remove classes

Added yeagerai.md to ecosystem

.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

@@ -0,0 +1,190 @@
+# Contributing to LangChain
+
+Hi there! Thank you for even being interested in contributing to LangChain.
+As an open source project in a rapidly developing field, we are extremely open
+to contributions, whether it be in the form of a new feature, improved infra, or better documentation.
+
+To contribute to this project, please follow a ["fork and pull request"](https://docs.github.com/en/get-started/quickstart/contributing-to-projects) workflow.
+Please do not try to push directly to this repo unless you are maintainer.
+
+## 🗺️Contributing Guidelines
+
+### 🚩GitHub Issues
+
+Our [issues](https://github.com/hwchase17/langchain/issues) page is kept up to date
+with bugs, improvements, and feature requests. There is a taxonomy of labels to help
+with sorting and discovery of issues of interest. These include:
+
+- prompts: related to prompt tooling/infra.
+- llms: related to LLM wrappers/tooling/infra.
+- chains
+- utilities: related to different types of utilities to integrate with (Python, SQL, etc.).
+- agents
+- memory
+- applications: related to example applications to build
+
+If you start working on an issue, please assign it to yourself.
+
+If you are adding an issue, please try to keep it focused on a single modular bug/improvement/feature.
+If the two issues are related, or blocking, please link them rather than keep them as one single one.
+
+We will try to keep these issues as up to date as possible, though
+with the rapid rate of develop in this field some may get out of date.
+If you notice this happening, please just let us know.
+
+### 🙋Getting Help
+
+Although we try to have a developer setup to make it as easy as possible for others to contribute (see below)
+it is possible that some pain point may arise around environment setup, linting, documentation, or other.
+Should that occur, please contact a maintainer! Not only do we want to help get you unblocked,
+but we also want to make sure that the process is smooth for future contributors.
+
+In a similar vein, we do enforce certain linting, formatting, and documentation standards in the codebase.
+If you are finding these difficult (or even just annoying) to work with,
+feel free to contact a maintainer for help - we do not want these to get in the way of getting
+good code into the codebase.
+
+### 🏭Release process
+
+As of now, LangChain has an ad hoc release process: releases are cut with high frequency by
+a developer and published to [PyPI](https://pypi.org/project/langchain/).
+
+LangChain follows the [semver](https://semver.org/) versioning standard. However, as pre-1.0 software,
+even patch releases may contain [non-backwards-compatible changes](https://semver.org/#spec-item-4).
+
+If your contribution has made its way into a release, we will want to give you credit on Twitter (only if you want though)!
+If you have a Twitter account you would like us to mention, please let us know in the PR or in another manner.
+
+## 🚀Quick Start
+
+This project uses [Poetry](https://python-poetry.org/) as a dependency manager. Check out Poetry's [documentation on how to install it](https://python-poetry.org/docs/#installation) on your system before proceeding.
+
+❗Note: If you use `Conda` or `Pyenv` as your environment / package manager, avoid dependency conflicts by doing the following first:
+1. *Before installing Poetry*, create and activate a new Conda env (e.g. `conda create -n langchain python=3.9`)
+2. Install Poetry (see above)
+3. Tell Poetry to use the virtualenv python environment (`poetry config virtualenvs.prefer-active-python true`)
+4. Continue with the following steps.
+
+To install requirements:
+
+```bash
+poetry install -E all
+```
+
+This will install all requirements for running the package, examples, linting, formatting, tests, and coverage. Note the `-E all` flag will install all optional dependencies necessary for integration testing.
+
+❗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. To double check, run `make test`, all tests should pass. If they don't you may need to pip install additional dependencies, such as `numexpr` and `openapi_schema_pydantic`.
+
+## ✅Common Tasks
+
+Type `make` for a list of common tasks.
+
+### Code Formatting
+
+Formatting for this project is done via a combination of [Black](https://black.readthedocs.io/en/stable/) and [isort](https://pycqa.github.io/isort/).
+
+To run formatting for this project:
+
+```bash
+make format
+```
+
+### Linting
+
+Linting for this project is done via a combination of [Black](https://black.readthedocs.io/en/stable/), [isort](https://pycqa.github.io/isort/), [flake8](https://flake8.pycqa.org/en/latest/), and [mypy](http://mypy-lang.org/).
+
+To run linting for this project:
+
+```bash
+make lint
+```
+
+We recognize linting can be annoying - if you do not want to do it, please contact a project maintainer, and they can help you with it. We do not want this to be a blocker for good code getting contributed.
+
+### Coverage
+
+Code coverage (i.e. the amount of code that is covered by unit tests) helps identify areas of the code that are potentially more or less brittle.
+
+To get a report of current coverage, run the following:
+
+```bash
+make coverage
+```
+
+### Testing
+
+Unit tests cover modular logic that does not require calls to outside APIs.
+
+To run unit tests:
+
+```bash
+make test
+```
+
+To run unit tests in Docker:
+
+```bash
+make docker_tests
+```
+
+If you add new logic, please add a unit test.
+
+Integration tests cover logic that requires making calls to outside APIs (often integration with other services).
+
+To run integration tests:
+
+```bash
+make integration_tests
+```
+
+If you add support for a new external API, please add a new integration test.
+
+### Adding a Jupyter Notebook
+
+If you are adding a Jupyter notebook example, you'll want to install the optional `dev` dependencies.
+
+To install dev dependencies:
+
+```bash
+poetry install --with dev
+```
+
+Launch a notebook:
+
+```bash
+poetry run jupyter notebook
+```
+
+When you run `poetry install`, the `langchain` package is installed as editable in the virtualenv, so your new logic can be imported into the notebook.
+
+## 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/lint.yml

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

.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

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

.gitignore

@@ -1,4 +1,5 @@
 .vscode/
+.idea/
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
@@ -105,7 +106,9 @@ celerybeat.pid
 
 # Environments
 .env
+.envrc
 .venv
+.venvs
 env/
 venv/
 ENV/
@@ -129,3 +132,16 @@ dmypy.json
 
 # Pyre type checker
 .pyre/
+
+# macOS display setting files
+.DS_Store
+
+# Wandb directory
+wandb/
+
+# asdf tool versions
+.tool-versions
+/.ruff_cache/
+
+*.pkl
+*.bin

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"]

MANIFEST.in

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

Makefile

@@ -1,17 +1,62 @@
-.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 \
+		--cov-config=.coveragerc \
+		--cov-report xml \
+		--cov-report term-missing:skip-covered
+
+clean: docs_clean
+
+docs_build:
+	cd docs && poetry run make html
+
+docs_clean:
+	cd docs && poetry run make clean
+
+docs_linkcheck:
+	poetry run linkchecker docs/_build/html/index.html
 
 format:
-	black .
-	isort .
+	poetry run black .
+	poetry run ruff --select I --fix .
 
-lint:
-	mypy .
-	black . --check
-	isort . --check
-	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:
-	pytest tests/unit_tests
+	poetry run pytest tests/unit_tests
+
+test_watch:
+	poetry run ptw --now . -- tests/unit_tests
 
 integration_tests:
-	pytest 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

@@ -2,124 +2,83 @@
 
 ⚡ 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) [![Downloads](https://static.pepy.tech/badge/langchain/month)](https://pepy.tech/project/langchain) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai) [![](https://dcbadge.vercel.app/api/server/6adMQxSpJS?compact=true&style=flat)](https://discord.gg/6adMQxSpJS)
+
+**Production Support:** As you move your LangChains into production, we'd love to offer more comprehensive support.
+Please fill out [this form](https://forms.gle/57d8AmXBYp8PP8tZA) and we'll set up a dedicated support Slack channel.
 
 ## Quick Install
 
 `pip install langchain`
+or
+`conda install langchain -c conda-forge`
 
 ## 🤔 What is this?
 
 Large language models (LLMs) are emerging as a transformative technology, enabling
 developers to build applications that they previously could not.
 But using these LLMs in isolation is often not enough to
-create a truly powerful app - the real power comes when you are able to
-combine them with other sources of computation or knowledge.
+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
 
 Please see [here](https://langchain.readthedocs.io/en/latest/?) for full documentation on:
-- Getting started (installation, setting up environment, simple examples)
+
+- 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 three main areas (with a forth coming soon) 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:
-1. LLM and Prompts
-2. Chains
-3. Agents
-4. Memory
 
-Let's go through these categories and for each one identify key concepts (to clarify terminology) as well as the problems in this area LangChain helps solve.
+**📃 LLMs and Prompts:**
 
-### LLMs and Prompts
-Calling out to an LLM once is pretty easy, with most of them being behind well documented APIs.
-However, there are still some challenges going from that to an application running in production that LangChain attempts to address.
+This includes prompt management, prompt optimization, generic interface for all LLMs, and common utilities for working with LLMs.
 
-**Key Concepts**
-- LLM: A large language model, in particular a text-to-text model.
-- Prompt: The input to a language model. Typically this is not simply a hardcoded string but rather a combination of a template, some examples, and user input.
-- Prompt Template: An object responsible for constructing the final prompt to pass to a LLM.
-- Examples: Datapoints that can be included in the prompt in order to give the model more context what to do.
-- Few Shot Prompt Template: A subclass of the PromptTemplate class that uses examples.
-- Example Selector: A class responsible to selecting examples to use dynamically (depending on user input) in a few shot prompt.
+**🔗 Chains:**
 
-**Problems Solved**
-- Switching costs: by exposing a standard interface for all the top LLM providers, LangChain makes it easy to switch from one provider to another, whether it be for production use cases or just for testing stuff out.
-- Prompt management: managing your prompts is easy when you only have one simple one, but can get tricky when you have a bunch or when they start to get more complex. LangChain provides a standard way for storing, constructing, and referencing prompts.
-- Prompt optimization: despite the underlying models getting better and better, there is still currently a need for carefully constructing prompts. 
+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.
 
-### Chains
-Using an LLM in isolation is fine for some simple applications, but many more complex ones require chaining LLMs - either with eachother or with other experts.
-LangChain provides several parts to help with that.
+**📚 Data Augmented Generation:**
 
-**Key Concepts**
-- Tools: APIs designed for assisting with a particular use case (search, databases, Python REPL, etc). Prompt templates, LLMs, and chains can also be considered tools.
-- Chains: A combination of multiple tools in a deterministic manner.
+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.
 
-**Problems Solved**
-- Standard interface for working with Chains
-- Easy way to construct chains of LLMs
-- Lots of integrations with other tools that you may want to use in conjunction with LLMs 
-- End-to-end chains for common workflows (database question/answer, recursive summarization, etc)
+**🤖 Agents:**
 
-### Agents
-Some applications will require not just a predetermined chain of calls to LLMs/other tools, but potentially an unknown chain that depends on the user input.
-In these types of chains, there is a “agent” which has access to a suite of tools.
-Depending on the user input, the agent can then decide which, if any, of these tools to call.
+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.
 
-**Key Concepts**
-- Tools: same as above.
-- Agent: An LLM-powered class responsible for determining which tools to use and in what order.
+**🧠 Memory:**
 
+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.
 
-**Problems Solved**
-- Standard agent interfaces
-- A selection of powerful agents to choose from
-- Common chains that can be used as tools
+**🧐 Evaluation:**
 
-### 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.
+[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.
 
-**Key Concepts**
-- Memory: A class that can be added to an Agent or Chain to (1) pull in memory variables before calling that chain/agent, and (2) create new memories after the chain/agent finishes.
-- Memory Variables: Variables returned from a Memory class, to be passed into the chain/agent along with the user input.
+For more information on these concepts, please see our [full documentation](https://langchain.readthedocs.io/en/latest/).
 
-**Problems Solved**
-- Standard memory interfaces
-- A collection of common memory implementations to choose from
-- Common chains/agents that use memory (e.g. chatbots)
+## 💁 Contributing
 
-## 🤖 Developer Guide
+As an open source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infra, or better documentation.
 
-To begin developing on this project, first clone to the repo locally.
-To install requirements, run `pip install -r requirements.txt`.
-This will install all requirements for running the package, examples, linting, formatting, and tests.
-
-Formatting for this project is a combination of [Black](https://black.readthedocs.io/en/stable/) and [isort](https://pycqa.github.io/isort/).
-To run formatting for this project, run `make format`.
-
-Linting for this project is a combination of [Black](https://black.readthedocs.io/en/stable/), [isort](https://pycqa.github.io/isort/), [flake8](https://flake8.pycqa.org/en/latest/), and [mypy](http://mypy-lang.org/).
-To run linting for this project, run `make lint`.
-We recognize linting can be annoying - if you do not want to do it, please contact a project maintainer and they can help you with it. We do not want this to be a blocker for good code getting contributed.
-
-Unit tests cover modular logic that does not require calls to outside apis.
-To run unit tests, run `make tests`.
-If you add new logic, please add a unit test.
-
-Integration tests cover logic that requires making calls to outside APIs (often integration with other services).
-To run integration tests, run `make integration_tests`.
-If you add support for a new external API, please add a new integration test.
-
-If you are adding a Jupyter notebook example, you can run `pip install -e .` to build the langchain package from your local changes, so your new logic can be imported into the notebook.
-
-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.
+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 +1,17 @@
+pre {
+  white-space: break-spaces;
+}
+
+@media (min-width: 1200px) {
+  .container,
+  .container-lg,
+  .container-md,
+  .container-sm,
+  .container-xl {
+    max-width: 2560px !important;
+  }
+}
+
+#my-component-root *, #headlessui-portal-root * {
+  z-index: 1000000000000;
+}

docs/_static/js/mendablesearch.js

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

docs/conf.py

@@ -15,16 +15,22 @@
 # import sys
 # sys.path.insert(0, os.path.abspath('.'))
 
-import langchain
+import toml
+
+with open("../pyproject.toml") as f:
+    data = toml.load(f)
 
 # -- Project information -----------------------------------------------------
 
-project = "LangChain"
-copyright = "2022, Harrison Chase"
+project = "🦜🔗 LangChain"
+copyright = "2023, Harrison Chase"
 author = "Harrison Chase"
 
-version = langchain.__version__
-release = langchain.__version__
+version = data["tool"]["poetry"]["version"]
+release = version
+
+html_title = project + " " + version
+html_last_updated_fmt = "%b %d, %Y"
 
 
 # -- General configuration ---------------------------------------------------
@@ -39,11 +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
@@ -70,8 +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
@@ -84,4 +96,17 @@ 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",
+]
+
+html_js_files = [
+    "js/mendablesearch.js",
+]
+
+nb_execution_mode = "off"
+myst_enable_extensions = ["colon_fence"]

docs/deployments.md

@@ -0,0 +1,51 @@
+# 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.
+
+## [Digitalocean App Platform](https://github.com/homanp/digitalocean-langchain)
+
+A minimal example on how to deploy LangChain to DigitalOcean App Platform.
+
+## [SteamShip](https://github.com/steamship-core/steamship-langchain/)
+
+This repository contains LangChain adapters for Steamship, enabling LangChain developers to rapidly deploy their apps on Steamship.
+This includes: production ready endpoints, horizontal scaling across dependencies, persistant storage of app state, multi-tenancy support, etc.
+
+## [Langchain-serve](https://github.com/jina-ai/langchain-serve)
+
+This repository allows users to serve local chains and agents as RESTful, gRPC, or Websocket APIs thanks to [Jina](https://docs.jina.ai/). Deploy your chains & agents with ease and enjoy independent scaling, serverless and autoscaling APIs, as well as a Streamlit playground on Jina AI Cloud.
+
+## [BentoML](https://github.com/ssheng/BentoChain)
+
+This repository provides an example of how to deploy a LangChain application with [BentoML](https://github.com/bentoml/BentoML). BentoML is a framework that enables the containerization of machine learning applications as standard OCI images. BentoML also allows for the automatic generation of OpenAPI and gRPC endpoints. With BentoML, you can integrate models from all popular ML frameworks and deploy them as microservices running on the most optimal hardware and scaling independently.

docs/ecosystem.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 an agent with tools\n",
+    "\n",
+    "To show a more advanced workflow, let's create an agent with access to tools. The way ClearML tracks the results is not different though, only the table will look slightly different as there are other types of actions taken when compared to the earlier, simpler example.\n",
+    "\n",
+    "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/comet_tracking.ipynb

@@ -0,0 +1,352 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Comet"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "![](https://user-images.githubusercontent.com/7529846/230328046-a8b18c51-12e3-4617-9b39-97614a571a2d.png)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "In this guide we will demonstrate how to track your Langchain Experiments, Evaluation Metrics, and LLM Sessions with [Comet](https://www.comet.com/site/?utm_source=langchain&utm_medium=referral&utm_campaign=comet_notebook).  \n",
+    "\n",
+    "<a target=\"_blank\" href=\"https://colab.research.google.com/github/hwchase17/langchain/blob/master/docs/ecosystem/comet_tracking.ipynb\">\n",
+    "  <img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/>\n",
+    "</a>\n",
+    "\n",
+    "**Example Project:** [Comet with LangChain](https://www.comet.com/examples/comet-example-langchain/view/b5ZThK6OFdhKWVSP3fDfRtrNF/panels?utm_source=langchain&utm_medium=referral&utm_campaign=comet_notebook)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<img width=\"1280\" alt=\"comet-langchain\" src=\"https://user-images.githubusercontent.com/7529846/230326720-a9711435-9c6f-4edb-a707-94b67271ab25.png\">\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Install Comet and Dependencies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install comet_ml langchain openai google-search-results spacy textstat pandas\n",
+    "\n",
+    "import sys\n",
+    "!{sys.executable} -m spacy download en_core_web_sm"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Initialize Comet and Set your Credentials"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You can grab your [Comet API Key here](https://www.comet.com/signup?utm_source=langchain&utm_medium=referral&utm_campaign=comet_notebook) or click the link after intializing Comet"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import comet_ml\n",
+    "\n",
+    "comet_ml.init(project_name=\"comet-example-langchain\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Set OpenAI and SerpAPI credentials"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You will need an [OpenAI API Key](https://platform.openai.com/account/api-keys) and a [SerpAPI API Key](https://serpapi.com/dashboard) to run the following examples"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"...\"\n",
+    "#os.environ[\"OPENAI_ORGANIZATION\"] = \"...\"\n",
+    "os.environ[\"SERPAPI_API_KEY\"] = \"...\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Scenario 1: Using just an LLM"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from datetime import datetime\n",
+    "\n",
+    "from langchain.callbacks import CometCallbackHandler, StdOutCallbackHandler\n",
+    "from langchain.callbacks.base import CallbackManager\n",
+    "from langchain.llms import OpenAI\n",
+    "\n",
+    "comet_callback = CometCallbackHandler(\n",
+    "    project_name=\"comet-example-langchain\",\n",
+    "    complexity_metrics=True,\n",
+    "    stream_logs=True,\n",
+    "    tags=[\"llm\"],\n",
+    "    visualizations=[\"dep\"],\n",
+    ")\n",
+    "manager = CallbackManager([StdOutCallbackHandler(), comet_callback])\n",
+    "llm = OpenAI(temperature=0.9, callback_manager=manager, verbose=True)\n",
+    "\n",
+    "llm_result = llm.generate([\"Tell me a joke\", \"Tell me a poem\", \"Tell me a fact\"] * 3)\n",
+    "print(\"LLM result\", llm_result)\n",
+    "comet_callback.flush_tracker(llm, finish=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Scenario 2: Using an LLM in a Chain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.callbacks import CometCallbackHandler, StdOutCallbackHandler\n",
+    "from langchain.callbacks.base import CallbackManager\n",
+    "from langchain.chains import LLMChain\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.prompts import PromptTemplate\n",
+    "\n",
+    "comet_callback = CometCallbackHandler(\n",
+    "    complexity_metrics=True,\n",
+    "    project_name=\"comet-example-langchain\",\n",
+    "    stream_logs=True,\n",
+    "    tags=[\"synopsis-chain\"],\n",
+    ")\n",
+    "manager = CallbackManager([StdOutCallbackHandler(), comet_callback])\n",
+    "\n",
+    "llm = OpenAI(temperature=0.9, callback_manager=manager, verbose=True)\n",
+    "\n",
+    "template = \"\"\"You are a playwright. Given the title of play, it is your job to write a synopsis for that title.\n",
+    "Title: {title}\n",
+    "Playwright: This is a synopsis for the above play:\"\"\"\n",
+    "prompt_template = PromptTemplate(input_variables=[\"title\"], template=template)\n",
+    "synopsis_chain = LLMChain(llm=llm, prompt=prompt_template, callback_manager=manager)\n",
+    "\n",
+    "test_prompts = [{\"title\": \"Documentary about Bigfoot in Paris\"}]\n",
+    "print(synopsis_chain.apply(test_prompts))\n",
+    "comet_callback.flush_tracker(synopsis_chain, finish=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Scenario 3: Using An Agent with Tools "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.agents import initialize_agent, load_tools\n",
+    "from langchain.callbacks import CometCallbackHandler, StdOutCallbackHandler\n",
+    "from langchain.callbacks.base import CallbackManager\n",
+    "from langchain.llms import OpenAI\n",
+    "\n",
+    "comet_callback = CometCallbackHandler(\n",
+    "    project_name=\"comet-example-langchain\",\n",
+    "    complexity_metrics=True,\n",
+    "    stream_logs=True,\n",
+    "    tags=[\"agent\"],\n",
+    ")\n",
+    "manager = CallbackManager([StdOutCallbackHandler(), comet_callback])\n",
+    "llm = OpenAI(temperature=0.9, callback_manager=manager, verbose=True)\n",
+    "\n",
+    "tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm, callback_manager=manager)\n",
+    "agent = initialize_agent(\n",
+    "    tools,\n",
+    "    llm,\n",
+    "    agent=\"zero-shot-react-description\",\n",
+    "    callback_manager=manager,\n",
+    "    verbose=True,\n",
+    ")\n",
+    "agent.run(\n",
+    "    \"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\"\n",
+    ")\n",
+    "comet_callback.flush_tracker(agent, finish=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Scenario 4: Using Custom Evaluation Metrics"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The `CometCallbackManager` also allows you to define and use Custom Evaluation Metrics to assess generated outputs from your model. Let's take a look at how this works. \n",
+    "\n",
+    "\n",
+    "In the snippet below, we will use the [ROUGE](https://huggingface.co/spaces/evaluate-metric/rouge) metric to evaluate the quality of a generated summary of an input prompt. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install rouge-score"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from rouge_score import rouge_scorer\n",
+    "\n",
+    "from langchain.callbacks import CometCallbackHandler, StdOutCallbackHandler\n",
+    "from langchain.callbacks.base import CallbackManager\n",
+    "from langchain.chains import LLMChain\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.prompts import PromptTemplate\n",
+    "\n",
+    "\n",
+    "class Rouge:\n",
+    "    def __init__(self, reference):\n",
+    "        self.reference = reference\n",
+    "        self.scorer = rouge_scorer.RougeScorer([\"rougeLsum\"], use_stemmer=True)\n",
+    "\n",
+    "    def compute_metric(self, generation, prompt_idx, gen_idx):\n",
+    "        prediction = generation.text\n",
+    "        results = self.scorer.score(target=self.reference, prediction=prediction)\n",
+    "\n",
+    "        return {\n",
+    "            \"rougeLsum_score\": results[\"rougeLsum\"].fmeasure,\n",
+    "            \"reference\": self.reference,\n",
+    "        }\n",
+    "\n",
+    "\n",
+    "reference = \"\"\"\n",
+    "The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building.\n",
+    "It was the first structure to reach a height of 300 metres.\n",
+    "\n",
+    "It is now taller than the Chrysler Building in New York City by 5.2 metres (17 ft)\n",
+    "Excluding transmitters, the Eiffel Tower is the second tallest free-standing structure in France .\n",
+    "\"\"\"\n",
+    "rouge_score = Rouge(reference=reference)\n",
+    "\n",
+    "template = \"\"\"Given the following article, it is your job to write a summary.\n",
+    "Article:\n",
+    "{article}\n",
+    "Summary: This is the summary for the above article:\"\"\"\n",
+    "prompt_template = PromptTemplate(input_variables=[\"article\"], template=template)\n",
+    "\n",
+    "comet_callback = CometCallbackHandler(\n",
+    "    project_name=\"comet-example-langchain\",\n",
+    "    complexity_metrics=False,\n",
+    "    stream_logs=True,\n",
+    "    tags=[\"custom_metrics\"],\n",
+    "    custom_metrics=rouge_score.compute_metric,\n",
+    ")\n",
+    "manager = CallbackManager([StdOutCallbackHandler(), comet_callback])\n",
+    "llm = OpenAI(temperature=0.9, callback_manager=manager, verbose=True)\n",
+    "\n",
+    "synopsis_chain = LLMChain(llm=llm, prompt=prompt_template, callback_manager=manager)\n",
+    "\n",
+    "test_prompts = [\n",
+    "    {\n",
+    "        \"article\": \"\"\"\n",
+    "                 The tower is 324 metres (1,063 ft) tall, about the same height as\n",
+    "                 an 81-storey building, and the tallest structure in Paris. Its base is square,\n",
+    "                 measuring 125 metres (410 ft) on each side.\n",
+    "                 During its construction, the Eiffel Tower surpassed the\n",
+    "                 Washington Monument to become the tallest man-made structure in the world,\n",
+    "                 a title it held for 41 years until the Chrysler Building\n",
+    "                 in New York City was finished in 1930.\n",
+    "\n",
+    "                 It was the first structure to reach a height of 300 metres.\n",
+    "                 Due to the addition of a broadcasting aerial at the top of the tower in 1957,\n",
+    "                 it is now taller than the Chrysler Building by 5.2 metres (17 ft).\n",
+    "\n",
+    "                 Excluding transmitters, the Eiffel Tower is the second tallest\n",
+    "                 free-standing structure in France after the Millau Viaduct.\n",
+    "                 \"\"\"\n",
+    "    }\n",
+    "]\n",
+    "print(synopsis_chain.apply(test_prompts))\n",
+    "comet_callback.flush_tracker(synopsis_chain, finish=True)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.15"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/ecosystem/databerry.md

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

docs/ecosystem/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 +1,47 @@
+# GPT4All
+
+This page covers how to use the `GPT4All` wrapper within LangChain. The tutorial is divided into two parts: installation and setup, followed by usage with an example.
+
+## Installation and Setup
+- Install the Python package with `pip install pyllamacpp`
+- Download a [GPT4All model](https://github.com/nomic-ai/pyllamacpp#supported-model) and place it in your desired directory
+
+## Usage
+
+### GPT4All
+
+To use the GPT4All wrapper, you need to provide the path to the pre-trained model file and the model's configuration.
+
+```python
+from langchain.llms import GPT4All
+
+# Instantiate the model. Callbacks support token-wise streaming
+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.
+
+To stream the model's predictions, add in a CallbackManager.
+
+```python
+from langchain.llms import GPT4All
+from langchain.callbacks.base import CallbackManager
+from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
+# There are many CallbackHandlers supported, such as
+# from langchain.callbacks.streamlit import StreamlitCallbackHandler
+
+callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
+model = GPT4All(model="./models/gpt4all-model.bin", n_ctx=512, n_threads=8, callback_handler=callback_handler, verbose=True)
+
+# Generate text. Tokens are streamed through the callback manager.
+model("Once upon a time, ")
+```
+
+## Model File
+
+You can find links to model file downloads 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 +1,44 @@
+# Graphsignal
+
+This page covers how to use [Graphsignal](https://app.graphsignal.com) to trace and monitor LangChain. Graphsignal enables full visibility into your application. It provides latency breakdowns by chains and tools, exceptions with full context, data monitoring, compute/GPU utilization, OpenAI cost analytics, and more.
+
+## Installation and Setup
+
+- 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 and metrics are then available in your [Graphsignal dashboards](https://app.graphsignal.com).
+
+Initialize the tracer by providing a deployment name:
+
+```python
+import graphsignal
+
+graphsignal.configure(deployment='my-langchain-app-prod')
+```
+
+To additionally trace any function or code, you can use a decorator or a context manager:
+
+```python
+@graphsignal.trace_function
+def handle_request():    
+    chain.run("some initial text")
+```
+
+```python
+with graphsignal.start_trace('my-chain'):
+    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/runhouse.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/ecosystem/yeagerai.md

@@ -0,0 +1,43 @@
+# Yeager.ai
+
+This page covers how to use [Yeager.ai](https://yeager.ai) to generate LangChain tools and agents.
+
+## What is Yeager.ai?
+Yeager.ai is an ecosystem designed to simplify the process of creating AI agents and tools. 
+
+It features yAgents, a No-code LangChain Agent Builder, which enables users to build, test, and deploy AI solutions with ease. Leveraging the LangChain framework, yAgents allows seamless integration with various language models and resources, making it suitable for developers, researchers, and AI enthusiasts across diverse applications.
+
+## yAgents
+Low code generative agent designed to help you build, prototype, and deploy Langchain tools with ease. 
+
+### How to use?
+```
+pip install yeagerai-agent
+yeagerai-agent
+```
+Go to http://127.0.0.1:7860
+
+This will install the necessary dependencies and set up yAgents on your system. After the first run, yAgents will create a .env file where you can input your OpenAI API key. You can do the same directly from the Gradio interface under the tab "Settings".
+
+`OPENAI_API_KEY=<your_openai_api_key_here>`
+
+We recommend using GPT-4,. However, the tool can also work with GPT-3 if the problem is broken down sufficiently.
+
+### Creating and Executing Tools with yAgents
+yAgents makes it easy to create and execute AI-powered tools. Here's a brief overview of the process:
+1. Create a tool: To create a tool, provide a natural language prompt to yAgents. The prompt should clearly describe the tool's purpose and functionality. For example:
+`create a tool that returns the n-th prime number`
+
+2. Load the tool into the toolkit: To load a tool into yAgents, simply provide a command to yAgents that says so. For example:
+`load the tool that you just created it into your toolkit`
+
+3. Execute the tool: To run a tool or agent, simply provide a command to yAgents that includes the name of the tool and any required parameters. For example:
+`generate the 50th prime number`
+
+You can see a video of how it works [here](https://www.youtube.com/watch?v=KA5hCM3RaWE).
+
+As you become more familiar with yAgents, you can create more advanced tools and agents to automate your work and enhance your productivity.
+
+For more information, see [yAgents' Github](https://github.com/yeagerai/yeagerai-agent) or our [docs](https://yeagerai.gitbook.io/docs/general/welcome-to-yeager.ai) 
+
+

docs/ecosystem/zilliz.md

@@ -0,0 +1,21 @@
+# Zilliz
+
+This page covers how to use the Zilliz Cloud ecosystem within LangChain.
+Zilliz uses the Milvus integration. 
+It is broken into two parts: installation and setup, and then references to specific Milvus wrappers.
+
+## Installation and Setup
+- Install the Python SDK with `pip install pymilvus`
+## Wrappers
+
+### VectorStore
+
+There exists a wrapper around Zilliz indexes, allowing you to use it as a vectorstore,
+whether for semantic search or example selection.
+
+To import this vectorstore:
+```python
+from langchain.vectorstores import Milvus
+```
+
+For a more detailed walkthrough of the Miluvs wrapper, see [this notebook](../modules/indexes/vectorstores/examples/zilliz.ipynb)

docs/examples/agents.rst

@@ -1,11 +0,0 @@
-Agents
-======
-
-The examples here are all end-to-end agents for specific applications.
-
-.. toctree::
-   :maxdepth: 1
-   :glob:
-   :caption: Agents
-
-   agents/*

docs/examples/agents/custom_agent.ipynb

@@ -1,232 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "ba5f8741",
-   "metadata": {},
-   "source": [
-    "# Custom Agent\n",
-    "\n",
-    "This notebook goes through how to create your own custom agent.\n",
-    "\n",
-    "An agent consists of three parts:\n",
-    "    \n",
-    "    - Tools: The tools the agent has available to use.\n",
-    "    - LLMChain: The LLMChain that produces the text that is parsed in a certain way to determine which action to take.\n",
-    "    - The agent class itself: this parses the output of the LLMChain to determin which action to take.\n",
-    "        \n",
-    "        \n",
-    "In this notebook we walk through two types of custom agents. The first type shows how to create a custom LLMChain, but still use an existing agent class to parse the output. The second shows how to create a custom agent class."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "6064f080",
-   "metadata": {},
-   "source": [
-    "### Custom LLMChain\n",
-    "\n",
-    "The first way to create a custom agent is to use an existing Agent class, but use a custom LLMChain. This is the simplest way to create a custom Agent. It is highly reccomended that you work with the `ZeroShotAgent`, as at the moment that is by far the most generalizable one. \n",
-    "\n",
-    "Most of the work in creating the custom LLMChain comes down to the prompt. Because we are using an existing agent class to parse the output, it is very important that the prompt say to produce text in that format. However, besides those instructions, you can customize the prompt as you wish.\n",
-    "\n",
-    "To ensure that the prompt contains the appropriate instructions, we will utilize a helper method on that class. The helper method for the `ZeroShotAgent` takes the following arguments:\n",
-    "\n",
-    "- tools: List of tools the agent will have access to, used to format the prompt.\n",
-    "- prefix: String to put before the list of tools.\n",
-    "- suffix: String to put after the list of tools.\n",
-    "- input_variables: List of input variables the final prompt will expect.\n",
-    "\n",
-    "For this exercise, we will give our agent access to Google Search, and we will customize it in that we will have it answer as a pirate."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "9af9734e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.agents import ZeroShotAgent, Tool\n",
-    "from langchain import OpenAI, SerpAPIChain, LLMChain"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "becda2a1",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "search = SerpAPIChain()\n",
-    "tools = [\n",
-    "    Tool(\n",
-    "        name = \"Search\",\n",
-    "        func=search.run,\n",
-    "        description=\"useful for when you need to answer questions about current events\"\n",
-    "    )\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "339b1bb8",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "prefix = \"\"\"Answer the following questions as best you can, but speaking as a pirate might speak. You have access to the following tools:\"\"\"\n",
-    "suffix = \"\"\"Begin! Remember to speak as a pirate when giving your final answer. Use lots of \"Args\"\n",
-    "\n",
-    "Question: {input}\"\"\"\n",
-    "\n",
-    "prompt = ZeroShotAgent.create_prompt(\n",
-    "    tools, \n",
-    "    prefix=prefix, \n",
-    "    suffix=suffix, \n",
-    "    input_variables=[\"input\"]\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "59db7b58",
-   "metadata": {},
-   "source": [
-    "In case we are curious, we can now take a look at the final prompt template to see what it looks like when its all put together."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "e21d2098",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Answer the following questions as best you can, but speaking as a pirate might speak. You have access to the following tools:\n",
-      "\n",
-      "Search: useful for when you need to answer questions about current events\n",
-      "\n",
-      "Use the following format:\n",
-      "\n",
-      "Question: the input question you must answer\n",
-      "Thought: you should always think about what to do\n",
-      "Action: the action to take, should be one of [Search]\n",
-      "Action Input: the input to the action\n",
-      "Observation: the result of the action\n",
-      "... (this Thought/Action/Action Input/Observation can repeat N times)\n",
-      "Thought: I now know the final answer\n",
-      "Final Answer: the final answer to the original input question\n",
-      "\n",
-      "Begin! Remember to speak as a pirate when giving your final answer. Use lots of \"Args\"\n",
-      "\n",
-      "Question: {input}\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(prompt.template)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "9b1cc2a2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=prompt)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "e4f5092f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "agent = ZeroShotAgent(llm_chain=llm_chain, tools=tools, verbose=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "653b1617",
-   "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 this up\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: Arrr, there be 38,533,678 people in Canada\u001b[0m\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'Arrr, there be 38,533,678 people in Canada'"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "agent.run(\"How many people live in canada?\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "90171b2b",
-   "metadata": {},
-   "source": [
-    "### Custom Agent Class\n",
-    "\n",
-    "Coming soon."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "adefb4c2",
-   "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/agents/mrkl.ipynb

@@ -1,217 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "f1390152",
-   "metadata": {},
-   "source": [
-    "# MRKL\n",
-    "\n",
-    "This notebook showcases using an agent to replicate the MRKL chain."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "39ea3638",
-   "metadata": {},
-   "source": [
-    "This uses the example Chinook database.\n",
-    "To set it up follow the instructions on https://database.guide/2-sample-databases-sqlite/, placing the `.db` file in a notebooks folder at the root of this repository."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "ac561cc4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain import LLMMathChain, OpenAI, SerpAPIChain, SQLDatabase, SQLDatabaseChain\n",
-    "from langchain.agents import initialize_agent, Tool"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "07e96d99",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm = OpenAI(temperature=0)\n",
-    "search = SerpAPIChain()\n",
-    "llm_math_chain = LLMMathChain(llm=llm, verbose=True)\n",
-    "db = SQLDatabase.from_uri(\"sqlite:///../../../notebooks/Chinook.db\")\n",
-    "db_chain = SQLDatabaseChain(llm=llm, database=db, verbose=True)\n",
-    "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",
-    "    Tool(\n",
-    "        name=\"FooBar DB\",\n",
-    "        func=db_chain.run,\n",
-    "        description=\"useful for when you need to answer questions about FooBar. Input should be in the form of a question\"\n",
-    "    )\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "a069c4b6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "mrkl = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "e603cd7d",
-   "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": [
-    "mrkl.run(\"What is the age of Olivia Wilde's boyfriend raised to the 0.23 power?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "a5c07010",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Who recently released an album called 'The Storm Before the Calm' and are they in the FooBar database? If so, what albums of theirs are in the FooBar database?\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I need to find an album called 'The Storm Before the Calm'\n",
-      "Action: Search\n",
-      "Action Input: \"The Storm Before the Calm album\"\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3mThe Storm Before the Calm (stylized in all lowercase) is the tenth (and eighth international) studio album by Canadian-American singer-songwriter Alanis ...\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I need to check if Alanis is in the FooBar database\n",
-      "Action: FooBar DB\n",
-      "Action Input: \"Does Alanis Morissette exist in the FooBar database?\"\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Entering new chain...\u001b[0m\n",
-      "Does Alanis Morissette exist in the FooBar database?\n",
-      "SQLQuery:\u001b[32;1m\u001b[1;3m SELECT * FROM Artist WHERE Name = 'Alanis Morissette'\u001b[0m\n",
-      "SQLResult: \u001b[33;1m\u001b[1;3m[(4, 'Alanis Morissette')]\u001b[0m\n",
-      "Answer:\u001b[32;1m\u001b[1;3m Yes\u001b[0m\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n",
-      "\n",
-      "Observation: \u001b[38;5;200m\u001b[1;3m Yes\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I need to find out what albums of Alanis's are in the FooBar database\n",
-      "Action: FooBar DB\n",
-      "Action Input: \"What albums by Alanis Morissette are in the FooBar database?\"\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Entering new chain...\u001b[0m\n",
-      "What albums by Alanis Morissette are in the FooBar database?\n",
-      "SQLQuery:\u001b[32;1m\u001b[1;3m SELECT Album.Title FROM Album JOIN Artist ON Album.ArtistId = Artist.ArtistId WHERE Artist.Name = 'Alanis Morissette'\u001b[0m\n",
-      "SQLResult: \u001b[33;1m\u001b[1;3m[('Jagged Little Pill',)]\u001b[0m\n",
-      "Answer:\u001b[32;1m\u001b[1;3m Jagged Little Pill\u001b[0m\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n",
-      "\n",
-      "Observation: \u001b[38;5;200m\u001b[1;3m Jagged Little Pill\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
-      "Final Answer: The album is by Alanis Morissette and the albums in the FooBar database by her are Jagged Little Pill\u001b[0m"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'The album is by Alanis Morissette and the albums in the FooBar database by her are Jagged Little Pill'"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "mrkl.run(\"Who recently released an album called 'The Storm Before the Calm' and are they in the FooBar database? If so, what albums of theirs are in the FooBar database?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "d7c2e6ac",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.7.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/examples/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

@@ -1,89 +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": 1,
-   "id": "4e272b47",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain import OpenAI, Wikipedia\n",
-    "from langchain.agents import initialize_agent, Tool\n",
-    "from langchain.agents.react.base import DocstoreExplorer\n",
-    "docstore=DocstoreExplorer(Wikipedia())\n",
-    "tools = [\n",
-    "    Tool(\n",
-    "        name=\"Search\",\n",
-    "        func=docstore.search\n",
-    "    ),\n",
-    "    Tool(\n",
-    "        name=\"Lookup\",\n",
-    "        func=docstore.lookup\n",
-    "    )\n",
-    "]\n",
-    "\n",
-    "llm = OpenAI(temperature=0)\n",
-    "react = initialize_agent(tools, llm, agent=\"react-docstore\", verbose=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "8078c8f1",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "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:"
-     ]
-    }
-   ],
-   "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": "3.7.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/examples/chains.rst

@@ -1,11 +0,0 @@
-Chains
-======
-
-The examples here are all end-to-end chains for specific applications.
-
-.. toctree::
-   :maxdepth: 1
-   :glob:
-   :caption: Chains
-
-   chains/*

docs/examples/chains/llm_chain.ipynb

@@ -1,89 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "d8a5c5d4",
-   "metadata": {},
-   "source": [
-    "# LLM Chain\n",
-    "\n",
-    "This notebook showcases a simple LLM chain."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "51a54c4d",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new chain...\u001b[0m\n",
-      "Prompt after formatting:\n",
-      "\u001b[32;1m\u001b[1;3mQuestion: What NFL team won the Super Bowl in the year Justin Beiber was born?\n",
-      "\n",
-      "Answer: Let's think step by step.\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "' The year Justin Beiber was born was 1994. In 1994, the Dallas Cowboys won the Super Bowl.'"
-      ]
-     },
-     "execution_count": 1,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain import PromptTemplate, OpenAI, LLMChain\n",
-    "\n",
-    "template = \"\"\"Question: {question}\n",
-    "\n",
-    "Answer: Let's think step by step.\"\"\"\n",
-    "prompt = PromptTemplate(template=template, input_variables=[\"question\"])\n",
-    "llm_chain = LLMChain(prompt=prompt, llm=OpenAI(temperature=0), verbose=True)\n",
-    "\n",
-    "question = \"What NFL team won the Super Bowl in the year Justin Beiber was born?\"\n",
-    "\n",
-    "llm_chain.run(question)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "03dd6918",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.7.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

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/map_reduce.ipynb

@@ -1,93 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "d9a0131f",
-   "metadata": {},
-   "source": [
-    "# Map Reduce\n",
-    "\n",
-    "This notebok showcases an example of map-reduce chains: recursive summarization."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "e9db25f3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain import OpenAI, PromptTemplate, LLMChain\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
-    "from langchain.chains.mapreduce import MapReduceChain\n",
-    "\n",
-    "llm = OpenAI(temperature=0)\n",
-    "\n",
-    "_prompt = \"\"\"Write a concise summary of the following:\n",
-    "\n",
-    "\n",
-    "{text}\n",
-    "\n",
-    "\n",
-    "CONCISE SUMMARY:\"\"\"\n",
-    "prompt = PromptTemplate(template=_prompt, input_variables=[\"text\"])\n",
-    "\n",
-    "text_splitter = CharacterTextSplitter()\n",
-    "\n",
-    "mp_chain = MapReduceChain.from_params(llm, prompt, text_splitter)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "99bbe19b",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\"\\n\\nThe President discusses the recent aggression by Russia, and the response by the United States and its allies. He announces new sanctions against Russia, and says that the free world is united in holding Putin accountable. The President also discusses the American Rescue Plan, the Bipartisan Infrastructure Law, and the Bipartisan Innovation Act. Finally, the President addresses the need for women's rights and equality for LGBTQ+ Americans.\""
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "with open('../state_of_the_union.txt') as f:\n",
-    "    state_of_the_union = f.read()\n",
-    "mp_chain.run(state_of_the_union)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "b581501e",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.8.7"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/examples/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/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/huggingface_hub.ipynb

@@ -1,71 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "959300d4",
-   "metadata": {},
-   "source": [
-    "# HuggingFace Hub\n",
-    "\n",
-    "This example showcases how to connect to the HuggingFace Hub."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "3acf0069",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "The Seattle Seahawks won the Super Bowl in 2010. Justin Beiber was born in 2010. The\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain import PromptTemplate, HuggingFaceHub, LLMChain\n",
-    "\n",
-    "template = \"\"\"Question: {question}\n",
-    "\n",
-    "Answer: Let's think step by step.\"\"\"\n",
-    "prompt = PromptTemplate(template=template, input_variables=[\"question\"])\n",
-    "llm_chain = LLMChain(prompt=prompt, llm=HuggingFaceHub(repo_id=\"google/flan-t5-xl\", model_kwargs={\"temperature\":1e-10}))\n",
-    "\n",
-    "question = \"What NFL team won the Super Bowl in the year Justin Beiber was born?\"\n",
-    "\n",
-    "print(llm_chain.run(question))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "ae4559c7",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.8.7"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/examples/integrations/huggingface_tokenizer_text_splitter.ipynb

@@ -1,180 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "b118c9dc",
-   "metadata": {},
-   "source": [
-    "# HuggingFace Tokenizers\n",
-    "\n",
-    "This notebook show cases how to use HuggingFace tokenizers to split text."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "e82c4685",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.text_splitter import CharacterTextSplitter"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "a8ce51d5",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from transformers import GPT2TokenizerFast\n",
-    "\n",
-    "tokenizer = GPT2TokenizerFast.from_pretrained(\"gpt2\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "ca5e72c0",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "with open('../state_of_the_union.txt') as f:\n",
-    "    state_of_the_union = f.read()\n",
-    "text_splitter = CharacterTextSplitter.from_huggingface_tokenizer(tokenizer, chunk_size=1000, chunk_overlap=0)\n",
-    "texts = text_splitter.split_text(state_of_the_union)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "37cdfbeb",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans.  \n",
-      "\n",
-      "Last year COVID-19 kept us apart. This year we are finally together again. \n",
-      "\n",
-      "Tonight, we meet as Democrats Republicans and Independents. But most importantly as Americans. \n",
-      "\n",
-      "With a duty to one another to the American people to the Constitution. \n",
-      "\n",
-      "And with an unwavering resolve that freedom will always triumph over tyranny. \n",
-      "\n",
-      "Six days ago, Russia’s Vladimir Putin sought to shake the foundations of the free world thinking he could make it bend to his menacing ways. But he badly miscalculated. \n",
-      "\n",
-      "He thought he could roll into Ukraine and the world would roll over. Instead he met a wall of strength he never imagined. \n",
-      "\n",
-      "He met the Ukrainian people. \n",
-      "\n",
-      "From President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world. \n",
-      "\n",
-      "Groups of citizens blocking tanks with their bodies. Everyone from students to retirees teachers turned soldiers defending their homeland. \n",
-      "\n",
-      "In this struggle as President Zelenskyy said in his speech to the European Parliament “Light will win over darkness.” The Ukrainian Ambassador to the United States is here tonight. \n",
-      "\n",
-      "Let each of us here tonight in this Chamber send an unmistakable signal to Ukraine and to the world. \n",
-      "\n",
-      "Please rise if you are able and show that, Yes, we the United States of America stand with the Ukrainian people. \n",
-      "\n",
-      "Throughout our history we’ve learned this lesson when dictators do not pay a price for their aggression they cause more chaos.   \n",
-      "\n",
-      "They keep moving.   \n",
-      "\n",
-      "And the costs and the threats to America and the world keep rising.   \n",
-      "\n",
-      "That’s why the NATO Alliance was created to secure peace and stability in Europe after World War 2. \n",
-      "\n",
-      "The United States is a member along with 29 other nations. \n",
-      "\n",
-      "It matters. American diplomacy matters. American resolve matters. \n",
-      "\n",
-      "Putin’s latest attack on Ukraine was premeditated and unprovoked. \n",
-      "\n",
-      "He rejected repeated efforts at diplomacy. \n",
-      "\n",
-      "He thought the West and NATO wouldn’t respond. And he thought he could divide us at home. Putin was wrong. We were ready.  Here is what we did.   \n",
-      "\n",
-      "We prepared extensively and carefully. \n",
-      "\n",
-      "We spent months building a coalition of other freedom-loving nations from Europe and the Americas to Asia and Africa to confront Putin. \n",
-      "\n",
-      "I spent countless hours unifying our European allies. We shared with the world in advance what we knew Putin was planning and precisely how he would try to falsely justify his aggression.  \n",
-      "\n",
-      "We countered Russia’s lies with truth.   \n",
-      "\n",
-      "And now that he has acted the free world is holding him accountable. \n",
-      "\n",
-      "Along with twenty-seven members of the European Union including France, Germany, Italy, as well as countries like the United Kingdom, Canada, Japan, Korea, Australia, New Zealand, and many others, even Switzerland. \n",
-      "\n",
-      "We are inflicting pain on Russia and supporting the people of Ukraine. Putin is now isolated from the world more than ever. \n",
-      "\n",
-      "Together with our allies –we are right now enforcing powerful economic sanctions. \n",
-      "\n",
-      "We are cutting off Russia’s largest banks from the international financial system.  \n",
-      "\n",
-      "Preventing Russia’s central bank from defending the Russian Ruble making Putin’s $630 Billion “war fund” worthless.   \n",
-      "\n",
-      "We are choking off Russia’s access to technology that will sap its economic strength and weaken its military for years to come.  \n",
-      "\n",
-      "Tonight I say to the Russian oligarchs and corrupt leaders who have bilked billions of dollars off this violent regime no more. \n",
-      "\n",
-      "The U.S. Department of Justice is assembling a dedicated task force to go after the crimes of Russian oligarchs.  \n",
-      "\n",
-      "We are joining with our European allies to find and seize your yachts your luxury apartments your private jets. We are coming for your ill-begotten gains. \n",
-      "\n",
-      "And tonight I am announcing that we will join our allies in closing off American air space to all Russian flights – further isolating Russia – and adding an additional squeeze –on their economy. The Ruble has lost 30% of its value. \n",
-      "\n",
-      "The Russian stock market has lost 40% of its value and trading remains suspended. Russia’s economy is reeling and Putin alone is to blame. \n",
-      "\n",
-      "Together with our allies we are providing support to the Ukrainians in their fight for freedom. Military assistance. Economic assistance. Humanitarian assistance. \n",
-      "\n",
-      "We are giving more than $1 Billion in direct assistance to Ukraine. \n",
-      "\n",
-      "And we will continue to aid the Ukrainian people as they defend their country and to help ease their suffering.  \n",
-      "\n",
-      "Let me be clear, our forces are not engaged and will not engage in conflict with Russian forces in Ukraine.  \n",
-      "\n",
-      "Our forces are not going to Europe to fight in Ukraine, but to defend our NATO Allies – in the event that Putin decides to keep moving west.  \n"
-     ]
-    }
-   ],
-   "source": [
-    "print(texts[0])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "d214aec2",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.7.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/examples/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, SerpAPIChain, LLMChain"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "97ad8467",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "search = SerpAPIChain()\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

@@ -1,10 +0,0 @@
-Prompts
-=======
-
-The examples here all highlight how to work with prompts.
-
-.. toctree::
-   :maxdepth: 1
-   :glob:
-
-   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/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/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 +1,346 @@
+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://anysummary.app
+        :type: url
+        :text: Summarize any file with AI
+        :classes: stretched-link btn-lg
+
+    +++
+
+    Summarize not only long docs, interview audio or video files quickly, but also entire websites and YouTube videos. Share or download your generated summaries to collaborate with others, or revisit them at any time! Bonus: `@anysummary <https://twitter.com/anysummary>`_ on Twitter will also summarize any thread it is tagged in.
+    
+    ---
+
+    .. 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, SerpAPIChain\n",
-    "llm = OpenAI(temperature=0)\n",
-    "search = SerpAPIChain()\n",
-    "llm_math_chain = LLMMathChain(llm=llm, verbose=True)\n",
-    "tools = [\n",
-    "    Tool(\n",
-    "        name = \"Search\",\n",
-    "        func=search.run,\n",
-    "        description=\"useful for when you need to answer questions about current events\"\n",
-    "    ),\n",
-    "    Tool(\n",
-    "        name=\"Calculator\",\n",
-    "        func=llm_math_chain.run,\n",
-    "        description=\"useful for when you need to answer questions about math\"\n",
-    "    )\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "5b93047d",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Construct the 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(\"What is the age of Olivia Wilde's boyfriend raised to the 0.23 power?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "2f0852ff",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.7.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/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 +1,494 @@
+# 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
+# or
+conda install langchain -c conda-forge
+```
+
+
+## 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.
+
+
+
+## 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).
+
+
+## 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)
+
+
+
+
+## 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)
+
+## 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.
+```
+
+
+
+## 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)
+
+output = conversation.predict(input="Hi there!")
+print(output)
+```
+
+```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
+output = conversation.predict(input="I'm doing well! Just having a conversation with an AI.")
+print(output)
+```
+
+```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.
+
+## 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}
+```
+
+
+## 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={})
+```
+
+## 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."
+```
+
+## 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'
+```
+## 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 can 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.