arbitrary tools, please start here.
-- `Example Notebook <agents/mrkl.ipynb>`_
-
-**Self-Ask-With-Search**
-
-- **Tools used**: Search
-- **Agent used**: `self-ask-with-search`
-- `Paper <https://ofir.io/self-ask.pdf>`_
-- `Example Notebook <agents/self_ask_with_search.ipynb>`_
-
-**ReAct**
-
-- **Tools used**: Wikipedia Docstore
-- **Agent used**: `react-docstore`
-- `Paper <https://arxiv.org/pdf/2210.03629.pdf>`_
-- `Example Notebook <agents/react.ipynb>`_
-
-
-
-Additionally, we also provide examples for how to do more customizability:
-
-**Custom Agent**
-
-- Purpose: How to create custom agents.
-- `Example Notebook <agents/custom_agent.ipynb>`_
-
-
-.. toctree::
-   :maxdepth: 1
-   :glob:
-   :hidden:
-
-   agents/*

docs/examples/agents/natbot.py

@@ -1,88 +0,0 @@
-"""Run NatBot."""
-import time
-
-from langchain.chains.natbot.base import NatBotChain
-from langchain.chains.natbot.crawler import Crawler  # type: ignore
-
-
-def run_cmd(cmd: str, _crawler: Crawler) -> None:
-    """Run command."""
-    cmd = cmd.split("\n")[0]
-
-    if cmd.startswith("SCROLL UP"):
-        _crawler.scroll("up")
-    elif cmd.startswith("SCROLL DOWN"):
-        _crawler.scroll("down")
-    elif cmd.startswith("CLICK"):
-        commasplit = cmd.split(",")
-        id = commasplit[0].split(" ")[1]
-        _crawler.click(id)
-    elif cmd.startswith("TYPE"):
-        spacesplit = cmd.split(" ")
-        id = spacesplit[1]
-        text_pieces = spacesplit[2:]
-        text = " ".join(text_pieces)
-        # Strip leading and trailing double quotes
-        text = text[1:-1]
-
-        if cmd.startswith("TYPESUBMIT"):
-            text += "\n"
-        _crawler.type(id, text)
-
-    time.sleep(2)
-
-
-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()
-    if len(i) > 0:
-        objective = i
-    quiet = False
-    nat_bot_chain = NatBotChain.from_default(objective)
-    _crawler = Crawler()
-    _crawler.go_to_page("google.com")
-    try:
-        while True:
-            browser_content = "\n".join(_crawler.crawl())
-            llm_command = nat_bot_chain.execute(_crawler.page.url, browser_content)
-            if not quiet:
-                print("URL: " + _crawler.page.url)
-                print("Objective: " + objective)
-                print("----------------\n" + browser_content + "\n----------------\n")
-            if len(llm_command) > 0:
-                print("Suggested command: " + llm_command)
-
-            command = input()
-            if command == "r" or command == "":
-                run_cmd(llm_command, _crawler)
-            elif command == "g":
-                url = input("URL:")
-                _crawler.go_to_page(url)
-            elif command == "u":
-                _crawler.scroll("up")
-                time.sleep(1)
-            elif command == "d":
-                _crawler.scroll("down")
-                time.sleep(1)
-            elif command == "c":
-                id = input("id:")
-                _crawler.click(id)
-                time.sleep(1)
-            elif command == "t":
-                id = input("id:")
-                text = input("text:")
-                _crawler.type(id, text)
-                time.sleep(1)
-            elif command == "o":
-                objective = input("Objective:")
-            else:
-                print(
-                    "(g) to visit url\n(u) scroll up\n(d) scroll down\n(c) to click"
-                    "\n(t) to type\n(h) to view commands again"
-                    "\n(r/enter) to run suggested command\n(o) change objective"
-                )
-    except KeyboardInterrupt:
-        print("\n[!] Ctrl+C detected, exiting gracefully.")
-        exit(0)

docs/examples/agents/react.ipynb

@@ -1,111 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "82140df0",
-   "metadata": {},
-   "source": [
-    "# ReAct\n",
-    "\n",
-    "This notebook showcases using an agent to implement the ReAct logic."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "4e272b47",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain import OpenAI, Wikipedia\n",
-    "from langchain.agents import initialize_agent, Tool\n",
-    "from langchain.agents.react.base import DocstoreExplorer\n",
-    "docstore=DocstoreExplorer(Wikipedia())\n",
-    "tools = [\n",
-    "    Tool(\n",
-    "        name=\"Search\",\n",
-    "        func=docstore.search\n",
-    "    ),\n",
-    "    Tool(\n",
-    "        name=\"Lookup\",\n",
-    "        func=docstore.lookup\n",
-    "    )\n",
-    "]\n",
-    "\n",
-    "llm = OpenAI(temperature=0, model_name=\"text-davinci-002\")\n",
-    "react = initialize_agent(tools, llm, agent=\"react-docstore\", verbose=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "8078c8f1",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new ReActDocstoreAgent chain...\u001b[0m\n",
-      "Author David Chanoff has collaborated with a U.S. Navy admiral who served as the ambassador to the United Kingdom under which President?\n",
-      "Thought 1:\u001b[32;1m\u001b[1;3m I need to search David Chanoff and find the U.S. Navy admiral he collaborated\n",
-      "with.\n",
-      "Action 1: Search[David Chanoff]\u001b[0m\n",
-      "Observation 1: \u001b[36;1m\u001b[1;3mDavid Chanoff is a noted author of non-fiction work. His work has typically involved collaborations with the principal protagonist of the work concerned. His collaborators have included; Augustus A. White, Joycelyn Elders, Đoàn Văn Toại, William J. Crowe, Ariel Sharon, Kenneth Good and Felix Zandman. He has also written about a wide range of subjects including literary history, education and foreign for The Washington Post, The New Republic and The New York Times Magazine. He has published more than twelve books.\u001b[0m\n",
-      "Thought 2:\u001b[32;1m\u001b[1;3m The U.S. Navy admiral David Chanoff collaborated with is William J. Crowe.\n",
-      "Action 2: Search[William J. Crowe]\u001b[0m\n",
-      "Observation 2: \u001b[36;1m\u001b[1;3mWilliam James Crowe Jr. (January 2, 1925 – October 18, 2007) was a United States Navy admiral and diplomat who served as the 11th chairman of the Joint Chiefs of Staff under Presidents Ronald Reagan and George H. W. Bush, and as the ambassador to the United Kingdom and Chair of the Intelligence Oversight Board under President Bill Clinton.\u001b[0m\n",
-      "Thought 3:\u001b[32;1m\u001b[1;3m William J. Crowe served as the ambassador to the United Kingdom under President Bill Clinton.\n",
-      "Action 3: Finish[Bill Clinton]\u001b[0m\n",
-      "\u001b[1m> Finished ReActDocstoreAgent chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'Bill Clinton'"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "question = \"Author David Chanoff has collaborated with a U.S. Navy admiral who served as the ambassador to the United Kingdom under which President?\"\n",
-    "react.run(question)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "4ff64e81",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (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": "3.10.8"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/examples/chains.rst

@@ -1,88 +0,0 @@
-Chains
-======
-
-The examples here are all end-to-end chains for specific applications.
-A chain is made up of links, which can be either primitives or other chains.
-
-The following primitives exist as options to use for links:
-
-#. `LLM: <../modules/llms.rst>`_ A language model takes text as input and outputs text.
-#. `PromptTemplate: <../modules/prompt.rst>`_ A prompt template takes arbitrary string inputs and returns a final formatted string.
-#. `TextSplitter: <../modules/text_splitter.rst>`_ A text splitter takes a longer document and splits it into smaller chunks.
-#. `Python REPL: <../modules/python.rst>`_ A Python REPL takes a string representing a Python command to run, runs that command, and then returns anything that was printed during that run.
-#. `SQL Database: <../modules/sql_database.rst>`_ A SQL database takes a string representing a SQL command as input and executes that command against the database. If any rows are returned, then those are cast to a string and returned.
-#. `Search: <../modules/serpapi.rst>`_ A search object takes a string as input and executes that against a search object, returning any results.
-#. `Docstore: <../modules/docstore.rst>`_ A docstore object can be used to lookup a document in a database by exact match.
-#. `Vectorstore: <../modules/vectorstore.rst>`_ A vectorstore object uses embeddings stored in a vector database to take in an input string and return documents similar to that string.
-
-With these primitives in mind, the following chains exist:
-
-**LLMChain**
-
-- **Links Used**: PromptTemplate, LLM
-- **Notes**: This chain is the simplest chain, and is widely used by almost every other chain. This chain takes arbitrary user input, creates a prompt with it from the PromptTemplate, passes that to the LLM, and then returns the output of the LLM as the final output.
-- `Example Notebook <chains/llm_chain.ipynb>`_
-
-**LLMMath**
-
-- **Links Used**: Python REPL, LLMChain
-- **Notes**: This chain takes user input (a math question), uses an LLMChain to convert it to python code snippet to run in the Python REPL, and then returns that as the result.
-- `Example Notebook <chains/llm_math.ipynb>`_
-
-**PAL**
-
-- **Links Used**: Python REPL, LLMChain
-- **Notes**: This chain takes user input (a reasoning question), uses an LLMChain to convert it to python code snippet to run in the Python REPL, and then returns that as the result.
-- `Paper <https://arxiv.org/abs/2211.10435>`_
-- `Example Notebook <chains/pal.ipynb>`_
-
-**Recursive Summarization**
-
-- **Links Used**: TextSplitter, LLMChain
-- **Notes**: This chain splits a document into chunks, runs a first LLMChain over each chunk to summarize it, and then runs a second LLMChain over those results to get a summary of the summaries.
-- `Example Notebook <chains/map_reduce.ipynb>`_
-
-**SQLDatabase Chain**
-
-- **Links Used**: SQLDatabase, LLMChain
-- **Notes**: This chain takes user input (a question), uses a first LLM chain to construct a SQL query to run against the SQL database, and then uses another LLMChain to take the results of that query and use it to answer the original question.
-- `Example Notebook <chains/sqlite.ipynb>`_
-
-
-**Vector Database Question-Answering**
-
-- **Links Used**: Vectorstore, LLMChain
-- **Notes**: This chain takes user input (a question), uses the Vectorstore and semantic search to find relevant documents, and then passes the documents plus the original question to another LLM to generate a final answer.
-- `Example Notebook <chains/vector_db_qa.ipynb>`_
-
-**Vector Database Question-Answering With Sources**
-
-- **Links Used**: Vectorstore, LLMChain
-- **Notes**: This chain takes user input (a question), uses the Vectorstore and semantic search to find relevant documents, and then passes the documents plus the original question to another LLM to generate a final answer with sources.
-- `Example Notebook <chains/vector_db_qa_with_sources.ipynb>`_
-
-**Question-Answering With Sources**
-
-- **Links Used**: LLMChain
-- **Notes**: These types of chains take a question and multiple documents as input, and return an answer plus sources for where that answer came from. There are multiple underlying types of chains to do this, for more information see TODO.
-- `Example Notebook <chains/qa_with_sources.ipynb>`_
-
-**Question-Answering**
-
-- **Links Used**: LLMChain
-- **Notes**: These types of chains take a question and multiple documents as input, and return an answer. There are multiple underlying types of chains to do this, for more information see TODO.
-- `Example Notebook <chains/question_answering.ipynb>`_
-
-**Summarization**
-
-- **Links Used**: LLMChain
-- **Notes**: These types of chains take multiple documents as input, and return a summary of all documents. There are multiple underlying types of chains to do this, for more information see TODO.
-- `Example Notebook <chains/summarize.ipynb>`_
-
-.. toctree::
-   :maxdepth: 1
-   :glob:
-   :caption: Chains
-   :hidden:
-
-   chains/*

docs/examples/chains/llm_bash.ipynb

@@ -1,87 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# BashChain\n",
-    "This notebook showcases using LLMs and a bash process to do perform simple filesystem commands."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new LLMBashChain chain...\u001b[0m\n",
-      "Please write a bash script that prints 'Hello World' to the console.\u001b[32;1m\u001b[1;3m\n",
-      "\n",
-      "```bash\n",
-      "echo \"Hello World\"\n",
-      "```\u001b[0m['```bash', 'echo \"Hello World\"', '```']\n",
-      "\n",
-      "Answer: \u001b[33;1m\u001b[1;3mHello World\n",
-      "\u001b[0m\n",
-      "\u001b[1m> Finished LLMBashChain chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'Hello World\\n'"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain.chains import LLMBashChain\n",
-    "from langchain.llms import OpenAI\n",
-    "\n",
-    "llm = OpenAI(temperature=0)\n",
-    "\n",
-    "text = \"Please write a bash script that prints 'Hello World' to the console.\"\n",
-    "\n",
-    "bash_chain = LLMBashChain(llm=llm, verbose=True)\n",
-    "\n",
-    "bash_chain.run(text)"
-   ]
-  },
-  {
-   "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": "3.10.8"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

docs/examples/chains/llm_math.ipynb

@@ -1,91 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "e71e720f",
-   "metadata": {},
-   "source": [
-    "# LLM Math\n",
-    "\n",
-    "This notebook showcases using LLMs and Python REPLs to do complex word math problems."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "44e9ba31",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new chain...\u001b[0m\n",
-      "How many of the integers between 0 and 99 inclusive are divisible by 8?\u001b[102m\n",
-      "\n",
-      "```python\n",
-      "count = 0\n",
-      "for i in range(100):\n",
-      "    if i % 8 == 0:\n",
-      "        count += 1\n",
-      "print(count)\n",
-      "```\n",
-      "\u001b[0m\n",
-      "Answer: \u001b[103m13\n",
-      "\u001b[0m\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'Answer: 13\\n'"
-      ]
-     },
-     "execution_count": 1,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain import OpenAI, LLMMathChain\n",
-    "\n",
-    "llm = OpenAI(temperature=0)\n",
-    "llm_math = LLMMathChain(llm=llm, verbose=True)\n",
-    "\n",
-    "llm_math.run(\"How many of the integers between 0 and 99 inclusive are divisible by 8?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "f62f0c75",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.4"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/examples/chains/qa_with_sources.ipynb

@@ -1,258 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "74148cee",
-   "metadata": {},
-   "source": [
-    "# Question Answering with Sources\n",
-    "\n",
-    "This notebook walks through how to use LangChain for question answering with sources over a list of documents. It covers three different chain types: `stuff`, `map_reduce`, and `refine`. For a more in depth explanation of what these chain types are, see [here](../../explanation/combine_docs.md)."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "ca2f0efc",
-   "metadata": {},
-   "source": [
-    "### Prepare Data\n",
-    "First we prepare the data. For this example we do similarity search over a vector database, but these documents could be fetched in any manner (the point of this notebook to highlight what to do AFTER you fetch the documents)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "78f28130",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
-    "from langchain.embeddings.cohere import CohereEmbeddings\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
-    "from langchain.vectorstores.elastic_vector_search import ElasticVectorSearch\n",
-    "from langchain.vectorstores.faiss import FAISS\n",
-    "from langchain.docstore.document import Document"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "4da195a3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "with open('../state_of_the_union.txt') as f:\n",
-    "    state_of_the_union = f.read()\n",
-    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
-    "texts = text_splitter.split_text(state_of_the_union)\n",
-    "\n",
-    "embeddings = OpenAIEmbeddings()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "5ec2b55b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "docsearch = FAISS.from_texts(texts, embeddings, metadatas=[{\"source\": i} for i in range(len(texts))])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "5286f58f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "query = \"What did the president say about Justice Breyer\"\n",
-    "docs = docsearch.similarity_search(query)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "005a47e9",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chains.qa_with_sources import load_qa_with_sources_chain\n",
-    "from langchain.llms import OpenAI"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "d82f899a",
-   "metadata": {},
-   "source": [
-    "### The `stuff` Chain\n",
-    "\n",
-    "This sections shows results of using the `stuff` Chain to do question answering with sources."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "fc1a5ed6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = load_qa_with_sources_chain(OpenAI(temperature=0), chain_type=\"stuff\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "e239964b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "docs = [Document(page_content=t, metadata={\"source\": i}) for i, t in enumerate(texts[:3])]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "7d766417",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'output_text': ' The president did not mention Justice Breyer.\\nSOURCES: 0-pl, 1-pl, 2-pl'}"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "query = \"What did the president say about Justice Breyer\"\n",
-    "chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "c5dbb304",
-   "metadata": {},
-   "source": [
-    "### The `map_reduce` Chain\n",
-    "\n",
-    "This sections shows results of using the `map_reduce` Chain to do question answering with sources."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "921db0a4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = load_qa_with_sources_chain(OpenAI(temperature=0), chain_type=\"map_reduce\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "e417926a",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.\n",
-      "Token indices sequence length is longer than the specified maximum sequence length for this model (1546 > 1024). Running this sequence through the model will result in indexing errors\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "{'output_text': ' The president did not mention Justice Breyer.\\nSOURCES: 0, 1, 2'}"
-      ]
-     },
-     "execution_count": 10,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "query = \"What did the president say about Justice Breyer\"\n",
-    "chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "5bf0e1ab",
-   "metadata": {},
-   "source": [
-    "### The `refine` Chain\n",
-    "\n",
-    "This sections shows results of using the `refine` Chain to do question answering with sources."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "904835c8",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = load_qa_with_sources_chain(OpenAI(temperature=0), chain_type=\"refine\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "f60875c6",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'output_text': \"\\n\\nThe president did not mention Justice Breyer in his speech to the European Parliament, which focused on building a coalition of freedom-loving nations to confront Putin, unifying European allies, countering Russia's lies with truth, and enforcing powerful economic sanctions. Source: 2\"}"
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "query = \"What did the president say about Justice Breyer\"\n",
-    "chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "929620d0",
-   "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": "3.10.8"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/examples/chains/question_answering.ipynb

@@ -1,248 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "05859721",
-   "metadata": {},
-   "source": [
-    "# Question Answering\n",
-    "\n",
-    "This notebook walks through how to use LangChain for question answering over a list of documents. It covers three different types of chaings: `stuff`, `map_reduce`, and `refine`. For a more in depth explanation of what these chain types are, see [here](../../explanation/combine_docs.md)."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "726f4996",
-   "metadata": {},
-   "source": [
-    "### Prepare Data\n",
-    "First we prepare the data. For this example we do similarity search over a vector database, but these documents could be fetched in any manner (the point of this notebook to highlight what to do AFTER you fetch the documents)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "17fcbc0f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
-    "from langchain.vectorstores.faiss import FAISS\n",
-    "from langchain.docstore.document import Document"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "291f0117",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "with open('../state_of_the_union.txt') as f:\n",
-    "    state_of_the_union = f.read()\n",
-    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
-    "texts = text_splitter.split_text(state_of_the_union)\n",
-    "\n",
-    "embeddings = OpenAIEmbeddings()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "fd9666a9",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "docsearch = FAISS.from_texts(texts, embeddings)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "d1eaf6e6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "query = \"What did the president say about Justice Breyer\"\n",
-    "docs = docsearch.similarity_search(query)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "a16e3453",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chains.question_answering import load_qa_chain\n",
-    "from langchain.llms import OpenAI"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f78787a0",
-   "metadata": {},
-   "source": [
-    "### The `stuff` Chain\n",
-    "\n",
-    "This sections shows results of using the `stuff` Chain to do question answering."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "180fd4c1",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = load_qa_chain(OpenAI(temperature=0), chain_type=\"stuff\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "d145ae31",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "docs = [Document(page_content=t) for t in texts[:3]]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "77fdf1aa",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'output_text': ' The president did not mention Justice Breyer.'}"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "query = \"What did the president say about Justice Breyer\"\n",
-    "chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "91522e29",
-   "metadata": {},
-   "source": [
-    "### The `map_reduce` Chain\n",
-    "\n",
-    "This sections shows results of using the `map_reduce` Chain to do question answering."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "b0060f51",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = load_qa_chain(OpenAI(temperature=0), chain_type=\"map_reduce\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "fbdb9137",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'output_text': ' The president did not mention Justice Breyer.'}"
-      ]
-     },
-     "execution_count": 10,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "query = \"What did the president say about Justice Breyer\"\n",
-    "chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "6ea50ad0",
-   "metadata": {},
-   "source": [
-    "### The `refine` Chain\n",
-    "\n",
-    "This sections shows results of using the `refine` Chain to do question answering."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "fb167057",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = load_qa_chain(OpenAI(temperature=0), chain_type=\"refine\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "d8b5286e",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'output_text': \"\\n\\nThe president did not mention Justice Breyer in his speech to the European Parliament about building a coalition of freedom-loving nations to confront Putin, unifying European allies, countering Russia's lies with truth, and enforcing powerful economic sanctions.\"}"
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "query = \"What did the president say about Justice Breyer\"\n",
-    "chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "49e9c6d7",
-   "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": "3.10.8"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/examples/chains/sqlite.ipynb

@@ -1,129 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "0ed6aab1",
-   "metadata": {
-    "pycharm": {
-     "name": "#%% md\n"
-    }
-   },
-   "source": [
-    "# SQLite example\n",
-    "\n",
-    "This example showcases hooking up an LLM to answer questions over a database."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "b2f66479",
-   "metadata": {
-    "pycharm": {
-     "name": "#%% md\n"
-    }
-   },
-   "source": [
-    "This uses the example Chinook database.\n",
-    "To set it up follow the instructions on https://database.guide/2-sample-databases-sqlite/, placing the `.db` file in a notebooks folder at the root of this repository."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "d0e27d88",
-   "metadata": {
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "from langchain import OpenAI, SQLDatabase, SQLDatabaseChain"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "72ede462",
-   "metadata": {
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "db = SQLDatabase.from_uri(\"sqlite:///../../../notebooks/Chinook.db\")\n",
-    "llm = OpenAI(temperature=0)\n",
-    "db_chain = SQLDatabaseChain(llm=llm, database=db, verbose=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "15ff81df",
-   "metadata": {
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new chain...\u001b[0m\n",
-      "How many employees are there?\n",
-      "SQLQuery:\u001b[102m SELECT COUNT(*) FROM Employee\u001b[0m\n",
-      "SQLResult: \u001b[103m[(8,)]\u001b[0m\n",
-      "Answer:\u001b[102m 8\u001b[0m\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "' 8'"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "db_chain.run(\"How many employees are there?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "61d91b85",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.7.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/examples/chains/summarize.ipynb

@@ -1,234 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "d9a0131f",
-   "metadata": {},
-   "source": [
-    "# Summarization\n",
-    "\n",
-    "This notebook walks through how to use LangChain for summarization over a list of documents. It covers three different chain types: `stuff`, `map_reduce`, and `refine`. For a more in depth explanation of what these chain types are, see [here](../../explanation/combine_docs.md)."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0b5660bf",
-   "metadata": {},
-   "source": [
-    "### Prepare Data\n",
-    "First we prepare the data. For this example we create multiple documents from one long one, but these documents could be fetched in any manner (the point of this notebook to highlight what to do AFTER you fetch the documents)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "e9db25f3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain import OpenAI, PromptTemplate, LLMChain\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
-    "from langchain.chains.mapreduce import MapReduceChain\n",
-    "\n",
-    "llm = OpenAI(temperature=0)\n",
-    "\n",
-    "\n",
-    "text_splitter = CharacterTextSplitter()\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "99bbe19b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "with open('../state_of_the_union.txt') as f:\n",
-    "    state_of_the_union = f.read()\n",
-    "texts = text_splitter.split_text(state_of_the_union)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "baa6e808",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.docstore.document import Document"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "8dff4f43",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "docs = [Document(page_content=t) for t in texts[:3]]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "27989fc4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chains.summarize import load_summarize_chain"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "ea2d5c99",
-   "metadata": {},
-   "source": [
-    "### The `stuff` Chain\n",
-    "\n",
-    "This sections shows results of using the `stuff` Chain to do summarization."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "f01f3196",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = load_summarize_chain(llm, chain_type=\"stuff\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "da4d9801",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "' In his speech, President Biden addressed the ongoing conflict between Russia and Ukraine, and the need for the United States and its allies to stand with Ukraine. He also discussed the American Rescue Plan, the Bipartisan Infrastructure Law, and the Bipartisan Innovation Act, which will help to create jobs, modernize infrastructure, and level the playing field with China. He also emphasized the importance of buying American products to support American jobs.'"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.run(docs)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "9c868e86",
-   "metadata": {},
-   "source": [
-    "### The `map_reduce` Chain\n",
-    "\n",
-    "This sections shows results of using the `map_reduce` Chain to do summarization."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "ef28e1d4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = load_summarize_chain(llm, chain_type=\"map_reduce\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "f82c5f9f",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\" In response to Vladimir Putin's aggression in Ukraine, the US and its allies have taken action to hold him accountable, including economic sanctions, cutting off access to technology, and seizing the assets of Russian oligarchs. They are also providing military, economic, and humanitarian assistance to the Ukrainians, and releasing 60 million barrels of oil from reserves around the world. President Biden has passed several laws to provide economic relief to Americans and create jobs, and is making sure taxpayer dollars support American jobs and businesses.\""
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.run(docs)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f61350f9",
-   "metadata": {},
-   "source": [
-    "### The `refine` Chain\n",
-    "\n",
-    "This sections shows results of using the `refine` Chain to do summarization."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "3bcbe31e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = load_summarize_chain(llm, chain_type=\"refine\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "c8cad866",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\"\\nIn this speech, the speaker addresses the American people and their allies, discussing the recent aggression of Russia's Vladimir Putin in Ukraine. The speaker outlines the actions taken by the United States and its allies to hold Putin accountable, including economic sanctions, cutting off access to technology, and seizing the assets of Russian oligarchs. The speaker also announces the closing of American airspace to Russian flights, further isolating Russia and adding an additional squeeze on their economy. The Russian stock market has lost 40% of its value and trading remains suspended. Together with our allies, the United States is providing military, economic, and humanitarian assistance to Ukraine, and has mobilized forces to protect NATO countries. The speaker also announces the release of 60 million barrels of oil from reserves around the world, with the United States releasing 30 million barrels from its own Strategic Petroleum Reserve. The speaker emphasizes that the United States and its allies will defend every inch of NATO territory and that Putin will pay a high price for his aggression. The speaker also acknowledges the hardships faced by the American people due to the pandemic and the American Rescue Plan, which has provided immediate economic relief for tens of millions of Americans, helped put food on their table, keep a roof over their heads, and cut the cost of health insurance. The speaker\""
-      ]
-     },
-     "execution_count": 11,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.run(docs)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "0da92750",
-   "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": "3.10.8"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/examples/chains/vector_db_qa.ipynb

@@ -1,104 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "07c1e3b9",
-   "metadata": {},
-   "source": [
-    "# Vector DB Question/Answering\n",
-    "\n",
-    "This example showcases question answering over a vector database."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "82525493",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
-    "from langchain.vectorstores.faiss import FAISS\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
-    "from langchain import OpenAI, VectorDBQA"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "5c7049db",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "with open('../state_of_the_union.txt') as f:\n",
-    "    state_of_the_union = f.read()\n",
-    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
-    "texts = text_splitter.split_text(state_of_the_union)\n",
-    "\n",
-    "embeddings = OpenAIEmbeddings()\n",
-    "docsearch = FAISS.from_texts(texts, embeddings)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "3018f865",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "qa = VectorDBQA.from_llm(llm=OpenAI(), vectorstore=docsearch)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "032a47f8",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator and federal public defender, and from a family of public school educators and police officers. He also said that she has received a broad range of support since she was nominated, from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
-    "qa.run(query)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "f056f6fd",
-   "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": "3.10.8"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/examples/chains/vector_db_qa_with_sources.ipynb

@@ -1,146 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "efc5be67",
-   "metadata": {},
-   "source": [
-    "# VectorDB Question Ansering with Sources\n",
-    "\n",
-    "This notebook goes over how to do question-answering with sources. It does this in a few different ways - first showing how you can use the `QAWithSourcesChain` to take in documents and use those, and next showing the `VectorDBQAWithSourcesChain`, which also does the lookup of the documents from a vector database. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "1c613960",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
-    "from langchain.embeddings.cohere import CohereEmbeddings\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
-    "from langchain.vectorstores.elastic_vector_search import ElasticVectorSearch\n",
-    "from langchain.vectorstores.faiss import FAISS"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "17d1306e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "with open('../state_of_the_union.txt') as f:\n",
-    "    state_of_the_union = f.read()\n",
-    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
-    "texts = text_splitter.split_text(state_of_the_union)\n",
-    "\n",
-    "embeddings = OpenAIEmbeddings()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "0e745d99",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "docsearch = FAISS.from_texts(texts, embeddings)"
-   ]
-  },
-  {
-   "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": "markdown",
-   "id": "e6fc81de",
-   "metadata": {},
-   "source": [
-    "### VectorDBQAWithSourcesChain\n",
-    "\n",
-    "This shows how to use the `VectorDBQAWithSourcesChain`, which uses a vector database to look up relevant documents."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "8aa571ae",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chains import VectorDBQAWithSourcesChain"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "aa859d4c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = VectorDBQAWithSourcesChain.from_llm(OpenAI(temperature=0), vectorstore=docsearch)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "8ba36fa7",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'answer': ' The president thanked Justice Breyer for his service.',\n",
-       " 'sources': '27-pl'}"
-      ]
-     },
-     "execution_count": 11,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain({\"question\": \"What did the president say about Justice Breyer\"}, return_only_outputs=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "980fae3b",
-   "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": "3.10.8"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/examples/integrations.rst

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

docs/examples/integrations/embeddings.ipynb

@@ -1,177 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "7ef4d402-6662-4a26-b612-35b542066487",
-   "metadata": {
-    "pycharm": {
-     "name": "#%% md\n"
-    }
-   },
-   "source": [
-    "#  Embeddings & VectorStores\n",
-    "\n",
-    "This notebook show cases how to use embeddings to create a VectorStore"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "965eecee",
-   "metadata": {
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
-    "from langchain.vectorstores.elastic_vector_search import ElasticVectorSearch\n",
-    "from langchain.vectorstores.faiss import FAISS"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "68481687",
-   "metadata": {
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "with open('../state_of_the_union.txt') as f:\n",
-    "    state_of_the_union = f.read()\n",
-    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
-    "texts = text_splitter.split_text(state_of_the_union)\n",
-    "\n",
-    "embeddings = OpenAIEmbeddings()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "015f4ff5",
-   "metadata": {
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "docsearch = FAISS.from_texts(texts, embeddings)\n",
-    "\n",
-    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
-    "docs = docsearch.similarity_search(query)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "67baf32e",
-   "metadata": {
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
-      "\n",
-      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
-      "\n",
-      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence. \n",
-      "\n",
-      "A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \n",
-      "\n",
-      "And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \n"
-     ]
-    }
-   ],
-   "source": [
-    "print(docs[0].page_content)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "eea6e627",
-   "metadata": {},
-   "source": [
-    "## Requires having ElasticSearch setup"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "4906b8a3",
-   "metadata": {
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "docsearch = ElasticVectorSearch.from_texts(texts, embeddings, elasticsearch_url=\"http://localhost:9200\")\n",
-    "\n",
-    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
-    "docs = docsearch.similarity_search(query)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "95f9eee9",
-   "metadata": {
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
-      "\n",
-      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
-      "\n",
-      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence. \n",
-      "\n",
-      "A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \n",
-      "\n",
-      "And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \n"
-     ]
-    }
-   ],
-   "source": [
-    "print(docs[0].page_content)"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.8.7"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/examples/integrations/textsplitter.ipynb

@@ -1,304 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "b118c9dc",
-   "metadata": {},
-   "source": [
-    "# Text Splitter\n",
-    "\n",
-    "When you want to deal wit long pieces of text, it is necessary to split up that text into chunks.\n",
-    "This notebook showcases several ways to do that.\n",
-    "\n",
-    "At a high level, text splitters work as following:\n",
-    "\n",
-    "1. Split the text up into small, semantically meaningful chunks (often sentences).\n",
-    "2. Start combining these small chunks into a larger chunk until you reach a certain size (as measured by some function).\n",
-    "3. Once you reach that size, make that chunk its own piece of text and then start creating a new chunk of text with some overlap (to keep context between chunks)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "e82c4685",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.text_splitter import CharacterTextSplitter, NLTKTextSplitter, SpacyTextSplitter\n",
-    "# This is a long document we can split up.\n",
-    "with open('../state_of_the_union.txt') as f:\n",
-    "    state_of_the_union = f.read()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "5c461b26",
-   "metadata": {},
-   "source": [
-    "## Character Text Splitting\n",
-    "\n",
-    "Let's start with the most simple method: let's split based on characters (by default \"\\n\\n\") and measure chunk length by number of characters."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "79ff6737",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "text_splitter = CharacterTextSplitter(        \n",
-    "    separator = \"\\n\\n\",\n",
-    "    chunk_size = 1000,\n",
-    "    chunk_overlap  = 200,\n",
-    "    length_function = len,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "38547666",
-   "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 Constitution. \\n\\nAnd with an unwavering resolve that freedom will always triumph over tyranny. \\n\\nSix days ago, Russia’s Vladimir Putin sought to shake the foundations of the free world thinking he could make it bend to his menacing ways. But he badly miscalculated. \\n\\nHe thought he could roll into Ukraine and the world would roll over. Instead he met a wall of strength he never imagined. \\n\\nHe met the Ukrainian people. \\n\\nFrom President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world. \\n\\nGroups of citizens blocking tanks with their bodies. Everyone from students to retirees teachers turned soldiers defending their homeland. '"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "texts = text_splitter.split_text(state_of_the_union)\n",
-    "texts[0]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "13dc0983",
-   "metadata": {},
-   "source": [
-    "## HuggingFace Length Function\n",
-    "Most LLMs are constrained by the number of tokens that you can pass in, which is not the same as the number of characters. In order to get a more accurate estimate, we can use HuggingFace tokenizers to count the text length."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "a8ce51d5",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.\n"
-     ]
-    }
-   ],
-   "source": [
-    "from transformers import GPT2TokenizerFast\n",
-    "\n",
-    "tokenizer = GPT2TokenizerFast.from_pretrained(\"gpt2\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "ca5e72c0",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "text_splitter = CharacterTextSplitter.from_huggingface_tokenizer(tokenizer, chunk_size=100, chunk_overlap=0)\n",
-    "texts = text_splitter.split_text(state_of_the_union)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "37cdfbeb",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans.  \n",
-      "\n",
-      "Last year COVID-19 kept us apart. This year we are finally together again. \n",
-      "\n",
-      "Tonight, we meet as Democrats Republicans and Independents. But most importantly as Americans. \n",
-      "\n",
-      "With a duty to one another to the American people to the Constitution. \n",
-      "\n",
-      "And with an unwavering resolve that freedom will always triumph over tyranny. \n"
-     ]
-    }
-   ],
-   "source": [
-    "print(texts[0])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "7683b36a",
-   "metadata": {},
-   "source": [
-    "## tiktoken (OpenAI) Length Function\n",
-    "You can also use tiktoken, a open source tokenizer package from OpenAI to estimate tokens used. Will probably be ore accurate for their models."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "825f7c0a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "text_splitter = CharacterTextSplitter.from_tiktoken_encoder(chunk_size=100, chunk_overlap=0)\n",
-    "texts = text_splitter.split_text(state_of_the_union)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "ae35d165",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans.  \n",
-      "\n",
-      "Last year COVID-19 kept us apart. This year we are finally together again. \n",
-      "\n",
-      "Tonight, we meet as Democrats Republicans and Independents. But most importantly as Americans. \n",
-      "\n",
-      "With a duty to one another to the American people to the Constitution. \n",
-      "\n",
-      "And with an unwavering resolve that freedom will always triumph over tyranny. \n"
-     ]
-    }
-   ],
-   "source": [
-    "print(texts[0])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "ea2973ac",
-   "metadata": {},
-   "source": [
-    "## NLTK Text Splitter\n",
-    "Rather than just splitting on \"\\n\\n\", we can use NLTK to split based on tokenizers."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "20fa9c23",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "text_splitter = NLTKTextSplitter(chunk_size=1000)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "5ea10835",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Madam Speaker, Madam Vice President, our First Lady and Second Gentleman.\\n\\nMembers of Congress and the Cabinet.\\n\\nJustices of the Supreme Court.\\n\\nMy fellow Americans.\\n\\nLast year COVID-19 kept us apart.\\n\\nThis year we are finally together again.\\n\\nTonight, we meet as Democrats Republicans and Independents.\\n\\nBut most importantly as Americans.\\n\\nWith a duty to one another to the American people to the Constitution.\\n\\nAnd with an unwavering resolve that freedom will always triumph over tyranny.\\n\\nSix days ago, Russia’s Vladimir Putin sought to shake the foundations of the free world thinking he could make it bend to his menacing ways.\\n\\nBut he badly miscalculated.\\n\\nHe thought he could roll into Ukraine and the world would roll over.\\n\\nInstead he met a wall of strength he never imagined.\\n\\nHe met the Ukrainian people.\\n\\nFrom President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world.\\n\\nGroups of citizens blocking tanks with their bodies.\\n\\nEveryone from students to retirees teachers turned soldiers defending their homeland.'"
-      ]
-     },
-     "execution_count": 16,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "texts = text_splitter.split_text(state_of_the_union)\n",
-    "texts[0]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "dab86b60",
-   "metadata": {},
-   "source": [
-    "## Spacy Text Splitter\n",
-    "Another alternative to NLTK is to use Spacy."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "f9cc9dfc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "text_splitter = SpacyTextSplitter(chunk_size=1000)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "id": "cef2b29e",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Madam Speaker, Madam Vice President, our First Lady and Second Gentleman.\\n\\nMembers of Congress and the Cabinet.\\n\\nJustices of the Supreme Court.\\n\\nMy fellow Americans.  \\n\\n\\n\\nLast year COVID-19 kept us apart.\\n\\nThis year we are finally together again.\\n\\n\\n\\n\\n\\nTonight, we meet as Democrats Republicans and Independents.\\n\\nBut most importantly as Americans.\\n\\n\\n\\n\\n\\nWith a duty to one another to the American people to the Constitution. \\n\\n\\n\\nAnd with an unwavering resolve that freedom will always triumph over tyranny.\\n\\n\\n\\n\\n\\nSix days ago, Russia’s Vladimir Putin sought to shake the foundations of the free world thinking he could make it bend to his menacing ways.\\n\\nBut he badly miscalculated.\\n\\n\\n\\n\\n\\nHe thought he could roll into Ukraine and the world would roll over.\\n\\nInstead he met a wall of strength he never imagined.\\n\\n\\n\\n\\n\\nHe met the Ukrainian people.\\n\\n\\n\\n\\n\\nFrom President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world.\\n\\n\\n\\n\\n\\nGroups of citizens blocking tanks with their bodies.\\n\\nEveryone from students to retirees teachers turned soldiers defending their homeland.'"
-      ]
-     },
-     "execution_count": 19,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "texts = text_splitter.split_text(state_of_the_union)\n",
-    "texts[0]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "a1a118b1",
-   "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": "3.10.8"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/examples/memory.rst

@@ -1,11 +0,0 @@
-Memory
-======
-
-The examples here are all related to working with the concept of Memory in LangChain.
-
-.. toctree::
-   :maxdepth: 1
-   :glob:
-   :caption: Memory
-
-   memory/*

docs/examples/memory/agent_with_memory.ipynb

@@ -1,325 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "fa6802ac",
-   "metadata": {},
-   "source": [
-    "# Adding Memory to an Agent\n",
-    "\n",
-    "This notebook goes over adding memory to an Agent. Before going through this notebook, please walkthrough the following notebooks, as this will build on top of both of them:\n",
-    "\n",
-    "- [Adding memory to an LLM Chain](adding_memory.ipynb)\n",
-    "- [Custom Agents](../agents/custom_agent.ipynb)\n",
-    "\n",
-    "In order to add a memory to an agent we are going to the the following steps:\n",
-    "\n",
-    "1. We are going to create an LLMChain with memory.\n",
-    "2. We are going to use that LLMChain to create a custom Agent.\n",
-    "\n",
-    "For the purposes of this exercise, we are going to create a simple custom Agent that has access to a search tool and utilizes the `ConversationBufferMemory` class."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "8db95912",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.agents import ZeroShotAgent, Tool\n",
-    "from langchain.chains.conversation.memory import ConversationBufferMemory\n",
-    "from langchain import OpenAI, SerpAPIWrapper, LLMChain"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "97ad8467",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "search = SerpAPIWrapper()\n",
-    "tools = [\n",
-    "    Tool(\n",
-    "        name = \"Search\",\n",
-    "        func=search.run,\n",
-    "        description=\"useful for when you need to answer questions about current events\"\n",
-    "    )\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "4ad2e708",
-   "metadata": {},
-   "source": [
-    "Notice the usage of the `chat_history` variable in the PromptTemplate, which matches up with the dynamic key name in the ConversationBufferMemory."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "e3439cd6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "prefix = \"\"\"Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:\"\"\"\n",
-    "suffix = \"\"\"Begin!\"\n",
-    "\n",
-    "{chat_history}\n",
-    "Question: {input}\"\"\"\n",
-    "\n",
-    "prompt = ZeroShotAgent.create_prompt(\n",
-    "    tools, \n",
-    "    prefix=prefix, \n",
-    "    suffix=suffix, \n",
-    "    input_variables=[\"input\", \"chat_history\"]\n",
-    ")\n",
-    "memory = ConversationBufferMemory(memory_key=\"chat_history\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0021675b",
-   "metadata": {},
-   "source": [
-    "We can now construct the LLMChain, with the Memory object, and then create the agent."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "c56a0e73",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=prompt, memory=memory)\n",
-    "agent = ZeroShotAgent(llm_chain=llm_chain, tools=tools, verbose=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "ca4bc1fb",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new chain...\u001b[0m\n",
-      "How many people live in canada?\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I should look up how many people live in canada\n",
-      "Action: Search\n",
-      "Action Input: \"How many people live in canada?\"\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3mThe current population of Canada is 38,533,678 as of Friday, November 25, 2022, based on Worldometer elaboration of the latest United Nations data. · Canada 2020 ...\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
-      "Final Answer: The current population of Canada is 38,533,678 as of Friday, November 25, 2022, based on Worldometer elaboration of the latest United Nations data.\u001b[0m\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'The current population of Canada is 38,533,678 as of Friday, November 25, 2022, based on Worldometer elaboration of the latest United Nations data.'"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "agent.run(\"How many people live in canada?\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "45627664",
-   "metadata": {},
-   "source": [
-    "To test the memory of this agent, we can ask a followup question that relies on information in the previous exchange to be answered correctly."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "eecc0462",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new chain...\u001b[0m\n",
-      "what is their national anthem called?\n",
-      "Thought:\u001b[32;1m\u001b[1;3m\n",
-      "AI:  I should look up the name of Canada's national anthem\n",
-      "Action: Search\n",
-      "Action Input: \"What is the name of Canada's national anthem?\"\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3mAfter 100 years of tradition, O Canada was proclaimed Canada's national anthem in 1980. The music for O Canada was composed in 1880 by Calixa ...\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m\n",
-      "AI:  I now know the final answer\n",
-      "Final Answer: After 100 years of tradition, O Canada was proclaimed Canada's national anthem in 1980. The music for O Canada was composed in 1880 by Calixa Lavallée.\u001b[0m\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "\"After 100 years of tradition, O Canada was proclaimed Canada's national anthem in 1980. The music for O Canada was composed in 1880 by Calixa Lavallée.\""
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "agent.run(\"what is their national anthem called?\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "cc3d0aa4",
-   "metadata": {},
-   "source": [
-    "We can see that the agent remembered that the previous question was about Canada, and properly asked Google Search what the name of Canada's national anthem was.\n",
-    "\n",
-    "For fun, let's compare this to an agent that does NOT have memory."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "3359d043",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "prefix = \"\"\"Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:\"\"\"\n",
-    "suffix = \"\"\"Begin!\"\n",
-    "\n",
-    "Question: {input}\"\"\"\n",
-    "\n",
-    "prompt = ZeroShotAgent.create_prompt(\n",
-    "    tools, \n",
-    "    prefix=prefix, \n",
-    "    suffix=suffix, \n",
-    "    input_variables=[\"input\"]\n",
-    ")\n",
-    "llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=prompt)\n",
-    "agent_without_memory = ZeroShotAgent(llm_chain=llm_chain, tools=tools, verbose=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "970d23df",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new chain...\u001b[0m\n",
-      "How many people live in canada?\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I should look up how many people live in canada\n",
-      "Action: Search\n",
-      "Action Input: \"How many people live in canada?\"\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3mThe current population of Canada is 38,533,678 as of Friday, November 25, 2022, based on Worldometer elaboration of the latest United Nations data. · Canada 2020 ...\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
-      "Final Answer: The current population of Canada is 38,533,678\u001b[0m\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'The current population of Canada is 38,533,678'"
-      ]
-     },
-     "execution_count": 10,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "agent_without_memory.run(\"How many people live in canada?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "d9ea82f0",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new chain...\u001b[0m\n",
-      "what is their national anthem called?\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I should probably look this up\n",
-      "Action: Search\n",
-      "Action Input: \"What is the national anthem of [country]\"\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3mMost nation states have an anthem, defined as \"a song, as of praise, devotion, or patriotism\"; most anthems are either marches or hymns in style.\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
-      "Final Answer: The national anthem is called \"the national anthem.\"\u001b[0m\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'The national anthem is called \"the national anthem.\"'"
-      ]
-     },
-     "execution_count": 11,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "agent_without_memory.run(\"what is their national anthem called?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "5b1f9223",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.7.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/examples/prompts.rst

@@ -1,35 +0,0 @@
-LLMs & Prompts
-==============
-
-The examples here all highlight how to work with LLMs and prompts.
-
-**LLMs**
-
-`LLM Functionality <prompts/llm_functionality.ipynb>`_: A walkthrough of all the functionality the standard LLM interface exposes.
-
-`LLM Serialization <prompts/llm_serialization.ipynb>`_: A walkthrough of how to serialize LLMs to and from disk.
-
-`Custom LLM <prompts/custom_llm.ipynb>`_: 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).
-
-
-**Prompts**
-
-`Prompt Management <prompts/prompt_management.ipynb>`_: A walkthrough of all the functionality LangChain supports for working with prompts.
-
-`Prompt Serialization <prompts/prompt_serialization.ipynb>`_: A walkthrough of how to serialize prompts to and from disk.
-
-`Few Shot Examples <prompts/few_shot_examples.ipynb>`_: How to include examples in the prompt.
-
-`Generate Examples <prompts/generate_examples.ipynb>`_: How to use existing examples to generate more examples.
-
-`Custom Example Selector <prompts/custom_example_selector.ipynb>`_: How to create and use a custom ExampleSelector (the class responsible for choosing which examples to use in a prompt).
-
-`Custom Prompt Template <prompts/custom_prompt_template.ipynb>`_: How to create and use a custom PromptTemplate, the logic that decides how input variables get formatted into a prompt.
-
-
-.. toctree::
-   :maxdepth: 1
-   :glob:
-   :hidden:
-
-   prompts/*

docs/examples/prompts/custom_example_selector.ipynb

@@ -1,176 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "f897c784",
-   "metadata": {},
-   "source": [
-    "# Custom ExampleSelector\n",
-    "\n",
-    "This notebook goes over how to implement a custom ExampleSelector. ExampleSelectors are used to select examples to use in few shot prompts.\n",
-    "\n",
-    "An ExampleSelector must implement two methods:\n",
-    "\n",
-    "1. An `add_example` method which takes in an example and adds it into the ExampleSelector\n",
-    "2. A `select_examples` method which takes in input variables (which are meant to be user input) and returns a list of examples to use in the few shot prompt.\n",
-    "\n",
-    "\n",
-    "Let's implement a custom ExampleSelector that just selects two examples at random."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "1a945da1",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.prompts.example_selector.base import BaseExampleSelector\n",
-    "from typing import Dict, List\n",
-    "import numpy as np"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "62cf0ad7",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "class CustomExampleSelector(BaseExampleSelector):\n",
-    "    \n",
-    "    def __init__(self, examples: List[Dict[str, str]]):\n",
-    "        self.examples = examples\n",
-    "    \n",
-    "    def add_example(self, example: Dict[str, str]) -> None:\n",
-    "        \"\"\"Add new example to store for a key.\"\"\"\n",
-    "        self.examples.append(example)\n",
-    "\n",
-    "    def select_examples(self, input_variables: Dict[str, str]) -> List[dict]:\n",
-    "        \"\"\"Select which examples to use based on the inputs.\"\"\"\n",
-    "        return np.random.choice(self.examples, size=2, replace=False)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "242d3213",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "examples = [{\"foo\": \"1\"}, {\"foo\": \"2\"}, {\"foo\": \"3\"}]\n",
-    "example_selector = CustomExampleSelector(examples)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2a038065",
-   "metadata": {},
-   "source": [
-    "Let's now try it out! We can select some examples and try adding examples."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "74fbbef5",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "array([{'foo': '2'}, {'foo': '3'}], dtype=object)"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "example_selector.select_examples({\"foo\": \"foo\"})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "9bbb5421",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "example_selector.add_example({\"foo\": \"4\"})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "c0eb9f22",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[{'foo': '1'}, {'foo': '2'}, {'foo': '3'}, {'foo': '4'}]"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "example_selector.examples"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "cc39b1e3",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "array([{'foo': '1'}, {'foo': '4'}], dtype=object)"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "example_selector.select_examples({\"foo\": \"foo\"})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "1739dd96",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.7.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/examples/prompts/custom_prompt_template.ipynb

@@ -1,116 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "a37d9694",
-   "metadata": {},
-   "source": [
-    "# Custom Prompt Template\n",
-    "\n",
-    "This notebook goes over how to create a custom prompt template, in case you want to create your own methodology for creating prompts.\n",
-    "\n",
-    "The only two requirements for all prompt templates are:\n",
-    "\n",
-    "1. They have a `input_variables` attribute that exposes what input variables this prompt template expects.\n",
-    "2. They expose a `format` method which takes in keyword arguments corresponding to the expected `input_variables` and returns the formatted prompt.\n",
-    "\n",
-    "Let's imagine that we want to create a prompt template that takes in input variables and formats them into the template AFTER capitalizing them. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "26f796e5",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.prompts import BasePromptTemplate\n",
-    "from pydantic import BaseModel"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "27919e96",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "class CustomPromptTemplate(BasePromptTemplate, BaseModel):\n",
-    "    template: str\n",
-    "        \n",
-    "    def format(self, **kwargs) -> str:\n",
-    "        capitalized_kwargs = {k: v.upper() for k, v in kwargs.items()}\n",
-    "        return self.template.format(**capitalized_kwargs)\n",
-    "        "
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "76d1d84d",
-   "metadata": {},
-   "source": [
-    "We can now see that when we use this, the input variables get formatted."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "eed1ff28",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "prompt = CustomPromptTemplate(input_variables=[\"foo\"], template=\"Capitalized: {foo}\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "94892a3c",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Capitalized: LOWERCASE'"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "prompt.format(foo=\"lowercase\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "d3d9a7c7",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.7.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/examples/prompts/few_shot_examples.ipynb

@@ -1,306 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "f8b01b97",
-   "metadata": {},
-   "source": [
-    "# Few Shot Prompt examples\n",
-    "Notebook showing off how canonical prompts in LangChain can be recreated as FewShotPrompts"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "18c67cc9",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.prompts.few_shot import FewShotPromptTemplate\n",
-    "from langchain.prompts.prompt import PromptTemplate"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "2a729c9f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Self Ask with Search\n",
-    "\n",
-    "examples = [\n",
-    "  {\n",
-    "    \"question\": \"Who lived longer, Muhammad Ali or Alan Turing?\",\n",
-    "    \"answer\": \"Are follow up questions needed here: Yes.\\nFollow up: How old was Muhammad Ali when he died?\\nIntermediate answer: Muhammad Ali was 74 years old when he died.\\nFollow up: How old was Alan Turing when he died?\\nIntermediate answer: Alan Turing was 41 years old when he died.\\nSo the final answer is: Muhammad Ali\"\n",
-    "  },\n",
-    "  {\n",
-    "    \"question\": \"When was the founder of craigslist born?\",\n",
-    "    \"answer\": \"Are follow up questions needed here: Yes.\\nFollow up: Who was the founder of craigslist?\\nIntermediate answer: Craigslist was founded by Craig Newmark.\\nFollow up: When was Craig Newmark born?\\nIntermediate answer: Craig Newmark was born on December 6, 1952.\\nSo the final answer is: December 6, 1952\"\n",
-    "  },\n",
-    "  {\n",
-    "    \"question\": \"Who was the maternal grandfather of George Washington?\",\n",
-    "    \"answer\": \"Are follow up questions needed here: Yes.\\nFollow up: Who was the mother of George Washington?\\nIntermediate answer: The mother of George Washington was Mary Ball Washington.\\nFollow up: Who was the father of Mary Ball Washington?\\nIntermediate answer: The father of Mary Ball Washington was Joseph Ball.\\nSo the final answer is: Joseph Ball\"\n",
-    "  },\n",
-    "  {\n",
-    "    \"question\": \"Are both the directors of Jaws and Casino Royale from the same country?\",\n",
-    "    \"answer\": \"Are follow up questions needed here: Yes.\\nFollow up: Who is the director of Jaws?\\nIntermediate Answer: The director of Jaws is Steven Spielberg.\\nFollow up: Where is Steven Spielberg from?\\nIntermediate Answer: The United States.\\nFollow up: Who is the director of Casino Royale?\\nIntermediate Answer: The director of Casino Royale is Martin Campbell.\\nFollow up: Where is Martin Campbell from?\\nIntermediate Answer: New Zealand.\\nSo the final answer is: No\"\n",
-    "  }\n",
-    "]\n",
-    "example_prompt = PromptTemplate(input_variables=[\"question\", \"answer\"], template=\"Question: {question}\\n{answer}\")\n",
-    "\n",
-    "prompt = FewShotPromptTemplate(\n",
-    "    examples=examples, \n",
-    "    example_prompt=example_prompt, \n",
-    "    suffix=\"Question: {input}\", \n",
-    "    input_variables=[\"input\"]\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "95fc0059",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# ReAct\n",
-    "\n",
-    "examples = [\n",
-    "  {\n",
-    "    \"question\": \"What is the elevation range for the area that the eastern sector of the Colorado orogeny extends into?\",\n",
-    "    \"answer\": \"Thought 1: I need to search Colorado orogeny, find the area that the eastern sector of the Colorado orogeny extends into, then find the elevation range of that area.\\nAction 1: Search[Colorado orogeny]\\nObservation 1: The Colorado orogeny was an episode of mountain building (an orogeny) in Colorado and surrounding areas.\\nThought 2: It does not mention the eastern sector. So I need to look up eastern sector.\\nAction 2: Lookup[eastern sector]\\nObservation 2: (Result 1 / 1) The eastern sector extends into the High Plains and is called the Central Plains orogeny.\\nThought 3: The eastern sector of Colorado orogeny extends into the High Plains. So I need to search High Plains and find its elevation range.\\nAction 3: Search[High Plains]\\nObservation 3: High Plains refers to one of two distinct land regions\\nThought 4: I need to instead search High Plains (United States).\\nAction 4: Search[High Plains (United States)]\\nObservation 4: The High Plains are a subregion of the Great Plains. From east to west, the High Plains rise in elevation from around 1,800 to 7,000 ft (550 to 2,130 m).[3]\\nThought 5: High Plains rise in elevation from around 1,800 to 7,000 ft, so the answer is 1,800 to 7,000 ft.\\nAction 5: Finish[1,800 to 7,000 ft]\"\n",
-    "  },\n",
-    "  {\n",
-    "    \"question\": \"Musician and satirist Allie Goertz wrote a song about the \\\"The Simpsons\\\" character Milhouse, who Matt Groening named after who?\",\n",
-    "    \"answer\": \"Thought 1: The question simplifies to \\\"The Simpsons\\\" character Milhouse is named after who. I only need to search Milhouse and find who it is named after.\\nAction 1: Search[Milhouse]\\nObservation 1: Milhouse Mussolini Van Houten is a recurring character in the Fox animated television series The Simpsons voiced by Pamela Hayden and created by Matt Groening.\\nThought 2: The paragraph does not tell who Milhouse is named after, maybe I can look up \\\"named after\\\".\\nAction 2: Lookup[named after]\\nObservation 2: (Result 1 / 1) Milhouse was named after U.S. president Richard Nixon, whose middle name was Milhous.\\nThought 3: Milhouse was named after U.S. president Richard Nixon, so the answer is Richard Nixon.\\nAction 3: Finish[Richard Nixon]\"\n",
-    "  },\n",
-    "  {\n",
-    "    \"question\": \"Which documentary is about Finnish rock groups, Adam Clayton Powell or The Saimaa Gesture?\",\n",
-    "    \"answer\": \"Thought 1: I need to search Adam Clayton Powell and The Saimaa Gesture, and find which documentary is about Finnish rock groups.\\nAction 1: Search[Adam Clayton Powell]\\nObservation 1 Could not find [Adam Clayton Powell]. Similar: [’Adam Clayton Powell III’, ’Seventh Avenue (Manhattan)’, ’Adam Clayton Powell Jr. State Office Building’, ’Isabel Washington Powell’, ’Adam Powell’, ’Adam Clayton Powell (film)’, ’Giancarlo Esposito’].\\nThought 2: To find the documentary, I can search Adam Clayton Powell (film).\\nAction 2: Search[Adam Clayton Powell (film)]\\nObservation 2: Adam Clayton Powell is a 1989 American documentary film directed by Richard Kilberg. The film is about the rise and fall of influential African-American politician Adam Clayton Powell Jr.[3][4] It was later aired as part of the PBS series The American Experience.\\nThought 3: Adam Clayton Powell (film) is a documentary about an African-American politician, not Finnish rock groups. So the documentary about Finnish rock groups must instead be The Saimaa Gesture.\\nAction 3: Finish[The Saimaa Gesture]\"\n",
-    "  },\n",
-    "  {\n",
-    "    \"question\": \"What profession does Nicholas Ray and Elia Kazan have in common?\",\n",
-    "    \"answer\": \"Thought 1: I need to search Nicholas Ray and Elia Kazan, find their professions, then find the profession they have in common.\\nAction 1: Search[Nicholas Ray]\\nObservation 1: Nicholas Ray (born Raymond Nicholas Kienzle Jr., August 7, 1911 - June 16, 1979) was an American film director, screenwriter, and actor best known for the 1955 film Rebel Without a Cause.\\nThought 2: Professions of Nicholas Ray are director, screenwriter, and actor. I need to search Elia Kazan next and find his professions.\\nAction 2: Search[Elia Kazan]\\nObservation 2: Elia Kazan was an American film and theatre director, producer, screenwriter and actor.\\nThought 3: Professions of Elia Kazan are director, producer, screenwriter, and actor. So profession Nicholas Ray and Elia Kazan have in common is director, screenwriter, and actor.\\nAction 3: Finish[director, screenwriter, actor]\"\n",
-    "  },\n",
-    "  {\n",
-    "    \"question\": \"Which magazine was started first Arthur’s Magazine or First for Women?\",\n",
-    "    \"answer\": \"Thought 1: I need to search Arthur’s Magazine and First for Women, and find which was started first.\\nAction 1: Search[Arthur’s Magazine]\\nObservation 1: Arthur’s Magazine (1844-1846) was an American literary periodical published in Philadelphia in the 19th century.\\nThought 2: Arthur’s Magazine was started in 1844. I need to search First for Women next.\\nAction 2: Search[First for Women]\\nObservation 2: First for Women is a woman’s magazine published by Bauer Media Group in the USA.[1] The magazine was started in 1989.\\nThought 3: First for Women was started in 1989. 1844 (Arthur’s Magazine) < 1989 (First for Women), so Arthur’s Magazine was started first.\\nAction 3: Finish[Arthur’s Magazine]\"\n",
-    "  },\n",
-    "  {\n",
-    "    \"question\": \"Were Pavel Urysohn and Leonid Levin known for the same type of work?\",\n",
-    "    \"answer\": \"Thought 1: I need to search Pavel Urysohn and Leonid Levin, find their types of work, then find if they are the same.\\nAction 1: Search[Pavel Urysohn]\\nObservation 1: Pavel Samuilovich Urysohn (February 3, 1898 - August 17, 1924) was a Soviet mathematician who is best known for his contributions in dimension theory.\\nThought 2: Pavel Urysohn is a mathematician. I need to search Leonid Levin next and find its type of work.\\nAction 2: Search[Leonid Levin]\\nObservation 2: Leonid Anatolievich Levin is a Soviet-American mathematician and computer scientist.\\nThought 3: Leonid Levin is a mathematician and computer scientist. So Pavel Urysohn and Leonid Levin have the same type of work.\\nAction 3: Finish[yes]\"\n",
-    "  }\n",
-    "]\n",
-    "example_prompt = PromptTemplate(input_variables=[\"question\", \"answer\"], template=\"Question: {question}\\n{answer}\")\n",
-    "\n",
-    "prompt = FewShotPromptTemplate(\n",
-    "    examples=examples, \n",
-    "    example_prompt=example_prompt, \n",
-    "    suffix=\"Question: {input}\", \n",
-    "    input_variables=[\"input\"]\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "897d4e08",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# LLM Math\n",
-    "examples = [\n",
-    "  {\n",
-    "    \"question\": \"What is 37593 * 67?\",\n",
-    "    \"answer\": \"```python\\nprint(37593 * 67)\\n```\\n```output\\n2518731\\n```\\nAnswer: 2518731\"\n",
-    "  }\n",
-    "]\n",
-    "example_prompt = PromptTemplate(input_variables=[\"question\", \"answer\"], template=\"Question: {question}\\n\\n{answer}\")\n",
-    "\n",
-    "prompt = FewShotPromptTemplate(\n",
-    "    examples=examples, \n",
-    "    example_prompt=example_prompt, \n",
-    "    suffix=\"Question: {input}\", \n",
-    "    input_variables=[\"input\"]\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "7ab7379f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# NatBot\n",
-    "example_seperator = \"==================================================\"\n",
-    "content_1 = \"\"\"<link id=1>About</link>\n",
-    "<link id=2>Store</link>\n",
-    "<link id=3>Gmail</link>\n",
-    "<link id=4>Images</link>\n",
-    "<link id=5>(Google apps)</link>\n",
-    "<link id=6>Sign in</link>\n",
-    "<img id=7 alt=\"(Google)\"/>\n",
-    "<input id=8 alt=\"Search\"></input>\n",
-    "<button id=9>(Search by voice)</button>\n",
-    "<button id=10>(Google Search)</button>\n",
-    "<button id=11>(I'm Feeling Lucky)</button>\n",
-    "<link id=12>Advertising</link>\n",
-    "<link id=13>Business</link>\n",
-    "<link id=14>How Search works</link>\n",
-    "<link id=15>Carbon neutral since 2007</link>\n",
-    "<link id=16>Privacy</link>\n",
-    "<link id=17>Terms</link>\n",
-    "<text id=18>Settings</text>\"\"\"\n",
-    "content_2 = \"\"\"<link id=1>About</link>\n",
-    "<link id=2>Store</link>\n",
-    "<link id=3>Gmail</link>\n",
-    "<link id=4>Images</link>\n",
-    "<link id=5>(Google apps)</link>\n",
-    "<link id=6>Sign in</link>\n",
-    "<img id=7 alt=\"(Google)\"/>\n",
-    "<input id=8 alt=\"Search\"></input>\n",
-    "<button id=9>(Search by voice)</button>\n",
-    "<button id=10>(Google Search)</button>\n",
-    "<button id=11>(I'm Feeling Lucky)</button>\n",
-    "<link id=12>Advertising</link>\n",
-    "<link id=13>Business</link>\n",
-    "<link id=14>How Search works</link>\n",
-    "<link id=15>Carbon neutral since 2007</link>\n",
-    "<link id=16>Privacy</link>\n",
-    "<link id=17>Terms</link>\n",
-    "<text id=18>Settings</text>\"\"\"\n",
-    "content_3 = \"\"\"<button id=1>For Businesses</button>\n",
-    "<button id=2>Mobile</button>\n",
-    "<button id=3>Help</button>\n",
-    "<button id=4 alt=\"Language Picker\">EN</button>\n",
-    "<link id=5>OpenTable logo</link>\n",
-    "<button id=6 alt =\"search\">Search</button>\n",
-    "<text id=7>Find your table for any occasion</text>\n",
-    "<button id=8>(Date selector)</button>\n",
-    "<text id=9>Sep 28, 2022</text>\n",
-    "<text id=10>7:00 PM</text>\n",
-    "<text id=11>2 people</text>\n",
-    "<input id=12 alt=\"Location, Restaurant, or Cuisine\"></input>\n",
-    "<button id=13>Let’s go</button>\n",
-    "<text id=14>It looks like you're in Peninsula. Not correct?</text>\n",
-    "<button id=15>Get current location</button>\n",
-    "<button id=16>Next</button>\"\"\"\n",
-    "examples = [\n",
-    "    {\n",
-    "        \"i\": 1,\n",
-    "        \"content\": content_1,\n",
-    "        \"objective\": \"Find a 2 bedroom house for sale in Anchorage AK for under $750k\",\n",
-    "        \"current_url\": \"https://www.google.com/\",\n",
-    "        \"command\": 'TYPESUBMIT 8 \"anchorage redfin\"'\n",
-    "    },\n",
-    "    {\n",
-    "        \"i\": 2,\n",
-    "        \"content\": content_2,\n",
-    "        \"objective\": \"Make a reservation for 4 at Dorsia at 8pm\",\n",
-    "        \"current_url\": \"https://www.google.com/\",\n",
-    "        \"command\": 'TYPESUBMIT 8 \"dorsia nyc opentable\"'\n",
-    "    },\n",
-    "    {\n",
-    "        \"i\": 3,\n",
-    "        \"content\": content_3,\n",
-    "        \"objective\": \"Make a reservation for 4 for dinner at Dorsia in New York City at 8pm\",\n",
-    "        \"current_url\": \"https://www.opentable.com/\",\n",
-    "        \"command\": 'TYPESUBMIT 12 \"dorsia new york city\"'\n",
-    "    },\n",
-    "]\n",
-    "example_prompt_template=\"\"\"EXAMPLE {i}:\n",
-    "==================================================\n",
-    "CURRENT BROWSER CONTENT:\n",
-    "------------------\n",
-    "{content}\n",
-    "------------------\n",
-    "OBJECTIVE: {objective}\n",
-    "CURRENT URL: {current_url}\n",
-    "YOUR COMMAND:\n",
-    "{command}\"\"\"\n",
-    "example_prompt = PromptTemplate(input_variables=[\"i\", \"content\", \"objective\", \"current_url\", \"command\"], template=example_prompt_template)\n",
-    "\n",
-    "\n",
-    "prefix = \"\"\"\n",
-    "You are an agent controlling a browser. You are given:\n",
-    "\t(1) an objective that you are trying to achieve\n",
-    "\t(2) the URL of your current web page\n",
-    "\t(3) a simplified text description of what's visible in the browser window (more on that below)\n",
-    "You can issue these commands:\n",
-    "\tSCROLL UP - scroll up one page\n",
-    "\tSCROLL DOWN - scroll down one page\n",
-    "\tCLICK X - click on a given element. You can only click on links, buttons, and inputs!\n",
-    "\tTYPE X \"TEXT\" - type the specified text into the input with id X\n",
-    "\tTYPESUBMIT X \"TEXT\" - same as TYPE above, except then it presses ENTER to submit the form\n",
-    "The format of the browser content is highly simplified; all formatting elements are stripped.\n",
-    "Interactive elements such as links, inputs, buttons are represented like this:\n",
-    "\t\t<link id=1>text</link>\n",
-    "\t\t<button id=2>text</button>\n",
-    "\t\t<input id=3>text</input>\n",
-    "Images are rendered as their alt text like this:\n",
-    "\t\t<img id=4 alt=\"\"/>\n",
-    "Based on your given objective, issue whatever command you believe will get you closest to achieving your goal.\n",
-    "You always start on Google; you should submit a search query to Google that will take you to the best page for\n",
-    "achieving your objective. And then interact with that page to achieve your objective.\n",
-    "If you find yourself on Google and there are no search results displayed yet, you should probably issue a command\n",
-    "like \"TYPESUBMIT 7 \"search query\"\" to get to a more useful page.\n",
-    "Then, if you find yourself on a Google search results page, you might issue the command \"CLICK 24\" to click\n",
-    "on the first link in the search results. (If your previous command was a TYPESUBMIT your next command should\n",
-    "probably be a CLICK.)\n",
-    "Don't try to interact with elements that you can't see.\n",
-    "Here are some examples:\n",
-    "\"\"\"\n",
-    "suffix=\"\"\"\n",
-    "The current browser content, objective, and current URL follow. Reply with your next command to the browser.\n",
-    "CURRENT BROWSER CONTENT:\n",
-    "------------------\n",
-    "{browser_content}\n",
-    "------------------\n",
-    "OBJECTIVE: {objective}\n",
-    "CURRENT URL: {url}\n",
-    "PREVIOUS COMMAND: {previous_command}\n",
-    "YOUR COMMAND:\n",
-    "\"\"\"\n",
-    "PROMPT = FewShotPromptTemplate(\n",
-    "    examples = examples,\n",
-    "    example_prompt=example_prompt,\n",
-    "    example_separator=example_seperator,\n",
-    "    input_variables=[\"browser_content\", \"url\", \"previous_command\", \"objective\"],\n",
-    "    prefix=prefix,\n",
-    "    suffix=suffix,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "ce5927c6",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.7.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/examples/prompts/generate_examples.ipynb

@@ -1,161 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "f5d249ee",
-   "metadata": {
-    "pycharm": {
-     "name": "#%% md\n"
-    }
-   },
-   "source": [
-    "# Generate Examples\n",
-    "\n",
-    "This notebook shows how to use LangChain to generate more examples similar to the ones you already have."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "1685fa2f",
-   "metadata": {
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.llms.openai import OpenAI\n",
-    "from langchain.example_generator import generate_example\n",
-    "from langchain.prompts import PromptTemplate"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "334ef4f7",
-   "metadata": {
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "# Use examples from ReAct\n",
-    "examples = [\n",
-    "  {\n",
-    "    \"question\": \"What is the elevation range for the area that the eastern sector of the Colorado orogeny extends into?\",\n",
-    "    \"answer\": \"Thought 1: I need to search Colorado orogeny, find the area that the eastern sector of the Colorado orogeny extends into, then find the elevation range of that area.\\nAction 1: Search[Colorado orogeny]\\nObservation 1: The Colorado orogeny was an episode of mountain building (an orogeny) in Colorado and surrounding areas.\\nThought 2: It does not mention the eastern sector. So I need to look up eastern sector.\\nAction 2: Lookup[eastern sector]\\nObservation 2: (Result 1 / 1) The eastern sector extends into the High Plains and is called the Central Plains orogeny.\\nThought 3: The eastern sector of Colorado orogeny extends into the High Plains. So I need to search High Plains and find its elevation range.\\nAction 3: Search[High Plains]\\nObservation 3: High Plains refers to one of two distinct land regions\\nThought 4: I need to instead search High Plains (United States).\\nAction 4: Search[High Plains (United States)]\\nObservation 4: The High Plains are a subregion of the Great Plains. From east to west, the High Plains rise in elevation from around 1,800 to 7,000 ft (550 to 2,130 m).[3]\\nThought 5: High Plains rise in elevation from around 1,800 to 7,000 ft, so the answer is 1,800 to 7,000 ft.\\nAction 5: Finish[1,800 to 7,000 ft]\"\n",
-    "  },\n",
-    "  {\n",
-    "    \"question\": \"Musician and satirist Allie Goertz wrote a song about the \\\"The Simpsons\\\" character Milhouse, who Matt Groening named after who?\",\n",
-    "    \"answer\": \"Thought 1: The question simplifies to \\\"The Simpsons\\\" character Milhouse is named after who. I only need to search Milhouse and find who it is named after.\\nAction 1: Search[Milhouse]\\nObservation 1: Milhouse Mussolini Van Houten is a recurring character in the Fox animated television series The Simpsons voiced by Pamela Hayden and created by Matt Groening.\\nThought 2: The paragraph does not tell who Milhouse is named after, maybe I can look up \\\"named after\\\".\\nAction 2: Lookup[named after]\\nObservation 2: (Result 1 / 1) Milhouse was named after U.S. president Richard Nixon, whose middle name was Milhous.\\nThought 3: Milhouse was named after U.S. president Richard Nixon, so the answer is Richard Nixon.\\nAction 3: Finish[Richard Nixon]\"\n",
-    "  },\n",
-    "  {\n",
-    "    \"question\": \"Which documentary is about Finnish rock groups, Adam Clayton Powell or The Saimaa Gesture?\",\n",
-    "    \"answer\": \"Thought 1: I need to search Adam Clayton Powell and The Saimaa Gesture, and find which documentary is about Finnish rock groups.\\nAction 1: Search[Adam Clayton Powell]\\nObservation 1 Could not find [Adam Clayton Powell]. Similar: [’Adam Clayton Powell III’, ’Seventh Avenue (Manhattan)’, ’Adam Clayton Powell Jr. State Office Building’, ’Isabel Washington Powell’, ’Adam Powell’, ’Adam Clayton Powell (film)’, ’Giancarlo Esposito’].\\nThought 2: To find the documentary, I can search Adam Clayton Powell (film).\\nAction 2: Search[Adam Clayton Powell (film)]\\nObservation 2: Adam Clayton Powell is a 1989 American documentary film directed by Richard Kilberg. The film is about the rise and fall of influential African-American politician Adam Clayton Powell Jr.[3][4] It was later aired as part of the PBS series The American Experience.\\nThought 3: Adam Clayton Powell (film) is a documentary about an African-American politician, not Finnish rock groups. So the documentary about Finnish rock groups must instead be The Saimaa Gesture.\\nAction 3: Finish[The Saimaa Gesture]\"\n",
-    "  },\n",
-    "  {\n",
-    "    \"question\": \"What profession does Nicholas Ray and Elia Kazan have in common?\",\n",
-    "    \"answer\": \"Thought 1: I need to search Nicholas Ray and Elia Kazan, find their professions, then find the profession they have in common.\\nAction 1: Search[Nicholas Ray]\\nObservation 1: Nicholas Ray (born Raymond Nicholas Kienzle Jr., August 7, 1911 - June 16, 1979) was an American film director, screenwriter, and actor best known for the 1955 film Rebel Without a Cause.\\nThought 2: Professions of Nicholas Ray are director, screenwriter, and actor. I need to search Elia Kazan next and find his professions.\\nAction 2: Search[Elia Kazan]\\nObservation 2: Elia Kazan was an American film and theatre director, producer, screenwriter and actor.\\nThought 3: Professions of Elia Kazan are director, producer, screenwriter, and actor. So profession Nicholas Ray and Elia Kazan have in common is director, screenwriter, and actor.\\nAction 3: Finish[director, screenwriter, actor]\"\n",
-    "  },\n",
-    "  {\n",
-    "    \"question\": \"Which magazine was started first Arthur’s Magazine or First for Women?\",\n",
-    "    \"answer\": \"Thought 1: I need to search Arthur’s Magazine and First for Women, and find which was started first.\\nAction 1: Search[Arthur’s Magazine]\\nObservation 1: Arthur’s Magazine (1844-1846) was an American literary periodical published in Philadelphia in the 19th century.\\nThought 2: Arthur’s Magazine was started in 1844. I need to search First for Women next.\\nAction 2: Search[First for Women]\\nObservation 2: First for Women is a woman’s magazine published by Bauer Media Group in the USA.[1] The magazine was started in 1989.\\nThought 3: First for Women was started in 1989. 1844 (Arthur’s Magazine) < 1989 (First for Women), so Arthur’s Magazine was started first.\\nAction 3: Finish[Arthur’s Magazine]\"\n",
-    "  },\n",
-    "  {\n",
-    "    \"question\": \"Were Pavel Urysohn and Leonid Levin known for the same type of work?\",\n",
-    "    \"answer\": \"Thought 1: I need to search Pavel Urysohn and Leonid Levin, find their types of work, then find if they are the same.\\nAction 1: Search[Pavel Urysohn]\\nObservation 1: Pavel Samuilovich Urysohn (February 3, 1898 - August 17, 1924) was a Soviet mathematician who is best known for his contributions in dimension theory.\\nThought 2: Pavel Urysohn is a mathematician. I need to search Leonid Levin next and find its type of work.\\nAction 2: Search[Leonid Levin]\\nObservation 2: Leonid Anatolievich Levin is a Soviet-American mathematician and computer scientist.\\nThought 3: Leonid Levin is a mathematician and computer scientist. So Pavel Urysohn and Leonid Levin have the same type of work.\\nAction 3: Finish[yes]\"\n",
-    "  }\n",
-    "]\n",
-    "example_template = PromptTemplate(template=\"Question: {question}\\n{answer}\", input_variables=[\"question\", \"answer\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "a7bd36bc",
-   "metadata": {
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "new_example = generate_example(examples, OpenAI(), example_template)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "e1efb008",
-   "metadata": {
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "['',\n",
-       " '',\n",
-       " 'Question: What is the highest mountain peak in North America?',\n",
-       " '',\n",
-       " 'Thought 1: I need to search North America and find the highest mountain peak.',\n",
-       " '',\n",
-       " 'Action 1: Search[North America]',\n",
-       " '',\n",
-       " 'Observation 1: North America is a continent entirely within the Northern Hemisphere and almost all within the Western Hemisphere.',\n",
-       " '',\n",
-       " 'Thought 2: I need to look up \"highest mountain peak\".',\n",
-       " '',\n",
-       " 'Action 2: Lookup[highest mountain peak]',\n",
-       " '',\n",
-       " 'Observation 2: (Result 1 / 1) Denali, formerly Mount McKinley, is the highest mountain peak in North America, with a summit elevation of 20,310 feet (6,190 m) above sea level.',\n",
-       " '',\n",
-       " 'Thought 3: Denali is the highest mountain peak in North America, with a summit elevation of 20,310 feet.',\n",
-       " '',\n",
-       " 'Action 3: Finish[20,310 feet]']"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "new_example.split('\\n')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "1ed01ba2",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.7.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/examples/prompts/llm_functionality.ipynb

@@ -1,412 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "20ac6b98",
-   "metadata": {},
-   "source": [
-    "# LLM Functionality\n",
-    "\n",
-    "This notebook goes over all the different features of the LLM class in LangChain.\n",
-    "\n",
-    "We will work with an OpenAI LLM wrapper, although these functionalities should exist for all LLM types."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "df924055",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.llms import OpenAI"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "182b484c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm = OpenAI(model_name=\"text-ada-001\", n=2, best_of=2)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "9695ccfc",
-   "metadata": {},
-   "source": [
-    "**Generate Text:** The most basic functionality an LLM has is just the ability to call it, passing in a string and getting back a string."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "9d12ac26",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'\\n\\nWhy did the chicken cross the road?\\n\\nTo get to the other side!'"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "llm(\"Tell me a joke\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e7d4d42d",
-   "metadata": {},
-   "source": [
-    "**Generate:** More broadly, you can call it with a list of inputs, getting back a more complete response than just the text. This complete response includes things like multiple top responses, as well as LLM provider specific information"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "f4dc241a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm_result = llm.generate([\"Tell me a joke\", \"Tell me a poem\"]*15)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "740392f6",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "30"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "len(llm_result.generations)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "ab6cdcf1",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[Generation(text='\\n\\nWhy did the chicken cross the road?\\n\\nTo get to the other side.'),\n",
-       " Generation(text='\\n\\nWhy did the chicken cross the road?\\n\\nTo get to the other side!')]"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "llm_result.generations[0]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "4946a778",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[Generation(text=\"\\n\\nA rose by the side of the road\\n\\nIs all I need to find my way\\n\\nTo the place I've been searching for\\n\\nAnd my heart is singing with joy\\n\\nWhen I look at this rose\\n\\nIt reminds me of the love I've found\\n\\nAnd I know that wherever I go\\n\\nI'll always find my rose by the side of the road.\"),\n",
-       " Generation(text=\"\\n\\nWhen I was younger\\nI thought that love\\nI was something like a fairytale\\nI would find my prince and they would be my people\\nI was naïve\\nI thought that\\n\\nLove was a something that happened\\nWhen I was younger\\nI was it for my fairytale prince\\nNow I realize\\nThat love is something that waits\\nFor when my prince comes\\nAnd when I am ready to be his wife\\nI'll tell you a poem\\n\\nWhen I was younger\\nI thought that love\\nI was something like a fairytale\\nI would find my prince and they would be my people\\nI was naïve\\nI thought that\\n\\nLove was a something that happened\\nAnd I would be happy\\nWhen my prince came\\nAnd I was ready to be his wife\")]"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "llm_result.generations[-1]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "242e4527",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'token_usage': {'completion_tokens': 3722,\n",
-       "  'prompt_tokens': 120,\n",
-       "  'total_tokens': 3842}}"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Provider specific info\n",
-    "llm_result.llm_output"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "bde8e04f",
-   "metadata": {},
-   "source": [
-    "**Number of Tokens:** You can also estimate how many tokens a piece of text will be in that model. This is useful because models have a context length (and cost more for more tokens), which means you need to be aware of how long the text you are passing in is.\n",
-    "\n",
-    "Notice that by default the tokens are estimated using a HuggingFace tokenizer."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "b623c774",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "3"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "llm.get_num_tokens(\"what a joke\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "ee6fcf8d",
-   "metadata": {},
-   "source": [
-    "### Caching\n",
-    "With LangChain, you can also enable caching of LLM calls. Note that currently this only applies for individual LLM calls."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "2626ca48",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import langchain\n",
-    "from langchain.cache import InMemoryCache\n",
-    "langchain.llm_cache = InMemoryCache()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "97762272",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# To make the caching really obvious, lets use a slower model.\n",
-    "llm = OpenAI(model_name=\"text-davinci-002\", n=2, best_of=2)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "e80c65e4",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "CPU times: user 31.2 ms, sys: 11.8 ms, total: 43.1 ms\n",
-      "Wall time: 1.75 s\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'\\n\\nWhy did the chicken cross the road?\\n\\nTo get to the other side!'"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "%%time\n",
-    "# The first time, it is not yet in cache, so it should take longer\n",
-    "llm(\"Tell me a joke\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "678408ec",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "CPU times: user 51 µs, sys: 1 µs, total: 52 µs\n",
-      "Wall time: 67.2 µs\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'\\n\\nWhy did the chicken cross the road?\\n\\nTo get to the other side!'"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "%%time\n",
-    "# The second time it is, so it goes faster\n",
-    "llm(\"Tell me a joke\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "3f0ac8d2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# We can do the same thing with a SQLite cache\n",
-    "from langchain.cache import SQLiteCache\n",
-    "langchain.llm_cache = SQLiteCache(database_path=\".langchain.db\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "0e1dcce3",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "CPU times: user 26.6 ms, sys: 11.2 ms, total: 37.7 ms\n",
-      "Wall time: 1.89 s\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'\\n\\nWhy did the chicken cross the road?\\n\\nTo get to the other side.'"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "%%time\n",
-    "# The first time, it is not yet in cache, so it should take longer\n",
-    "llm(\"Tell me a joke\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "efadd750",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "CPU times: user 2.69 ms, sys: 1.57 ms, total: 4.27 ms\n",
-      "Wall time: 2.73 ms\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'\\n\\nWhy did the chicken cross the road?\\n\\nTo get to the other side.'"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "%%time\n",
-    "# The second time it is, so it goes faster\n",
-    "llm(\"Tell me a joke\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "6053408b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# You can use SQLAlchemyCache to cache with any SQL database supported by SQLAlchemy.\n",
-    "from langchain.cache import SQLAlchemyCache\n",
-    "from sqlalchemy import create_engine\n",
-    "\n",
-    "engine = create_engine(\"postgresql://postgres:postgres@localhost:5432/postgres\")\n",
-    "langchain.llm_cache = SQLAlchemyCache(engine)"
-   ]
-  }
- ],
- "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": "3.9.12 (main, Jun  1 2022, 06:34:44) \n[Clang 12.0.0 ]"
-  },
-  "vscode": {
-   "interpreter": {
-    "hash": "1235b9b19e8e9828b5c1fdb2cd89fe8d3de0fcde5ef5f3db36e4b671adb8660f"
-   }
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/examples/prompts/prompt_management.ipynb

@@ -1,610 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "43fb16cb",
-   "metadata": {},
-   "source": [
-    "# Prompt Management\n",
-    "\n",
-    "Managing your prompts is annoying and tedious, with everyone writing their own slightly different variants of the same ideas. But it shouldn't be this way. \n",
-    "\n",
-    "LangChain provides a standard and flexible way for specifying and managing all your prompts, as well as clear and specific terminology around them. This notebook goes through the core components of working with prompts, showing how to use them as well as explaining what they do.\n",
-    "\n",
-    "This notebook covers how to work with prompts in Python. If you are interested in how to work with serialized versions of prompts and load them from disk, see [this notebook](prompt_serialization.ipynb)."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "890aad4d",
-   "metadata": {},
-   "source": [
-    "### The BasePromptTemplate Interface\n",
-    "\n",
-    "A prompt template is a mechanism for constructing a prompt to pass to the language model given some user input. Below is the interface that all different types of prompt templates should expose.\n",
-    "\n",
-    "```python\n",
-    "class BasePromptTemplate(ABC):\n",
-    "\n",
-    "    input_variables: List[str]\n",
-    "    \"\"\"A list of the names of the variables the prompt template expects.\"\"\"\n",
-    "\n",
-    "    @abstractmethod\n",
-    "    def format(self, **kwargs: Any) -> str:\n",
-    "        \"\"\"Format the prompt with the inputs.\n",
-    "\n",
-    "        Args:\n",
-    "            kwargs: Any arguments to be passed to the prompt template.\n",
-    "\n",
-    "        Returns:\n",
-    "            A formatted string.\n",
-    "\n",
-    "        Example:\n",
-    "\n",
-    "        .. code-block:: python\n",
-    "\n",
-    "            prompt.format(variable1=\"foo\")\n",
-    "        \"\"\"\n",
-    "```\n",
-    "\n",
-    "The only two things that define a prompt are:\n",
-    "\n",
-    "1. `input_variables`: The user inputted variables that are needed to format the prompt.\n",
-    "2. `format`: A method which takes in keyword arguments are returns a formatted prompt. The keys are expected to be the input variables\n",
-    "    \n",
-    "The rest of the logic of how the prompt is constructed is left up to different implementations. Let's take a look at some below."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "cddb465e",
-   "metadata": {},
-   "source": [
-    "### PromptTemplate\n",
-    "\n",
-    "This is the most simple type of prompt template, consisting of a string template that takes any number of input variables. The template should be formatted as a Python f-string, although we will support other formats (Jinja, Mako, etc) in the future. \n",
-    "\n",
-    "If you just want to use a hardcoded prompt template, you should use this implementation.\n",
-    "\n",
-    "Let's walk through a few examples."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "094229f4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.prompts import PromptTemplate"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "ab46bd2a",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Tell me a joke.'"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# An example prompt with no input variables\n",
-    "no_input_prompt = PromptTemplate(input_variables=[], template=\"Tell me a joke.\")\n",
-    "no_input_prompt.format()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "c3ad0fa8",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Tell me a funny joke.'"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# An example prompt with one input variable\n",
-    "one_input_prompt = PromptTemplate(input_variables=[\"adjective\"], template=\"Tell me a {adjective} joke.\")\n",
-    "one_input_prompt.format(adjective=\"funny\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "ba577dcf",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Tell me a funny joke about chickens.'"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# An example prompt with multiple input variables\n",
-    "multiple_input_prompt = PromptTemplate(\n",
-    "    input_variables=[\"adjective\", \"content\"], \n",
-    "    template=\"Tell me a {adjective} joke about {content}.\"\n",
-    ")\n",
-    "multiple_input_prompt.format(adjective=\"funny\", content=\"chickens\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "1492b49d",
-   "metadata": {},
-   "source": [
-    "### Few Shot Prompts\n",
-    "\n",
-    "A FewShotPromptTemplate is a prompt template that includes some examples. If you have collected some examples of how the task should be done, you can insert them into prompt using this class.\n",
-    "\n",
-    "Examples are datapoints that can be included in the prompt in order to give the model more context what to do. Examples are represented as a dictionary of key-value pairs, with the key being the input (or label) name, and the value being the input (or label) value. \n",
-    "\n",
-    "In addition to the example, we also need to specify how the example should be formatted when it's inserted in the prompt. We can do this using the above `PromptTemplate`!"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "3eb36972",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# These are some examples of a pretend task of creating antonyms.\n",
-    "examples = [\n",
-    "    {\"input\": \"happy\", \"output\": \"sad\"},\n",
-    "    {\"input\": \"tall\", \"output\": \"short\"},\n",
-    "]\n",
-    "# This how we specify how the example should be formatted.\n",
-    "example_prompt = PromptTemplate(\n",
-    "    input_variables=[\"input\",\"output\"],\n",
-    "    template=\"Input: {input}\\nOutput: {output}\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "80a91d96",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.prompts import FewShotPromptTemplate"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "7931e5f2",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Give the antonym of every input\n",
-      "\n",
-      "Input: happy\n",
-      "Output: sad\n",
-      "\n",
-      "Input: tall\n",
-      "Output: short\n",
-      "\n",
-      "Input: big\n",
-      "Output:\n"
-     ]
-    }
-   ],
-   "source": [
-    "prompt_from_string_examples = FewShotPromptTemplate(\n",
-    "    # These are the examples we want to insert into the prompt.\n",
-    "    examples=examples,\n",
-    "    # This is how we want to format the examples when we insert them into the prompt.\n",
-    "    example_prompt=example_prompt,\n",
-    "    # The prefix is some text that goes before the examples in the prompt.\n",
-    "    # Usually, this consists of intructions.\n",
-    "    prefix=\"Give the antonym of every input\",\n",
-    "    # The suffix is some text that goes after the examples in the prompt.\n",
-    "    # Usually, this is where the user input will go\n",
-    "    suffix=\"Input: {adjective}\\nOutput:\", \n",
-    "    # The input variables are the variables that the overall prompt expects.\n",
-    "    input_variables=[\"adjective\"],\n",
-    "    # The example_separator is the string we will use to join the prefix, examples, and suffix together with.\n",
-    "    example_separator=\"\\n\\n\"\n",
-    "    \n",
-    ")\n",
-    "print(prompt_from_string_examples.format(adjective=\"big\"))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "bf038596",
-   "metadata": {},
-   "source": [
-    "### ExampleSelector\n",
-    "If you have a large number of examples, you may need to select which ones to include in the prompt. The ExampleSelector is the class responsible for doing so. The base interface is defined as below.\n",
-    "\n",
-    "```python\n",
-    "class BaseExampleSelector(ABC):\n",
-    "    \"\"\"Interface for selecting examples to include in prompts.\"\"\"\n",
-    "\n",
-    "    @abstractmethod\n",
-    "    def select_examples(self, input_variables: Dict[str, str]) -> List[dict]:\n",
-    "        \"\"\"Select which examples to use based on the inputs.\"\"\"\n",
-    "\n",
-    "```\n",
-    "\n",
-    "The only method it needs to expose is a `select_examples` method. This takes in the input variables and then returns a list of examples. It is up to each specific implementation as to how those examples are selected. Let's take a look at some below."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "861a4d1f",
-   "metadata": {},
-   "source": [
-    "### LengthBased ExampleSelector\n",
-    "\n",
-    "This ExampleSelector selects which examples to use based on length. This is useful when you are worried about constructing a prompt that will go over the length of the context window. For longer inputs, it will select fewer examples to include, while for shorter inputs it will select more.\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "7c469c95",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.prompts.example_selector import LengthBasedExampleSelector"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "0ec6d950",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# These are a lot of examples of a pretend task of creating antonyms.\n",
-    "examples = [\n",
-    "    {\"input\": \"happy\", \"output\": \"sad\"},\n",
-    "    {\"input\": \"tall\", \"output\": \"short\"},\n",
-    "    {\"input\": \"energetic\", \"output\": \"lethargic\"},\n",
-    "    {\"input\": \"sunny\", \"output\": \"gloomy\"},\n",
-    "    {\"input\": \"windy\", \"output\": \"calm\"},\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "207e55f7",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "example_selector = LengthBasedExampleSelector(\n",
-    "    # These are the examples is has available to choose from.\n",
-    "    examples=examples, \n",
-    "    # This is the PromptTemplate being used to format the examples.\n",
-    "    example_prompt=example_prompt, \n",
-    "    # This is the maximum length that the formatted examples should be.\n",
-    "    # Length is measured by the get_text_length function below.\n",
-    "    max_length=25,\n",
-    "    # This is the function used to get the length of a string, which is used\n",
-    "    # to determine which examples to include. It is commented out because\n",
-    "    # it is provided as a default value if none is specified.\n",
-    "    # get_text_length: Callable[[str], int] = lambda x: len(re.split(\"\\n| \", x))\n",
-    ")\n",
-    "dynamic_prompt = FewShotPromptTemplate(\n",
-    "    # We provide an ExampleSelector instead of examples.\n",
-    "    example_selector=example_selector,\n",
-    "    example_prompt=example_prompt,\n",
-    "    prefix=\"Give the antonym of every input\",\n",
-    "    suffix=\"Input: {adjective}\\nOutput:\", \n",
-    "    input_variables=[\"adjective\"],\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "d00b4385",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Give the antonym of every input\n",
-      "\n",
-      "Input: happy\n",
-      "Output: sad\n",
-      "\n",
-      "Input: tall\n",
-      "Output: short\n",
-      "\n",
-      "Input: energetic\n",
-      "Output: lethargic\n",
-      "\n",
-      "Input: sunny\n",
-      "Output: gloomy\n",
-      "\n",
-      "Input: windy\n",
-      "Output: calm\n",
-      "\n",
-      "Input: big\n",
-      "Output:\n"
-     ]
-    }
-   ],
-   "source": [
-    "# An example with small input, so it selects all examples.\n",
-    "print(dynamic_prompt.format(adjective=\"big\"))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "878bcde9",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Give the antonym of every input\n",
-      "\n",
-      "Input: happy\n",
-      "Output: sad\n",
-      "\n",
-      "Input: big and huge and massive and large and gigantic and tall and much much much much much bigger than everything else\n",
-      "Output:\n"
-     ]
-    }
-   ],
-   "source": [
-    "# An example with long input, so it selects only one example.\n",
-    "long_string = \"big and huge and massive and large and gigantic and tall and much much much much much bigger than everything else\"\n",
-    "print(dynamic_prompt.format(adjective=long_string))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "e4bebcd9",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Give the antonym of every input\n",
-      "\n",
-      "Input: happy\n",
-      "Output: sad\n",
-      "\n",
-      "Input: tall\n",
-      "Output: short\n",
-      "\n",
-      "Input: energetic\n",
-      "Output: lethargic\n",
-      "\n",
-      "Input: sunny\n",
-      "Output: gloomy\n",
-      "\n",
-      "Input: windy\n",
-      "Output: calm\n",
-      "\n",
-      "Input: big\n",
-      "Output: small\n",
-      "\n",
-      "Input: enthusiastic\n",
-      "Output:\n"
-     ]
-    }
-   ],
-   "source": [
-    "# You can add an example to an example selector as well.\n",
-    "new_example = {\"input\": \"big\", \"output\": \"small\"}\n",
-    "dynamic_prompt.example_selector.add_example(new_example)\n",
-    "print(dynamic_prompt.format(adjective=\"enthusiastic\"))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2d007b0a",
-   "metadata": {},
-   "source": [
-    "### Similarity ExampleSelector\n",
-    "\n",
-    "The SemanticSimilarityExampleSelector selects examples based on which examples are most similar to the inputs. It does this by finding the examples with the embeddings that have the greatest cosine similarity with the inputs.\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "241bfe80",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.prompts.example_selector import SemanticSimilarityExampleSelector\n",
-    "from langchain.vectorstores import FAISS\n",
-    "from langchain.embeddings import OpenAIEmbeddings"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "50d0a701",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "example_selector = SemanticSimilarityExampleSelector.from_examples(\n",
-    "    # This is the list of examples available to select from.\n",
-    "    examples, \n",
-    "    # This is the embedding class used to produce embeddings which are used to measure semantic similarity.\n",
-    "    OpenAIEmbeddings(), \n",
-    "    # This is the VectorStore class that is used to store the embeddings and do a similarity search over.\n",
-    "    FAISS, \n",
-    "    # This is the number of examples to produce.\n",
-    "    k=1\n",
-    ")\n",
-    "similar_prompt = FewShotPromptTemplate(\n",
-    "    # We provide an ExampleSelector instead of examples.\n",
-    "    example_selector=example_selector,\n",
-    "    example_prompt=example_prompt,\n",
-    "    prefix=\"Give the antonym of every input\",\n",
-    "    suffix=\"Input: {adjective}\\nOutput:\", \n",
-    "    input_variables=[\"adjective\"],\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "4c8fdf45",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Give the antonym of every input\n",
-      "\n",
-      "Input: happy\n",
-      "Output: sad\n",
-      "\n",
-      "Input: worried\n",
-      "Output:\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Input is a feeling, so should select the happy/sad example\n",
-    "print(similar_prompt.format(adjective=\"worried\"))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "829af21a",
-   "metadata": {
-    "scrolled": true
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Give the antonym of every input\n",
-      "\n",
-      "Input: tall\n",
-      "Output: short\n",
-      "\n",
-      "Input: fat\n",
-      "Output:\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Input is a measurement, so should select the tall/short example\n",
-    "print(similar_prompt.format(adjective=\"fat\"))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "3c16fe23",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Give the antonym of every input\n",
-      "\n",
-      "Input: enthusiastic\n",
-      "Output: apathetic\n",
-      "\n",
-      "Input: joyful\n",
-      "Output:\n"
-     ]
-    }
-   ],
-   "source": [
-    "# You can add new examples to the SemanticSimilarityExampleSelector as well\n",
-    "similar_prompt.example_selector.add_example({\"input\": \"enthusiastic\", \"output\": \"apathetic\"})\n",
-    "print(similar_prompt.format(adjective=\"joyful\"))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "dbc32551",
-   "metadata": {},
-   "source": [
-    "### Serialization\n",
-    "\n",
-    "PromptTemplates and examples can be serialized and loaded from disk, making it easy to share and store prompts. For a detailed walkthrough on how to do that, see [this notebook](prompt_serialization.ipynb)."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "1e1e13c6",
-   "metadata": {},
-   "source": [
-    "### Customizability\n",
-    "The above covers all the ways currently supported in LangChain to represent prompts and example selectors. However, due to the simple interface that the base classes (`BasePromptTemplate`, `BaseExampleSelector`) expose, it should be easy to subclass them and write your own implementation in your own codebase. And of course, if you'd like to contribute that back to LangChain, we'd love that :)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "c746d6f4",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.7.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/explanation/combine_docs.md

@@ -1,128 +0,0 @@
-# Data Augmented Generation
-
-## Overview
-
-Language models are trained on large amounts of unstructured data, which makes them really good at general purpose text generation. However, there are many instances where you may want the language model to generate text based not on generic data but rather on specific data. Some common examples of this include:
-
-- Summarization of a specific piece of text (a website, a private document, etc)
-- Question answering over a specific piece of text (a website, a private document, etc)
-- Question answering over multiple pieces of text (multiple websites, multiple private documents, etc)
-- Using the results of some external call to an API (results from a SQL query, etc)
-
-All of these examples are instances when you do not want the LLM to generate text based solely on the data it was trained over, but rather you want it to incorporate other external data in some way. At a high level, this process can be broken down into two steps:
-
-1. Fetching: Fetching the relevant data to include.
-2. Augmenting: Passing the data in as context to the LLM.
-
-This guide is intended to provide an overview of how to do this. This includes an overview of the literature, as well as common tools, abstractions and chains for doing this.
-
-## Related Literature
-There are a lot of related papers in this area. Most of them are focused on end-to-end methods that optimize the fetching of the relevant data as well as passing it in as context. These are a few of the papers that are particularly relevant:
-
-**[RAG](https://arxiv.org/abs/2005.11401):** Retrieval Augmented Generation. 
-This paper introduces RAG models where the parametric memory is a pre-trained seq2seq model and the non-parametric memory is a dense vector index of Wikipedia, accessed with a pre-trained neural retriever.
-
-**[REALM](https://arxiv.org/abs/2002.08909):** Retrieval-Augmented Language Model Pre-Training. 
-To capture knowledge in a more modular and interpretable way, this paper augments language model pre-training with a latent knowledge retriever, which allows the model to retrieve and attend over documents from a large corpus such as Wikipedia, used during pre-training, fine-tuning and inference.
-
-**[HayStack](https://haystack.deepset.ai/):** This is not a paper, but rather an open source library aimed at semantic search, question answering, summarization, and document ranking for a wide range of NLP applications. The underpinnings of this library are focused on the same `fetching` and `augmenting` concepts discussed here, and incorporate some of the methods in the above papers.
-
-These papers/open-source projects are centered around retrieval of documents, which is important for question-answering tasks over a large corpus of documents (which is how they are evaluated). However, we use the terminology of `Data Augmented Generation` to highlight that retrieval from some document store is only one possible way of fetching relevant data to include. Other methods to fetch relevant data could involve hitting an API, querying a database, or just working with user provided data (eg a specific document that they want to summarize).
-
-Let's now deep dive on the two steps involved: fetching and augmenting.
-
-## Fetching
-There are many ways to fetch relevant data to pass in as context to a LM, and these methods largely depend
-on the use case.
-
-**User provided:** In some cases, the user may provide the relevant data, and no algorithm for fetching is needed.
-An example of this is for summarization of specific documents: the user will provide the document to be summarized,
-and task the language model with summarizing it.
-
-**Document Retrieval:** One of the more common use cases involves fetching relevant documents or pieces of text from
-a large corpus of data. A common example of this is question answering over a private collection of documents.
-
-**API Querying:** Another common way to fetch data is from an API query. One example of this is WebGPT like system,
-where you first query Google (or another search API) for relevant information, and then those results are used in
-the generation step. Another example could be querying a structured database (like SQL) and then using a language model
-to synthesize those results.
-
-There are two big issues to deal with in fetching:
-
-1. Fetching small enough pieces of information
-2. Not fetching too many pieces of information (eg fetching only the most relevant pieces)
-
-### Text Splitting
-One big issue with all of these methods is how to make sure you are working with pieces of text that are not too large.
-This is important because most language models have a context length, and so you cannot (yet) just pass a 
-large document in as context. Therefor, it is important to not only fetch relevant data but also make sure it is
-small enough chunks.
-
-LangChain provides some utilities to help with splitting up larger pieces of data. This comes in the form of the TextSplitter class.
-The class takes in a document and splits it up into chunks, with several parameters that control the
-size of the chunks as well as the overlap in the chunks (important for maintaining context).
-See [this walkthrough](../examples/integrations/textsplitter.ipynb) for more information.
-
-### Relevant Documents
-A second large issue related fetching data is to make sure you are not fetching too many documents, and are only fetching
-the documents that are relevant to the query/question at hand. There are a few ways to deal with this.
-
-One concrete example of this is vector stores for document retrieval, often used for semantic search or question answering.
-With this method, larger documents are split up into
-smaller chunks and then each chunk of text is passed to an embedding function which creates an embedding for that piece of text.
-Those are embeddings are then stored in a database. When a new search query or question comes in, an embedding is
-created for that query/question and then documents with embeddings most similar to that embedding are fetched. 
-Examples of vector database companies include [Pinecone](https://www.pinecone.io/) and [Weaviate](https://weaviate.io/).
-
-Although this is perhaps the most common way of document retrieval, people are starting to think about alternative
-data structures and indexing techniques specifically for working with language models. For a leading example of this,
-check out [GPT Index](https://github.com/jerryjliu/gpt_index) - a collection of data structures created by and optimized
-for language models.
-
-## Augmenting
-So you've fetched your relevant data - now what? How do you pass them to the language model in a format it can understand?
-There are a few different methods, or chains, for doing so. LangChain supports three of the more common ones - and
-we are actively looking to include more, so if you have any ideas please reach out! Note that there is not
-one best method - the decision of which one to use is often very context specific. In order from simplest to
-most complex:
-
-### Stuffing
-Stuffing is the simplest method, whereby you simply stuff all the related data into the prompt as context
-to pass to the language model. This is implemented in LangChain as the `StuffDocumentsChain`.
-
-**Pros:** Only makes a single call to the LLM. When generating text, the LLM has access to all the data at once.
-
-**Cons:** Most LLMs have a context length, and for large documents (or many documents) this will not work as it will result in a prompt larger than the context length.
-
-The main downside of this method is that it only works one smaller pieces of data. Once you are working
-with many pieces of data, this approach is no longer feasible. The next two approaches are designed to help deal with that.
-
-### Map Reduce
-This method involves an initial prompt on each chunk of data (for summarization tasks, this 
-could be a summary of that chunk; for question-answering tasks, it could be an answer based solely on that chunk).
-Then a different prompt is run to combine all the initial outputs. This is implemented in the LangChain as the `MapReduceDocumentsChain`.
-
-**Pros:** Can scale to larger documents (and more documents) than `StuffDocumentsChain`. The calls to the LLM on individual documents are independent and can therefore be parallelized.
-
-**Cons:** Requires many more calls to the LLM than `StuffDocumentsChain`. Loses some information during the final combining call.
-
-### Refine
-This method involves an initial prompt on the first chunk of data, generating some output.
-For the remaining documents, that output is passed in, along with the next document, 
-asking the LLM to refine the output based on the new document. 
-
-**Pros:** Can pull in more relevant context, and may be less lossy than `RefineDocumentsChain`.
-
-**Cons:** Requires many more calls to the LLM than `StuffDocumentsChain`. The calls are also NOT independent, meaning they cannot be paralleled like `MapReduceDocumentsChain`. There is also some potential dependencies on the ordering of the documents.
-
-## Use Cases
-LangChain supports the above three methods of augmenting LLMs with external data.
-These methods can be used to underpin several common use cases and they are discussed below.
-For all three of these use cases, all three methods are supported.
-It is important to note that a large part of these implementations is the prompts
-that are used. We provide default prompts for all three use cases, but these can be configured.
-This is in case you discover a prompt that works better for your specific application.
-
-- [Question-Answering With Sources](../examples/chains/qa_with_sources.ipynb)
-- [Question-Answering](../examples/chains/question_answering.ipynb)
-- [Summarization](../examples/chains/summarize.ipynb)

docs/explanation/cool_demos.md

@@ -1,45 +0,0 @@
-# Cool Demos
-
-Lots of people have built some pretty awesome stuff with LangChain.
-This is a collection of our favorites.
-If you see any other demos that you think we should highlight, be sure to let us know!
-
-## Open Source
-
-### [YouTube Transcription Question Answering with Sources](https://colab.research.google.com/drive/1sKSTjt9cPstl_WMZ86JsgEqFG-aSAwkn?usp=sharing)
-An end-to-end example of doing question answering on YouTube transcripts, returning the timestamps as sources to legitimize the answer.
-
-### [ThoughtSource](https://github.com/OpenBioLink/ThoughtSource)
-A central, open resource and community around data and tools related to chain-of-thought reasoning in large language models.
-
-### [Notion Database Question-Answering Bot](https://github.com/hwchase17/notion-qa)
-Open source GitHub project shows how to use LangChain to create a
-chatbot that can answer questions about an arbitrary Notion database.
-
-### [GPT Index](https://github.com/jerryjliu/gpt_index)
-GPT Index is a project consisting of a set of data structures that are created using GPT-3 and can be traversed using GPT-3 in order to answer queries.
-
-### [Grover's Algorithm](https://github.com/JavaFXpert/llm-grovers-search-party)
-Leveraging Qiskit, OpenAI and LangChain to demonstrate Grover's algorithm
-
-### [ReAct TextWorld](https://colab.research.google.com/drive/19WTIWC3prw5LDMHmRMvqNV2loD9FHls6?usp=sharing)
-Leveraging the ReActTextWorldAgent to play TextWorld with an LLM!
-
-
-## Not Open Source
-
-### [Daimon](https://twitter.com/sjwhitmore/status/1580593217153531908?s=20&t=neQvtZZTlp623U3LZwz3bQ)
-A chat-based AI personal assistant with long-term memory about you.
-
-### [Clerkie](https://twitter.com/krrish_dh/status/1581028925618106368?s=20&t=neQvtZZTlp623U3LZwz3bQ)
-Stack Tracing QA Bot to help debug complex stack tracing (especially the ones that go multi-function/file deep). 
-
-### [Sales Email Writer](https://twitter.com/Raza_Habib496/status/1596880140490838017?s=20&t=6MqEQYWfSqmJwsKahjCVOA)
-By Raza Habib, this demo utilizes LangChain + SerpAPI + HumanLoop to write sales emails.
-Give it a company name and a person, this application will use Google Search (via SerpAPI) to get
-more information on the company and the person, and then write them a sales message.
-
-### [Question-Answering on a Web Browser](https://twitter.com/chillzaza_/status/1592961099384905730?s=20&t=EhU8jl0KyCPJ7vE9Rnz-cQ)
-By Zahid Khawaja, this demo utilizes question answering to answer questions about a given website.
-A followup added this for [Youtube videos](https://twitter.com/chillzaza_/status/1593739682013220865?s=20&t=EhU8jl0KyCPJ7vE9Rnz-cQ),
-and then another followup added it for [Wikipedia](https://twitter.com/chillzaza_/status/1594847151238037505?s=20&t=EhU8jl0KyCPJ7vE9Rnz-cQ).

docs/explanation/core_concepts.md

@@ -1,37 +0,0 @@
-# Core Concepts
-
-This section goes over the core concepts of LangChain.
-Understanding these will go a long way in helping you understand the codebase and how to construct chains.
-
-## PromptTemplates
-PromptTemplates generically have a `format` method that takes in variables and returns a formatted string.
-The most simple implementation of this is to have a template string with some variables in it, and then format it with the incoming variables.
-More complex iterations dynamically construct the template string from few shot examples, etc.
-
-For a more detailed explanation of how LangChain approaches prompts and prompt templates, see [here](/examples/prompts/prompt_management).
-
-## LLMs
-Wrappers around Large Language Models (in particular, the `generate` ability of large language models) are some of the core functionality of LangChain.
-These wrappers are classes that are callable: they take in an input string, and return the generated output string.
-
-## Embeddings
-These classes are very similar to the LLM classes in that they are wrappers around models, 
-but rather than return a string they return an embedding (list of floats). This are particularly useful when 
-implementing semantic search functionality. They expose separate methods for embedding queries versus embedding documents.
-
-## Vectorstores
-These are datastores that store documents. They expose a method for passing in a string and finding similar documents.
-
-## Chains
-These are pipelines that combine multiple of the above ideas. 
-They vary greatly in complexity and are combination of generic, highly configurable pipelines and more narrow (but usually more complex) pipelines.
-
-## Agents
-As opposed to a chain, whether the steps to be taken are known ahead of time, agents
-use an LLM to determine which tools to call and in what order.
-
-## Memory
-By default, Chains and Agents are stateless, meaning that they treat each incoming query independently.
-In some applications (chatbots being a GREAT example) it is highly important to remember previous interactions,
-both at a short term but also at a long term level. The concept of "Memory" exists to do exactly that.
-

docs/gallery.rst

@@ -0,0 +1,335 @@
+LangChain Gallery
+=============
+
+Lots of people have built some pretty awesome stuff with LangChain.
+This is a collection of our favorites.
+If you see any other demos that you think we should highlight, be sure to let us know!
+
+
+Open Source
+-----------
+
+.. panels::
+    :body: text-center
+
+    ---
+
+    .. link-button:: https://github.com/bborn/howdoi.ai
+        :type: url
+        :text: HowDoI.ai
+        :classes: stretched-link btn-lg
+
+    +++
+
+    This is an experiment in building a large-language-model-backed chatbot. It can hold a conversation, remember previous comments/questions, 
+    and answer all types of queries (history, web search, movie data, weather, news, and more).
+
+    ---
+
+    .. link-button:: https://colab.research.google.com/drive/1sKSTjt9cPstl_WMZ86JsgEqFG-aSAwkn?usp=sharing
+        :type: url
+        :text: YouTube Transcription QA with Sources
+        :classes: stretched-link btn-lg
+
+    +++
+
+    An end-to-end example of doing question answering on YouTube transcripts, returning the timestamps as sources to legitimize the answer.
+
+    ---
+
+    .. link-button:: https://github.com/normandmickey/MrsStax
+        :type: url
+        :text: QA Slack Bot
+        :classes: stretched-link btn-lg
+
+    +++
+
+    This application is a Slack Bot that uses Langchain and OpenAI's GPT3 language model to provide domain specific answers. You provide the documents.
+
+    ---
+
+    .. link-button:: https://github.com/OpenBioLink/ThoughtSource
+        :type: url
+        :text: ThoughtSource
+        :classes: stretched-link btn-lg
+
+    +++
+
+    A central, open resource and community around data and tools related to chain-of-thought reasoning in large language models.
+
+    ---
+
+    .. link-button:: https://github.com/blackhc/llm-strategy
+        :type: url
+        :text: LLM Strategy
+        :classes: stretched-link btn-lg
+    
+    +++
+
+    This Python package adds a decorator llm_strategy that connects to an LLM (such as OpenAI’s GPT-3) and uses the LLM to "implement" abstract methods in interface classes. It does this by forwarding requests to the LLM and converting the responses back to Python data using Python's @dataclasses.
+
+    ---
+
+    .. link-button:: https://github.com/JohnNay/llm-lobbyist
+        :type: url
+        :text: Zero-Shot Corporate Lobbyist
+        :classes: stretched-link btn-lg
+
+    +++
+
+    A notebook showing how to use GPT to help with the work of a corporate lobbyist.
+
+    ---
+
+    .. link-button:: https://dagster.io/blog/chatgpt-langchain
+        :type: url
+        :text: Dagster Documentation ChatBot
+        :classes: stretched-link btn-lg
+
+    +++
+
+    A jupyter notebook demonstrating how you could create a semantic search engine on documents in one of your Google Folders
+
+    ---
+
+    .. link-button:: https://github.com/venuv/langchain_semantic_search
+        :type: url
+        :text: Google Folder Semantic Search
+        :classes: stretched-link btn-lg
+
+    +++
+
+    Build a GitHub support bot with GPT3, LangChain, and Python.
+
+    ---
+
+    .. link-button:: https://huggingface.co/spaces/team7/talk_with_wind
+        :type: url
+        :text: Talk With Wind
+        :classes: stretched-link btn-lg
+
+    +++
+
+    Record sounds of anything (birds, wind, fire, train station) and chat with it.
+
+    ---
+
+    .. link-button:: https://huggingface.co/spaces/JavaFXpert/Chat-GPT-LangChain
+        :type: url
+        :text: ChatGPT LangChain
+        :classes: stretched-link btn-lg
+
+    +++
+
+    This simple application demonstrates a conversational agent implemented with OpenAI GPT-3.5 and LangChain. When necessary, it leverages tools for complex math, searching the internet, and accessing news and weather.
+
+    ---
+
+    .. link-button:: https://huggingface.co/spaces/JavaFXpert/gpt-math-techniques
+        :type: url
+        :text: GPT Math Techniques
+        :classes: stretched-link btn-lg
+
+    +++
+
+    A Hugging Face spaces project showing off the benefits of using PAL for math problems.
+
+    ---
+
+    .. link-button:: https://colab.research.google.com/drive/1xt2IsFPGYMEQdoJFNgWNAjWGxa60VXdV
+        :type: url
+        :text: GPT Political Compass
+        :classes: stretched-link btn-lg
+
+    +++
+
+    Measure the political compass of GPT.
+
+    ---
+
+    .. link-button:: https://github.com/hwchase17/notion-qa
+        :type: url
+        :text: Notion Database Question-Answering Bot
+        :classes: stretched-link btn-lg
+    
+    +++
+
+    Open source GitHub project shows how to use LangChain to create a chatbot that can answer questions about an arbitrary Notion database.
+
+    ---
+
+    .. link-button:: https://github.com/jerryjliu/llama_index
+        :type: url
+        :text: LlamaIndex
+        :classes: stretched-link btn-lg
+    
+    +++
+
+    LlamaIndex (formerly GPT Index) is a project consisting of a set of data structures that are created using GPT-3 and can be traversed using GPT-3 in order to answer queries.
+
+    ---
+
+    .. link-button:: https://github.com/JavaFXpert/llm-grovers-search-party
+        :type: url
+        :text: Grover's Algorithm
+        :classes: stretched-link btn-lg
+
+    +++
+
+    Leveraging Qiskit, OpenAI and LangChain to demonstrate Grover's algorithm
+
+    ---
+
+    .. link-button:: https://huggingface.co/spaces/rituthombre/QNim
+        :type: url
+        :text: QNimGPT
+        :classes: stretched-link btn-lg
+
+    +++
+
+    A chat UI to play Nim, where a player can select an opponent, either a quantum computer or an AI
+
+    ---
+
+    .. link-button:: https://colab.research.google.com/drive/19WTIWC3prw5LDMHmRMvqNV2loD9FHls6?usp=sharing
+        :type: url
+        :text: ReAct TextWorld
+        :classes: stretched-link btn-lg
+
+    +++
+
+    Leveraging the ReActTextWorldAgent to play TextWorld with an LLM!
+
+    ---
+
+    .. link-button:: https://github.com/jagilley/fact-checker
+        :type: url
+        :text: Fact Checker
+        :classes: stretched-link btn-lg
+    
+    +++
+
+    This repo is a simple demonstration of using LangChain to do fact-checking with prompt chaining.
+    
+    ---
+
+    .. link-button:: https://github.com/arc53/docsgpt
+        :type: url
+        :text: DocsGPT
+        :classes: stretched-link btn-lg
+    
+    +++
+
+    Answer questions about the documentation of any project    
+
+Misc. Colab Notebooks
+~~~~~~~~~~~~~~~
+
+.. panels::
+    :body: text-center
+
+    ---
+
+    .. link-button:: https://colab.research.google.com/drive/1AAyEdTz-Z6ShKvewbt1ZHUICqak0MiwR?usp=sharing
+        :type: url
+        :text: Wolfram Alpha in Conversational Agent
+        :classes: stretched-link btn-lg
+    
+    +++
+
+    Give ChatGPT a WolframAlpha neural implant
+    
+    ---
+
+    .. link-button:: https://colab.research.google.com/drive/1UsCLcPy8q5PMNQ5ytgrAAAHa124dzLJg?usp=sharing
+        :type: url
+        :text: Tool Updates in Agents
+        :classes: stretched-link btn-lg
+    
+    +++
+
+    Agent improvements (6th Jan 2023)
+    
+    ---
+
+    .. link-button:: https://colab.research.google.com/drive/1UsCLcPy8q5PMNQ5ytgrAAAHa124dzLJg?usp=sharing
+        :type: url
+        :text: Conversational Agent with Tools (Langchain AGI)
+        :classes: stretched-link btn-lg
+    
+    +++
+
+    Langchain AGI (23rd Dec 2022)    
+
+Proprietary
+-----------
+
+.. panels::
+    :body: text-center
+
+    ---
+
+    .. link-button:: https://twitter.com/sjwhitmore/status/1580593217153531908?s=20&t=neQvtZZTlp623U3LZwz3bQ
+        :type: url
+        :text: Daimon
+        :classes: stretched-link btn-lg
+
+    +++
+
+    A chat-based AI personal assistant with long-term memory about you.
+
+    ---
+
+    .. link-button:: https://twitter.com/dory111111/status/1608406234646052870?s=20&t=XYlrbKM0ornJsrtGa0br-g
+        :type: url
+        :text: AI Assisted SQL Query Generator
+        :classes: stretched-link btn-lg
+
+    +++
+
+    An app to write SQL using natural language, and execute against real DB.
+
+    ---
+
+    .. link-button:: https://twitter.com/krrish_dh/status/1581028925618106368?s=20&t=neQvtZZTlp623U3LZwz3bQ
+        :type: url
+        :text: Clerkie
+        :classes: stretched-link btn-lg
+
+    +++
+
+    Stack Tracing QA Bot to help debug complex stack tracing (especially the ones that go multi-function/file deep).
+
+    ---
+
+    .. link-button:: https://twitter.com/Raza_Habib496/status/1596880140490838017?s=20&t=6MqEQYWfSqmJwsKahjCVOA
+        :type: url
+        :text: Sales Email Writer
+        :classes: stretched-link btn-lg
+
+    +++
+
+    By Raza Habib, this demo utilizes LangChain + SerpAPI + HumanLoop to write sales emails. Give it a company name and a person, this application will use Google Search (via SerpAPI) to get more information on the company and the person, and then write them a sales message.
+
+    ---
+
+    .. link-button:: https://twitter.com/chillzaza_/status/1592961099384905730?s=20&t=EhU8jl0KyCPJ7vE9Rnz-cQ
+        :type: url
+        :text: Question-Answering on a Web Browser
+        :classes: stretched-link btn-lg
+
+    +++
+
+    By Zahid Khawaja, this demo utilizes question answering to answer questions about a given website. A followup added this for `YouTube videos <https://twitter.com/chillzaza_/status/1593739682013220865?s=20&t=EhU8jl0KyCPJ7vE9Rnz-cQ>`_, and then another followup added it for `Wikipedia <https://twitter.com/chillzaza_/status/1594847151238037505?s=20&t=EhU8jl0KyCPJ7vE9Rnz-cQ>`_.
+
+    ---
+
+    .. link-button:: https://mynd.so
+        :type: url
+        :text: Mynd
+        :classes: stretched-link btn-lg
+
+    +++
+
+    A journaling app for self-care that uses AI to uncover insights and patterns over time.
+    

docs/getting_started/agents.ipynb

@@ -1,196 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "5436020b",
-   "metadata": {},
-   "source": [
-    "# Agents\n",
-    "\n",
-    "Agents use an LLM to determine which actions to take and in what order.\n",
-    "An action can either be using a tool and observing its output, or returning to the user.\n",
-    "\n",
-    "When used correctly agents can be extremely powerful. The purpose of this notebook is to show you how to easily use agents through the simplest, highest level API. If you want more low level control over various components, check out the documentation for custom agents (coming soon)."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "3c6226b9",
-   "metadata": {},
-   "source": [
-    "## Concepts\n",
-    "\n",
-    "In order to load agents, you should understand the following concepts:\n",
-    "\n",
-    "- Tool: A function that performs a specific duty. This can be things like: Google Search, Database lookup, Python REPL, other chains. The interface for a tool is currently a function that is expected to have a string as an input, with a string as an output.\n",
-    "- LLM: The language model powering the agent.\n",
-    "- Agent: The agent to use. This should be a string that references a support agent class. Because this notebook focuses on the simplest, highest level API, this only covers using the standard supported agents. If you want to implement a custom agent, see the documentation for custom agents (coming soon).\n",
-    "\n",
-    "**For a list of supported agents and their specifications, see [here](../explanation/agents.md)**"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "05d4b21e",
-   "metadata": {},
-   "source": [
-    "## Tools\n",
-    "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",
-    "    \"\"\"Interface for tools.\"\"\"\n",
-    "\n",
-    "    name: str\n",
-    "    func: Callable[[str], str]\n",
-    "    description: Optional[str] = None\n",
-    "```\n",
-    "\n",
-    "The two required components of a Tool are the name and then the tool itself. A tool description is optional, as it is needed for some agents but not all."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2558a02d",
-   "metadata": {},
-   "source": [
-    "## Loading an agent\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "36ed392e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Import things that are needed generically\n",
-    "from langchain.agents import initialize_agent, Tool\n",
-    "from langchain.llms import OpenAI"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "56ff7670",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Load the tool configs that are needed.\n",
-    "from langchain import LLMMathChain, SerpAPIWrapper\n",
-    "llm = OpenAI(temperature=0)\n",
-    "search = SerpAPIWrapper()\n",
-    "llm_math_chain = LLMMathChain(llm=llm, verbose=True)\n",
-    "tools = [\n",
-    "    Tool(\n",
-    "        name = \"Search\",\n",
-    "        func=search.run,\n",
-    "        description=\"useful for when you need to answer questions about current events\"\n",
-    "    ),\n",
-    "    Tool(\n",
-    "        name=\"Calculator\",\n",
-    "        func=llm_math_chain.run,\n",
-    "        description=\"useful for when you need to answer questions about math\"\n",
-    "    )\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "5b93047d",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Construct the agent. We will use the default agent type here.\n",
-    "# See documentation for a full list of options.\n",
-    "llm = OpenAI(temperature=0)\n",
-    "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "6f96a891",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "What is the age of Olivia Wilde's boyfriend raised to the 0.23 power?\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I need to find the age of Olivia Wilde's boyfriend\n",
-      "Action: Search\n",
-      "Action Input: \"Olivia Wilde's boyfriend\"\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3mOlivia Wilde started dating Harry Styles after ending her years-long engagement to Jason Sudeikis — see their relationship timeline.\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I need to find the age of Harry Styles\n",
-      "Action: Search\n",
-      "Action Input: \"Harry Styles age\"\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3m28 years\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I need to calculate 28 to the 0.23 power\n",
-      "Action: Calculator\n",
-      "Action Input: 28^0.23\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Entering new chain...\u001b[0m\n",
-      "28^0.23\u001b[32;1m\u001b[1;3m\n",
-      "\n",
-      "```python\n",
-      "print(28**0.23)\n",
-      "```\n",
-      "\u001b[0m\n",
-      "Answer: \u001b[33;1m\u001b[1;3m2.1520202182226886\n",
-      "\u001b[0m\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n",
-      "\n",
-      "Observation: \u001b[33;1m\u001b[1;3mAnswer: 2.1520202182226886\n",
-      "\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
-      "Final Answer: 2.1520202182226886\u001b[0m"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'2.1520202182226886'"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "agent.run(\"How old is Olivia Wilde's boyfriend? What is that number raised to the 0.23 power?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "2f0852ff",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.7.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/getting_started/environment.md

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

docs/getting_started/getting_started.md

@@ -0,0 +1,502 @@
+# Quickstart Guide
+
+
+This tutorial gives you a quick walkthrough about building an end-to-end language model application with LangChain.
+
+## Installation
+
+To get started, install LangChain with the following command:
+
+```bash
+pip install langchain
+```
+
+
+## Environment Setup
+
+Using LangChain will usually require integrations with one or more model providers, data stores, apis, etc.
+
+For this example, we will be using OpenAI's APIs, so we will first need to install their SDK:
+
+```bash
+pip install openai
+```
+
+We will then need to set the environment variable in the terminal.
+
+```bash
+export OPENAI_API_KEY="..."
+```
+
+Alternatively, you could do this from inside the Jupyter notebook (or Python script):
+
+```python
+import os
+os.environ["OPENAI_API_KEY"] = "..."
+```
+
+
+## Building a Language Model Application: LLMs
+
+Now that we have installed LangChain and set up our environment, we can start building our language model application.
+
+LangChain provides many modules that can be used to build language model applications. Modules can be combined to create more complex applications, or be used individually for simple applications.
+
+
+
+`````{dropdown} LLMs: Get predictions from a language model
+
+The most basic building block of LangChain is calling an LLM on some input.
+Let's walk through a simple example of how to do this. 
+For this purpose, let's pretend we are building a service that generates a company name based on what the company makes.
+
+In order to do this, we first need to import the LLM wrapper.
+
+```python
+from langchain.llms import OpenAI
+```
+
+We can then initialize the wrapper with any arguments.
+In this example, we probably want the outputs to be MORE random, so we'll initialize it with a HIGH temperature.
+
+```python
+llm = OpenAI(temperature=0.9)
+```
+
+We can now call it on some input!
+
+```python
+text = "What would be a good company name for a company that makes colorful socks?"
+print(llm(text))
+```
+
+```pycon
+Feetful of Fun
+```
+
+For more details on how to use LLMs within LangChain, see the [LLM getting started guide](../modules/models/llms/getting_started.ipynb).
+`````
+
+
+`````{dropdown} Prompt Templates: Manage prompts for LLMs
+
+Calling an LLM is a great first step, but it's just the beginning.
+Normally when you use an LLM in an application, you are not sending user input directly to the LLM.
+Instead, you are probably taking user input and constructing a prompt, and then sending that to the LLM.
+
+For example, in the previous example, the text we passed in was hardcoded to ask for a name for a company that made colorful socks.
+In this imaginary service, what we would want to do is take only the user input describing what the company does, and then format the prompt with that information.
+
+This is easy to do with LangChain!
+
+First lets define the prompt template:
+
+```python
+from langchain.prompts import PromptTemplate
+
+prompt = PromptTemplate(
+    input_variables=["product"],
+    template="What is a good name for a company that makes {product}?",
+)
+```
+
+Let's now see how this works! We can call the `.format` method to format it.
+
+```python
+print(prompt.format(product="colorful socks"))
+```
+
+```pycon
+What is a good name for a company that makes colorful socks?
+```
+
+
+[For more details, check out the getting started guide for prompts.](../modules/prompts/chat_prompt_template.ipynb)
+
+`````
+
+
+
+`````{dropdown} Chains: Combine LLMs and prompts in multi-step workflows
+
+Up until now, we've worked with the PromptTemplate and LLM primitives by themselves. But of course, a real application is not just one primitive, but rather a combination of them.
+
+A chain in LangChain is made up of links, which can be either primitives like LLMs or other chains.
+
+The most core type of chain is an LLMChain, which consists of a PromptTemplate and an LLM.
+
+Extending the previous example, we can construct an LLMChain which takes user input, formats it with a PromptTemplate, and then passes the formatted response to an LLM.
+
+```python
+from langchain.prompts import PromptTemplate
+from langchain.llms import OpenAI
+
+llm = OpenAI(temperature=0.9)
+prompt = PromptTemplate(
+    input_variables=["product"],
+    template="What is a good name for a company that makes {product}?",
+)
+```
+
+We can now create a very simple chain that will take user input, format the prompt with it, and then send it to the LLM:
+
+```python
+from langchain.chains import LLMChain
+chain = LLMChain(llm=llm, prompt=prompt)
+```
+
+Now we can run that chain only specifying the product!
+
+```python
+chain.run("colorful socks")
+# -> '\n\nSocktastic!'
+```
+
+There we go! There's the first chain - an LLM Chain.
+This is one of the simpler types of chains, but understanding how it works will set you up well for working with more complex chains.
+
+[For more details, check out the getting started guide for chains.](../modules/chains/getting_started.ipynb)
+
+`````
+
+
+`````{dropdown} Agents: Dynamically Call Chains Based on User Input
+
+So far the chains we've looked at run in a predetermined order.
+
+Agents no longer do: they use an LLM to determine which actions to take and in what order. An action can either be using a tool and observing its output, or returning to the user.
+
+When used correctly agents can be extremely powerful. In this tutorial, we show you how to easily use agents through the simplest, highest level API.
+
+
+In order to load agents, you should understand the following concepts:
+
+- Tool: A function that performs a specific duty. This can be things like: Google Search, Database lookup, Python REPL, other chains. The interface for a tool is currently a function that is expected to have a string as an input, with a string as an output.
+- LLM: The language model powering the agent.
+- Agent: The agent to use. This should be a string that references a support agent class. Because this notebook focuses on the simplest, highest level API, this only covers using the standard supported agents. If you want to implement a custom agent, see the documentation for custom agents (coming soon).
+
+**Agents**: For a list of supported agents and their specifications, see [here](../modules/agents/agents.md).
+
+**Tools**: For a list of predefined tools and their specifications, see [here](../modules/agents/tools.md).
+
+For this example, you will also need to install the SerpAPI Python package.
+
+```bash
+pip install google-search-results
+```
+
+And set the appropriate environment variables.
+
+```python
+import os
+os.environ["SERPAPI_API_KEY"] = "..."
+```
+
+Now we can get started!
+
+```python
+from langchain.agents import load_tools
+from langchain.agents import initialize_agent
+from langchain.agents import AgentType
+from langchain.llms import OpenAI
+
+# First, let's load the language model we're going to use to control the agent.
+llm = OpenAI(temperature=0)
+
+# Next, let's load some tools to use. Note that the `llm-math` tool uses an LLM, so we need to pass that in.
+tools = load_tools(["serpapi", "llm-math"], llm=llm)
+
+
+# Finally, let's initialize an agent with the tools, the language model, and the type of agent we want to use.
+agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
+
+# Now let's test it out!
+agent.run("What was the high temperature in SF yesterday in Fahrenheit? What is that number raised to the .023 power?")
+```
+
+```pycon
+> Entering new AgentExecutor chain...
+ I need to find the temperature first, then use the calculator to raise it to the .023 power.
+Action: Search
+Action Input: "High temperature in SF yesterday"
+Observation: San Francisco Temperature Yesterday. Maximum temperature yesterday: 57 °F (at 1:56 pm) Minimum temperature yesterday: 49 °F (at 1:56 am) Average temperature ...
+Thought: I now have the temperature, so I can use the calculator to raise it to the .023 power.
+Action: Calculator
+Action Input: 57^.023
+Observation: Answer: 1.0974509573251117
+
+Thought: I now know the final answer
+Final Answer: The high temperature in SF yesterday in Fahrenheit raised to the .023 power is 1.0974509573251117.
+
+> Finished chain.
+```
+
+
+`````
+
+
+`````{dropdown} Memory: Add State to Chains and Agents
+
+So far, all the chains and agents we've gone through have been stateless. But often, you may want a chain or agent to have some concept of "memory" so that it may remember information about its previous interactions. The clearest and simple example of this is when designing a chatbot - you want it to remember previous messages so it can use context from that to have a better conversation. This would be a type of "short-term memory". On the more complex side, you could imagine a chain/agent remembering key pieces of information over time - this would be a form of "long-term memory". For more concrete ideas on the latter, see this [awesome paper](https://memprompt.com/).
+
+LangChain provides several specially created chains just for this purpose. This notebook walks through using one of those chains (the `ConversationChain`) with two different types of memory.
+
+By default, the `ConversationChain` has a simple type of memory that remembers all previous inputs/outputs and adds them to the context that is passed. Let's take a look at using this chain (setting `verbose=True` so we can see the prompt).
+
+```python
+from langchain import OpenAI, ConversationChain
+
+llm = OpenAI(temperature=0)
+conversation = ConversationChain(llm=llm, verbose=True)
+
+conversation.predict(input="Hi there!")
+```
+
+```pycon
+> Entering new chain...
+Prompt after formatting:
+The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
+
+Current conversation:
+
+Human: Hi there!
+AI:
+
+> Finished chain.
+' Hello! How are you today?'
+```
+
+```python
+conversation.predict(input="I'm doing well! Just having a conversation with an AI.")
+```
+
+```pycon
+> Entering new chain...
+Prompt after formatting:
+The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
+
+Current conversation:
+
+Human: Hi there!
+AI:  Hello! How are you today?
+Human: I'm doing well! Just having a conversation with an AI.
+AI:
+
+> Finished chain.
+" That's great! What would you like to talk about?"
+```
+`````
+
+## Building a Language Model Application: Chat Models
+
+Similarly, you can use chat models instead of LLMs. Chat models are a variation on language models. While chat models use language models under the hood, the interface they expose is a bit different: rather than expose a "text in, text out" API, they expose an interface where "chat messages" are the inputs and outputs.
+
+Chat model APIs are fairly new, so we are still figuring out the correct abstractions.
+
+
+`````{dropdown} Get Message Completions from a Chat Model
+You can get chat completions by passing one or more messages to the chat model. The response will be a message. The types of messages currently supported in LangChain are `AIMessage`, `HumanMessage`, `SystemMessage`, and `ChatMessage` -- `ChatMessage` takes in an arbitrary role parameter. Most of the time, you'll just be dealing with `HumanMessage`, `AIMessage`, and `SystemMessage`.
+
+```python
+from langchain.chat_models import ChatOpenAI
+from langchain.schema import (
+    AIMessage,
+    HumanMessage,
+    SystemMessage
+)
+
+chat = ChatOpenAI(temperature=0)
+```
+
+You can get completions by passing in a single message.
+
+```python
+chat([HumanMessage(content="Translate this sentence from English to French. I love programming.")])
+# -> AIMessage(content="J'aime programmer.", additional_kwargs={})
+```
+
+You can also pass in multiple messages for OpenAI's gpt-3.5-turbo and gpt-4 models.
+
+```python
+messages = [
+    SystemMessage(content="You are a helpful assistant that translates English to French."),
+    HumanMessage(content="Translate this sentence from English to French. I love programming.")
+]
+chat(messages)
+# -> AIMessage(content="J'aime programmer.", additional_kwargs={})
+```
+
+You can go one step further and generate completions for multiple sets of messages using `generate`. This returns an `LLMResult` with an additional `message` parameter:
+```python
+batch_messages = [
+    [
+        SystemMessage(content="You are a helpful assistant that translates English to French."),
+        HumanMessage(content="Translate this sentence from English to French. I love programming.")
+    ],
+    [
+        SystemMessage(content="You are a helpful assistant that translates English to French."),
+        HumanMessage(content="Translate this sentence from English to French. I love artificial intelligence.")
+    ],
+]
+result = chat.generate(batch_messages)
+result
+# -> LLMResult(generations=[[ChatGeneration(text="J'aime programmer.", generation_info=None, message=AIMessage(content="J'aime programmer.", additional_kwargs={}))], [ChatGeneration(text="J'aime l'intelligence artificielle.", generation_info=None, message=AIMessage(content="J'aime l'intelligence artificielle.", additional_kwargs={}))]], llm_output={'token_usage': {'prompt_tokens': 71, 'completion_tokens': 18, 'total_tokens': 89}})
+```
+
+You can recover things like token usage from this LLMResult:
+```
+result.llm_output['token_usage']
+# -> {'prompt_tokens': 71, 'completion_tokens': 18, 'total_tokens': 89}
+```
+`````
+
+`````{dropdown} Chat Prompt Templates
+Similar to LLMs, you can make use of templating by using a `MessagePromptTemplate`. You can build a `ChatPromptTemplate` from one or more `MessagePromptTemplate`s. You can use `ChatPromptTemplate`'s `format_prompt` -- this returns a `PromptValue`, which you can convert to a string or `Message` object, depending on whether you want to use the formatted value as input to an llm or chat model.
+
+For convience, there is a `from_template` method exposed on the template. If you were to use this template, this is what it would look like:
+
+```python
+from langchain.chat_models import ChatOpenAI
+from langchain.prompts.chat import (
+    ChatPromptTemplate,
+    SystemMessagePromptTemplate,
+    HumanMessagePromptTemplate,
+)
+
+chat = ChatOpenAI(temperature=0)
+
+template="You are a helpful assistant that translates {input_language} to {output_language}."
+system_message_prompt = SystemMessagePromptTemplate.from_template(template)
+human_template="{text}"
+human_message_prompt = HumanMessagePromptTemplate.from_template(human_template)
+
+chat_prompt = ChatPromptTemplate.from_messages([system_message_prompt, human_message_prompt])
+
+# get a chat completion from the formatted messages
+chat(chat_prompt.format_prompt(input_language="English", output_language="French", text="I love programming.").to_messages())
+# -> AIMessage(content="J'aime programmer.", additional_kwargs={})
+```
+`````
+
+`````{dropdown} Chains with Chat Models
+The `LLMChain` discussed in the above section can be used with chat models as well:
+
+```python
+from langchain.chat_models import ChatOpenAI
+from langchain import LLMChain
+from langchain.prompts.chat import (
+    ChatPromptTemplate,
+    SystemMessagePromptTemplate,
+    HumanMessagePromptTemplate,
+)
+
+chat = ChatOpenAI(temperature=0)
+
+template="You are a helpful assistant that translates {input_language} to {output_language}."
+system_message_prompt = SystemMessagePromptTemplate.from_template(template)
+human_template="{text}"
+human_message_prompt = HumanMessagePromptTemplate.from_template(human_template)
+chat_prompt = ChatPromptTemplate.from_messages([system_message_prompt, human_message_prompt])
+
+chain = LLMChain(llm=chat, prompt=chat_prompt)
+chain.run(input_language="English", output_language="French", text="I love programming.")
+# -> "J'aime programmer."
+```
+`````
+
+`````{dropdown} Agents with Chat Models
+Agents can also be used with chat models, you can initialize one using `AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION` as the agent type.
+
+```python
+from langchain.agents import load_tools
+from langchain.agents import initialize_agent
+from langchain.agents import AgentType
+from langchain.chat_models import ChatOpenAI
+from langchain.llms import OpenAI
+
+# First, let's load the language model we're going to use to control the agent.
+chat = ChatOpenAI(temperature=0)
+
+# Next, let's load some tools to use. Note that the `llm-math` tool uses an LLM, so we need to pass that in.
+llm = OpenAI(temperature=0)
+tools = load_tools(["serpapi", "llm-math"], llm=llm)
+
+
+# Finally, let's initialize an agent with the tools, the language model, and the type of agent we want to use.
+agent = initialize_agent(tools, chat, agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
+
+# Now let's test it out!
+agent.run("Who is Olivia Wilde's boyfriend? What is his current age raised to the 0.23 power?")
+```
+
+```pycon
+
+> Entering new AgentExecutor chain...
+Thought: I need to use a search engine to find Olivia Wilde's boyfriend and a calculator to raise his age to the 0.23 power.
+Action:
+{
+  "action": "Search",
+  "action_input": "Olivia Wilde boyfriend"
+}
+
+Observation: Sudeikis and Wilde's relationship ended in November 2020. Wilde was publicly served with court documents regarding child custody while she was presenting Don't Worry Darling at CinemaCon 2022. In January 2021, Wilde began dating singer Harry Styles after meeting during the filming of Don't Worry Darling.
+Thought:I need to use a search engine to find Harry Styles' current age.
+Action:
+{
+  "action": "Search",
+  "action_input": "Harry Styles age"
+}
+
+Observation: 29 years
+Thought:Now I need to calculate 29 raised to the 0.23 power.
+Action:
+{
+  "action": "Calculator",
+  "action_input": "29^0.23"
+}
+
+Observation: Answer: 2.169459462491557
+
+Thought:I now know the final answer.
+Final Answer: 2.169459462491557
+
+> Finished chain.
+'2.169459462491557'
+```
+`````
+
+`````{dropdown} Memory: Add State to Chains and Agents
+You can use Memory with chains and agents initialized with chat models. The main difference between this and Memory for LLMs is that rather than trying to condense all previous messages into a string, we can keep them as their own unique memory object.
+
+```python
+from langchain.prompts import (
+    ChatPromptTemplate, 
+    MessagesPlaceholder, 
+    SystemMessagePromptTemplate, 
+    HumanMessagePromptTemplate
+)
+from langchain.chains import ConversationChain
+from langchain.chat_models import ChatOpenAI
+from langchain.memory import ConversationBufferMemory
+
+prompt = ChatPromptTemplate.from_messages([
+    SystemMessagePromptTemplate.from_template("The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know."),
+    MessagesPlaceholder(variable_name="history"),
+    HumanMessagePromptTemplate.from_template("{input}")
+])
+
+llm = ChatOpenAI(temperature=0)
+memory = ConversationBufferMemory(return_messages=True)
+conversation = ConversationChain(memory=memory, prompt=prompt, llm=llm)
+
+conversation.predict(input="Hi there!")
+# -> 'Hello! How can I assist you today?'
+
+
+conversation.predict(input="I'm doing well! Just having a conversation with an AI.")
+# -> "That sounds like fun! I'm happy to chat with you. Is there anything specific you'd like to talk about?"
+
+conversation.predict(input="Tell me about yourself.")
+# -> "Sure! I am an AI language model created by OpenAI. I was trained on a large dataset of text from the internet, which allows me to understand and generate human-like language. I can answer questions, provide information, and even have conversations like this one. Is there anything else you'd like to know about me?"
+```
+`````

docs/getting_started/installation.md

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

docs/getting_started/llm.md

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

docs/getting_started/llm_chain.md

@@ -1,37 +0,0 @@
-# LLM Chains
-
-Calling an LLM is a great first step, but it's just the beginning.
-Normally when you use an LLM in an application, you are not sending user input directly to the LLM.
-Instead, you are probably taking user input and constructing a prompt, and then sending that to the LLM.
-
-For example, in the previous example, the text we passed in was hardcoded to ask for a name for a company that made colorful socks.
-In this imaginary service, what we would want to do is take only the user input describing what the company does, and then format the prompt with that information.
-
-This is easy to do with LangChain!
-
-First lets define the prompt:
-
-```python
-from langchain.prompts import PromptTemplate
-
-prompt = PromptTemplate(
-    input_variables=["product"],
-    template="What is a good name for a company that makes {product}?",
-)
-```
-
-We can now create a very simple chain that will take user input, format the prompt with it, and then send it to the LLM:
-
-```python
-from langchain.chains import LLMChain
-chain = LLMChain(llm=llm, prompt=prompt)
-```
-
-Now we can run that chain only specifying the product!
-
-```python
-chain.run("colorful socks")
-```
-
-There we go! There's the first chain - an LLM Chain.
-This is one of the simpler types of chains, but understanding how it works will set you up well for working with more complex chains.

docs/getting_started/memory.ipynb

@@ -1,333 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "id": "d31df93e",
-      "metadata": {},
-      "source": [
-        "# Memory\n",
-        "So far, all the chains and agents we've gone through have been stateless. But often, you may want a chain or agent to have some concept of \"memory\" so that it may remember information about its previous interactions. The clearest and simple example of this is when designing a chatbot - you want it to remember previous messages so it can use context from that to have a better conversation. This would be a type of \"short-term memory\". On the more complex side, you could imagine a chain/agent remembering key pieces of information over time - this would be a form of \"long-term memory\". For more concrete ideas on the latter, see this [awesome paper](https://memprompt.com/).\n",
-        "\n",
-        "LangChain provides several specially created chains just for this purpose. This notebook walks through using one of those chains (the `ConversationChain`) with two different types of memory."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "d051c1da",
-      "metadata": {},
-      "source": [
-        "### ConversationChain with default memory\n",
-        "By default, the `ConversationChain` has a simple type of memory that remembers all previous inputs/outputs and adds them to the context that is passed. Let's take a look at using this chain (setting `verbose=True` so we can see the prompt)."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 1,
-      "id": "ae046bff",
-      "metadata": {},
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "\n",
-            "\n",
-            "\u001b[1m> Entering new chain...\u001b[0m\n",
-            "Prompt after formatting:\n",
-            "\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
-            "\n",
-            "Current conversation:\n",
-            "\n",
-            "Human: Hi there!\n",
-            "AI:\u001b[0m\n",
-            "\n",
-            "\u001b[1m> Finished chain.\u001b[0m\n"
-          ]
-        },
-        {
-          "data": {
-            "text/plain": [
-              "' Hello! How are you today?'"
-            ]
-          },
-          "execution_count": 1,
-          "metadata": {},
-          "output_type": "execute_result"
-        }
-      ],
-      "source": [
-        "from langchain import OpenAI, ConversationChain\n",
-        "\n",
-        "llm = OpenAI(temperature=0)\n",
-        "conversation = ConversationChain(llm=llm, verbose=True)\n",
-        "\n",
-        "conversation.predict(input=\"Hi there!\")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 2,
-      "id": "d8e2a6ff",
-      "metadata": {},
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "\n",
-            "\n",
-            "\u001b[1m> Entering new chain...\u001b[0m\n",
-            "Prompt after formatting:\n",
-            "\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
-            "\n",
-            "Current conversation:\n",
-            "\n",
-            "Human: Hi there!\n",
-            "AI:  Hello! How are you today?\n",
-            "Human: I'm doing well! Just having a conversation with an AI.\n",
-            "AI:\u001b[0m\n",
-            "\n",
-            "\u001b[1m> Finished chain.\u001b[0m\n"
-          ]
-        },
-        {
-          "data": {
-            "text/plain": [
-              "\" That's great! What would you like to talk about?\""
-            ]
-          },
-          "execution_count": 2,
-          "metadata": {},
-          "output_type": "execute_result"
-        }
-      ],
-      "source": [
-        "conversation.predict(input=\"I'm doing well! Just having a conversation with an AI.\")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 3,
-      "id": "15eda316",
-      "metadata": {},
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "\n",
-            "\n",
-            "\u001b[1m> Entering new chain...\u001b[0m\n",
-            "Prompt after formatting:\n",
-            "\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
-            "\n",
-            "Current conversation:\n",
-            "\n",
-            "Human: Hi there!\n",
-            "AI:  Hello! How are you today?\n",
-            "Human: I'm doing well! Just having a conversation with an AI.\n",
-            "AI:  That's great! What would you like to talk about?\n",
-            "Human: Tell me about yourself.\n",
-            "AI:\u001b[0m\n",
-            "\n",
-            "\u001b[1m> Finished chain.\u001b[0m\n"
-          ]
-        },
-        {
-          "data": {
-            "text/plain": [
-              "'  I am an AI created to provide information and support to humans. I enjoy learning and exploring new things.'"
-            ]
-          },
-          "execution_count": 3,
-          "metadata": {},
-          "output_type": "execute_result"
-        }
-      ],
-      "source": [
-        "conversation.predict(input=\"Tell me about yourself.\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "4fad9448",
-      "metadata": {},
-      "source": [
-        "### ConversationChain with ConversationSummaryMemory\n",
-        "Now let's take a look at using a slightly more complex type of memory - `ConversationSummaryMemory`. This type of memory creates a summary of the conversation over time. This can be useful for condensing information from the conversation over time.\n",
-        "\n",
-        "Let's walk through an example, again setting `verbose=True` so we can see the prompt."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 4,
-      "id": "f60a2fe8",
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from langchain.chains.conversation.memory import ConversationSummaryMemory"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 5,
-      "id": "b7274f2c",
-      "metadata": {},
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "\n",
-            "\n",
-            "\u001b[1m> Entering new chain...\u001b[0m\n",
-            "Prompt after formatting:\n",
-            "\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
-            "\n",
-            "Current conversation:\n",
-            "\n",
-            "Human: Hi, what's up?\n",
-            "AI:\u001b[0m\n",
-            "\n",
-            "\u001b[1m> Finished chain.\u001b[0m\n"
-          ]
-        },
-        {
-          "data": {
-            "text/plain": [
-              "\"\\n\\nI'm doing well, thank you for asking. I'm currently working on a project that I'm really excited about.\""
-            ]
-          },
-          "execution_count": 5,
-          "metadata": {},
-          "output_type": "execute_result"
-        }
-      ],
-      "source": [
-        "conversation_with_summary = ConversationChain(llm=llm, memory=ConversationSummaryMemory(llm=OpenAI()), verbose=True)\n",
-        "conversation_with_summary.predict(input=\"Hi, what's up?\")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 6,
-      "id": "a6b6b88f",
-      "metadata": {},
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "\n",
-            "\n",
-            "\u001b[1m> Entering new chain...\u001b[0m\n",
-            "Prompt after formatting:\n",
-            "\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
-            "\n",
-            "Current conversation:\n",
-            "\n",
-            "The human and artificial intelligence are talking. The human asked the AI what it is doing, and the AI said that it is working on a project that it is excited about.\n",
-            "Human: Tell me more about it!\n",
-            "AI:\u001b[0m\n",
-            "\n",
-            "\u001b[1m> Finished chain.\u001b[0m\n"
-          ]
-        },
-        {
-          "data": {
-            "text/plain": [
-              "\"\\n\\nI'm working on a project that I'm really excited about. It's a lot of work, but I think it's going to be really great when it's finished. I can't wait to show it to you!\""
-            ]
-          },
-          "execution_count": 6,
-          "metadata": {},
-          "output_type": "execute_result"
-        }
-      ],
-      "source": [
-        "conversation_with_summary.predict(input=\"Tell me more about it!\")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 7,
-      "id": "dad869fe",
-      "metadata": {},
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "\n",
-            "\n",
-            "\u001b[1m> Entering new chain...\u001b[0m\n",
-            "Prompt after formatting:\n",
-            "\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
-            "\n",
-            "Current conversation:\n",
-            "\n",
-            "\n",
-            "The human and artificial intelligence are talking. The human asked the AI what it is doing, and the AI said that it is working on a project that it is excited about. The AI said that the project is a lot of work, but it is going to be great when it is finished.\n",
-            "Human: Very cool -- what is the scope of the project?\n",
-            "AI:\u001b[0m\n",
-            "\n",
-            "\u001b[1m> Finished chain.\u001b[0m\n"
-          ]
-        },
-        {
-          "data": {
-            "text/plain": [
-              "'\\n\\nThe project is quite large in scope. It involves a lot of data analysis and work with artificial intelligence algorithms.'"
-            ]
-          },
-          "execution_count": 7,
-          "metadata": {},
-          "output_type": "execute_result"
-        }
-      ],
-      "source": [
-        "conversation_with_summary.predict(input=\"Very cool -- what is the scope of the project?\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "5c8735cc",
-      "metadata": {},
-      "source": [
-        "### More Resources on Memory\n",
-        "\n",
-        "This just scratches the surface of what you can do with memory. For more examples on things like how to implement custom memory classes, how to add memory to a custom LLM chain and how to use memory with an agent, please see the [How-To: Memory](../../examples/memory) section. For even more advanced ideas on memory (which will hopefully be included in LangChain soon!) see the [MemPrompt](https://memprompt.com/) paper."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "id": "436dda66",
-      "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/getting_started/sequential_chains.ipynb

@@ -1,265 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "4f73605d",
-   "metadata": {},
-   "source": [
-    "# Sequential Chains"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "3b235f7a",
-   "metadata": {},
-   "source": [
-    "The next step after calling a language model is make a series of calls to a language model. This is particularly useful when you want to take the output from one call and use it as the input to another.\n",
-    "\n",
-    "In this notebook we will walk through some examples for how to do this, using sequential chains. Sequential chains are defined as a series of chains, called in deterministic order. There are two types of sequential chains:\n",
-    "\n",
-    "- `SimpleSequentialChain`: The simplest form of sequential chains, where each step has a singular input/output, and the output of one step is the input to the next.\n",
-    "- `SequentialChain`: A more general form of sequential chains, allowing for multiple inputs/outputs."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "5162794e",
-   "metadata": {},
-   "source": [
-    "## SimpleSequentialChain\n",
-    "\n",
-    "In this series of chains, each individual chain has a single input and a single output, and the output of one step is used as input to the next.\n",
-    "\n",
-    "Let's walk through a toy example of doing this, where the first chain takes in the title of an imaginary play and then generates a synopsis for that title, and the second chain takes in the synopsis of that play and generates an imaginary review for that play."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "3f2f9b8c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.llms import OpenAI\n",
-    "from langchain.chains import LLMChain\n",
-    "from langchain.prompts import PromptTemplate"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "b8237d1a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# This is an LLMChain to write a synopsis given a title of a play.\n",
-    "llm = OpenAI(temperature=.7)\n",
-    "template = \"\"\"You are a playwright. Given the title of play, it is your job to write a synopsis for that title.\n",
-    "\n",
-    "Title: {title}\n",
-    "Playwright: This is a synopsis for the above play:\"\"\"\n",
-    "prompt_template = PromptTemplate(input_variables=[\"title\"], template=template)\n",
-    "synopsis_chain = LLMChain(llm=llm, prompt=prompt_template)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "4a391730",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# This is an LLMChain to write a review of a play given a synopsis.\n",
-    "llm = OpenAI(temperature=.7)\n",
-    "template = \"\"\"You are a play critic from the New York Times. Given the synopsis of play, it is your job to write a review for that play.\n",
-    "\n",
-    "Play Synopsis:\n",
-    "{synopsis}\n",
-    "Review from a New York Times play critic of the above play:\"\"\"\n",
-    "prompt_template = PromptTemplate(input_variables=[\"synopsis\"], template=template)\n",
-    "review_chain = LLMChain(llm=llm, prompt=prompt_template)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "9368bd63",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# This is the overall chain where we run these two chains in sequence.\n",
-    "from langchain.chains import SimpleSequentialChain\n",
-    "overall_chain = SimpleSequentialChain(chains=[synopsis_chain, review_chain], verbose=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "d39e15f5",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new chain...\u001b[0m\n",
-      "\u001b[36;1m\u001b[1;3m\n",
-      "\n",
-      "A young couple, John and Mary, are enjoying a day at the beach. As the sun sets, they share a romantic moment. However, their happiness is short-lived, as a tragic accident claims John's life. Mary is left devastated by the loss of her husband.\u001b[0m\n",
-      "\u001b[33;1m\u001b[1;3m\n",
-      "\n",
-      "\"A young couple's happiness is cut short by tragedy in this moving play. Mary is left devastated by the loss of her husband, John, in a freak accident. The play captures the pain and grief of loss, as well as the strength of love. A must-see for fans of theater.\"\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    }
-   ],
-   "source": [
-    "review = overall_chain.run(\"Tragedy at sunset on the beach\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "c6649a01",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\"A young couple's happiness is cut short by tragedy in this moving play. Mary is left devastated by the loss of her husband, John, in a freak accident. The play captures the pain and grief of loss, as well as the strength of love. A must-see for fans of theater.\"\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(review)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "c3f1549a",
-   "metadata": {},
-   "source": [
-    "## Sequential Chain\n",
-    "Of course, not all sequential chains will be as simple as passing a single string as an argument and getting a single string as output for all steps in the chain. In this next example, we will experiment with more complex chains that involve multiple inputs, and where there also multiple final outputs. \n",
-    "\n",
-    "Of particular importance is how we name the input/output variable names. In the above example we didn't have to think about that because we were just passing the output of one chain directly as input to the next, but here we do have worry about that because we have multiple inputs."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "02016a51",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# This is an LLMChain to write a synopsis given a title of a play and the era it is set in.\n",
-    "llm = OpenAI(temperature=.7)\n",
-    "template = \"\"\"You are a playwright. Given the title of play and the era it is set in, it is your job to write a synopsis for that title.\n",
-    "\n",
-    "Title: {title}\n",
-    "Era: {era}\n",
-    "Playwright: This is a synopsis for the above play:\"\"\"\n",
-    "prompt_template = PromptTemplate(input_variables=[\"title\", 'era'], template=template)\n",
-    "synopsis_chain = LLMChain(llm=llm, prompt=prompt_template, output_key=\"synopsis\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "8bd38cc2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# This is an LLMChain to write a review of a play given a synopsis.\n",
-    "llm = OpenAI(temperature=.7)\n",
-    "template = \"\"\"You are a play critic from the New York Times. Given the synopsis of play, it is your job to write a review for that play.\n",
-    "\n",
-    "Play Synopsis:\n",
-    "{synopsis}\n",
-    "Review from a New York Times play critic of the above play:\"\"\"\n",
-    "prompt_template = PromptTemplate(input_variables=[\"synopsis\"], template=template)\n",
-    "review_chain = LLMChain(llm=llm, prompt=prompt_template, output_key=\"review\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "524523af",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# This is the overall chain where we run these two chains in sequence.\n",
-    "from langchain.chains import SequentialChain\n",
-    "overall_chain = SequentialChain(\n",
-    "    chains=[synopsis_chain, review_chain],\n",
-    "    input_variables=[\"era\", \"title\"],\n",
-    "    # Here we return multiple variables\n",
-    "    output_variables=[\"synopsis\", \"review\"],\n",
-    "    verbose=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "3fd3a7be",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new chain...\u001b[0m\n",
-      "\u001b[1mChain 0\u001b[0m:\n",
-      "{'synopsis': \"\\n\\nThe play is set in Victorian England and follows the tragic story of a young woman who drowns while swimming at sunset on the beach. Her body is found the next morning by a fisherman who raises the alarm. The young woman's family and friends are devastated by her death and the play ends with their mourning her loss.\"}\n",
-      "\n",
-      "\u001b[1mChain 1\u001b[0m:\n",
-      "{'review': '\\n\\n\"The play is a tragedy, pure and simple. It is the story of a young woman\\'s death, told through the eyes of those who loved her. It is a sad, beautiful play that will stay with you long after you\\'ve seen it. The acting is superb, and the writing is exquisite. If you are looking for a play that will touch your heart and make you think, this is it.\"'}\n",
-      "\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    }
-   ],
-   "source": [
-    "review = overall_chain({\"title\":\"Tragedy at sunset on the beach\", \"era\": \"Victorian England\"})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "6be70d27",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.7.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/glossary.md

@@ -1,81 +1,90 @@
 # Glossary
 
 This is a collection of terminology commonly used when developing LLM applications.
-It contains reference to external papers or sources where the concept was first introduced, 
+It contains reference to external papers or sources where the concept was first introduced,
 as well as to places in LangChain where the concept is used.
 
-### Chain of Thought Prompting
+## Chain of Thought Prompting
 
-A prompting technique used to encourage the model to generate a series of intermediate reasoning steps. 
+A prompting technique used to encourage the model to generate a series of intermediate reasoning steps.
 A less formal way to induce this behavior is to include “Let’s think step-by-step” in the prompt.
 
 Resources:
+
 - [Chain-of-Thought Paper](https://arxiv.org/pdf/2201.11903.pdf)
 - [Step-by-Step Paper](https://arxiv.org/abs/2112.00114)
 
-### Action Plan Generation
+## Action Plan Generation
 
-A prompt usage that uses a language model to generate actions to take. 
+A prompt usage that uses a language model to generate actions to take.
 The results of these actions can then be fed back into the language model to generate a subsequent action.
 
 Resources:
+
 - [WebGPT Paper](https://arxiv.org/pdf/2112.09332.pdf)
 - [SayCan Paper](https://say-can.github.io/assets/palm_saycan.pdf)
 
-### ReAct Prompting
+## ReAct Prompting
 
-A prompting technique that combines Chain-of-Thought prompting with action plan generation. 
-This induces the to model to think about what action to take, then take it. 
+A prompting technique that combines Chain-of-Thought prompting with action plan generation.
+This induces the to model to think about what action to take, then take it.
 
 Resources:
+
 - [Paper](https://arxiv.org/pdf/2210.03629.pdf)
-- [LangChain Example](https://github.com/hwchase17/langchain/blob/master/docs/examples/agents/react.ipynb)
+- [LangChain Example](modules/agents/agents/examples/react.ipynb)
 
-### Self-ask
+## Self-ask
 
-A prompting method that builds on top of chain-of-thought prompting. 
-In this method, the model explicitly asks itself follow-up questions, which are then answered by an external search engine. 
+A prompting method that builds on top of chain-of-thought prompting.
+In this method, the model explicitly asks itself follow-up questions, which are then answered by an external search engine.
 
 Resources:
+
 - [Paper](https://ofir.io/self-ask.pdf)
-- [LangChain Example](https://github.com/hwchase17/langchain/blob/master/docs/examples/agents/self_ask_with_search.ipynb)
+- [LangChain Example](modules/agents/agents/examples/self_ask_with_search.ipynb)
 
-### Prompt Chaining
+## Prompt Chaining
 
-Combining multiple LLM calls together, with the output of one step being the input to the next. 
+Combining multiple LLM calls together, with the output of one-step being the input to the next.
+
+Resources:
 
-Resources: 
 - [PromptChainer Paper](https://arxiv.org/pdf/2203.06566.pdf)
 - [Language Model Cascades](https://arxiv.org/abs/2207.10342)
 - [ICE Primer Book](https://primer.ought.org/)
 - [Socratic Models](https://socraticmodels.github.io/)
 
-### Memetic Proxy
+## Memetic Proxy
 
-Encouraging the LLM to respond in a certain way framing the discussion in a context that the model knows of and that will result in that type of response. For example, as a conversation between a student and a teacher. 
+Encouraging the LLM to respond in a certain way framing the discussion in a context that the model knows of and that will result in that type of response. For example, as a conversation between a student and a teacher.
 
 Resources:
+
 - [Paper](https://arxiv.org/pdf/2102.07350.pdf)
 
-### Self Consistency
+## Self Consistency
 
-A decoding strategy that samples a diverse set of reasoning paths and then selects the most consistent answer. 
-Is most effective when combined with Chain-of-thought prompting. 
+A decoding strategy that samples a diverse set of reasoning paths and then selects the most consistent answer.
+Is most effective when combined with Chain-of-thought prompting.
 
 Resources:
+
 - [Paper](https://arxiv.org/pdf/2203.11171.pdf)
 
-### Inception
+## Inception
 
-Also called “First Person Instruction”. 
-Encouraging the model to think a certain way by including the start of the model’s response in the prompt. 
+Also called “First Person Instruction”.
+Encouraging the model to think a certain way by including the start of the model’s response in the prompt.
 
 Resources:
+
 - [Example](https://twitter.com/goodside/status/1583262455207460865?s=20&t=8Hz7XBnK1OF8siQrxxCIGQ)
 
-### MemPrompt
+## MemPrompt
 
 MemPrompt maintains a memory of errors and user feedback, and uses them to prevent repetition of mistakes.
 
 Resources:
+
 - [Paper](https://memprompt.com/)