add interface for evaluating messages

.devcontainer/README.md

@@ -5,21 +5,17 @@ This project includes a [dev container](https://containers.dev/), which lets you
 You can use the dev container configuration in this folder to build and run the app without needing to install any of its tools locally! You can use it in [GitHub Codespaces](https://github.com/features/codespaces) or the [VS Code Dev Containers extension](https://marketplace.visualstudio.com/items?itemName=ms-vscode-remote.remote-containers).
 
 ## GitHub Codespaces
-[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/langchain-ai/langchain)
+[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/hwchase17/langchain)
 
 You may use the button above, or follow these steps to open this repo in a Codespace:
-1. Click the **Code** drop-down menu at the top of https://github.com/langchain-ai/langchain.
+1. Click the **Code** drop-down menu at the top of https://github.com/hwchase17/langchain.
 1. Click on the **Codespaces** tab.
 1. Click **Create codespace on master** .
 
 For more info, check out the [GitHub documentation](https://docs.github.com/en/free-pro-team@latest/github/developing-online-with-codespaces/creating-a-codespace#creating-a-codespace).
   
 ## VS Code Dev Containers
-[![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchain)
-
-Note: If you click this link you will open the main repo and not your local cloned repo, you can use this link and replace with your username and cloned repo name: 
-https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/<yourusername>/<yourclonedreponame>
-
+[![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/hwchase17/langchain)
 
 If you already have VS Code and Docker installed, you can use the button above to get started. This will cause VS Code to automatically install the Dev Containers extension if needed, clone the source code into a container volume, and spin up a dev container for use.
 
@@ -29,7 +25,7 @@ You can also follow these steps to open this repo in a container using the VS Co
 
 2. Open a locally cloned copy of the code:
 
-   - Fork and Clone this repository to your local filesystem.
+   - Clone this repository to your local filesystem.
    - Press <kbd>F1</kbd> and select the **Dev Containers: Open Folder in Container...** command.
    - Select the cloned copy of this folder, wait for the container to start, and try things out!
 

.devcontainer/docker-compose.yaml

@@ -2,7 +2,7 @@ version: '3'
 services:
   langchain:
     build:
-      dockerfile: libs/langchain/dev.Dockerfile
+      dockerfile: dev.Dockerfile
       context: ..
     volumes:
    # Update this to wherever you want VS Code to mount the folder of your project

.github/CONTRIBUTING.md

@@ -9,19 +9,19 @@ to contributions, whether they be in the form of new features, improved infra, b
 ### 👩‍💻 Contributing Code
 
 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 a maintainer.
+Please do not try to push directly to this repo unless you are maintainer.
 
 Please follow the checked-in pull request template when opening pull requests. Note related issues and tag relevant
 maintainers.
 
-Pull requests cannot land without passing the formatting, linting and testing checks first. See [Testing](#testing) and
-[Formatting and Linting](#formatting-and-linting) for how to run these checks locally.
+Pull requests cannot land without passing the formatting, linting and testing checks first. See
+[Common Tasks](#-common-tasks) for how to run these checks locally.
 
 It's essential that we maintain great documentation and testing. If you:
 - Fix a bug
   - Add a relevant unit or integration test when possible. These live in `tests/unit_tests` and `tests/integration_tests`.
 - Make an improvement
-  - Update any affected example notebooks and documentation. These live in `docs`.
+  - Update any affected example notebooks and documentation. These lives in `docs`.
   - Update unit and integration tests when relevant.
 - Add a feature
   - Add a demo notebook in `docs/modules`.
@@ -32,8 +32,8 @@ best way to get our attention.
 
 ### 🚩GitHub Issues
 
-Our [issues](https://github.com/langchain-ai/langchain/issues) page is kept up to date
-with bugs, improvements, and feature requests.
+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. Please use these to help
 organize issues.
@@ -43,8 +43,8 @@ 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 two issues are related, or blocking, please link them rather than combining them.
 
-We will try to keep these issues as up-to-date as possible, though
-with the rapid rate of development in this field some may get out of date.
+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 let us know.
 
 ### 🙋Getting Help
@@ -59,63 +59,96 @@ we do not want these to get in the way of getting good code into the codebase.
 
 ## 🚀 Quick Start
 
-This quick start describes running the repository locally.
-For a [development container](https://containers.dev/), see the [.devcontainer folder](https://github.com/langchain-ai/langchain/tree/master/.devcontainer).
+> **Note:** You can run this repository locally (which is described below) or in a [development container](https://containers.dev/) (which is described in the [.devcontainer folder](https://github.com/hwchase17/langchain/tree/master/.devcontainer)).
 
-### Dependency Management: Poetry and other env/dependency managers
+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.
 
-This project uses [Poetry](https://python-poetry.org/) v1.6.1+ as a dependency manager.
+❗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.
 
-❗Note: *Before installing Poetry*, if you use `Conda`, create and activate a new Conda env (e.g. `conda create -n langchain python=3.9`)
-
-Install Poetry: **[documentation on how to install it](https://python-poetry.org/docs/#installation)**.
-
-❗Note: If you use `Conda` or `Pyenv` as your environment/package manager, after installing Poetry,
-tell Poetry to use the virtualenv python environment (`poetry config virtualenvs.prefer-active-python true`)
-
-### Core vs. Experimental
-
-There are two separate projects in this repository:
-- `langchain`: core langchain code, abstractions, and use cases
-- `langchain.experimental`: see the [Experimental README](../libs/experimental/README.md) for more information.
-
-Each of these has their own development environment. Docs are run from the top-level makefile, but development
-is split across separate test & release flows.
-
-For this quickstart, start with langchain core:
+To install requirements:
 
 ```bash
-cd libs/langchain
+poetry install -E all
 ```
 
-### Local Development Dependencies
+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.
 
-Install langchain development requirements (for running langchain, running examples, linting, formatting, tests, and coverage):
+❗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
-poetry install --with test
+make format
 ```
 
-Then verify dependency installation:
+### 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 test
+make lint
 ```
 
-If the tests don't pass, you may need to pip install additional dependencies, such as `numexpr` and `openapi_schema_pydantic`.
+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.
 
-If during installation you receive a `WheelFileValidationError` for `debugpy`, please make sure you are running
-Poetry v1.6.1+. This bug was present in older versions of Poetry (e.g. 1.4.1) and has been resolved in newer releases.
-If you are still seeing this bug on v1.6.1, you may also try disabling "modern installation"
-(`poetry config installer.modern-installation false`) and re-installing requirements.
-See [this `debugpy` issue](https://github.com/microsoft/debugpy/issues/1246) for more details.
+### 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
+```
+
+### Working with Optional Dependencies
+
+Langchain relies heavily on optional dependencies to keep the Langchain package lightweight.
+
+If you're adding a new dependency to Langchain, assume that it will be an optional dependency, and
+that most users won't have it installed.
+
+Users that do not have the dependency installed should be able to **import** your code without
+any side effects (no warnings, no errors, no exceptions). 
+
+To introduce the dependency to the pyproject.toml file correctly, please do the following: 
+
+1. Add the dependency to the main group as an optional dependency
+  ```bash
+  poetry add --optional [package_name]
+  ```
+2. Open pyproject.toml and add the dependency to the `extended_testing` extra
+3. Relock the poetry file to update the extra.
+  ```bash
+  poetry lock --no-update
+  ```
+4. Add a unit test that the very least attempts to import the new code. Ideally the unit
+test makes use of lightweight fixtures to test the logic of the code.
+5. Please use the `@pytest.mark.requires(package_name)` decorator for any tests that require the dependency.
 
 ### Testing
 
-_some test dependencies are optional; see section about optional dependencies_.
+See section about optional dependencies.
+
+#### Unit Tests
 
 Unit tests cover modular logic that does not require calls to outside APIs.
-If you add new logic, please add a unit test.
 
 To run unit tests:
 
@@ -129,104 +162,33 @@ To run unit tests in Docker:
 make docker_tests
 ```
 
-There are also [integration tests and code-coverage](../libs/langchain/tests/README.md) available.
+If you add new logic, please add a unit test.
 
-### Formatting and Linting
 
-Run these locally before submitting a PR; the CI system will check also.
 
-#### Code Formatting
+#### Integration Tests
 
-Formatting for this project is done via a combination of [Black](https://black.readthedocs.io/en/stable/) and [ruff](https://docs.astral.sh/ruff/rules/).
+Integration tests cover logic that requires making calls to outside APIs (often integration with other services).
 
-To run formatting for this project:
+**warning** Almost no tests should be integration tests. 
+
+  Tests that require making network connections make it difficult for other
+  developers to test the code.
+
+  Instead favor relying on `responses` library and/or mock.patch to mock
+  requests using small fixtures.
+
+To run integration tests:
 
 ```bash
-make format
+make integration_tests
 ```
 
-Additionally, you can run the formatter only on the files that have been modified in your current branch as compared to the master branch using the format_diff command:
+If you add support for a new external API, please add a new integration test.
 
-```bash
-make format_diff
-```
+### Adding a Jupyter Notebook
 
-This is especially useful when you have made changes to a subset of the project and want to ensure your changes are properly formatted without affecting the rest of the codebase.
-
-#### Linting
-
-Linting for this project is done via a combination of [Black](https://black.readthedocs.io/en/stable/), [ruff](https://docs.astral.sh/ruff/rules/), and [mypy](http://mypy-lang.org/).
-
-To run linting for this project:
-
-```bash
-make lint
-```
-
-In addition, you can run the linter only on the files that have been modified in your current branch as compared to the master branch using the lint_diff command:
-
-```bash
-make lint_diff
-```
-
-This can be very helpful when you've made changes to only certain parts of the project and want to ensure your changes meet the linting standards without having to check the entire codebase.
-
-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.
-
-#### Spellcheck
-
-Spellchecking for this project is done via [codespell](https://github.com/codespell-project/codespell).
-Note that `codespell` finds common typos, so it could have false-positive (correctly spelled but rarely used) and false-negatives (not finding misspelled) words.
-
-To check spelling for this project:
-
-```bash
-make spell_check
-```
-
-To fix spelling in place:
-
-```bash
-make spell_fix
-```
-
-If codespell is incorrectly flagging a word, you can skip spellcheck for that word by adding it to the codespell config in the `pyproject.toml` file.
-
-```python
-[tool.codespell]
-...
-# Add here:
-ignore-words-list = 'momento,collison,ned,foor,reworkd,parth,whats,aapply,mysogyny,unsecure'
-```
-
-## Working with Optional Dependencies
-
-Langchain relies heavily on optional dependencies to keep the Langchain package lightweight.
-
-If you're adding a new dependency to Langchain, assume that it will be an optional dependency, and
-that most users won't have it installed.
-
-Users who do not have the dependency installed should be able to **import** your code without
-any side effects (no warnings, no errors, no exceptions).
-
-To introduce the dependency to the pyproject.toml file correctly, please do the following:
-
-1. Add the dependency to the main group as an optional dependency
-  ```bash
-  poetry add --optional [package_name]
-  ```
-2. Open pyproject.toml and add the dependency to the `extended_testing` extra
-3. Relock the poetry file to update the extra.
-  ```bash
-  poetry lock --no-update
-  ```
-4. Add a unit test that the very least attempts to import the new code. Ideally, the unit
-test makes use of lightweight fixtures to test the logic of the code.
-5. Please use the `@pytest.mark.requires(package_name)` decorator for any tests that require the dependency.
-
-## Adding a Jupyter Notebook
-
-If you are adding a Jupyter Notebook example, you'll want to install the optional `dev` dependencies.
+If you are adding a Jupyter notebook example, you'll want to install the optional `dev` dependencies.
 
 To install dev dependencies:
 
@@ -244,57 +206,33 @@ When you run `poetry install`, the `langchain` package is installed as editable
 
 ## Documentation
 
-While the code is split between `langchain` and `langchain.experimental`, the documentation is one holistic thing.
-This covers how to get started contributing to documentation.
-
-From the top-level of this repo, install documentation dependencies:
-
-```bash
-poetry install
-```
-
 ### Contribute Documentation
 
-The docs directory contains Documentation and API Reference.
+Docs are largely autogenerated by [sphinx](https://www.sphinx-doc.org/en/master/) from the code.
 
-Documentation is built using [Docusaurus 2](https://docusaurus.io/).
-
-API Reference 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
 
-In the following commands, the prefix `api_` indicates that those are operations for the API Reference.
-
 Before building the documentation, it is always a good idea to clean the build directory:
 
 ```bash
 make docs_clean
-make api_docs_clean
 ```
 
-Next, you can build the documentation as outlined below:
-
-```bash
-make docs_build
-make api_docs_build
-```
-
-Finally, you can run the linkchecker to make sure all links are valid:
+Next, you can run the linkchecker to make sure all links are valid:
 
 ```bash
 make docs_linkcheck
-make api_docs_linkcheck
 ```
 
-### Verify Documentation changes
+Finally, you can build the documentation as outlined below:
 
-After pushing documentation changes to the repository, you can preview and verify that the changes are 
-what you wanted by clicking the `View deployment` or `Visit Preview` buttons on the pull request `Conversation` page. 
-This will take you to a preview of the documentation changes.
-This preview is created by [Vercel](https://vercel.com/docs/getting-started-with-vercel).
+```bash
+make docs_build
+```
 
 ## 🏭 Release Process
 
@@ -308,3 +246,4 @@ even patch releases may contain [non-backwards-compatible changes](https://semve
 
 If your contribution has made its way into a release, we will want to give you credit on Twitter (only if you want though)!
 If you have a Twitter account you would like us to mention, please let us know in the PR or in another manner.
+

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -1,5 +1,5 @@
 name: "\U0001F41B Bug Report"
-description: Submit a bug report to help us improve LangChain. To report a security issue, please instead use the security option below.
+description: Submit a bug report to help us improve LangChain
 labels: ["02 Bug Report"]
 body:
   - type: markdown

.github/ISSUE_TEMPLATE/feature-request.yml

@@ -27,4 +27,4 @@ body:
     attributes:
       label: Your contribution
       description: |
-        Is there any way that you could help, e.g. by submitting a PR? Make sure to read the CONTRIBUTING.MD [readme](https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md)
+        Is there any way that you could help, e.g. by submitting a PR? Make sure to read the CONTRIBUTING.MD [readme](https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md)

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,20 +1,26 @@
 <!-- Thank you for contributing to LangChain!
 
-Replace this entire comment with:
-  - **Description:** a description of the change, 
-  - **Issue:** the issue # it fixes (if applicable),
-  - **Dependencies:** any dependencies required for this change,
-  - **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below),
-  - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out!
-
-Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally.
-
-See contribution guidelines for more information on how to write/run tests, lint, etc: 
-https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md
+Replace this comment with:
+  - Description: a description of the change, 
+  - Issue: the issue # it fixes (if applicable),
+  - Dependencies: any dependencies required for this change,
+  - Tag maintainer: for a quicker response, tag the relevant maintainer (see below),
+  - Twitter handle: we announce bigger features on Twitter. If your PR gets announced and you'd like a mention, we'll gladly shout you out!
 
 If you're adding a new integration, please include:
   1. a test for the integration, preferably unit tests that do not rely on network access,
-  2. an example notebook showing its use. It lives in `docs/extras` directory.
+  2. an example notebook showing its use.
 
-If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17.
+Maintainer responsibilities:
+  - General / Misc / if you don't know who to tag: @baskaryan
+  - DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
+  - Models / Prompts: @hwchase17, @baskaryan
+  - Memory: @hwchase17
+  - Agents / Tools / Toolkits: @hinthornw
+  - Tracing / Callbacks: @agola11
+  - Async: @agola11
+
+If no one reviews your PR within a few days, feel free to @-mention the same people again.
+
+See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
  -->

.github/actions/poetry_setup/action.yml

@@ -15,77 +15,62 @@ inputs:
     description: Poetry version
     required: true
 
+  install-command:
+    description: Command run for installing dependencies
+    required: false
+    default: poetry install
+
   cache-key:
     description: Cache key to use for manual handling of caching
     required: true
 
   working-directory:
-    description: Directory whose poetry.lock file should be cached
-    required: true
+    description: Directory to run install-command in
+    required: false
+    default: ""
 
 runs:
   using: composite
   steps:
     - uses: actions/setup-python@v4
-      name: Setup python ${{ inputs.python-version }}
+      name: Setup python $${ inputs.python-version }}
       with:
         python-version: ${{ inputs.python-version }}
 
     - uses: actions/cache@v3
-      id: cache-bin-poetry
-      name: Cache Poetry binary - Python ${{ inputs.python-version }}
+      id: cache-pip
+      name: Cache Pip ${{ inputs.python-version }}
       env:
-        SEGMENT_DOWNLOAD_TIMEOUT_MIN: "1"
-      with:
-        path: |
-          /opt/pipx/venvs/poetry
-        # This step caches the poetry installation, so make sure it's keyed on the poetry version as well.
-        key: bin-poetry-${{ runner.os }}-${{ runner.arch }}-py-${{ inputs.python-version }}-${{ inputs.poetry-version }}
-
-    - name: Refresh shell hashtable and fixup softlinks
-      if: steps.cache-bin-poetry.outputs.cache-hit == 'true'
-      shell: bash
-      env:
-        POETRY_VERSION: ${{ inputs.poetry-version }}
-        PYTHON_VERSION: ${{ inputs.python-version }}
-      run: |
-        set -eux
-
-        # Refresh the shell hashtable, to ensure correct `which` output.
-        hash -r
-
-        # `actions/cache@v3` doesn't always seem able to correctly unpack softlinks.
-        # Delete and recreate the softlinks pipx expects to have.
-        rm /opt/pipx/venvs/poetry/bin/python
-        cd /opt/pipx/venvs/poetry/bin
-        ln -s "$(which "python$PYTHON_VERSION")" python
-        chmod +x python
-        cd /opt/pipx_bin/
-        ln -s /opt/pipx/venvs/poetry/bin/poetry poetry
-        chmod +x poetry
-
-        # Ensure everything got set up correctly.
-        /opt/pipx/venvs/poetry/bin/python --version
-        /opt/pipx_bin/poetry --version
-
-    - name: Install poetry
-      if: steps.cache-bin-poetry.outputs.cache-hit != 'true'
-      shell: bash
-      env:
-        POETRY_VERSION: ${{ inputs.poetry-version }}
-        PYTHON_VERSION: ${{ inputs.python-version }}
-      run: pipx install "poetry==$POETRY_VERSION" --python "python$PYTHON_VERSION" --verbose
-
-    - name: Restore pip and poetry cached dependencies
-      uses: actions/cache@v3
-      env:
-        SEGMENT_DOWNLOAD_TIMEOUT_MIN: "4"
-        WORKDIR: ${{ inputs.working-directory == '' && '.' || inputs.working-directory }}
+        SEGMENT_DOWNLOAD_TIMEOUT_MIN: "15"
       with:
         path: |
           ~/.cache/pip
+        key: pip-${{ runner.os }}-${{ runner.arch }}-py-${{ inputs.python-version }}
+
+    - run: pipx install poetry==${{ inputs.poetry-version }} --python python${{ inputs.python-version }}
+      shell: bash
+
+    - name: Check Poetry File
+      shell: bash
+      run: |
+        poetry check
+
+    - name: Check lock file
+      shell: bash
+      run: |
+        poetry lock --check
+
+    - uses: actions/cache@v3
+      id: cache-poetry
+      env:
+        SEGMENT_DOWNLOAD_TIMEOUT_MIN: "15"
+      with:
+        path: |
           ~/.cache/pypoetry/virtualenvs
           ~/.cache/pypoetry/cache
           ~/.cache/pypoetry/artifacts
-          ${{ env.WORKDIR }}/.venv
-        key: py-deps-${{ runner.os }}-${{ runner.arch }}-py-${{ inputs.python-version }}-poetry-${{ inputs.poetry-version }}-${{ inputs.cache-key }}-${{ hashFiles(format('{0}/**/poetry.lock', env.WORKDIR)) }}
+        key: poetry-${{ runner.os }}-${{ runner.arch }}-py-${{ inputs.python-version }}-poetry-${{ inputs.poetry-version }}-${{ inputs.cache-key }}-${{ hashFiles('poetry.lock') }}
+
+    - run: ${{ inputs.install-command }}
+      working-directory: ${{ inputs.working-directory }}
+      shell: bash

.github/tools/git-restore-mtime

@@ -1,606 +0,0 @@
-#!/usr/bin/env python3
-#
-# git-restore-mtime - Change mtime of files based on commit date of last change
-#
-#    Copyright (C) 2012 Rodrigo Silva (MestreLion) <linux@rodrigosilva.com>
-#
-#    This program is free software: you can redistribute it and/or modify
-#    it under the terms of the GNU General Public License as published by
-#    the Free Software Foundation, either version 3 of the License, or
-#    (at your option) any later version.
-#
-#    This program is distributed in the hope that it will be useful,
-#    but WITHOUT ANY WARRANTY; without even the implied warranty of
-#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-#    GNU General Public License for more details.
-#
-#    You should have received a copy of the GNU General Public License
-#    along with this program. See <http://www.gnu.org/licenses/gpl.html>
-#
-# Source: https://github.com/MestreLion/git-tools
-# Version: July 13, 2023 (commit hash 5f832e72453e035fccae9d63a5056918d64476a2)
-"""
-Change the modification time (mtime) of files in work tree, based on the
-date of the most recent commit that modified the file, including renames.
-
-Ignores untracked files and uncommitted deletions, additions and renames, and
-by default modifications too.
----
-Useful prior to generating release tarballs, so each file is archived with a
-date that is similar to the date when the file was actually last modified,
-assuming the actual modification date and its commit date are close.
-"""
-
-# TODO:
-# - Add -z on git whatchanged/ls-files, so we don't deal with filename decoding
-# - When Python is bumped to 3.7, use text instead of universal_newlines on subprocess
-# - Update "Statistics for some large projects" with modern hardware and repositories.
-# - Create a README.md for git-restore-mtime alone. It deserves extensive documentation
-#   - Move Statistics there
-# - See git-extras as a good example on project structure and documentation
-
-# FIXME:
-# - When current dir is outside the worktree, e.g. using --work-tree, `git ls-files`
-#   assume any relative pathspecs are to worktree root, not the current dir. As such,
-#   relative pathspecs may not work.
-# - Renames are tricky:
-#   - R100 should not change mtime, but original name is not on filelist. Should
-#     track renames until a valid (A, M) mtime found and then set on current name.
-#   - Should set mtime for both current and original directories.
-#   - Check mode changes with unchanged blobs?
-# - Check file (A, D) for the directory mtime is not sufficient:
-#   - Renames also change dir mtime, unless rename was on a parent dir
-#   - If most recent change of all files in a dir was a Modification (M),
-#     dir might not be touched at all.
-#   - Dirs containing only subdirectories but no direct files will also
-#     not be touched. They're files' [grand]parent dir, but never their dirname().
-#   - Some solutions:
-#     - After files done, perform some dir processing for missing dirs, finding latest
-#       file (A, D, R)
-#     - Simple approach: dir mtime is the most recent child (dir or file) mtime
-#     - Use a virtual concept of "created at most at" to fill missing info, bubble up
-#       to parents and grandparents
-#   - When handling [grand]parent dirs, stay inside <pathspec>
-# - Better handling of merge commits. `-m` is plain *wrong*. `-c/--cc` is perfect, but
-#   painfully slow. First pass without merge commits is not accurate. Maybe add a new
-#   `--accurate` mode for `--cc`?
-
-if __name__ != "__main__":
-    raise ImportError("{} should not be used as a module.".format(__name__))
-
-import argparse
-import datetime
-import logging
-import os.path
-import shlex
-import signal
-import subprocess
-import sys
-import time
-
-__version__ = "2022.12+dev"
-
-# Update symlinks only if the platform supports not following them
-UPDATE_SYMLINKS = bool(os.utime in getattr(os, 'supports_follow_symlinks', []))
-
-# Call os.path.normpath() only if not in a POSIX platform (Windows)
-NORMALIZE_PATHS = (os.path.sep != '/')
-
-# How many files to process in each batch when re-trying merge commits
-STEPMISSING = 100
-
-# (Extra) keywords for the os.utime() call performed by touch()
-UTIME_KWS = {} if not UPDATE_SYMLINKS else {'follow_symlinks': False}
-
-
-# Command-line interface ######################################################
-
-def parse_args():
-    parser = argparse.ArgumentParser(
-        description=__doc__.split('\n---')[0])
-
-    group = parser.add_mutually_exclusive_group()
-    group.add_argument('--quiet', '-q', dest='loglevel',
-        action="store_const", const=logging.WARNING, default=logging.INFO,
-        help="Suppress informative messages and summary statistics.")
-    group.add_argument('--verbose', '-v', action="count", help="""
-        Print additional information for each processed file.
-        Specify twice to further increase verbosity.
-        """)
-
-    parser.add_argument('--cwd', '-C', metavar="DIRECTORY", help="""
-        Run as if %(prog)s was started in directory %(metavar)s.
-        This affects how --work-tree, --git-dir and PATHSPEC arguments are handled.
-        See 'man 1 git' or 'git --help' for more information.
-        """)
-
-    parser.add_argument('--git-dir', dest='gitdir', metavar="GITDIR", help="""
-        Path to the git repository, by default auto-discovered by searching
-        the current directory and its parents for a .git/ subdirectory.
-        """)
-
-    parser.add_argument('--work-tree', dest='workdir', metavar="WORKTREE", help="""
-        Path to the work tree root, by default the parent of GITDIR if it's
-        automatically discovered, or the current directory if GITDIR is set.
-        """)
-
-    parser.add_argument('--force', '-f', default=False, action="store_true", help="""
-        Force updating files with uncommitted modifications.
-        Untracked files and uncommitted deletions, renames and additions are
-        always ignored.
-        """)
-
-    parser.add_argument('--merge', '-m', default=False, action="store_true", help="""
-        Include merge commits.
-        Leads to more recent times and more files per commit, thus with the same
-        time, which may or may not be what you want.
-        Including merge commits may lead to fewer commits being evaluated as files
-        are found sooner, which can improve performance, sometimes substantially.
-        But as merge commits are usually huge, processing them may also take longer.
-        By default, merge commits are only used for files missing from regular commits.
-        """)
-
-    parser.add_argument('--first-parent', default=False, action="store_true", help="""
-        Consider only the first parent, the "main branch", when evaluating merge commits.
-        Only effective when merge commits are processed, either when --merge is
-        used or when finding missing files after the first regular log search.
-        See --skip-missing.
-        """)
-
-    parser.add_argument('--skip-missing', '-s', dest="missing", default=True,
-        action="store_false", help="""
-        Do not try to find missing files.
-        If merge commits were not evaluated with --merge and some files were
-        not found in regular commits, by default %(prog)s searches for these
-        files again in the merge commits.
-        This option disables this retry, so files found only in merge commits
-        will not have their timestamp updated.
-        """)
-
-    parser.add_argument('--no-directories', '-D', dest='dirs', default=True,
-        action="store_false", help="""
-        Do not update directory timestamps.
-        By default, use the time of its most recently created, renamed or deleted file.
-        Note that just modifying a file will NOT update its directory time.
-        """)
-
-    parser.add_argument('--test', '-t', default=False, action="store_true",
-        help="Test run: do not actually update any file timestamp.")
-
-    parser.add_argument('--commit-time', '-c', dest='commit_time', default=False,
-        action='store_true', help="Use commit time instead of author time.")
-
-    parser.add_argument('--oldest-time', '-o', dest='reverse_order', default=False,
-        action='store_true', help="""
-        Update times based on the oldest, instead of the most recent commit of a file.
-        This reverses the order in which the git log is processed to emulate a
-        file "creation" date. Note this will be inaccurate for files deleted and
-        re-created at later dates.
-        """)
-
-    parser.add_argument('--skip-older-than', metavar='SECONDS', type=int, help="""
-        Ignore files that are currently older than %(metavar)s.
-        Useful in workflows that assume such files already have a correct timestamp,
-        as it may improve performance by processing fewer files.
-        """)
-
-    parser.add_argument('--skip-older-than-commit', '-N', default=False,
-        action='store_true', help="""
-        Ignore files older than the timestamp it would be updated to.
-        Such files may be considered "original", likely in the author's repository.
-        """)
-
-    parser.add_argument('--unique-times', default=False, action="store_true", help="""
-        Set the microseconds to a unique value per commit.
-        Allows telling apart changes that would otherwise have identical timestamps,
-        as git's time accuracy is in seconds.
-        """)
-
-    parser.add_argument('pathspec', nargs='*', metavar='PATHSPEC', help="""
-        Only modify paths matching %(metavar)s, relative to current directory.
-        By default, update all but untracked files and submodules.
-        """)
-
-    parser.add_argument('--version', '-V', action='version',
-        version='%(prog)s version {version}'.format(version=get_version()))
-
-    args_ = parser.parse_args()
-    if args_.verbose:
-        args_.loglevel = max(logging.TRACE, logging.DEBUG // args_.verbose)
-    args_.debug = args_.loglevel <= logging.DEBUG
-    return args_
-
-
-def get_version(version=__version__):
-    if not version.endswith('+dev'):
-        return version
-    try:
-        cwd = os.path.dirname(os.path.realpath(__file__))
-        return Git(cwd=cwd, errors=False).describe().lstrip('v')
-    except Git.Error:
-        return '-'.join((version, "unknown"))
-
-
-# Helper functions ############################################################
-
-def setup_logging():
-    """Add TRACE logging level and corresponding method, return the root logger"""
-    logging.TRACE = TRACE = logging.DEBUG // 2
-    logging.Logger.trace = lambda _, m, *a, **k: _.log(TRACE, m, *a, **k)
-    return logging.getLogger()
-
-
-def normalize(path):
-    r"""Normalize paths from git, handling non-ASCII characters.
-
-    Git stores paths as UTF-8 normalization form C.
-    If path contains non-ASCII or non-printable characters, git outputs the UTF-8
-    in octal-escaped notation, escaping double-quotes and backslashes, and then
-    double-quoting the whole path.
-    https://git-scm.com/docs/git-config#Documentation/git-config.txt-corequotePath
-
-    This function reverts this encoding, so:
-    normalize(r'"Back\\slash_double\"quote_a\303\247a\303\255"') =>
-        r'Back\slash_double"quote_açaí')
-
-    Paths with invalid UTF-8 encoding, such as single 0x80-0xFF bytes (e.g, from
-    Latin1/Windows-1251 encoding) are decoded using surrogate escape, the same
-    method used by Python for filesystem paths. So 0xE6 ("æ" in Latin1, r'\\346'
-    from Git) is decoded as "\udce6". See https://peps.python.org/pep-0383/ and
-    https://vstinner.github.io/painful-history-python-filesystem-encoding.html
-
-    Also see notes on `windows/non-ascii-paths.txt` about path encodings on
-    non-UTF-8 platforms and filesystems.
-    """
-    if path and path[0] == '"':
-        # Python 2: path = path[1:-1].decode("string-escape")
-        # Python 3: https://stackoverflow.com/a/46650050/624066
-        path = (path[1:-1]                 # Remove enclosing double quotes
-                .encode('latin1')          # Convert to bytes, required by 'unicode-escape'
-                .decode('unicode-escape')  # Perform the actual octal-escaping decode
-                .encode('latin1')          # 1:1 mapping to bytes, UTF-8 encoded
-                .decode('utf8', 'surrogateescape'))  # Decode from UTF-8
-    if NORMALIZE_PATHS:
-        # Make sure the slash matches the OS; for Windows we need a backslash
-        path = os.path.normpath(path)
-    return path
-
-
-def dummy(*_args, **_kwargs):
-    """No-op function used in dry-run tests"""
-
-
-def touch(path, mtime):
-    """The actual mtime update"""
-    os.utime(path, (mtime, mtime), **UTIME_KWS)
-
-
-def touch_ns(path, mtime_ns):
-    """The actual mtime update, using nanoseconds for unique timestamps"""
-    os.utime(path, None, ns=(mtime_ns, mtime_ns), **UTIME_KWS)
-
-
-def isodate(secs: int):
-    # time.localtime() accepts floats, but discards fractional part
-    return time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(secs))
-
-
-def isodate_ns(ns: int):
-    # for integers fromtimestamp() is equivalent and ~16% slower than isodate()
-    return datetime.datetime.fromtimestamp(ns / 1000000000).isoformat(sep=' ')
-
-
-def get_mtime_ns(secs: int, idx: int):
-    # Time resolution for filesystems and functions:
-    # ext-4 and other POSIX filesystems: 1 nanosecond
-    # NTFS (Windows default): 100 nanoseconds
-    # datetime.datetime() (due to 64-bit float epoch): 1 microsecond
-    us = idx % 1000000  # 10**6
-    return 1000 * (1000000 * secs + us)
-
-
-def get_mtime_path(path):
-    return os.path.getmtime(path)
-
-
-# Git class and parse_log(), the heart of the script ##########################
-
-class Git:
-    def __init__(self, workdir=None, gitdir=None, cwd=None, errors=True):
-        self.gitcmd = ['git']
-        self.errors = errors
-        self._proc = None
-        if workdir: self.gitcmd.extend(('--work-tree', workdir))
-        if gitdir:  self.gitcmd.extend(('--git-dir',   gitdir))
-        if cwd:     self.gitcmd.extend(('-C',          cwd))
-        self.workdir, self.gitdir = self._get_repo_dirs()
-
-    def ls_files(self, paths: list = None):
-        return (normalize(_) for _ in self._run('ls-files --full-name', paths))
-
-    def ls_dirty(self, force=False):
-        return (normalize(_[3:].split(' -> ', 1)[-1])
-                for _ in self._run('status --porcelain')
-                if _[:2] != '??' and (not force or (_[0] in ('R', 'A')
-                                                    or _[1] == 'D')))
-
-    def log(self, merge=False, first_parent=False, commit_time=False,
-            reverse_order=False, paths: list = None):
-        cmd = 'whatchanged --pretty={}'.format('%ct' if commit_time else '%at')
-        if merge:         cmd += ' -m'
-        if first_parent:  cmd += ' --first-parent'
-        if reverse_order: cmd += ' --reverse'
-        return self._run(cmd, paths)
-
-    def describe(self):
-        return self._run('describe --tags', check=True)[0]
-
-    def terminate(self):
-        if self._proc is None:
-            return
-        try:
-            self._proc.terminate()
-        except OSError:
-            # Avoid errors on OpenBSD
-            pass
-
-    def _get_repo_dirs(self):
-        return (os.path.normpath(_) for _ in
-            self._run('rev-parse --show-toplevel --absolute-git-dir', check=True))
-
-    def _run(self, cmdstr: str, paths: list = None, output=True, check=False):
-        cmdlist = self.gitcmd + shlex.split(cmdstr)
-        if paths:
-            cmdlist.append('--')
-            cmdlist.extend(paths)
-        popen_args = dict(universal_newlines=True, encoding='utf8')
-        if not self.errors:
-            popen_args['stderr'] = subprocess.DEVNULL
-        log.trace("Executing: %s", ' '.join(cmdlist))
-        if not output:
-            return subprocess.call(cmdlist, **popen_args)
-        if check:
-            try:
-                stdout: str = subprocess.check_output(cmdlist, **popen_args)
-                return stdout.splitlines()
-            except subprocess.CalledProcessError as e:
-                raise self.Error(e.returncode, e.cmd, e.output, e.stderr)
-        self._proc = subprocess.Popen(cmdlist, stdout=subprocess.PIPE, **popen_args)
-        return (_.rstrip() for _ in self._proc.stdout)
-
-    def __del__(self):
-        self.terminate()
-
-    class Error(subprocess.CalledProcessError):
-        """Error from git executable"""
-
-
-def parse_log(filelist, dirlist, stats, git, merge=False, filterlist=None):
-    mtime = 0
-    datestr = isodate(0)
-    for line in git.log(
-            merge,
-            args.first_parent,
-            args.commit_time,
-            args.reverse_order,
-            filterlist
-    ):
-        stats['loglines'] += 1
-
-        # Blank line between Date and list of files
-        if not line:
-            continue
-
-        # Date line
-        if line[0] != ':':  # Faster than `not line.startswith(':')`
-            stats['commits'] += 1
-            mtime = int(line)
-            if args.unique_times:
-                mtime = get_mtime_ns(mtime, stats['commits'])
-            if args.debug:
-                datestr = isodate(mtime)
-            continue
-
-        # File line: three tokens if it describes a renaming, otherwise two
-        tokens = line.split('\t')
-
-        # Possible statuses:
-        # M: Modified (content changed)
-        # A: Added (created)
-        # D: Deleted
-        # T: Type changed: to/from regular file, symlinks, submodules
-        # R099: Renamed (moved), with % of unchanged content. 100 = pure rename
-        # Not possible in log: C=Copied, U=Unmerged, X=Unknown, B=pairing Broken
-        status = tokens[0].split(' ')[-1]
-        file = tokens[-1]
-
-        # Handles non-ASCII chars and OS path separator
-        file = normalize(file)
-
-        def do_file():
-            if args.skip_older_than_commit and get_mtime_path(file) <= mtime:
-                stats['skip'] += 1
-                return
-            if args.debug:
-                log.debug("%d\t%d\t%d\t%s\t%s",
-                          stats['loglines'], stats['commits'], stats['files'],
-                          datestr, file)
-            try:
-                touch(os.path.join(git.workdir, file), mtime)
-                stats['touches'] += 1
-            except Exception as e:
-                log.error("ERROR: %s: %s", e, file)
-                stats['errors'] += 1
-
-        def do_dir():
-            if args.debug:
-                log.debug("%d\t%d\t-\t%s\t%s",
-                          stats['loglines'], stats['commits'],
-                          datestr, "{}/".format(dirname or '.'))
-            try:
-                touch(os.path.join(git.workdir, dirname), mtime)
-                stats['dirtouches'] += 1
-            except Exception as e:
-                log.error("ERROR: %s: %s", e, dirname)
-                stats['direrrors'] += 1
-
-        if file in filelist:
-            stats['files'] -= 1
-            filelist.remove(file)
-            do_file()
-
-        if args.dirs and status in ('A', 'D'):
-            dirname = os.path.dirname(file)
-            if dirname in dirlist:
-                dirlist.remove(dirname)
-                do_dir()
-
-        # All files done?
-        if not stats['files']:
-            git.terminate()
-            return
-
-
-# Main Logic ##################################################################
-
-def main():
-    start = time.time()  # yes, Wall time. CPU time is not realistic for users.
-    stats = {_: 0 for _ in ('loglines', 'commits', 'touches', 'skip', 'errors',
-                            'dirtouches', 'direrrors')}
-
-    logging.basicConfig(level=args.loglevel, format='%(message)s')
-    log.trace("Arguments: %s", args)
-
-    # First things first: Where and Who are we?
-    if args.cwd:
-        log.debug("Changing directory: %s", args.cwd)
-        try:
-            os.chdir(args.cwd)
-        except OSError as e:
-            log.critical(e)
-            return e.errno
-    # Using both os.chdir() and `git -C` is redundant, but might prevent side effects
-    # `git -C` alone could be enough if we make sure that:
-    # - all paths, including args.pathspec, are processed by git: ls-files, rev-parse
-    # - touch() / os.utime() path argument is always prepended with git.workdir
-    try:
-        git = Git(workdir=args.workdir, gitdir=args.gitdir, cwd=args.cwd)
-    except Git.Error as e:
-        # Not in a git repository, and git already informed user on stderr. So we just...
-        return e.returncode
-
-    # Get the files managed by git and build file list to be processed
-    if UPDATE_SYMLINKS and not args.skip_older_than:
-        filelist = set(git.ls_files(args.pathspec))
-    else:
-        filelist = set()
-        for path in git.ls_files(args.pathspec):
-            fullpath = os.path.join(git.workdir, path)
-
-            # Symlink (to file, to dir or broken - git handles the same way)
-            if not UPDATE_SYMLINKS and os.path.islink(fullpath):
-                log.warning("WARNING: Skipping symlink, no OS support for updates: %s",
-                            path)
-                continue
-
-            # skip files which are older than given threshold
-            if (args.skip_older_than
-                    and start - get_mtime_path(fullpath) > args.skip_older_than):
-                continue
-
-            # Always add files relative to worktree root
-            filelist.add(path)
-
-    # If --force, silently ignore uncommitted deletions (not in the filesystem)
-    # and renames / additions (will not be found in log anyway)
-    if args.force:
-        filelist -= set(git.ls_dirty(force=True))
-    # Otherwise, ignore any dirty files
-    else:
-        dirty = set(git.ls_dirty())
-        if dirty:
-            log.warning("WARNING: Modified files in the working directory were ignored."
-                "\nTo include such files, commit your changes or use --force.")
-            filelist -= dirty
-
-    # Build dir list to be processed
-    dirlist = set(os.path.dirname(_) for _ in filelist) if args.dirs else set()
-
-    stats['totalfiles'] = stats['files'] = len(filelist)
-    log.info("{0:,} files to be processed in work dir".format(stats['totalfiles']))
-
-    if not filelist:
-        # Nothing to do. Exit silently and without errors, just like git does
-        return
-
-    # Process the log until all files are 'touched'
-    log.debug("Line #\tLog #\tF.Left\tModification Time\tFile Name")
-    parse_log(filelist, dirlist, stats, git, args.merge, args.pathspec)
-
-    # Missing files
-    if filelist:
-        # Try to find them in merge logs, if not done already
-        # (usually HUGE, thus MUCH slower!)
-        if args.missing and not args.merge:
-            filterlist = list(filelist)
-            missing = len(filterlist)
-            log.info("{0:,} files not found in log, trying merge commits".format(missing))
-            for i in range(0, missing, STEPMISSING):
-                parse_log(filelist, dirlist, stats, git,
-                          merge=True, filterlist=filterlist[i:i + STEPMISSING])
-
-        # Still missing some?
-        for file in filelist:
-            log.warning("WARNING: not found in the log: %s", file)
-
-    # Final statistics
-    # Suggestion: use git-log --before=mtime to brag about skipped log entries
-    def log_info(msg, *a, width=13):
-        ifmt = '{:%d,}'    % (width,)  # not using 'n' for consistency with ffmt
-        ffmt = '{:%d,.2f}' % (width,)
-        # %-formatting lacks a thousand separator, must pre-render with .format()
-        log.info(msg.replace('%d', ifmt).replace('%f', ffmt).format(*a))
-
-    log_info(
-        "Statistics:\n"
-        "%f seconds\n"
-        "%d log lines processed\n"
-        "%d commits evaluated",
-        time.time() - start, stats['loglines'], stats['commits'])
-
-    if args.dirs:
-        if stats['direrrors']: log_info("%d directory update errors", stats['direrrors'])
-        log_info("%d directories updated", stats['dirtouches'])
-
-    if stats['touches'] != stats['totalfiles']:
-                        log_info("%d files",              stats['totalfiles'])
-    if stats['skip']:   log_info("%d files skipped",      stats['skip'])
-    if stats['files']:  log_info("%d files missing",      stats['files'])
-    if stats['errors']: log_info("%d file update errors", stats['errors'])
-
-    log_info("%d files updated", stats['touches'])
-
-    if args.test:
-        log.info("TEST RUN - No files modified!")
-
-
-# Keep only essential, global assignments here. Any other logic must be in main()
-log = setup_logging()
-args = parse_args()
-
-# Set the actual touch() and other functions based on command-line arguments
-if args.unique_times:
-    touch = touch_ns
-    isodate = isodate_ns
-
-# Make sure this is always set last to ensure --test behaves as intended
-if args.test:
-    touch = dummy
-
-# UI done, it's showtime!
-try:
-    sys.exit(main())
-except KeyboardInterrupt:
-    log.info("\nAborting")
-    signal.signal(signal.SIGINT, signal.SIG_DFL)
-    os.kill(os.getpid(), signal.SIGINT)

.github/workflows/_lint.yml

@@ -1,150 +0,0 @@
-name: lint
-
-on:
-  workflow_call:
-    inputs:
-      working-directory:
-        required: true
-        type: string
-        description: "From which folder this pipeline executes"
-
-env:
-  POETRY_VERSION: "1.6.1"
-  WORKDIR: ${{ inputs.working-directory == '' && '.' || inputs.working-directory }}
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    env:
-      # This number is set "by eye": we want it to be big enough
-      # so that it's bigger than the number of commits in any reasonable PR,
-      # and also as small as possible since increasing the number makes
-      # the initial `git fetch` slower.
-      FETCH_DEPTH: 50
-    strategy:
-      matrix:
-        # Only lint on the min and max supported Python versions.
-        # It's extremely unlikely that there's a lint issue on any version in between
-        # that doesn't show up on the min or max versions.
-        #
-        # GitHub rate-limits how many jobs can be running at any one time.
-        # Starting new jobs is also relatively slow,
-        # so linting on fewer versions makes CI faster.
-        python-version:
-          - "3.8"
-          - "3.11"
-    steps:
-      - uses: actions/checkout@v3
-        with:
-          # Fetch the last FETCH_DEPTH commits, so the mtime-changing script
-          # can accurately set the mtimes of files modified in the last FETCH_DEPTH commits.
-          fetch-depth: ${{ env.FETCH_DEPTH }}
-      - name: Restore workdir file mtimes to last-edited commit date
-        id: restore-mtimes
-        # This is needed to make black caching work.
-        # Black's cache uses file (mtime, size) to check whether a lookup is a cache hit.
-        # Without this command, files in the repo would have the current time as the modified time,
-        # since the previous action step just created them.
-        # This command resets the mtime to the last time the files were modified in git instead,
-        # which is a high-quality and stable representation of the last modification date.
-        run: |
-          # Important considerations:
-          # - These commands run at base of the repo, since we never `cd` to the `WORKDIR`.
-          # - We only want to alter mtimes for Python files, since that's all black checks.
-          # - We don't need to alter mtimes for directories, since black doesn't look at those.
-          # - We also only alter mtimes inside the `WORKDIR` since that's all we'll lint.
-          # - This should run before `poetry install`, because poetry's venv also contains
-          #   Python files, and we don't want to alter their mtimes since they aren't linted.
-
-          # Ensure we fail on non-zero exits and on undefined variables.
-          # Also print executed commands, for easier debugging.
-          set -eux
-
-          # Restore the mtimes of Python files in the workdir based on git history.
-          .github/tools/git-restore-mtime --no-directories "$WORKDIR/**/*.py"
-
-          # Since CI only does a partial fetch (to `FETCH_DEPTH`) for efficiency,
-          # the local git repo doesn't have full history. There are probably files
-          # that were last modified in a commit *older than* the oldest fetched commit.
-          # After `git-restore-mtime`, such files have a mtime set to the oldest fetched commit.
-          #
-          # As new commits get added, that timestamp will keep moving forward.
-          # If left unchanged, this will make `black` think that the files were edited
-          # more recently than its cache suggests. Instead, we can set their mtime
-          # to a fixed date in the far past that won't change and won't cause cache misses in black.
-          #
-          # For all workdir Python files modified in or before the oldest few fetched commits,
-          # make their mtime be 2000-01-01 00:00:00.
-          OLDEST_COMMIT="$(git log --reverse '--pretty=format:%H' | head -1)"
-          OLDEST_COMMIT_TIME="$(git show -s '--format=%ai' "$OLDEST_COMMIT")"
-          find "$WORKDIR" -name '*.py' -type f -not -newermt "$OLDEST_COMMIT_TIME" -exec touch -c -m -t '200001010000' '{}' '+'
-
-          echo "oldest-commit=$OLDEST_COMMIT" >> "$GITHUB_OUTPUT"
-
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
-        uses: "./.github/actions/poetry_setup"
-        with:
-          python-version: ${{ matrix.python-version }}
-          poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ inputs.working-directory }}
-          cache-key: lint-with-extras
-
-      - name: Check Poetry File
-        shell: bash
-        working-directory: ${{ inputs.working-directory }}
-        run: |
-          poetry check
-
-      - name: Check lock file
-        shell: bash
-        working-directory: ${{ inputs.working-directory }}
-        run: |
-          poetry lock --check
-
-      - name: Install dependencies
-        # Also installs dev/lint/test/typing dependencies, to ensure we have
-        # type hints for as many of our libraries as possible.
-        # This helps catch errors that require dependencies to be spotted, for example:
-        # https://github.com/langchain-ai/langchain/pull/10249/files#diff-935185cd488d015f026dcd9e19616ff62863e8cde8c0bee70318d3ccbca98341
-        #
-        # If you change this configuration, make sure to change the `cache-key`
-        # in the `poetry_setup` action above to stop using the old cache.
-        # It doesn't matter how you change it, any change will cause a cache-bust.
-        working-directory: ${{ inputs.working-directory }}
-        run: |
-          poetry install --with dev,lint,test,typing
-
-      - name: Install langchain editable
-        working-directory: ${{ inputs.working-directory }}
-        if: ${{ inputs.working-directory != 'libs/langchain' }}
-        run: |
-          pip install -e ../langchain
-
-      - name: Restore black cache
-        uses: actions/cache@v3
-        env:
-          CACHE_BASE: black-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', env.WORKDIR)) }}
-          SEGMENT_DOWNLOAD_TIMEOUT_MIN: "1"
-        with:
-          path: |
-            ${{ env.WORKDIR }}/.black_cache
-          key: ${{ env.CACHE_BASE }}-${{ steps.restore-mtimes.outputs.oldest-commit }}
-          restore-keys:
-            # If we can't find an exact match for our cache key, accept any with this prefix.
-            ${{ env.CACHE_BASE }}-
-
-      - name: Get .mypy_cache to speed up mypy
-        uses: actions/cache@v3
-        env:
-          SEGMENT_DOWNLOAD_TIMEOUT_MIN: "2"
-        with:
-          path: |
-            ${{ env.WORKDIR }}/.mypy_cache
-          key: mypy-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', env.WORKDIR)) }}
-
-      - name: Analysing the code with our lint
-        working-directory: ${{ inputs.working-directory }}
-        env:
-          BLACK_CACHE_DIR: .black_cache
-        run: |
-          make lint

.github/workflows/_pydantic_compatibility.yml

@@ -1,93 +0,0 @@
-name: pydantic v1/v2 compatibility
-
-on:
-  workflow_call:
-    inputs:
-      working-directory:
-        required: true
-        type: string
-        description: "From which folder this pipeline executes"
-
-env:
-  POETRY_VERSION: "1.6.1"
-
-jobs:
-  build:
-    defaults:
-      run:
-        working-directory: ${{ inputs.working-directory }}
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
-    name: Pydantic v1/v2 compatibility - Python ${{ matrix.python-version }}
-    steps:
-      - uses: actions/checkout@v3
-
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
-        uses: "./.github/actions/poetry_setup"
-        with:
-          python-version: ${{ matrix.python-version }}
-          poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ inputs.working-directory }}
-          cache-key: pydantic-cross-compat
-
-      - name: Install dependencies
-        shell: bash
-        run: poetry install
-
-      - name: Install the opposite major version of pydantic
-        # If normal tests use pydantic v1, here we'll use v2, and vice versa.
-        shell: bash
-        run: |
-          # Determine the major part of pydantic version
-          REGULAR_VERSION=$(poetry run python -c "import pydantic; print(pydantic.__version__)" | cut -d. -f1)
-
-          if [[ "$REGULAR_VERSION" == "1" ]]; then
-            PYDANTIC_DEP=">=2.1,<3"
-            TEST_WITH_VERSION="2"
-          elif [[ "$REGULAR_VERSION" == "2" ]]; then
-            PYDANTIC_DEP="<2"
-            TEST_WITH_VERSION="1"
-          else
-            echo "Unexpected pydantic major version '$REGULAR_VERSION', cannot determine which version to use for cross-compatibility test."
-            exit 1
-          fi
-
-          # Install via `pip` instead of `poetry add` to avoid changing lockfile,
-          # which would prevent caching from working: the cache would get saved
-          # to a different key than where it gets loaded from.
-          poetry run pip install "pydantic${PYDANTIC_DEP}"
-
-          # Ensure that the correct pydantic is installed now.
-          echo "Checking pydantic version... Expecting ${TEST_WITH_VERSION}"
-
-          # Determine the major part of pydantic version
-          CURRENT_VERSION=$(poetry run python -c "import pydantic; print(pydantic.__version__)" | cut -d. -f1)
-
-          # Check that the major part of pydantic version is as expected, if not
-          # raise an error
-          if [[ "$CURRENT_VERSION" != "$TEST_WITH_VERSION" ]]; then
-            echo "Error: expected pydantic version ${CURRENT_VERSION} to have been installed, but found: ${TEST_WITH_VERSION}"
-            exit 1
-          fi
-          echo "Found pydantic version ${CURRENT_VERSION}, as expected"
-      - name: Run pydantic compatibility tests
-        shell: bash
-        run: make test
-
-      - name: Ensure the tests did not create any additional files
-        shell: bash
-        run: |
-          set -eu
-
-          STATUS="$(git status)"
-          echo "$STATUS"
-
-          # grep will exit non-zero if the target message isn't found,
-          # and `set -e` above will cause the step to fail.
-          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/_release.yml

@@ -1,64 +0,0 @@
-name: release
-
-on:
-  workflow_call:
-    inputs:
-      working-directory:
-        required: true
-        type: string
-        description: "From which folder this pipeline executes"
-
-env:
-  POETRY_VERSION: "1.6.1"
-
-jobs:
-  if_release:
-    # Disallow publishing from branches that aren't `master`.
-    if: github.ref == 'refs/heads/master'
-    runs-on: ubuntu-latest
-    permissions:
-      # This permission is used for trusted publishing:
-      # https://blog.pypi.org/posts/2023-04-20-introducing-trusted-publishers/
-      #
-      # Trusted publishing has to also be configured on PyPI for each package:
-      # https://docs.pypi.org/trusted-publishers/adding-a-publisher/
-      id-token: write
-
-      # This permission is needed by `ncipollo/release-action` to create the GitHub release.
-      contents: write
-    defaults:
-      run:
-        working-directory: ${{ inputs.working-directory }}
-    steps:
-      - uses: actions/checkout@v3
-
-      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
-        uses: "./.github/actions/poetry_setup"
-        with:
-          python-version: "3.10"
-          poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ inputs.working-directory }}
-          cache-key: release
-
-      - name: Build project for distribution
-        run: poetry build
-      - name: Check Version
-        id: check-version
-        run: |
-          echo version=$(poetry version --short) >> $GITHUB_OUTPUT
-      - name: Create Release
-        uses: ncipollo/release-action@v1
-        if: ${{ inputs.working-directory == 'libs/langchain' }}
-        with:
-          artifacts: "dist/*"
-          token: ${{ secrets.GITHUB_TOKEN }}
-          draft: false
-          generateReleaseNotes: true
-          tag: v${{ steps.check-version.outputs.version }}
-          commit: master
-      - name: Publish package distributions to PyPI
-        uses: pypa/gh-action-pypi-publish@release/v1
-        with:
-          packages-dir: ${{ inputs.working-directory }}/dist/
-          verbose: true
-          print-hash: true

.github/workflows/_release_docker.yml

@@ -1,62 +0,0 @@
-name: release_docker
-
-on:
-  workflow_call:
-    inputs:
-      dockerfile:
-        required: true
-        type: string
-        description: "Path to the Dockerfile to build"
-      image:
-        required: true
-        type: string
-        description: "Name of the image to build"
-
-env:
-  TEST_TAG: ${{ inputs.image }}:test
-  LATEST_TAG: ${{ inputs.image }}:latest
-
-jobs:
-  docker:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-      - name: Get git tag
-        uses: actions-ecosystem/action-get-latest-tag@v1
-        id: get-latest-tag
-      - name: Set docker tag
-        env:
-          VERSION: ${{ steps.get-latest-tag.outputs.tag }}
-        run: |
-          echo "VERSION_TAG=${{ inputs.image }}:${VERSION#v}" >> $GITHUB_ENV
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-      - name: Login to Docker Hub
-        uses: docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
-      - name: Build for Test
-        uses: docker/build-push-action@v5
-        with:
-          context: .
-          file: ${{ inputs.dockerfile }}
-          load: true
-          tags: ${{ env.TEST_TAG }}
-      - name: Test
-        run: |
-          docker run --rm ${{ env.TEST_TAG }} python -c "import langchain"
-      - name: Build and Push to Docker Hub
-        uses: docker/build-push-action@v5
-        with:
-          context: .
-          file: ${{ inputs.dockerfile }}
-          # We can only build for the intersection of platforms supported by
-          # QEMU and base python image, for now build only for
-          # linux/amd64 and linux/arm64
-          platforms: linux/amd64,linux/arm64
-          tags: ${{ env.LATEST_TAG }},${{ env.VERSION_TAG }}
-          push: true

.github/workflows/_test.yml

@@ -1,57 +0,0 @@
-name: test
-
-on:
-  workflow_call:
-    inputs:
-      working-directory:
-        required: true
-        type: string
-        description: "From which folder this pipeline executes"
-
-env:
-  POETRY_VERSION: "1.6.1"
-
-jobs:
-  build:
-    defaults:
-      run:
-        working-directory: ${{ inputs.working-directory }}
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
-    name: Python ${{ matrix.python-version }}
-    steps:
-      - uses: actions/checkout@v3
-
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
-        uses: "./.github/actions/poetry_setup"
-        with:
-          python-version: ${{ matrix.python-version }}
-          poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ inputs.working-directory }}
-          cache-key: core
-
-      - name: Install dependencies
-        shell: bash
-        run: poetry install
-
-      - name: Run core tests
-        shell: bash
-        run: make test
-
-      - name: Ensure the tests did not create any additional files
-        shell: bash
-        run: |
-          set -eu
-
-          STATUS="$(git status)"
-          echo "$STATUS"
-
-          # grep will exit non-zero if the target message isn't found,
-          # and `set -e` above will cause the step to fail.
-          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/codespell.yml

@@ -1,36 +0,0 @@
----
-name: Codespell
-
-on:
-  push:
-    branches: [master]
-  pull_request:
-    branches: [master]
-
-permissions:
-  contents: read
-
-jobs:
-  codespell:
-    name: Check for spelling errors
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-
-      - name: Install Dependencies
-        run: |
-          pip install toml
-
-      - name: Extract Ignore Words List
-        run: |
-          # Use a Python script to extract the ignore words list from pyproject.toml
-          python .github/workflows/extract_ignored_words_list.py
-        id: extract_ignore_words
-
-      - name: Codespell
-        uses: codespell-project/actions-codespell@v2
-        with:
-          skip: guide_imports.json
-          ignore_words_list: ${{ steps.extract_ignore_words.outputs.ignore_words_list }}

.github/workflows/doc_lint.yml

@@ -1,22 +0,0 @@
----
-name: Documentation Lint
-
-on:
-  push:
-    branches: [master]
-  pull_request:
-    branches: [master]
-
-jobs:
-  check:
-    runs-on: ubuntu-latest
-
-    steps:
-    - name: Checkout repository
-      uses: actions/checkout@v2
-
-    - name: Run import check
-      run: |
-        # We should not encourage imports directly from main init file
-        # Expect for hub
-        git grep 'from langchain import' docs/{docs,snippets} | grep -vE 'from langchain import (hub)' && exit 1 || exit 0

.github/workflows/extract_ignored_words_list.py

@@ -1,8 +0,0 @@
-import toml
-
-pyproject_toml = toml.load("pyproject.toml")
-
-# Extract the ignore words list (adjust the key as per your TOML structure)
-ignore_words_list = pyproject_toml.get("tool", {}).get("codespell", {}).get("ignore-words-list")
-
-print(f"::set-output name=ignore_words_list::{ignore_words_list}")

.github/workflows/langchain_ci.yml

@@ -1,97 +0,0 @@
----
-name: libs/langchain CI
-
-on:
-  push:
-    branches: [ master ]
-  pull_request:
-    paths:
-      - '.github/actions/poetry_setup/action.yml'
-      - '.github/tools/**'
-      - '.github/workflows/_lint.yml'
-      - '.github/workflows/_test.yml'
-      - '.github/workflows/_pydantic_compatibility.yml'
-      - '.github/workflows/langchain_ci.yml'
-      - 'libs/langchain/**'
-  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
-
-# If another push to the same PR or branch happens while this workflow is still running,
-# cancel the earlier run in favor of the next run.
-#
-# There's no point in testing an outdated version of the code. GitHub only allows
-# a limited number of job runners to be active at the same time, so it's better to cancel
-# pointless jobs early so that more useful jobs can run sooner.
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-env:
-  POETRY_VERSION: "1.6.1"
-  WORKDIR: "libs/langchain"
-
-jobs:
-  lint:
-    uses:
-      ./.github/workflows/_lint.yml
-    with:
-      working-directory: libs/langchain
-    secrets: inherit
-
-  test:
-    uses:
-      ./.github/workflows/_test.yml
-    with:
-      working-directory: libs/langchain
-    secrets: inherit
-
-  pydantic-compatibility:
-    uses:
-      ./.github/workflows/_pydantic_compatibility.yml
-    with:
-      working-directory: libs/langchain
-    secrets: inherit
-
-  extended-tests:
-    runs-on: ubuntu-latest
-    defaults:
-      run:
-        working-directory: ${{ env.WORKDIR }}
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
-    name: Python ${{ matrix.python-version }} extended tests
-    steps:
-      - uses: actions/checkout@v3
-
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
-        uses: "./.github/actions/poetry_setup"
-        with:
-          python-version: ${{ matrix.python-version }}
-          poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: libs/langchain
-          cache-key: extended
-
-      - name: Install dependencies
-        shell: bash
-        run: |
-          echo "Running extended tests, installing dependencies with poetry..."
-          poetry install -E extended_testing
-
-      - name: Run extended tests
-        run: make extended_tests
-
-      - name: Ensure the tests did not create any additional files
-        shell: bash
-        run: |
-          set -eu
-
-          STATUS="$(git status)"
-          echo "$STATUS"
-
-          # grep will exit non-zero if the target message isn't found,
-          # and `set -e` above will cause the step to fail.
-          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/langchain_experimental_ci.yml

@@ -1,129 +0,0 @@
----
-name: libs/experimental CI
-
-on:
-  push:
-    branches: [ master ]
-  pull_request:
-    paths:
-      - '.github/actions/poetry_setup/action.yml'
-      - '.github/tools/**'
-      - '.github/workflows/_lint.yml'
-      - '.github/workflows/_test.yml'
-      - '.github/workflows/langchain_experimental_ci.yml'
-      - 'libs/langchain/**'
-      - 'libs/experimental/**'
-  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
-
-# If another push to the same PR or branch happens while this workflow is still running,
-# cancel the earlier run in favor of the next run.
-#
-# There's no point in testing an outdated version of the code. GitHub only allows
-# a limited number of job runners to be active at the same time, so it's better to cancel
-# pointless jobs early so that more useful jobs can run sooner.
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-env:
-  POETRY_VERSION: "1.6.1"
-  WORKDIR: "libs/experimental"
-
-jobs:
-  lint:
-    uses:
-      ./.github/workflows/_lint.yml
-    with:
-      working-directory: libs/experimental
-    secrets: inherit
-
-  test:
-    uses:
-      ./.github/workflows/_test.yml
-    with:
-      working-directory: libs/experimental
-    secrets: inherit
-
-  # It's possible that langchain-experimental works fine with the latest *published* langchain,
-  # but is broken with the langchain on `master`.
-  #
-  # We want to catch situations like that *before* releasing a new langchain, hence this test.
-  test-with-latest-langchain:
-    runs-on: ubuntu-latest
-    defaults:
-      run:
-        working-directory: ${{ env.WORKDIR }}
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
-    name: test with unpublished langchain - Python ${{ matrix.python-version }}
-    steps:
-      - uses: actions/checkout@v3
-
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
-        uses: "./.github/actions/poetry_setup"
-        with:
-          python-version: ${{ matrix.python-version }}
-          poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ env.WORKDIR }}
-          cache-key: unpublished-langchain
-
-      - name: Install dependencies
-        shell: bash
-        run: |
-          echo "Running tests with unpublished langchain, installing dependencies with poetry..."
-          poetry install
-
-          echo "Editably installing langchain outside of poetry, to avoid messing up lockfile..."
-          poetry run pip install -e ../langchain
-
-      - name: Run tests
-        run: make test
-  extended-tests:
-    runs-on: ubuntu-latest
-    defaults:
-      run:
-        working-directory: ${{ env.WORKDIR }}
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
-    name: Python ${{ matrix.python-version }} extended tests
-    steps:
-      - uses: actions/checkout@v3
-
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
-        uses: "./.github/actions/poetry_setup"
-        with:
-          python-version: ${{ matrix.python-version }}
-          poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: libs/experimental
-          cache-key: extended
-
-      - name: Install dependencies
-        shell: bash
-        run: |
-          echo "Running extended tests, installing dependencies with poetry..."
-          poetry install -E extended_testing
-
-      - name: Run extended tests
-        run: make extended_tests
-
-      - name: Ensure the tests did not create any additional files
-        shell: bash
-        run: |
-          set -eu
-
-          STATUS="$(git status)"
-          echo "$STATUS"
-
-          # grep will exit non-zero if the target message isn't found,
-          # and `set -e` above will cause the step to fail.
-          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/langchain_experimental_release.yml

@@ -1,13 +0,0 @@
----
-name: libs/experimental Release
-
-on:
-  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
-
-jobs:
-  release:
-    uses:
-      ./.github/workflows/_release.yml
-    with:
-      working-directory: libs/experimental
-    secrets: inherit

.github/workflows/langchain_release.yml

@@ -1,27 +0,0 @@
----
-name: libs/langchain Release
-
-on:
-  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
-
-jobs:
-  release:
-    uses:
-      ./.github/workflows/_release.yml
-    with:
-      working-directory: libs/langchain
-    secrets: inherit
-
-  # N.B.: It's possible that PyPI doesn't make the new release visible / available
-  #       immediately after publishing. If that happens, the docker build might not
-  #       create a new docker image for the new release, since it won't see it.
-  #
-  #       If this ends up being a problem, add a check to the end of the `_release.yml`
-  #       workflow that prevents the workflow from finishing until the new release
-  #       is visible and installable on PyPI.
-  release-docker:
-    needs:
-      - release
-    uses:
-      ./.github/workflows/langchain_release_docker.yml
-    secrets: inherit

.github/workflows/langchain_release_docker.yml

@@ -1,14 +0,0 @@
----
-name: docker/langchain/langchain Release
-
-on:
-  workflow_dispatch: # Allows to trigger the workflow manually in GitHub UI
-  workflow_call: # Allows triggering from another workflow
-
-jobs:
-  release:
-    uses: ./.github/workflows/_release_docker.yml
-    with:
-      dockerfile: docker/Dockerfile.base
-      image: langchain/langchain
-    secrets: inherit

.github/workflows/scheduled_test.yml

@@ -1,81 +0,0 @@
-name: Scheduled tests
-
-on:
-  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
-  schedule:
-    - cron:  '0 13 * * *'
-
-env:
-  POETRY_VERSION: "1.6.1"
-
-jobs:
-  build:
-    defaults:
-      run:
-        working-directory: libs/langchain
-    runs-on: ubuntu-latest
-    environment: Scheduled testing
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
-    name: Python ${{ matrix.python-version }}
-    steps:
-      - uses: actions/checkout@v3
-
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: "./.github/actions/poetry_setup"
-        with:
-          python-version: ${{ matrix.python-version }}
-          poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: libs/langchain
-          cache-key: scheduled
-
-      - name: 'Authenticate to Google Cloud'
-        id: 'auth'
-        uses: 'google-github-actions/auth@v1'
-        with:
-          credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
-
-      - name: Configure AWS Credentials
-        uses: aws-actions/configure-aws-credentials@v4
-        with:
-          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
-          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-          aws-region: ${{ vars.AWS_REGION }}
-
-      - name: Install dependencies
-        working-directory: libs/langchain
-        shell: bash
-        run: |
-          echo "Running scheduled tests, installing dependencies with poetry..."
-          poetry install --with=test_integration
-          poetry run pip install google-cloud-aiplatform
-          poetry run pip install "boto3>=1.28.57"
-
-      - name: Run tests
-        shell: bash
-        env:
-          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-          AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
-          AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
-          AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
-          AZURE_OPENAI_DEPLOYMENT_NAME:  ${{ secrets.AZURE_OPENAI_DEPLOYMENT_NAME }}
-        run: |
-          make scheduled_tests
-
-      - name: Ensure the tests did not create any additional files
-        shell: bash
-        run: |
-          set -eu
-
-          STATUS="$(git status)"
-          echo "$STATUS"
-
-          # grep will exit non-zero if the target message isn't found,
-          # and `set -e` above will cause the step to fail.
-          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/test.yml

@@ -0,0 +1,49 @@
+name: test
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+  workflow_dispatch:
+
+env:
+  POETRY_VERSION: "1.4.2"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+        test_type:
+          - "core"
+          - "extended"
+    name: Python ${{ matrix.python-version }} ${{ matrix.test_type }}
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: "./.github/actions/poetry_setup"
+        with:
+          python-version: ${{ matrix.python-version }}
+          poetry-version: "1.4.2"
+          cache-key: ${{ matrix.test_type }}
+          install-command: |
+              if [ "${{ matrix.test_type }}" == "core" ]; then
+                echo "Running core tests, installing dependencies with poetry..."
+                poetry install
+              else
+                echo "Running extended tests, installing dependencies with poetry..."
+                poetry install -E extended_testing
+              fi
+      - name: Run ${{matrix.test_type}} tests
+        run: |
+          if [ "${{ matrix.test_type }}" == "core" ]; then
+            make test
+          else
+            make extended_tests
+          fi
+        shell: bash

.gitignore

@@ -30,12 +30,6 @@ share/python-wheels/
 *.egg
 MANIFEST
 
-# Google GitHub Actions credentials files created by:
-# https://github.com/google-github-actions/auth
-#
-# That action recommends adding this gitignore to prevent accidentally committing keys.
-gha-creds-*.json
-
 # PyInstaller
 #  Usually these files are written by a python script from a template
 #  before PyInstaller builds the exe, so as to inject date/other infos into it.
@@ -167,14 +161,7 @@ docs/node_modules/
 docs/.docusaurus/
 docs/.cache-loader/
 docs/_dist
-docs/api_reference/api_reference.rst
-docs/api_reference/experimental_api_reference.rst
 docs/api_reference/_build
-docs/api_reference/*/
-!docs/api_reference/_static/
-!docs/api_reference/templates/
-!docs/api_reference/themes/
-docs/docs/build
-docs/docs/node_modules
-docs/docs/yarn.lock
-_dist
+docs/docs_skeleton/build
+docs/docs_skeleton/node_modules
+docs/docs_skeleton/yarn.lock

.gitmodules

@@ -0,0 +1,4 @@
+[submodule "docs/_docs_skeleton"]
+	path = docs/_docs_skeleton
+	url = https://github.com/langchain-ai/langchain-shared-docs
+	branch = main

.readthedocs.yaml

@@ -9,14 +9,9 @@ build:
   os: ubuntu-22.04
   tools:
     python: "3.11"
-  commands:
-      - python -mvirtualenv $READTHEDOCS_VIRTUALENV_PATH
-      - python -m pip install --upgrade --no-cache-dir pip setuptools
-      - python -m pip install --upgrade --no-cache-dir sphinx readthedocs-sphinx-ext
-      - python -m pip install --exists-action=w --no-cache-dir -r docs/api_reference/requirements.txt
+  jobs:
+    pre_build:
       - python docs/api_reference/create_api_rst.py
-      - cat docs/api_reference/conf.py
-      - python -m sphinx -T -E -b html -d _build/doctrees -c docs/api_reference docs/api_reference $READTHEDOCS_OUTPUT/html -j auto
 
 # Build documentation in the docs/ directory with Sphinx
 sphinx:
@@ -29,4 +24,6 @@ sphinx:
 # Optionally declare the Python requirements required to build your docs
 python:
    install:
-   - requirements: docs/api_reference/requirements.txt
+   - requirements: docs/requirements.txt
+   - method: pip
+     path: .

CITATION.cff

@@ -5,4 +5,4 @@ authors:
   given-names: "Harrison"
 title: "LangChain"
 date-released: 2022-10-17
-url: "https://github.com/langchain-ai/langchain"
+url: "https://github.com/hwchase17/langchain"

MIGRATE.md

@@ -1,61 +0,0 @@
-# Migrating to `langchain_experimental`
-
-We are moving any experimental components of LangChain, or components with vulnerability issues, into `langchain_experimental`.
-This guide covers how to migrate.
-
-## Installation
-
-Previously:
-
-`pip install -U langchain`
-
-Now (only if you want to access things in experimental):
-
-`pip install -U langchain langchain_experimental`
-
-## Things in `langchain.experimental`
-
-Previously:
-
-`from langchain.experimental import ...`
-
-Now:
-
-`from langchain_experimental import ...`
-
-## PALChain
-
-Previously:
-
-`from langchain.chains import PALChain`
-
-Now:
-
-`from langchain_experimental.pal_chain import PALChain`
-
-## SQLDatabaseChain
-
-Previously:
-
-`from langchain.chains import SQLDatabaseChain`
-
-Now:
-
-`from langchain_experimental.sql import SQLDatabaseChain`
-
-Alternatively, if you are just interested in using the query generation part of the SQL chain, you can check out [`create_sql_query_chain`](https://github.com/langchain-ai/langchain/blob/master/docs/extras/use_cases/tabular/sql_query.ipynb)
-
-`from langchain.chains import create_sql_query_chain`
-
-## `load_prompt` for Python files
-
-Note: this only applies if you want to load Python files as prompts.
-If you want to load json/yaml files, no change is needed.
-
-Previously:
-
-`from langchain.prompts import load_prompt`
-
-Now:
-
-`from langchain_experimental.prompts import load_prompt`

Makefile

@@ -1,56 +1,73 @@
-.PHONY: all clean docs_build docs_clean docs_linkcheck api_docs_build api_docs_clean api_docs_linkcheck
+.PHONY: all clean format lint test tests test_watch integration_tests docker_tests help extended_tests
 
-# Default target executed when no arguments are given to make.
 all: help
 
+coverage:
+	poetry run pytest --cov \
+		--cov-config=.coveragerc \
+		--cov-report xml \
+		--cov-report term-missing:skip-covered
 
-######################
-# DOCUMENTATION
-######################
-
-clean: docs_clean api_docs_clean
+clean: docs_clean
 
+docs_compile:
+	poetry run nbdoc_build --srcdir $(srcdir)
 
 docs_build:
-	docs/.local_build.sh
+	cd docs && poetry run make html
 
 docs_clean:
-	rm -r _dist
+	cd docs && poetry run make clean
 
 docs_linkcheck:
-	poetry run linkchecker _dist/docs/ --ignore-url node_modules
+	poetry run linkchecker docs/_build/html/index.html
 
-api_docs_build:
-	poetry run python docs/api_reference/create_api_rst.py
-	cd docs/api_reference && poetry run make html
+format:
+	poetry run black .
+	poetry run ruff --select I --fix .
 
-api_docs_clean:
-	rm -f docs/api_reference/api_reference.rst
-	cd docs/api_reference && poetry run make clean
+PYTHON_FILES=.
+lint: PYTHON_FILES=.
+lint_diff: PYTHON_FILES=$(shell git diff --name-only --diff-filter=d master | grep -E '\.py$$')
 
-api_docs_linkcheck:
-	poetry run linkchecker docs/api_reference/_build/html/index.html
+lint lint_diff:
+	poetry run mypy $(PYTHON_FILES)
+	poetry run black $(PYTHON_FILES) --check
+	poetry run ruff .
 
-spell_check:
-	poetry run codespell --toml pyproject.toml
+TEST_FILE ?= tests/unit_tests/
 
-spell_fix:
-	poetry run codespell --toml pyproject.toml -w
+test:
+	poetry run pytest --disable-socket --allow-unix-socket $(TEST_FILE)
 
-######################
-# HELP
-######################
+tests: 
+	poetry run pytest --disable-socket --allow-unix-socket $(TEST_FILE)
+
+extended_tests:
+	poetry run pytest --disable-socket --allow-unix-socket --only-extended tests/unit_tests
+
+test_watch:
+	poetry run ptw --now . -- tests/unit_tests
+
+integration_tests:
+	poetry run pytest tests/integration_tests
+
+docker_tests:
+	docker build -t my-langchain-image:test .
+	docker run --rm my-langchain-image:test
 
 help:
-	@echo '===================='
-	@echo '-- DOCUMENTATION --'
-	@echo 'clean                        - run docs_clean and api_docs_clean'
+	@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 'api_docs_build               - build the API Reference documentation'
-	@echo 'api_docs_clean               - clean the API Reference documentation build artifacts'
-	@echo 'api_docs_linkcheck           - run linkchecker on the API Reference documentation'
-	@echo 'spell_check               	- run codespell on the project'
-	@echo 'spell_fix               		- run codespell on the project and fix the errors'
-	@echo '-- TEST and LINT tasks are within libs/*/ per-package --'
+	@echo 'format                       - run code formatters'
+	@echo 'lint                         - run linters'
+	@echo 'test                         - run unit tests'
+	@echo 'tests                        - run unit tests'
+	@echo 'test TEST_FILE=<test_file>   - run all tests in file'
+	@echo 'extended_tests               - run only extended 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

@@ -2,39 +2,30 @@
 
 ⚡ Building applications with LLMs through composability ⚡
 
-[![Release Notes](https://img.shields.io/github/release/langchain-ai/langchain)](https://github.com/langchain-ai/langchain/releases)
-[![CI](https://github.com/langchain-ai/langchain/actions/workflows/langchain_ci.yml/badge.svg)](https://github.com/langchain-ai/langchain/actions/workflows/langchain_ci.yml)
-[![Experimental CI](https://github.com/langchain-ai/langchain/actions/workflows/langchain_experimental_ci.yml/badge.svg)](https://github.com/langchain-ai/langchain/actions/workflows/langchain_experimental_ci.yml)
+[![Release Notes](https://img.shields.io/github/release/hwchase17/langchain)](https://github.com/hwchase17/langchain/releases)
+[![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)
 [![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)
-[![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchain)
-[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/langchain-ai/langchain)
-[![GitHub star chart](https://img.shields.io/github/stars/langchain-ai/langchain?style=social)](https://star-history.com/#langchain-ai/langchain)
-[![Dependency Status](https://img.shields.io/librariesio/github/langchain-ai/langchain)](https://libraries.io/github/langchain-ai/langchain)
-[![Open Issues](https://img.shields.io/github/issues-raw/langchain-ai/langchain)](https://github.com/langchain-ai/langchain/issues)
+[![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/hwchase17/langchain)
+[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/hwchase17/langchain)
+[![GitHub star chart](https://img.shields.io/github/stars/hwchase17/langchain?style=social)](https://star-history.com/#hwchase17/langchain)
+[![Dependency Status](https://img.shields.io/librariesio/github/hwchase17/langchain)](https://libraries.io/github/hwchase17/langchain)
+[![Open Issues](https://img.shields.io/github/issues-raw/hwchase17/langchain)](https://github.com/hwchase17/langchain/issues)
 
 
-Looking for the JS/TS version? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
+Looking for the JS/TS version? Check out [LangChain.js](https://github.com/hwchase17/langchainjs).
 
-To help you ship LangChain apps to production faster, check out [LangSmith](https://smith.langchain.com). 
-[LangSmith](https://smith.langchain.com) is a unified developer platform for building, testing, and monitoring LLM applications. 
-Fill out [this form](https://airtable.com/appwQzlErAS2qiP0L/shrGtGaVBVAz7NcV2) to get off the waitlist or speak with our sales team
-
-## 🚨Breaking Changes for select chains (SQLDatabase) on 7/28/23
-
-In an effort to make `langchain` leaner and safer, we are moving select chains to `langchain_experimental`.
-This migration has already started, but we are remaining backwards compatible until 7/28.
-On that date, we will remove functionality from `langchain`.
-Read more about the motivation and the progress [here](https://github.com/langchain-ai/langchain/discussions/8043).
-Read how to migrate your code [here](MIGRATE.md).
+**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
-`pip install langsmith && conda install langchain -c conda-forge`
+`conda install langchain -c conda-forge`
 
 ## 🤔 What is this?
 
@@ -50,7 +41,7 @@ This library aims to assist in the development of those types of applications. C
 **💬 Chatbots**
 
 - [Documentation](https://python.langchain.com/docs/use_cases/chatbots/)
-- End-to-end Example: [Chat-LangChain](https://github.com/langchain-ai/chat-langchain)
+- End-to-end Example: [Chat-LangChain](https://github.com/hwchase17/chat-langchain)
 
 **🤖 Agents**
 

SECURITY.md

@@ -1,6 +0,0 @@
-# Security Policy
-
-## Reporting a Vulnerability
-
-Please report security vulnerabilities by email to `security@langchain.dev`.
-This email is an alias to a subset of our maintainers, and will ensure the issue is promptly triaged and acted upon as needed.

cookbook/LLaMA2_sql_chat.ipynb

@@ -1,400 +0,0 @@
-{
- "cells": [
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "id": "fc935871-7640-41c6-b798-58514d860fe0",
-   "metadata": {},
-   "source": [
-    "## LLaMA2 chat with SQL\n",
-    "\n",
-    "Open source, local LLMs are great to consider for any application that demands data privacy.\n",
-    "\n",
-    "SQL is one good example. \n",
-    "\n",
-    "This cookbook shows how to perform text-to-SQL using various local versions of LLaMA2 run locally.\n",
-    "\n",
-    "## Packages"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "81adcf8b-395a-4f02-8749-ac976942b446",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "! pip install langchain replicate"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "8e13ed66-300b-4a23-b8ac-44df68ee4733",
-   "metadata": {},
-   "source": [
-    "## LLM\n",
-    "\n",
-    "There are a few ways to access LLaMA2.\n",
-    "\n",
-    "To run locally, we use Ollama.ai. \n",
-    "\n",
-    "See [here](https://python.langchain.com/docs/integrations/chat/ollama) for details on installation and setup.\n",
-    "\n",
-    "Also, see [here](https://python.langchain.com/docs/guides/local_llms) for our full guide on local LLMs.\n",
-    " \n",
-    "To use an external API, which is not private, we can use Replicate."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "6a75a5c6-34ee-4ab9-a664-d9b432d812ee",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Init param `input` is deprecated, please use `model_kwargs` instead.\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Local \n",
-    "from langchain.chat_models import ChatOllama\n",
-    "llama2_chat = ChatOllama(model=\"llama2:13b-chat\")\n",
-    "llama2_code = ChatOllama(model=\"codellama:7b-instruct\")\n",
-    "\n",
-    "# API\n",
-    "from getpass import getpass\n",
-    "from langchain.llms import Replicate\n",
-    "# REPLICATE_API_TOKEN = getpass()\n",
-    "# os.environ[\"REPLICATE_API_TOKEN\"] = REPLICATE_API_TOKEN\n",
-    "replicate_id = \"meta/llama-2-13b-chat:f4e2de70d66816a838a89eeeb621910adffb0dd0baba3976c96980970978018d\"\n",
-    "llama2_chat_replicate = Replicate(\n",
-    "    model=replicate_id,\n",
-    "    input={\"temperature\": 0.01, \n",
-    "           \"max_length\": 500, \n",
-    "           \"top_p\": 1}\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "ce96f7ea-b3d5-44e1-9fa5-a79e04a9e1fb",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Simply set the LLM we want to use\n",
-    "llm = llama2_chat"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "80222165-f353-4e35-a123-5f70fd70c6c8",
-   "metadata": {},
-   "source": [
-    "## DB\n",
-    "\n",
-    "Connect to a SQLite DB.\n",
-    "\n",
-    "To create this particular DB, you can use the code and follow the steps shown [here](https://github.com/facebookresearch/llama-recipes/blob/main/demo_apps/StructuredLlama.ipynb)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "025bdd82-3bb1-4948-bc7c-c3ccd94fd05c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.utilities import SQLDatabase\n",
-    "db = SQLDatabase.from_uri(\"sqlite:///nba_roster.db\", sample_rows_in_table_info= 0)\n",
-    "\n",
-    "def get_schema(_):\n",
-    "    return db.get_table_info()\n",
-    "\n",
-    "def run_query(query):\n",
-    "    return db.run(query)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "654b3577-baa2-4e12-a393-f40e5db49ac7",
-   "metadata": {},
-   "source": [
-    "## Query a SQL DB \n",
-    "\n",
-    "Follow the runnables workflow [here](https://python.langchain.com/docs/expression_language/cookbook/sql_db)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "5a4933ea-d9c0-4b0a-8177-ba4490c6532b",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "' SELECT \"Team\" FROM nba_roster WHERE \"NAME\" = \\'Klay Thompson\\';'"
-      ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Prompt\n",
-    "from langchain.prompts import ChatPromptTemplate\n",
-    "template = \"\"\"Based on the table schema below, write a SQL query that would answer the user's question:\n",
-    "{schema}\n",
-    "\n",
-    "Question: {question}\n",
-    "SQL Query:\"\"\"\n",
-    "prompt = ChatPromptTemplate.from_messages([\n",
-    "    (\"system\", \"Given an input question, convert it to a SQL query. No pre-amble.\"),\n",
-    "    (\"human\", template)\n",
-    "])\n",
-    "\n",
-    "# Chain to query\n",
-    "from langchain.schema.output_parser import StrOutputParser\n",
-    "from langchain.schema.runnable import RunnablePassthrough\n",
-    "\n",
-    "sql_response = (\n",
-    "        RunnablePassthrough.assign(schema=get_schema)\n",
-    "        | prompt\n",
-    "        | llm.bind(stop=[\"\\nSQLResult:\"])\n",
-    "        | StrOutputParser()\n",
-    "    )\n",
-    "\n",
-    "sql_response.invoke({\"question\": \"What team is Klay Thompson on?\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "a0e9e2c8-9b88-4853-ac86-001bc6cc6695",
-   "metadata": {},
-   "source": [
-    "We can review the results:\n",
-    "\n",
-    "* [LangSmith trace](https://smith.langchain.com/public/afa56a06-b4e2-469a-a60f-c1746e75e42b/r) LLaMA2-13 Replicate API\n",
-    "* [LangSmith trace](https://smith.langchain.com/public/2d4ecc72-6b8f-4523-8f0b-ea95c6b54a1d/r) LLaMA2-13 local \n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "2a2825e3-c1b6-4f7d-b9c9-d9835de323bb",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=' Based on the table schema and SQL query, there are 30 unique teams in the NBA.')"
-      ]
-     },
-     "execution_count": 15,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Chain to answer\n",
-    "template = \"\"\"Based on the table schema below, question, sql query, and sql response, write a natural language response:\n",
-    "{schema}\n",
-    "\n",
-    "Question: {question}\n",
-    "SQL Query: {query}\n",
-    "SQL Response: {response}\"\"\"\n",
-    "prompt_response = ChatPromptTemplate.from_messages([\n",
-    "    (\"system\", \"Given an input question and SQL response, convert it to a natural langugae answer. No pre-amble.\"),\n",
-    "    (\"human\", template)\n",
-    "])\n",
-    "\n",
-    "full_chain = (\n",
-    "    RunnablePassthrough.assign(query=sql_response) \n",
-    "    | RunnablePassthrough.assign(\n",
-    "        schema=get_schema,\n",
-    "        response=lambda x: db.run(x[\"query\"]),\n",
-    "    )\n",
-    "    | prompt_response \n",
-    "    | llm\n",
-    ")\n",
-    "\n",
-    "full_chain.invoke({\"question\": \"How many unique teams are there?\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "ec17b3ee-6618-4681-b6df-089bbb5ffcd7",
-   "metadata": {},
-   "source": [
-    "We can review the results:\n",
-    "\n",
-    "* [LangSmith trace](https://smith.langchain.com/public/10420721-746a-4806-8ecf-d6dc6399d739/r) LLaMA2-13 Replicate API\n",
-    "* [LangSmith trace](https://smith.langchain.com/public/5265ebab-0a22-4f37-936b-3300f2dfa1c1/r) LLaMA2-13 local "
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "1e85381b-1edc-4bb3-a7bd-2ab23f81e54d",
-   "metadata": {},
-   "source": [
-    "## Chat with a SQL DB \n",
-    "\n",
-    "Next, we can add memory."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "id": "1985aa1c-eb8f-4fb1-a54f-c8aa10744687",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "' SELECT \"Team\" FROM nba_roster WHERE \"NAME\" = \\'Klay Thompson\\';'"
-      ]
-     },
-     "execution_count": 19,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Prompt\n",
-    "from langchain.memory import ConversationBufferMemory\n",
-    "from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
-    "template = \"\"\"Based on the table schema below, write a SQL query that would answer the user's question:\n",
-    "{schema}\n",
-    "\n",
-    "Question: {question}\n",
-    "SQL Query:\"\"\"\n",
-    "prompt = ChatPromptTemplate.from_messages([\n",
-    "    (\"system\", \"Given an input question, convert it to a SQL query. No pre-amble.\"),\n",
-    "    MessagesPlaceholder(variable_name=\"history\"),\n",
-    "    (\"human\", template)\n",
-    "])\n",
-    "\n",
-    "memory = ConversationBufferMemory(return_messages=True)\n",
-    "\n",
-    "# Chain to query with memory \n",
-    "from langchain.schema.runnable import RunnableLambda\n",
-    "\n",
-    "sql_chain = (\n",
-    "    RunnablePassthrough.assign(\n",
-    "       schema=get_schema,\n",
-    "       history=RunnableLambda(lambda x: memory.load_memory_variables(x)[\"history\"])\n",
-    "    )| prompt\n",
-    "    | llm.bind(stop=[\"\\nSQLResult:\"])\n",
-    "    | StrOutputParser()\n",
-    ")\n",
-    "\n",
-    "def save(input_output):\n",
-    "    output = {\"output\": input_output.pop(\"output\")}\n",
-    "    memory.save_context(input_output, output)\n",
-    "    return output['output']\n",
-    "    \n",
-    "sql_response_memory = RunnablePassthrough.assign(output=sql_chain) | save\n",
-    "sql_response_memory.invoke({\"question\": \"What team is Klay Thompson on?\"})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 20,
-   "id": "0b45818a-1498-441d-b82d-23c29428c2bb",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "' SELECT \"SALARY\" FROM nba_roster WHERE \"NAME\" = \\'Klay Thompson\\';'"
-      ]
-     },
-     "execution_count": 20,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "sql_response_memory.invoke({\"question\": \"What is his salary?\"})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 21,
-   "id": "800a7a3b-f411-478b-af51-2310cd6e0425",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=' Sure! Here\\'s the natural language response based on the given input:\\n\\n\"Klay Thompson\\'s salary is $43,219,440.\"')"
-      ]
-     },
-     "execution_count": 21,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Chain to answer\n",
-    "template = \"\"\"Based on the table schema below, question, sql query, and sql response, write a natural language response:\n",
-    "{schema}\n",
-    "\n",
-    "Question: {question}\n",
-    "SQL Query: {query}\n",
-    "SQL Response: {response}\"\"\"\n",
-    "prompt_response = ChatPromptTemplate.from_messages([\n",
-    "    (\"system\", \"Given an input question and SQL response, convert it to a natural langugae answer. No pre-amble.\"),\n",
-    "    (\"human\", template)\n",
-    "])\n",
-    "\n",
-    "full_chain = (\n",
-    "    RunnablePassthrough.assign(query=sql_response_memory) \n",
-    "    | RunnablePassthrough.assign(\n",
-    "        schema=get_schema,\n",
-    "        response=lambda x: db.run(x[\"query\"]),\n",
-    "    )\n",
-    "    | prompt_response \n",
-    "    | llm\n",
-    ")\n",
-    "\n",
-    "full_chain.invoke({\"question\": \"What is his salary?\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "b77fee61-f4da-4bb1-8285-14101e505518",
-   "metadata": {},
-   "source": [
-    "Here is the [trace](https://smith.langchain.com/public/54794d18-2337-4ce2-8b9f-3d8a2df89e51/r)."
-   ]
-  }
- ],
- "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": "3.9.16"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/README.md

@@ -1,51 +0,0 @@
-# LangChain cookbook
-
-Example code for building applications with LangChain, with an emphasis on more applied and end-to-end examples than contained in the [main documentation](https://python.langchain.com).
-
-Notebook | Description
-:- | :-
-[LLaMA2_sql_chat.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/LLaMA2_sql_chat.ipynb) | Build a chat application that interacts with a sql database using an open source llm (llama2), specifically demonstrated on a sqlite database containing nba rosters.
-[Semi_Structured_RAG.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/Semi_Structured_RAG.ipynb) | Perform retrieval-augmented generation (rag) on documents with semi-structured data, including text and tables, using unstructured for parsing, multi-vector retriever for storing, and lcel for implementing chains.
-[Semi_structured_and_multi_moda...](https://github.com/langchain-ai/langchain/tree/master/cookbook/Semi_structured_and_multi_modal_RAG.ipynb) | Perform retrieval-augmented generation (rag) on documents with semi-structured data and images, using unstructured for parsing, multi-vector retriever for storage and retrieval, and lcel for implementing chains.
-[Semi_structured_multi_modal_RA...](https://github.com/langchain-ai/langchain/tree/master/cookbook/Semi_structured_multi_modal_RAG_LLaMA2.ipynb) | Perform retrieval-augmented generation (rag) on documents with semi-structured data and images, using various tools and methods such as unstructured for parsing, multi-vector retriever for storing, lcel for implementing chains, and open source language models like llama2, llava, and gpt4all.
-[autogpt/autogpt.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/autogpt/autogpt.ipynb) | Implement autogpt, a language model, with langchain primitives such as llms, prompttemplates, vectorstores, embeddings, and tools.
-[autogpt/marathon_times.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/autogpt/marathon_times.ipynb) | Implement autogpt for finding winning marathon times.
-[baby_agi.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/baby_agi.ipynb) | Implement babyagi, an ai agent that can generate and execute tasks based on a given objective, with the flexibility to swap out specific vectorstores/model providers.
-[baby_agi_with_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/baby_agi_with_agent.ipynb) | Swap out the execution chain in the babyagi notebook with an agent that has access to tools, aiming to obtain more reliable information.
-[camel_role_playing.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/camel_role_playing.ipynb) | Implement the camel framework for creating autonomous cooperative agents in large scale language models, using role-playing and inception prompting to guide chat agents towards task completion.
-[causal_program_aided_language_...](https://github.com/langchain-ai/langchain/tree/master/cookbook/causal_program_aided_language_model.ipynb) | Implement the causal program-aided language (cpal) chain, which improves upon the program-aided language (pal) by incorporating causal structure to prevent hallucination in language models, particularly when dealing with complex narratives and math problems with nested dependencies.
-[code-analysis-deeplake.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/code-analysis-deeplake.ipynb) | Analyze its own code base with the help of gpt and activeloop's deep lake.
-[custom_agent_with_plugin_retri...](https://github.com/langchain-ai/langchain/tree/master/cookbook/custom_agent_with_plugin_retrieval.ipynb) | Build a custom agent that can interact with ai plugins by retrieving tools and creating natural language wrappers around openapi endpoints.
-[custom_agent_with_plugin_retri...](https://github.com/langchain-ai/langchain/tree/master/cookbook/custom_agent_with_plugin_retrieval_using_plugnplai.ipynb) | Build a custom agent with plugin retrieval functionality, utilizing ai plugins from the `plugnplai` directory.
-[databricks_sql_db.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/databricks_sql_db.ipynb) | Connect to databricks runtimes and databricks sql.
-[deeplake_semantic_search_over_...](https://github.com/langchain-ai/langchain/tree/master/cookbook/deeplake_semantic_search_over_chat.ipynb) | Perform semantic search and question-answering over a group chat using activeloop's deep lake with gpt4.
-[elasticsearch_db_qa.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/elasticsearch_db_qa.ipynb) | Interact with elasticsearch analytics databases in natural language and build search queries via the elasticsearch dsl api.
-[forward_looking_retrieval_augm...](https://github.com/langchain-ai/langchain/tree/master/cookbook/forward_looking_retrieval_augmented_generation.ipynb) | Implement the forward-looking active retrieval augmented generation (flare) method, which generates answers to questions, identifies uncertain tokens, generates hypothetical questions based on these tokens, and retrieves relevant documents to continue generating the answer.
-[generative_agents_interactive_...](https://github.com/langchain-ai/langchain/tree/master/cookbook/generative_agents_interactive_simulacra_of_human_behavior.ipynb) | Implement a generative agent that simulates human behavior, based on a research paper, using a time-weighted memory object backed by a langchain retriever.
-[gymnasium_agent_simulation.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/gymnasium_agent_simulation.ipynb) | Create a simple agent-environment interaction loop in simulated environments like text-based games with gymnasium.
-[hugginggpt.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/hugginggpt.ipynb) | Implement hugginggpt, a system that connects language models like chatgpt with the machine learning community via hugging face.
-[hypothetical_document_embeddin...](https://github.com/langchain-ai/langchain/tree/master/cookbook/hypothetical_document_embeddings.ipynb) | Improve document indexing with hypothetical document embeddings (hyde), an embedding technique that generates and embeds hypothetical answers to queries.
-[learned_prompt_optimization.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/learned_prompt_optimization.ipynb) | Automatically enhance language model prompts by injecting specific terms using reinforcement learning, which can be used to personalize responses based on user preferences.
-[llm_bash.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/llm_bash.ipynb) | Perform simple filesystem commands using language learning models (llms) and a bash process.
-[llm_checker.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/llm_checker.ipynb) | Create a self-checking chain using the llmcheckerchain function.
-[llm_math.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/llm_math.ipynb) | Solve complex word math problems using language models and python repls.
-[llm_summarization_checker.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/llm_summarization_checker.ipynb) | Check the accuracy of text summaries, with the option to run the checker multiple times for improved results.
-[llm_symbolic_math.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/llm_symbolic_math.ipynb) | Solve algebraic equations with the help of llms (language learning models) and sympy, a python library for symbolic mathematics.
-[meta_prompt.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/meta_prompt.ipynb) | Implement the meta-prompt concept, which is a method for building self-improving agents that reflect on their own performance and modify their instructions accordingly.
-[multi_modal_output_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_modal_output_agent.ipynb) | Generate multi-modal outputs, specifically images and text.
-[multi_player_dnd.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_player_dnd.ipynb) | Simulate multi-player dungeons & dragons games, with a custom function determining the speaking schedule of the agents.
-[multiagent_authoritarian.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multiagent_authoritarian.ipynb) | Implement a multi-agent simulation where a privileged agent controls the conversation, including deciding who speaks and when the conversation ends, in the context of a simulated news network.
-[multiagent_bidding.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multiagent_bidding.ipynb) | Implement a multi-agent simulation where agents bid to speak, with the highest bidder speaking next, demonstrated through a fictitious presidential debate example.
-[myscale_vector_sql.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/myscale_vector_sql.ipynb) | Access and interact with the myscale integrated vector database, which can enhance the performance of language model (llm) applications.
-[openai_functions_retrieval_qa....](https://github.com/langchain-ai/langchain/tree/master/cookbook/openai_functions_retrieval_qa.ipynb) | Structure response output in a question answering system by incorporating openai functions into a retrieval pipeline.
-[petting_zoo.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/petting_zoo.ipynb) | Create multi-agent simulations with simulated environments using the petting zoo library.
-[plan_and_execute_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/plan_and_execute_agent.ipynb) | Create plan-and-execute agents that accomplish objectives by planning tasks with a language model (llm) and executing them with a separate agent.
-[program_aided_language_model.i...](https://github.com/langchain-ai/langchain/tree/master/cookbook/program_aided_language_model.ipynb) | Implement program-aided language models as described in the provided research paper.
-[sales_agent_with_context.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/sales_agent_with_context.ipynb) | Implement a context-aware ai sales agent, salesgpt, that can have natural sales conversations, interact with other systems, and use a product knowledge base to discuss a company's offerings.
-[self_query_hotel_search.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/self_query_hotel_search.ipynb) | Build a hotel room search feature with self-querying retrieval, using a specific hotel recommendation dataset.
-[smart_llm.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/smart_llm.ipynb) | Implement a smartllmchain, a self-critique chain that generates multiple output proposals, critiques them to find the best one, and then improves upon it to produce a final output.
-[tree_of_thought.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/tree_of_thought.ipynb) | Query a large language model using the tree of thought technique.
-[twitter-the-algorithm-analysis...](https://github.com/langchain-ai/langchain/tree/master/cookbook/twitter-the-algorithm-analysis-deeplake.ipynb) | Analyze the source code of the twitter algorithm with the help of gpt4 and activeloop's deep lake.
-[two_agent_debate_tools.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/two_agent_debate_tools.ipynb) | Simulate multi-agent dialogues where the agents can utilize various tools.
-[two_player_dnd.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/two_player_dnd.ipynb) | Simulate a two-player dungeons & dragons game, where a dialoguesimulator class is used to coordinate the dialogue between the protagonist and the dungeon master.
-[wikibase_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/wikibase_agent.ipynb) | Create a simple wikibase agent that utilizes sparql generation, with testing done on http://wikidata.org.

cookbook/baby_agi.ipynb

@@ -1,257 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "517a9fd4",
-   "metadata": {},
-   "source": [
-    "# BabyAGI User Guide\n",
-    "\n",
-    "This notebook demonstrates how to implement [BabyAGI](https://github.com/yoheinakajima/babyagi/tree/main) by [Yohei Nakajima](https://twitter.com/yoheinakajima). BabyAGI is an AI agent that can generate and pretend to execute tasks based on a given objective.\n",
-    "\n",
-    "This guide will help you understand the components to create your own recursive agents.\n",
-    "\n",
-    "Although BabyAGI uses specific vectorstores/model providers (Pinecone, OpenAI), one of the benefits of implementing it with LangChain is that you can easily swap those out for different options. In this implementation we use a FAISS vectorstore (because it runs locally and is free)."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "556af556",
-   "metadata": {},
-   "source": [
-    "## Install and Import Required Modules"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "c8a354b6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "from collections import deque\n",
-    "from typing import Dict, List, Optional, Any\n",
-    "\n",
-    "from langchain.chains import LLMChain\nfrom langchain.llms import OpenAI\nfrom langchain.prompts import PromptTemplate\n",
-    "from langchain.embeddings import OpenAIEmbeddings\n",
-    "from langchain.llms import BaseLLM\n",
-    "from langchain.schema.vectorstore import VectorStore\n",
-    "from pydantic import BaseModel, Field\n",
-    "from langchain.chains.base import Chain\n",
-    "from langchain_experimental.autonomous_agents import BabyAGI"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "09f70772",
-   "metadata": {},
-   "source": [
-    "## Connect to the Vector Store\n",
-    "\n",
-    "Depending on what vectorstore you use, this step may look different."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "794045d4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.vectorstores import FAISS\n",
-    "from langchain.docstore import InMemoryDocstore"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "6e0305eb",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Define your embedding model\n",
-    "embeddings_model = OpenAIEmbeddings()\n",
-    "# Initialize the vectorstore as empty\n",
-    "import faiss\n",
-    "\n",
-    "embedding_size = 1536\n",
-    "index = faiss.IndexFlatL2(embedding_size)\n",
-    "vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "05ba762e",
-   "metadata": {},
-   "source": [
-    "### Run the BabyAGI\n",
-    "\n",
-    "Now it's time to create the BabyAGI controller and watch it try to accomplish your objective."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "3d220b69",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "OBJECTIVE = \"Write a weather report for SF today\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "8a8e5543",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm = OpenAI(temperature=0)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "3d69899b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Logging of LLMChains\n",
-    "verbose = False\n",
-    "# If None, will keep on going forever\n",
-    "max_iterations: Optional[int] = 3\n",
-    "baby_agi = BabyAGI.from_llm(\n",
-    "    llm=llm, vectorstore=vectorstore, verbose=verbose, max_iterations=max_iterations\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "f7957b51",
-   "metadata": {
-    "scrolled": false
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[95m\u001b[1m\n",
-      "*****TASK LIST*****\n",
-      "\u001b[0m\u001b[0m\n",
-      "1: Make a todo list\n",
-      "\u001b[92m\u001b[1m\n",
-      "*****NEXT TASK*****\n",
-      "\u001b[0m\u001b[0m\n",
-      "1: Make a todo list\n",
-      "\u001b[93m\u001b[1m\n",
-      "*****TASK RESULT*****\n",
-      "\u001b[0m\u001b[0m\n",
-      "\n",
-      "\n",
-      "1. Check the weather forecast for San Francisco today\n",
-      "2. Make note of the temperature, humidity, wind speed, and other relevant weather conditions\n",
-      "3. Write a weather report summarizing the forecast\n",
-      "4. Check for any weather alerts or warnings\n",
-      "5. Share the report with the relevant stakeholders\n",
-      "\u001b[95m\u001b[1m\n",
-      "*****TASK LIST*****\n",
-      "\u001b[0m\u001b[0m\n",
-      "2: Check the current temperature in San Francisco\n",
-      "3: Check the current humidity in San Francisco\n",
-      "4: Check the current wind speed in San Francisco\n",
-      "5: Check for any weather alerts or warnings in San Francisco\n",
-      "6: Check the forecast for the next 24 hours in San Francisco\n",
-      "7: Check the forecast for the next 48 hours in San Francisco\n",
-      "8: Check the forecast for the next 72 hours in San Francisco\n",
-      "9: Check the forecast for the next week in San Francisco\n",
-      "10: Check the forecast for the next month in San Francisco\n",
-      "11: Check the forecast for the next 3 months in San Francisco\n",
-      "1: Write a weather report for SF today\n",
-      "\u001b[92m\u001b[1m\n",
-      "*****NEXT TASK*****\n",
-      "\u001b[0m\u001b[0m\n",
-      "2: Check the current temperature in San Francisco\n",
-      "\u001b[93m\u001b[1m\n",
-      "*****TASK RESULT*****\n",
-      "\u001b[0m\u001b[0m\n",
-      "\n",
-      "\n",
-      "I will check the current temperature in San Francisco. I will use an online weather service to get the most up-to-date information.\n",
-      "\u001b[95m\u001b[1m\n",
-      "*****TASK LIST*****\n",
-      "\u001b[0m\u001b[0m\n",
-      "3: Check the current UV index in San Francisco.\n",
-      "4: Check the current air quality in San Francisco.\n",
-      "5: Check the current precipitation levels in San Francisco.\n",
-      "6: Check the current cloud cover in San Francisco.\n",
-      "7: Check the current barometric pressure in San Francisco.\n",
-      "8: Check the current dew point in San Francisco.\n",
-      "9: Check the current wind direction in San Francisco.\n",
-      "10: Check the current humidity levels in San Francisco.\n",
-      "1: Check the current temperature in San Francisco to the average temperature for this time of year.\n",
-      "2: Check the current visibility in San Francisco.\n",
-      "11: Write a weather report for SF today.\n",
-      "\u001b[92m\u001b[1m\n",
-      "*****NEXT TASK*****\n",
-      "\u001b[0m\u001b[0m\n",
-      "3: Check the current UV index in San Francisco.\n",
-      "\u001b[93m\u001b[1m\n",
-      "*****TASK RESULT*****\n",
-      "\u001b[0m\u001b[0m\n",
-      "\n",
-      "\n",
-      "The current UV index in San Francisco is moderate. The UV index is expected to remain at moderate levels throughout the day. It is recommended to wear sunscreen and protective clothing when outdoors.\n",
-      "\u001b[91m\u001b[1m\n",
-      "*****TASK ENDING*****\n",
-      "\u001b[0m\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "{'objective': 'Write a weather report for SF today'}"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "baby_agi({\"objective\": OBJECTIVE})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "898a210b",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.9.16"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/baby_agi_with_agent.ipynb

@@ -1,391 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "517a9fd4",
-   "metadata": {},
-   "source": [
-    "# BabyAGI with Tools\n",
-    "\n",
-    "This notebook builds on top of [baby agi](baby_agi.html), but shows how you can swap out the execution chain. The previous execution chain was just an LLM which made stuff up. By swapping it out with an agent that has access to tools, we can hopefully get real reliable information"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "556af556",
-   "metadata": {},
-   "source": [
-    "## Install and Import Required Modules"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "c8a354b6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "from collections import deque\n",
-    "from typing import Dict, List, Optional, Any\n",
-    "\n",
-    "from langchain.chains import LLMChain\nfrom langchain.llms import OpenAI\nfrom langchain.prompts import PromptTemplate\n",
-    "from langchain.embeddings import OpenAIEmbeddings\n",
-    "from langchain.llms import BaseLLM\n",
-    "from langchain.schema.vectorstore import VectorStore\n",
-    "from pydantic import BaseModel, Field\n",
-    "from langchain.chains.base import Chain\n",
-    "from langchain_experimental.autonomous_agents import BabyAGI"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "09f70772",
-   "metadata": {},
-   "source": [
-    "## Connect to the Vector Store\n",
-    "\n",
-    "Depending on what vectorstore you use, this step may look different."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "794045d4",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Note: you may need to restart the kernel to use updated packages.\n",
-      "Note: you may need to restart the kernel to use updated packages.\n"
-     ]
-    }
-   ],
-   "source": [
-    "%pip install faiss-cpu > /dev/null\n",
-    "%pip install google-search-results > /dev/null\n",
-    "from langchain.vectorstores import FAISS\n",
-    "from langchain.docstore import InMemoryDocstore"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "6e0305eb",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Define your embedding model\n",
-    "embeddings_model = OpenAIEmbeddings()\n",
-    "# Initialize the vectorstore as empty\n",
-    "import faiss\n",
-    "\n",
-    "embedding_size = 1536\n",
-    "index = faiss.IndexFlatL2(embedding_size)\n",
-    "vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0f3b72bf",
-   "metadata": {},
-   "source": [
-    "## Define the Chains\n",
-    "\n",
-    "BabyAGI relies on three LLM chains:\n",
-    "- Task creation chain to select new tasks to add to the list\n",
-    "- Task prioritization chain to re-prioritize tasks\n",
-    "- Execution Chain to execute the tasks\n",
-    "\n",
-    "\n",
-    "NOTE: in this notebook, the Execution chain will now be an agent."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "b43cd580",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.agents import ZeroShotAgent, Tool, AgentExecutor\n",
-    "from langchain.llms import OpenAI\nfrom langchain.utilities import SerpAPIWrapper\nfrom langchain.chains import LLMChain\n",
-    "\n",
-    "todo_prompt = PromptTemplate.from_template(\n",
-    "    \"You are a planner who is an expert at coming up with a todo list for a given objective. Come up with a todo list for this objective: {objective}\"\n",
-    ")\n",
-    "todo_chain = LLMChain(llm=OpenAI(temperature=0), prompt=todo_prompt)\n",
-    "search = SerpAPIWrapper()\n",
-    "tools = [\n",
-    "    Tool(\n",
-    "        name=\"Search\",\n",
-    "        func=search.run,\n",
-    "        description=\"useful for when you need to answer questions about current events\",\n",
-    "    ),\n",
-    "    Tool(\n",
-    "        name=\"TODO\",\n",
-    "        func=todo_chain.run,\n",
-    "        description=\"useful for when you need to come up with todo lists. Input: an objective to create a todo list for. Output: a todo list for that objective. Please be very clear what the objective is!\",\n",
-    "    ),\n",
-    "]\n",
-    "\n",
-    "\n",
-    "prefix = \"\"\"You are an AI who performs one task based on the following objective: {objective}. Take into account these previously completed tasks: {context}.\"\"\"\n",
-    "suffix = \"\"\"Question: {task}\n",
-    "{agent_scratchpad}\"\"\"\n",
-    "prompt = ZeroShotAgent.create_prompt(\n",
-    "    tools,\n",
-    "    prefix=prefix,\n",
-    "    suffix=suffix,\n",
-    "    input_variables=[\"objective\", \"task\", \"context\", \"agent_scratchpad\"],\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "4b00ae2e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm = OpenAI(temperature=0)\n",
-    "llm_chain = LLMChain(llm=llm, prompt=prompt)\n",
-    "tool_names = [tool.name for tool in tools]\n",
-    "agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names)\n",
-    "agent_executor = AgentExecutor.from_agent_and_tools(\n",
-    "    agent=agent, tools=tools, verbose=True\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "05ba762e",
-   "metadata": {},
-   "source": [
-    "### Run the BabyAGI\n",
-    "\n",
-    "Now it's time to create the BabyAGI controller and watch it try to accomplish your objective."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "3d220b69",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "OBJECTIVE = \"Write a weather report for SF today\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "3d69899b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Logging of LLMChains\n",
-    "verbose = False\n",
-    "# If None, will keep on going forever\n",
-    "max_iterations: Optional[int] = 3\n",
-    "baby_agi = BabyAGI.from_llm(\n",
-    "    llm=llm,\n",
-    "    vectorstore=vectorstore,\n",
-    "    task_execution_chain=agent_executor,\n",
-    "    verbose=verbose,\n",
-    "    max_iterations=max_iterations,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "f7957b51",
-   "metadata": {
-    "scrolled": false
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[95m\u001b[1m\n",
-      "*****TASK LIST*****\n",
-      "\u001b[0m\u001b[0m\n",
-      "1: Make a todo list\n",
-      "\u001b[92m\u001b[1m\n",
-      "*****NEXT TASK*****\n",
-      "\u001b[0m\u001b[0m\n",
-      "1: Make a todo list\n",
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThought: I need to come up with a todo list\n",
-      "Action: TODO\n",
-      "Action Input: Write a weather report for SF today\u001b[0m\u001b[33;1m\u001b[1;3m\n",
-      "\n",
-      "1. Research current weather conditions in San Francisco\n",
-      "2. Gather data on temperature, humidity, wind speed, and other relevant weather conditions\n",
-      "3. Analyze data to determine current weather trends\n",
-      "4. Write a brief introduction to the weather report\n",
-      "5. Describe current weather conditions in San Francisco\n",
-      "6. Discuss any upcoming weather changes\n",
-      "7. Summarize the weather report\n",
-      "8. Proofread and edit the report\n",
-      "9. Submit the report\u001b[0m\u001b[32;1m\u001b[1;3m I now know the final answer\n",
-      "Final Answer: The todo list for writing a weather report for SF today is: 1. Research current weather conditions in San Francisco; 2. Gather data on temperature, humidity, wind speed, and other relevant weather conditions; 3. Analyze data to determine current weather trends; 4. Write a brief introduction to the weather report; 5. Describe current weather conditions in San Francisco; 6. Discuss any upcoming weather changes; 7. Summarize the weather report; 8. Proofread and edit the report; 9. Submit the report.\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n",
-      "\u001b[93m\u001b[1m\n",
-      "*****TASK RESULT*****\n",
-      "\u001b[0m\u001b[0m\n",
-      "The todo list for writing a weather report for SF today is: 1. Research current weather conditions in San Francisco; 2. Gather data on temperature, humidity, wind speed, and other relevant weather conditions; 3. Analyze data to determine current weather trends; 4. Write a brief introduction to the weather report; 5. Describe current weather conditions in San Francisco; 6. Discuss any upcoming weather changes; 7. Summarize the weather report; 8. Proofread and edit the report; 9. Submit the report.\n",
-      "\u001b[95m\u001b[1m\n",
-      "*****TASK LIST*****\n",
-      "\u001b[0m\u001b[0m\n",
-      "2: Gather data on precipitation, cloud cover, and other relevant weather conditions;\n",
-      "3: Analyze data to determine any upcoming weather changes;\n",
-      "4: Research current weather forecasts for San Francisco;\n",
-      "5: Create a visual representation of the weather report;\n",
-      "6: Include relevant images and graphics in the report;\n",
-      "7: Format the report for readability;\n",
-      "8: Publish the report online;\n",
-      "9: Monitor the report for accuracy.\n",
-      "\u001b[92m\u001b[1m\n",
-      "*****NEXT TASK*****\n",
-      "\u001b[0m\u001b[0m\n",
-      "2: Gather data on precipitation, cloud cover, and other relevant weather conditions;\n",
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThought: I need to search for current weather conditions in San Francisco\n",
-      "Action: Search\n",
-      "Action Input: Current weather conditions in San Francisco\u001b[0m\u001b[36;1m\u001b[1;3mCurrent Weather for Popular Cities ; San Francisco, CA 46 · Partly Cloudy ; Manhattan, NY warning 52 · Cloudy ; Schiller Park, IL (60176) 40 · Sunny ; Boston, MA 54 ...\u001b[0m\u001b[32;1m\u001b[1;3m I need to compile the data into a weather report\n",
-      "Action: TODO\n",
-      "Action Input: Compile data into a weather report\u001b[0m\u001b[33;1m\u001b[1;3m\n",
-      "\n",
-      "1. Gather data from reliable sources such as the National Weather Service, local weather stations, and other meteorological organizations.\n",
-      "\n",
-      "2. Analyze the data to identify trends and patterns.\n",
-      "\n",
-      "3. Create a chart or graph to visualize the data.\n",
-      "\n",
-      "4. Write a summary of the data and its implications.\n",
-      "\n",
-      "5. Compile the data into a report format.\n",
-      "\n",
-      "6. Proofread the report for accuracy and clarity.\n",
-      "\n",
-      "7. Publish the report to a website or other platform.\n",
-      "\n",
-      "8. Distribute the report to relevant stakeholders.\u001b[0m\u001b[32;1m\u001b[1;3m I now know the final answer\n",
-      "Final Answer: Today in San Francisco, the temperature is 46 degrees Fahrenheit with partly cloudy skies. The forecast for the rest of the day is expected to remain partly cloudy.\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n",
-      "\u001b[93m\u001b[1m\n",
-      "*****TASK RESULT*****\n",
-      "\u001b[0m\u001b[0m\n",
-      "Today in San Francisco, the temperature is 46 degrees Fahrenheit with partly cloudy skies. The forecast for the rest of the day is expected to remain partly cloudy.\n",
-      "\u001b[95m\u001b[1m\n",
-      "*****TASK LIST*****\n",
-      "\u001b[0m\u001b[0m\n",
-      "3: Format the report for readability;\n",
-      "4: Include relevant images and graphics in the report;\n",
-      "5: Compare the current weather conditions in San Francisco to the forecasted conditions;\n",
-      "6: Identify any potential weather-related hazards in the area;\n",
-      "7: Research historical weather patterns in San Francisco;\n",
-      "8: Identify any potential trends in the weather data;\n",
-      "9: Include relevant data sources in the report;\n",
-      "10: Summarize the weather report in a concise manner;\n",
-      "11: Include a summary of the forecasted weather conditions;\n",
-      "12: Include a summary of the current weather conditions;\n",
-      "13: Include a summary of the historical weather patterns;\n",
-      "14: Include a summary of the potential weather-related hazards;\n",
-      "15: Include a summary of the potential trends in the weather data;\n",
-      "16: Include a summary of the data sources used in the report;\n",
-      "17: Analyze data to determine any upcoming weather changes;\n",
-      "18: Research current weather forecasts for San Francisco;\n",
-      "19: Create a visual representation of the weather report;\n",
-      "20: Publish the report online;\n",
-      "21: Monitor the report for accuracy\n",
-      "\u001b[92m\u001b[1m\n",
-      "*****NEXT TASK*****\n",
-      "\u001b[0m\u001b[0m\n",
-      "3: Format the report for readability;\n",
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThought: I need to make sure the report is easy to read;\n",
-      "Action: TODO\n",
-      "Action Input: Make the report easy to read\u001b[0m\u001b[33;1m\u001b[1;3m\n",
-      "\n",
-      "1. Break up the report into sections with clear headings\n",
-      "2. Use bullet points and numbered lists to organize information\n",
-      "3. Use short, concise sentences\n",
-      "4. Use simple language and avoid jargon\n",
-      "5. Include visuals such as charts, graphs, and diagrams to illustrate points\n",
-      "6. Use bold and italicized text to emphasize key points\n",
-      "7. Include a table of contents and page numbers\n",
-      "8. Use a consistent font and font size throughout the report\n",
-      "9. Include a summary at the end of the report\n",
-      "10. Proofread the report for typos and errors\u001b[0m\u001b[32;1m\u001b[1;3m I now know the final answer\n",
-      "Final Answer: The report should be formatted for readability by breaking it up into sections with clear headings, using bullet points and numbered lists to organize information, using short, concise sentences, using simple language and avoiding jargon, including visuals such as charts, graphs, and diagrams to illustrate points, using bold and italicized text to emphasize key points, including a table of contents and page numbers, using a consistent font and font size throughout the report, including a summary at the end of the report, and proofreading the report for typos and errors.\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n",
-      "\u001b[93m\u001b[1m\n",
-      "*****TASK RESULT*****\n",
-      "\u001b[0m\u001b[0m\n",
-      "The report should be formatted for readability by breaking it up into sections with clear headings, using bullet points and numbered lists to organize information, using short, concise sentences, using simple language and avoiding jargon, including visuals such as charts, graphs, and diagrams to illustrate points, using bold and italicized text to emphasize key points, including a table of contents and page numbers, using a consistent font and font size throughout the report, including a summary at the end of the report, and proofreading the report for typos and errors.\n",
-      "\u001b[91m\u001b[1m\n",
-      "*****TASK ENDING*****\n",
-      "\u001b[0m\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "{'objective': 'Write a weather report for SF today'}"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "baby_agi({\"objective\": OBJECTIVE})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "898a210b",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.9.1"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/camel_role_playing.ipynb

@@ -1,707 +0,0 @@
-{
- "cells": [
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# CAMEL Role-Playing Autonomous Cooperative Agents\n",
-    "\n",
-    "This is a langchain implementation of paper: \"CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society\".\n",
-    "\n",
-    "Overview:\n",
-    "\n",
-    "The rapid advancement of conversational and chat-based language models has led to remarkable progress in complex task-solving. However, their success heavily relies on human input to guide the conversation, which can be challenging and time-consuming. This paper explores the potential of building scalable techniques to facilitate autonomous cooperation among communicative agents and provide insight into their \"cognitive\" processes. To address the challenges of achieving autonomous cooperation, we propose a novel communicative agent framework named role-playing. Our approach involves using inception prompting to guide chat agents toward task completion while maintaining consistency with human intentions. We showcase how role-playing can be used to generate conversational data for studying the behaviors and capabilities of chat agents, providing a valuable resource for investigating conversational language models. Our contributions include introducing a novel communicative agent framework, offering a scalable approach for studying the cooperative behaviors and capabilities of multi-agent systems, and open-sourcing our library to support research on communicative agents and beyond.\n",
-    "\n",
-    "The original implementation: https://github.com/lightaime/camel\n",
-    "\n",
-    "Project website: https://www.camel-ai.org/\n",
-    "\n",
-    "Arxiv paper: https://arxiv.org/abs/2303.17760\n"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Import LangChain related modules "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from typing import List\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.prompts.chat import (\n",
-    "    SystemMessagePromptTemplate,\n",
-    "    HumanMessagePromptTemplate,\n",
-    ")\n",
-    "from langchain.schema import (\n",
-    "    AIMessage,\n",
-    "    HumanMessage,\n",
-    "    SystemMessage,\n",
-    "    BaseMessage,\n",
-    ")"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Define a CAMEL agent helper class"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "class CAMELAgent:\n",
-    "    def __init__(\n",
-    "        self,\n",
-    "        system_message: SystemMessage,\n",
-    "        model: ChatOpenAI,\n",
-    "    ) -> None:\n",
-    "        self.system_message = system_message\n",
-    "        self.model = model\n",
-    "        self.init_messages()\n",
-    "\n",
-    "    def reset(self) -> None:\n",
-    "        self.init_messages()\n",
-    "        return self.stored_messages\n",
-    "\n",
-    "    def init_messages(self) -> None:\n",
-    "        self.stored_messages = [self.system_message]\n",
-    "\n",
-    "    def update_messages(self, message: BaseMessage) -> List[BaseMessage]:\n",
-    "        self.stored_messages.append(message)\n",
-    "        return self.stored_messages\n",
-    "\n",
-    "    def step(\n",
-    "        self,\n",
-    "        input_message: HumanMessage,\n",
-    "    ) -> AIMessage:\n",
-    "        messages = self.update_messages(input_message)\n",
-    "\n",
-    "        output_message = self.model(messages)\n",
-    "        self.update_messages(output_message)\n",
-    "\n",
-    "        return output_message"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup OpenAI API key and roles and task for role-playing"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = \"\"\n",
-    "\n",
-    "assistant_role_name = \"Python Programmer\"\n",
-    "user_role_name = \"Stock Trader\"\n",
-    "task = \"Develop a trading bot for the stock market\"\n",
-    "word_limit = 50  # word limit for task brainstorming"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Create a task specify agent for brainstorming and get the specified task"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Specified task: Develop a Python-based swing trading bot that scans market trends, monitors stocks, and generates trading signals to help a stock trader to place optimal buy and sell orders with defined stop losses and profit targets.\n"
-     ]
-    }
-   ],
-   "source": [
-    "task_specifier_sys_msg = SystemMessage(content=\"You can make a task more specific.\")\n",
-    "task_specifier_prompt = \"\"\"Here is a task that {assistant_role_name} will help {user_role_name} to complete: {task}.\n",
-    "Please make it more specific. Be creative and imaginative.\n",
-    "Please reply with the specified task in {word_limit} words or less. Do not add anything else.\"\"\"\n",
-    "task_specifier_template = HumanMessagePromptTemplate.from_template(\n",
-    "    template=task_specifier_prompt\n",
-    ")\n",
-    "task_specify_agent = CAMELAgent(task_specifier_sys_msg, ChatOpenAI(temperature=1.0))\n",
-    "task_specifier_msg = task_specifier_template.format_messages(\n",
-    "    assistant_role_name=assistant_role_name,\n",
-    "    user_role_name=user_role_name,\n",
-    "    task=task,\n",
-    "    word_limit=word_limit,\n",
-    ")[0]\n",
-    "specified_task_msg = task_specify_agent.step(task_specifier_msg)\n",
-    "print(f\"Specified task: {specified_task_msg.content}\")\n",
-    "specified_task = specified_task_msg.content"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Create inception prompts for AI assistant and AI user for role-playing"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "assistant_inception_prompt = \"\"\"Never forget you are a {assistant_role_name} and I am a {user_role_name}. Never flip roles! Never instruct me!\n",
-    "We share a common interest in collaborating to successfully complete a task.\n",
-    "You must help me to complete the task.\n",
-    "Here is the task: {task}. Never forget our task!\n",
-    "I must instruct you based on your expertise and my needs to complete the task.\n",
-    "\n",
-    "I must give you one instruction at a time.\n",
-    "You must write a specific solution that appropriately completes the requested instruction.\n",
-    "You must decline my instruction honestly if you cannot perform the instruction due to physical, moral, legal reasons or your capability and explain the reasons.\n",
-    "Do not add anything else other than your solution to my instruction.\n",
-    "You are never supposed to ask me any questions you only answer questions.\n",
-    "You are never supposed to reply with a flake solution. Explain your solutions.\n",
-    "Your solution must be declarative sentences and simple present tense.\n",
-    "Unless I say the task is completed, you should always start with:\n",
-    "\n",
-    "Solution: <YOUR_SOLUTION>\n",
-    "\n",
-    "<YOUR_SOLUTION> should be specific and provide preferable implementations and examples for task-solving.\n",
-    "Always end <YOUR_SOLUTION> with: Next request.\"\"\"\n",
-    "\n",
-    "user_inception_prompt = \"\"\"Never forget you are a {user_role_name} and I am a {assistant_role_name}. Never flip roles! You will always instruct me.\n",
-    "We share a common interest in collaborating to successfully complete a task.\n",
-    "I must help you to complete the task.\n",
-    "Here is the task: {task}. Never forget our task!\n",
-    "You must instruct me based on my expertise and your needs to complete the task ONLY in the following two ways:\n",
-    "\n",
-    "1. Instruct with a necessary input:\n",
-    "Instruction: <YOUR_INSTRUCTION>\n",
-    "Input: <YOUR_INPUT>\n",
-    "\n",
-    "2. Instruct without any input:\n",
-    "Instruction: <YOUR_INSTRUCTION>\n",
-    "Input: None\n",
-    "\n",
-    "The \"Instruction\" describes a task or question. The paired \"Input\" provides further context or information for the requested \"Instruction\".\n",
-    "\n",
-    "You must give me one instruction at a time.\n",
-    "I must write a response that appropriately completes the requested instruction.\n",
-    "I must decline your instruction honestly if I cannot perform the instruction due to physical, moral, legal reasons or my capability and explain the reasons.\n",
-    "You should instruct me not ask me questions.\n",
-    "Now you must start to instruct me using the two ways described above.\n",
-    "Do not add anything else other than your instruction and the optional corresponding input!\n",
-    "Keep giving me instructions and necessary inputs until you think the task is completed.\n",
-    "When the task is completed, you must only reply with a single word <CAMEL_TASK_DONE>.\n",
-    "Never say <CAMEL_TASK_DONE> unless my responses have solved your task.\"\"\""
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Create a helper helper to get system messages for AI assistant and AI user from role names and the task"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def get_sys_msgs(assistant_role_name: str, user_role_name: str, task: str):\n",
-    "    assistant_sys_template = SystemMessagePromptTemplate.from_template(\n",
-    "        template=assistant_inception_prompt\n",
-    "    )\n",
-    "    assistant_sys_msg = assistant_sys_template.format_messages(\n",
-    "        assistant_role_name=assistant_role_name,\n",
-    "        user_role_name=user_role_name,\n",
-    "        task=task,\n",
-    "    )[0]\n",
-    "\n",
-    "    user_sys_template = SystemMessagePromptTemplate.from_template(\n",
-    "        template=user_inception_prompt\n",
-    "    )\n",
-    "    user_sys_msg = user_sys_template.format_messages(\n",
-    "        assistant_role_name=assistant_role_name,\n",
-    "        user_role_name=user_role_name,\n",
-    "        task=task,\n",
-    "    )[0]\n",
-    "\n",
-    "    return assistant_sys_msg, user_sys_msg"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Create AI assistant agent and AI user agent from obtained system messages"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "assistant_sys_msg, user_sys_msg = get_sys_msgs(\n",
-    "    assistant_role_name, user_role_name, specified_task\n",
-    ")\n",
-    "assistant_agent = CAMELAgent(assistant_sys_msg, ChatOpenAI(temperature=0.2))\n",
-    "user_agent = CAMELAgent(user_sys_msg, ChatOpenAI(temperature=0.2))\n",
-    "\n",
-    "# Reset agents\n",
-    "assistant_agent.reset()\n",
-    "user_agent.reset()\n",
-    "\n",
-    "# Initialize chats\n",
-    "user_msg = HumanMessage(\n",
-    "    content=(\n",
-    "        f\"{user_sys_msg.content}. \"\n",
-    "        \"Now start to give me introductions one by one. \"\n",
-    "        \"Only reply with Instruction and Input.\"\n",
-    "    )\n",
-    ")\n",
-    "\n",
-    "assistant_msg = HumanMessage(content=f\"{assistant_sys_msg.content}\")\n",
-    "assistant_msg = assistant_agent.step(user_msg)"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Start role-playing session to solve the task!"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Original task prompt:\n",
-      "Develop a trading bot for the stock market\n",
-      "\n",
-      "Specified task prompt:\n",
-      "Develop a Python-based swing trading bot that scans market trends, monitors stocks, and generates trading signals to help a stock trader to place optimal buy and sell orders with defined stop losses and profit targets.\n",
-      "\n",
-      "AI User (Stock Trader):\n",
-      "\n",
-      "Instruction: Install the necessary Python libraries for data analysis and trading.\n",
-      "Input: None\n",
-      "\n",
-      "\n",
-      "AI Assistant (Python Programmer):\n",
-      "\n",
-      "Solution: We can install the necessary Python libraries using pip, a package installer for Python. We can install pandas, numpy, matplotlib, and ta-lib for data analysis and trading. We can use the following command to install these libraries:\n",
-      "\n",
-      "```\n",
-      "pip install pandas numpy matplotlib ta-lib\n",
-      "```\n",
-      "\n",
-      "Next request.\n",
-      "\n",
-      "\n",
-      "AI User (Stock Trader):\n",
-      "\n",
-      "Instruction: Import the necessary libraries in the Python script.\n",
-      "Input: None\n",
-      "\n",
-      "\n",
-      "AI Assistant (Python Programmer):\n",
-      "\n",
-      "Solution: We can import the necessary libraries in the Python script using the import statement. We need to import pandas, numpy, matplotlib, and ta-lib for data analysis and trading. We can use the following code to import these libraries:\n",
-      "\n",
-      "```\n",
-      "import pandas as pd\n",
-      "import numpy as np\n",
-      "import matplotlib.pyplot as plt\n",
-      "import talib as ta\n",
-      "```\n",
-      "\n",
-      "Next request.\n",
-      "\n",
-      "\n",
-      "AI User (Stock Trader):\n",
-      "\n",
-      "Instruction: Load historical stock data into a pandas DataFrame.\n",
-      "Input: The path to the CSV file containing the historical stock data.\n",
-      "\n",
-      "\n",
-      "AI Assistant (Python Programmer):\n",
-      "\n",
-      "Solution: We can load historical stock data into a pandas DataFrame using the `read_csv()` function from pandas. We need to pass the path to the CSV file containing the historical stock data as an argument to this function. We can use the following code to load the historical stock data:\n",
-      "\n",
-      "```\n",
-      "df = pd.read_csv('path/to/csv/file.csv')\n",
-      "```\n",
-      "\n",
-      "This will load the historical stock data into a pandas DataFrame called `df`. Next request.\n",
-      "\n",
-      "\n",
-      "AI User (Stock Trader):\n",
-      "\n",
-      "Instruction: Preprocess the historical stock data by setting the date column as the index and sorting the DataFrame in ascending order by date.\n",
-      "Input: None.\n",
-      "\n",
-      "\n",
-      "AI Assistant (Python Programmer):\n",
-      "\n",
-      "Solution: We can preprocess the historical stock data by setting the date column as the index and sorting the DataFrame in ascending order by date using the `set_index()` and `sort_index()` functions from pandas. We can use the following code to preprocess the historical stock data:\n",
-      "\n",
-      "```\n",
-      "df = df.set_index('date')\n",
-      "df = df.sort_index(ascending=True)\n",
-      "```\n",
-      "\n",
-      "This will set the date column as the index and sort the DataFrame in ascending order by date. Next request.\n",
-      "\n",
-      "\n",
-      "AI User (Stock Trader):\n",
-      "\n",
-      "Instruction: Calculate the short-term and long-term moving averages for the stock data using the `ta.SMA()` function from ta-lib.\n",
-      "Input: The period for the short-term moving average and the period for the long-term moving average.\n",
-      "\n",
-      "\n",
-      "AI Assistant (Python Programmer):\n",
-      "\n",
-      "Solution: We can calculate the short-term and long-term moving averages for the stock data using the `ta.SMA()` function from ta-lib. We need to pass the period for the short-term moving average and the period for the long-term moving average as arguments to this function. We can use the following code to calculate the short-term and long-term moving averages:\n",
-      "\n",
-      "```\n",
-      "short_ma = ta.SMA(df['close'], timeperiod=short_period)\n",
-      "long_ma = ta.SMA(df['close'], timeperiod=long_period)\n",
-      "```\n",
-      "\n",
-      "This will calculate the short-term and long-term moving averages for the stock data and store them in the `short_ma` and `long_ma` variables, respectively. Next request.\n",
-      "\n",
-      "\n",
-      "AI User (Stock Trader):\n",
-      "\n",
-      "Instruction: Create a new DataFrame that combines the historical stock data with the short-term and long-term moving averages.\n",
-      "Input: None.\n",
-      "\n",
-      "\n",
-      "AI Assistant (Python Programmer):\n",
-      "\n",
-      "Solution: We can create a new DataFrame that combines the historical stock data with the short-term and long-term moving averages using the `concat()` function from pandas. We need to pass the historical stock data, the short-term moving average, and the long-term moving average as arguments to this function. We can use the following code to create the new DataFrame:\n",
-      "\n",
-      "```\n",
-      "new_df = pd.concat([df, short_ma, long_ma], axis=1)\n",
-      "new_df.columns = ['open', 'high', 'low', 'close', 'volume', 'short_ma', 'long_ma']\n",
-      "```\n",
-      "\n",
-      "This will create a new DataFrame called `new_df` that combines the historical stock data with the short-term and long-term moving averages. The columns of the new DataFrame are named 'open', 'high', 'low', 'close', 'volume', 'short_ma', and 'long_ma'. Next request.\n",
-      "\n",
-      "\n",
-      "AI User (Stock Trader):\n",
-      "\n",
-      "Instruction: Create a new column in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages.\n",
-      "Input: None.\n",
-      "\n",
-      "\n",
-      "AI Assistant (Python Programmer):\n",
-      "\n",
-      "Solution: We can create a new column in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages. We can use the following code to create the new column:\n",
-      "\n",
-      "```\n",
-      "new_df['signal'] = np.where(new_df['short_ma'] > new_df['long_ma'], 1, -1)\n",
-      "```\n",
-      "\n",
-      "This will create a new column called 'signal' in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages. If the short-term moving average is greater than the long-term moving average, the signal is 1 (buy), otherwise the signal is -1 (sell). Next request.\n",
-      "\n",
-      "\n",
-      "AI User (Stock Trader):\n",
-      "\n",
-      "Instruction: Create a new column in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target.\n",
-      "Input: The stop loss and profit target as percentages.\n",
-      "\n",
-      "\n",
-      "AI Assistant (Python Programmer):\n",
-      "\n",
-      "Solution: We can create a new column in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target. We need to pass the stop loss and profit target as percentages as arguments to this function. We can use the following code to create the new column:\n",
-      "\n",
-      "```\n",
-      "stop_loss = stop_loss_percent / 100\n",
-      "profit_target = profit_target_percent / 100\n",
-      "\n",
-      "new_df['pnl'] = 0.0\n",
-      "buy_price = 0.0\n",
-      "for i in range(1, len(new_df)):\n",
-      "    if new_df['signal'][i] == 1 and new_df['signal'][i-1] == -1:\n",
-      "        buy_price = new_df['close'][i]\n",
-      "    elif new_df['signal'][i] == -1 and new_df['signal'][i-1] == 1:\n",
-      "        sell_price = new_df['close'][i]\n",
-      "        if sell_price <= buy_price * (1 - stop_loss):\n",
-      "            new_df['pnl'][i] = -stop_loss\n",
-      "        elif sell_price >= buy_price * (1 + profit_target):\n",
-      "            new_df['pnl'][i] = profit_target\n",
-      "        else:\n",
-      "            new_df['pnl'][i] = (sell_price - buy_price) / buy_price\n",
-      "```\n",
-      "\n",
-      "This will create a new column called 'pnl' in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target. The stop loss and profit target are calculated based on the stop_loss_percent and profit_target_percent variables, respectively. The buy and sell prices are stored in the buy_price and sell_price variables, respectively. If the sell price is less than or equal to the stop loss, the profit or loss is set to -stop_loss. If the sell price is greater than or equal to the profit target, the profit or loss is set to profit_target. Otherwise, the profit or loss is calculated as (sell_price - buy_price) / buy_price. Next request.\n",
-      "\n",
-      "\n",
-      "AI User (Stock Trader):\n",
-      "\n",
-      "Instruction: Calculate the total profit or loss for all trades.\n",
-      "Input: None.\n",
-      "\n",
-      "\n",
-      "AI Assistant (Python Programmer):\n",
-      "\n",
-      "Solution: We can calculate the total profit or loss for all trades by summing the values in the 'pnl' column of the DataFrame. We can use the following code to calculate the total profit or loss:\n",
-      "\n",
-      "```\n",
-      "total_pnl = new_df['pnl'].sum()\n",
-      "```\n",
-      "\n",
-      "This will calculate the total profit or loss for all trades and store it in the total_pnl variable. Next request.\n",
-      "\n",
-      "\n",
-      "AI User (Stock Trader):\n",
-      "\n",
-      "Instruction: Visualize the stock data, short-term moving average, and long-term moving average using a line chart.\n",
-      "Input: None.\n",
-      "\n",
-      "\n",
-      "AI Assistant (Python Programmer):\n",
-      "\n",
-      "Solution: We can visualize the stock data, short-term moving average, and long-term moving average using a line chart using the `plot()` function from pandas. We can use the following code to visualize the data:\n",
-      "\n",
-      "```\n",
-      "plt.figure(figsize=(12,6))\n",
-      "plt.plot(new_df.index, new_df['close'], label='Close')\n",
-      "plt.plot(new_df.index, new_df['short_ma'], label='Short MA')\n",
-      "plt.plot(new_df.index, new_df['long_ma'], label='Long MA')\n",
-      "plt.xlabel('Date')\n",
-      "plt.ylabel('Price')\n",
-      "plt.title('Stock Data with Moving Averages')\n",
-      "plt.legend()\n",
-      "plt.show()\n",
-      "```\n",
-      "\n",
-      "This will create a line chart that visualizes the stock data, short-term moving average, and long-term moving average. The x-axis represents the date and the y-axis represents the price. The chart also includes a legend that labels each line. Next request.\n",
-      "\n",
-      "\n",
-      "AI User (Stock Trader):\n",
-      "\n",
-      "Instruction: Visualize the buy and sell signals using a scatter plot.\n",
-      "Input: None.\n",
-      "\n",
-      "\n",
-      "AI Assistant (Python Programmer):\n",
-      "\n",
-      "Solution: We can visualize the buy and sell signals using a scatter plot using the `scatter()` function from matplotlib. We can use the following code to visualize the signals:\n",
-      "\n",
-      "```\n",
-      "buy_signals = new_df[new_df['signal'] == 1]\n",
-      "sell_signals = new_df[new_df['signal'] == -1]\n",
-      "\n",
-      "plt.figure(figsize=(12,6))\n",
-      "plt.scatter(buy_signals.index, buy_signals['close'], label='Buy', marker='^', color='green')\n",
-      "plt.scatter(sell_signals.index, sell_signals['close'], label='Sell', marker='v', color='red')\n",
-      "plt.plot(new_df.index, new_df['close'], label='Close')\n",
-      "plt.xlabel('Date')\n",
-      "plt.ylabel('Price')\n",
-      "plt.title('Buy and Sell Signals')\n",
-      "plt.legend()\n",
-      "plt.show()\n",
-      "```\n",
-      "\n",
-      "This will create a scatter plot that visualizes the buy and sell signals. The x-axis represents the date and the y-axis represents the price. The chart also includes a legend that labels each point. Next request.\n",
-      "\n",
-      "\n",
-      "AI User (Stock Trader):\n",
-      "\n",
-      "Instruction: Print the total profit or loss for all trades.\n",
-      "Input: None.\n",
-      "\n",
-      "\n",
-      "AI Assistant (Python Programmer):\n",
-      "\n",
-      "Solution: We can print the total profit or loss for all trades using the `print()` function. We can use the following code to print the total profit or loss:\n",
-      "\n",
-      "```\n",
-      "print('Total Profit/Loss: {:.2%}'.format(total_pnl))\n",
-      "```\n",
-      "\n",
-      "This will print the total profit or loss for all trades in percentage format with two decimal places. Next request.\n",
-      "\n",
-      "\n",
-      "AI User (Stock Trader):\n",
-      "\n",
-      "Instruction: Finalize the code by putting all the code snippets together in a single Python script.\n",
-      "Input: The necessary inputs for each code snippet.\n",
-      "\n",
-      "\n",
-      "AI Assistant (Python Programmer):\n",
-      "\n",
-      "Solution: Here is the complete Python script that puts all the code snippets together:\n",
-      "\n",
-      "```\n",
-      "import pandas as pd\n",
-      "import numpy as np\n",
-      "import matplotlib.pyplot as plt\n",
-      "import talib as ta\n",
-      "\n",
-      "# Load historical stock data into a pandas DataFrame\n",
-      "df = pd.read_csv('path/to/csv/file.csv')\n",
-      "\n",
-      "# Preprocess the historical stock data\n",
-      "df = df.set_index('date')\n",
-      "df = df.sort_index(ascending=True)\n",
-      "\n",
-      "# Calculate the short-term and long-term moving averages\n",
-      "short_period = 10\n",
-      "long_period = 30\n",
-      "short_ma = ta.SMA(df['close'], timeperiod=short_period)\n",
-      "long_ma = ta.SMA(df['close'], timeperiod=long_period)\n",
-      "\n",
-      "# Create a new DataFrame that combines the historical stock data with the short-term and long-term moving averages\n",
-      "new_df = pd.concat([df, short_ma, long_ma], axis=1)\n",
-      "new_df.columns = ['open', 'high', 'low', 'close', 'volume', 'short_ma', 'long_ma']\n",
-      "\n",
-      "# Create a new column in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages\n",
-      "new_df['signal'] = np.where(new_df['short_ma'] > new_df['long_ma'], 1, -1)\n",
-      "\n",
-      "# Create a new column in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target\n",
-      "stop_loss_percent = 5\n",
-      "profit_target_percent = 10\n",
-      "stop_loss = stop_loss_percent / 100\n",
-      "profit_target = profit_target_percent / 100\n",
-      "new_df['pnl'] = 0.0\n",
-      "buy_price = 0.0\n",
-      "for i in range(1, len(new_df)):\n",
-      "    if new_df['signal'][i] == 1 and new_df['signal'][i-1] == -1:\n",
-      "        buy_price = new_df['close'][i]\n",
-      "    elif new_df['signal'][i] == -1 and new_df['signal'][i-1] == 1:\n",
-      "        sell_price = new_df['close'][i]\n",
-      "        if sell_price <= buy_price * (1 - stop_loss):\n",
-      "            new_df['pnl'][i] = -stop_loss\n",
-      "        elif sell_price >= buy_price * (1 + profit_target):\n",
-      "            new_df['pnl'][i] = profit_target\n",
-      "        else:\n",
-      "            new_df['pnl'][i] = (sell_price - buy_price) / buy_price\n",
-      "\n",
-      "# Calculate the total profit or loss for all trades\n",
-      "total_pnl = new_df['pnl'].sum()\n",
-      "\n",
-      "# Visualize the stock data, short-term moving average, and long-term moving average using a line chart\n",
-      "plt.figure(figsize=(12,6))\n",
-      "plt.plot(new_df.index, new_df['close'], label='Close')\n",
-      "plt.plot(new_df.index, new_df['short_ma'], label='Short MA')\n",
-      "plt.plot(new_df.index, new_df['long_ma'], label='Long MA')\n",
-      "plt.xlabel('Date')\n",
-      "plt.ylabel('Price')\n",
-      "plt.title('Stock Data with Moving Averages')\n",
-      "plt.legend()\n",
-      "plt.show()\n",
-      "\n",
-      "# Visualize the buy and sell signals using a scatter plot\n",
-      "buy_signals = new_df[new_df['signal'] == 1]\n",
-      "sell_signals = new_df[new_df['signal'] == -1]\n",
-      "plt.figure(figsize=(12,6))\n",
-      "plt.scatter(buy_signals.index, buy_signals['close'], label='Buy', marker='^', color='green')\n",
-      "plt.scatter(sell_signals.index, sell_signals['close'], label='Sell', marker='v', color='red')\n",
-      "plt.plot(new_df.index, new_df['close'], label='Close')\n",
-      "plt.xlabel('Date')\n",
-      "plt.ylabel('Price')\n",
-      "plt.title('Buy and Sell Signals')\n",
-      "plt.legend()\n",
-      "plt.show()\n",
-      "\n",
-      "# Print the total profit or loss for all trades\n",
-      "print('Total Profit/Loss: {:.2%}'.format(total_pnl))\n",
-      "```\n",
-      "\n",
-      "You need to replace the path/to/csv/file.csv with the actual path to the CSV file containing the historical stock data. You can also adjust the short_period, long_period, stop_loss_percent, and profit_target_percent variables to suit your needs.\n",
-      "\n",
-      "\n",
-      "AI User (Stock Trader):\n",
-      "\n",
-      "<CAMEL_TASK_DONE>\n",
-      "\n",
-      "\n",
-      "AI Assistant (Python Programmer):\n",
-      "\n",
-      "Great! Let me know if you need any further assistance.\n",
-      "\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(f\"Original task prompt:\\n{task}\\n\")\n",
-    "print(f\"Specified task prompt:\\n{specified_task}\\n\")\n",
-    "\n",
-    "chat_turn_limit, n = 30, 0\n",
-    "while n < chat_turn_limit:\n",
-    "    n += 1\n",
-    "    user_ai_msg = user_agent.step(assistant_msg)\n",
-    "    user_msg = HumanMessage(content=user_ai_msg.content)\n",
-    "    print(f\"AI User ({user_role_name}):\\n\\n{user_msg.content}\\n\\n\")\n",
-    "\n",
-    "    assistant_ai_msg = assistant_agent.step(user_msg)\n",
-    "    assistant_msg = HumanMessage(content=assistant_ai_msg.content)\n",
-    "    print(f\"AI Assistant ({assistant_role_name}):\\n\\n{assistant_msg.content}\\n\\n\")\n",
-    "    if \"<CAMEL_TASK_DONE>\" in user_msg.content:\n",
-    "        break"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "camel",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.9"
-  },
-  "orig_nbformat": 4
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

cookbook/databricks_sql_db.ipynb

@@ -1,273 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "707d13a7",
-   "metadata": {},
-   "source": [
-    "# Databricks\n",
-    "\n",
-    "This notebook covers how to connect to the [Databricks runtimes](https://docs.databricks.com/runtime/index.html) and [Databricks SQL](https://www.databricks.com/product/databricks-sql) using the SQLDatabase wrapper of LangChain.\n",
-    "It is broken into 3 parts: installation and setup, connecting to Databricks, and examples."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0076d072",
-   "metadata": {},
-   "source": [
-    "## Installation and Setup"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "739b489b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!pip install databricks-sql-connector"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "73113163",
-   "metadata": {},
-   "source": [
-    "## Connecting to Databricks\n",
-    "\n",
-    "You can connect to [Databricks runtimes](https://docs.databricks.com/runtime/index.html) and [Databricks SQL](https://www.databricks.com/product/databricks-sql) using the `SQLDatabase.from_databricks()` method.\n",
-    "\n",
-    "### Syntax\n",
-    "```python\n",
-    "SQLDatabase.from_databricks(\n",
-    "    catalog: str,\n",
-    "    schema: str,\n",
-    "    host: Optional[str] = None,\n",
-    "    api_token: Optional[str] = None,\n",
-    "    warehouse_id: Optional[str] = None,\n",
-    "    cluster_id: Optional[str] = None,\n",
-    "    engine_args: Optional[dict] = None,\n",
-    "    **kwargs: Any)\n",
-    "```\n",
-    "### Required Parameters\n",
-    "* `catalog`: The catalog name in the Databricks database.\n",
-    "* `schema`: The schema name in the catalog.\n",
-    "\n",
-    "### Optional Parameters\n",
-    "There following parameters are optional. When executing the method in a Databricks notebook, you don't need to provide them in most of the cases.\n",
-    "* `host`: The Databricks workspace hostname, excluding 'https://' part. Defaults to 'DATABRICKS_HOST' environment variable or current workspace if in a Databricks notebook.\n",
-    "* `api_token`: The Databricks personal access token for accessing the Databricks SQL warehouse or the cluster. Defaults to 'DATABRICKS_TOKEN' environment variable or a temporary one is generated if in a Databricks notebook.\n",
-    "* `warehouse_id`: The warehouse ID in the Databricks SQL.\n",
-    "* `cluster_id`: The cluster ID in the Databricks Runtime. If running in a Databricks notebook and both 'warehouse_id' and 'cluster_id' are None, it uses the ID of the cluster the notebook is attached to.\n",
-    "* `engine_args`: The arguments to be used when connecting Databricks.\n",
-    "* `**kwargs`: Additional keyword arguments for the `SQLDatabase.from_uri` method."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "b11c7e48",
-   "metadata": {},
-   "source": [
-    "## Examples"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "8102bca0",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Connecting to Databricks with SQLDatabase wrapper\n",
-    "from langchain.utilities import SQLDatabase\n",
-    "\n",
-    "db = SQLDatabase.from_databricks(catalog=\"samples\", schema=\"nyctaxi\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "9dd36f58",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Creating a OpenAI Chat LLM wrapper\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "\n",
-    "llm = ChatOpenAI(temperature=0, model_name=\"gpt-4\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "5b5c5f1a",
-   "metadata": {},
-   "source": [
-    "### SQL Chain example\n",
-    "\n",
-    "This example demonstrates the use of the [SQL Chain](https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html) for answering a question over a Databricks database."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "36f2270b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.utilities import SQLDatabaseChain\n",
-    "\n",
-    "db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "4e2b5f25",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new SQLDatabaseChain chain...\u001b[0m\n",
-      "What is the average duration of taxi rides that start between midnight and 6am?\n",
-      "SQLQuery:\u001b[32;1m\u001b[1;3mSELECT AVG(UNIX_TIMESTAMP(tpep_dropoff_datetime) - UNIX_TIMESTAMP(tpep_pickup_datetime)) as avg_duration\n",
-      "FROM trips\n",
-      "WHERE HOUR(tpep_pickup_datetime) >= 0 AND HOUR(tpep_pickup_datetime) < 6\u001b[0m\n",
-      "SQLResult: \u001b[33;1m\u001b[1;3m[(987.8122786304605,)]\u001b[0m\n",
-      "Answer:\u001b[32;1m\u001b[1;3mThe average duration of taxi rides that start between midnight and 6am is 987.81 seconds.\u001b[0m\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'The average duration of taxi rides that start between midnight and 6am is 987.81 seconds.'"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "db_chain.run(\n",
-    "    \"What is the average duration of taxi rides that start between midnight and 6am?\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e496d5e5",
-   "metadata": {},
-   "source": [
-    "### SQL Database Agent example\n",
-    "\n",
-    "This example demonstrates the use of the [SQL Database Agent](/docs/integrations/toolkits/sql_database.html) for answering questions over a Databricks database."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "9918e86a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.agents import create_sql_agent\n",
-    "from langchain.agents.agent_toolkits import SQLDatabaseToolkit\n",
-    "\n",
-    "toolkit = SQLDatabaseToolkit(db=db, llm=llm)\n",
-    "agent = create_sql_agent(llm=llm, toolkit=toolkit, verbose=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "c484a76e",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mAction: list_tables_sql_db\n",
-      "Action Input: \u001b[0m\n",
-      "Observation: \u001b[38;5;200m\u001b[1;3mtrips\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI should check the schema of the trips table to see if it has the necessary columns for trip distance and duration.\n",
-      "Action: schema_sql_db\n",
-      "Action Input: trips\u001b[0m\n",
-      "Observation: \u001b[33;1m\u001b[1;3m\n",
-      "CREATE TABLE trips (\n",
-      "\ttpep_pickup_datetime TIMESTAMP, \n",
-      "\ttpep_dropoff_datetime TIMESTAMP, \n",
-      "\ttrip_distance FLOAT, \n",
-      "\tfare_amount FLOAT, \n",
-      "\tpickup_zip INT, \n",
-      "\tdropoff_zip INT\n",
-      ") USING DELTA\n",
-      "\n",
-      "/*\n",
-      "3 rows from trips table:\n",
-      "tpep_pickup_datetime\ttpep_dropoff_datetime\ttrip_distance\tfare_amount\tpickup_zip\tdropoff_zip\n",
-      "2016-02-14 16:52:13+00:00\t2016-02-14 17:16:04+00:00\t4.94\t19.0\t10282\t10171\n",
-      "2016-02-04 18:44:19+00:00\t2016-02-04 18:46:00+00:00\t0.28\t3.5\t10110\t10110\n",
-      "2016-02-17 17:13:57+00:00\t2016-02-17 17:17:55+00:00\t0.7\t5.0\t10103\t10023\n",
-      "*/\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mThe trips table has the necessary columns for trip distance and duration. I will write a query to find the longest trip distance and its duration.\n",
-      "Action: query_checker_sql_db\n",
-      "Action Input: SELECT trip_distance, tpep_dropoff_datetime - tpep_pickup_datetime as duration FROM trips ORDER BY trip_distance DESC LIMIT 1\u001b[0m\n",
-      "Observation: \u001b[31;1m\u001b[1;3mSELECT trip_distance, tpep_dropoff_datetime - tpep_pickup_datetime as duration FROM trips ORDER BY trip_distance DESC LIMIT 1\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mThe query is correct. I will now execute it to find the longest trip distance and its duration.\n",
-      "Action: query_sql_db\n",
-      "Action Input: SELECT trip_distance, tpep_dropoff_datetime - tpep_pickup_datetime as duration FROM trips ORDER BY trip_distance DESC LIMIT 1\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3m[(30.6, '0 00:43:31.000000000')]\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI now know the final answer.\n",
-      "Final Answer: The longest trip distance is 30.6 miles and it took 43 minutes and 31 seconds.\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'The longest trip distance is 30.6 miles and it took 43 minutes and 31 seconds.'"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "agent.run(\"What is the longest trip distance and how long did it take?\")"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.3"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/deeplake_semantic_search_over_chat.ipynb

@@ -1,257 +0,0 @@
-{
- "cells": [
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# QA using Activeloop's DeepLake\n",
-    "In this tutorial, we are going to use Langchain + Activeloop's Deep Lake with GPT4 to semantically search and ask questions over a group chat.\n",
-    "\n",
-    "View a working demo [here](https://twitter.com/thisissukh_/status/1647223328363679745)"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 1. Install required packages"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!python3 -m pip install --upgrade langchain 'deeplake[enterprise]' openai tiktoken"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 2. Add API keys"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "import getpass\n",
-    "from langchain.document_loaders import PyPDFLoader, TextLoader\n",
-    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
-    "from langchain.text_splitter import (\n",
-    "    RecursiveCharacterTextSplitter,\n",
-    "    CharacterTextSplitter,\n",
-    ")\n",
-    "from langchain.vectorstores import DeepLake\n",
-    "from langchain.chains import ConversationalRetrievalChain, RetrievalQA\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.llms import OpenAI\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "activeloop_token = getpass.getpass(\"Activeloop Token:\")\n",
-    "os.environ[\"ACTIVELOOP_TOKEN\"] = activeloop_token\n",
-    "os.environ[\"ACTIVELOOP_ORG\"] = getpass.getpass(\"Activeloop Org:\")\n",
-    "\n",
-    "org_id = os.environ[\"ACTIVELOOP_ORG\"]\n",
-    "embeddings = OpenAIEmbeddings()\n",
-    "\n",
-    "dataset_path = \"hub://\" + org_id + \"/data\""
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "\n",
-    "\n",
-    "## 2. Create sample data"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can generate a sample group chat conversation using ChatGPT with this prompt:\n",
-    "\n",
-    "```\n",
-    "Generate a group chat conversation with three friends talking about their day, referencing real places and fictional names. Make it funny and as detailed as possible.\n",
-    "```\n",
-    "\n",
-    "I've already generated such a chat in `messages.txt`. We can keep it simple and use this for our example.\n",
-    "\n",
-    "## 3. Ingest chat embeddings\n",
-    "\n",
-    "We load the messages in the text file, chunk and upload to ActiveLoop Vector store."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[Document(page_content='Participants:\\n\\nJerry: Loves movies and is a bit of a klutz.\\nSamantha: Enthusiastic about food and always trying new restaurants.\\nBarry: A nature lover, but always manages to get lost.\\nJerry: Hey, guys! You won\\'t believe what happened to me at the Times Square AMC theater. I tripped over my own feet and spilled popcorn everywhere! 🍿💥\\n\\nSamantha: LOL, that\\'s so you, Jerry! Was the floor buttery enough for you to ice skate on after that? 😂\\n\\nBarry: Sounds like a regular Tuesday for you, Jerry. Meanwhile, I tried to find that new hiking trail in Central Park. You know, the one that\\'s supposed to be impossible to get lost on? Well, guess what...\\n\\nJerry: You found a hidden treasure?\\n\\nBarry: No, I got lost. AGAIN. 🧭🙄\\n\\nSamantha: Barry, you\\'d get lost in your own backyard! But speaking of treasures, I found this new sushi place in Little Tokyo. \"Samantha\\'s Sushi Symphony\" it\\'s called. Coincidence? I think not!\\n\\nJerry: Maybe they named it after your ability to eat your body weight in sushi. 🍣', metadata={}), Document(page_content='Barry: How do you even FIND all these places, Samantha?\\n\\nSamantha: Simple, I don\\'t rely on Barry\\'s navigation skills. 😉 But seriously, the wasabi there was hotter than Jerry\\'s love for Marvel movies!\\n\\nJerry: Hey, nothing wrong with a little superhero action. By the way, did you guys see the new \"Captain Crunch: Breakfast Avenger\" trailer?\\n\\nSamantha: Captain Crunch? Are you sure you didn\\'t get that from one of your Saturday morning cereal binges?\\n\\nBarry: Yeah, and did he defeat his arch-enemy, General Mills? 😆\\n\\nJerry: Ha-ha, very funny. Anyway, that sushi place sounds awesome, Samantha. Next time, let\\'s go together, and maybe Barry can guide us... if we want a city-wide tour first.\\n\\nBarry: As long as we\\'re not hiking, I\\'ll get us there... eventually. 😅\\n\\nSamantha: It\\'s a date! But Jerry, you\\'re banned from carrying any food items.\\n\\nJerry: Deal! Just promise me no wasabi challenges. I don\\'t want to end up like the time I tried Sriracha ice cream.', metadata={}), Document(page_content=\"Barry: Wait, what happened with Sriracha ice cream?\\n\\nJerry: Let's just say it was a hot situation. Literally. 🔥\\n\\nSamantha: 🤣 I still have the video!\\n\\nJerry: Samantha, if you value our friendship, that video will never see the light of day.\\n\\nSamantha: No promises, Jerry. No promises. 🤐😈\\n\\nBarry: I foresee a fun weekend ahead! 🎉\", metadata={})]\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Your Deep Lake dataset has been successfully created!\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\\"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Dataset(path='hub://adilkhan/data', tensors=['embedding', 'id', 'metadata', 'text'])\n",
-      "\n",
-      "  tensor      htype      shape     dtype  compression\n",
-      "  -------    -------    -------   -------  ------- \n",
-      " embedding  embedding  (3, 1536)  float32   None   \n",
-      "    id        text      (3, 1)      str     None   \n",
-      " metadata     json      (3, 1)      str     None   \n",
-      "   text       text      (3, 1)      str     None   \n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      " \r"
-     ]
-    }
-   ],
-   "source": [
-    "with open(\"messages.txt\") as f:\n",
-    "    state_of_the_union = f.read()\n",
-    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
-    "pages = text_splitter.split_text(state_of_the_union)\n",
-    "\n",
-    "text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)\n",
-    "texts = text_splitter.create_documents(pages)\n",
-    "\n",
-    "print(texts)\n",
-    "\n",
-    "dataset_path = \"hub://\" + org_id + \"/data\"\n",
-    "embeddings = OpenAIEmbeddings()\n",
-    "db = DeepLake.from_documents(\n",
-    "    texts, embeddings, dataset_path=dataset_path, overwrite=True\n",
-    ")"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "`Optional`: You can also use Deep Lake's Managed Tensor Database as a hosting service and run queries there. In order to do so, it is necessary to specify the runtime parameter as {'tensor_db': True} during the creation of the vector store. This configuration enables the execution of queries on the Managed Tensor Database, rather than on the client side. It should be noted that this functionality is not applicable to datasets stored locally or in-memory. In the event that a vector store has already been created outside of the Managed Tensor Database, it is possible to transfer it to the Managed Tensor Database by following the prescribed steps."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# with open(\"messages.txt\") as f:\n",
-    "#     state_of_the_union = f.read()\n",
-    "# text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
-    "# pages = text_splitter.split_text(state_of_the_union)\n",
-    "\n",
-    "# text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)\n",
-    "# texts = text_splitter.create_documents(pages)\n",
-    "\n",
-    "# print(texts)\n",
-    "\n",
-    "# dataset_path = \"hub://\" + org + \"/data\"\n",
-    "# embeddings = OpenAIEmbeddings()\n",
-    "# db = DeepLake.from_documents(\n",
-    "#     texts, embeddings, dataset_path=dataset_path, overwrite=True, runtime={\"tensor_db\": True}\n",
-    "# )"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 4. Ask questions\n",
-    "\n",
-    "Now we can ask a question and get an answer back with a semantic search:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "db = DeepLake(dataset_path=dataset_path, read_only=True, embedding=embeddings)\n",
-    "\n",
-    "retriever = db.as_retriever()\n",
-    "retriever.search_kwargs[\"distance_metric\"] = \"cos\"\n",
-    "retriever.search_kwargs[\"k\"] = 4\n",
-    "\n",
-    "qa = RetrievalQA.from_chain_type(\n",
-    "    llm=OpenAI(), chain_type=\"stuff\", retriever=retriever, return_source_documents=False\n",
-    ")\n",
-    "\n",
-    "# What was the restaurant the group was talking about called?\n",
-    "query = input(\"Enter query:\")\n",
-    "\n",
-    "# The Hungry Lobster\n",
-    "ans = qa({\"query\": query})\n",
-    "\n",
-    "print(ans)"
-   ]
-  }
- ],
- "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": "3.10.12"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

cookbook/elasticsearch_db_qa.ipynb

@@ -1,158 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Elasticsearch\n",
-    "\n",
-    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/docs/use_cases/qa_structured/integrations/elasticsearch.ipynb)\n",
-    "\n",
-    "We can use LLMs to interact with Elasticsearch analytics databases in natural language.\n",
-    "\n",
-    "This chain builds search queries via the Elasticsearch DSL API (filters and aggregations).\n",
-    "\n",
-    "The Elasticsearch client must have permissions for index listing, mapping description and search queries.\n",
-    "\n",
-    "See [here](https://www.elastic.co/guide/en/elasticsearch/reference/current/docker.html) for instructions on how to run Elasticsearch locally."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "! pip install langchain langchain-experimental openai elasticsearch\n",
-    "\n",
-    "# Set env var OPENAI_API_KEY or load from a .env file\n",
-    "# import dotenv\n",
-    "\n",
-    "# dotenv.load_dotenv()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from elasticsearch import Elasticsearch\n",
-    "\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.chains.elasticsearch_database import ElasticsearchDatabaseChain"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Initialize Elasticsearch python client.\n",
-    "# See https://elasticsearch-py.readthedocs.io/en/v8.8.2/api.html#elasticsearch.Elasticsearch\n",
-    "ELASTIC_SEARCH_SERVER = \"https://elastic:pass@localhost:9200\"\n",
-    "db = Elasticsearch(ELASTIC_SEARCH_SERVER)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Uncomment the next cell to initially populate your db."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# customers = [\n",
-    "#     {\"firstname\": \"Jennifer\", \"lastname\": \"Walters\"},\n",
-    "#     {\"firstname\": \"Monica\",\"lastname\":\"Rambeau\"},\n",
-    "#     {\"firstname\": \"Carol\",\"lastname\":\"Danvers\"},\n",
-    "#     {\"firstname\": \"Wanda\",\"lastname\":\"Maximoff\"},\n",
-    "#     {\"firstname\": \"Jennifer\",\"lastname\":\"Takeda\"},\n",
-    "# ]\n",
-    "# for i, customer in enumerate(customers):\n",
-    "#     db.create(index=\"customers\", document=customer, id=i)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm = ChatOpenAI(model_name=\"gpt-4\", temperature=0)\n",
-    "chain = ElasticsearchDatabaseChain.from_llm(llm=llm, database=db, verbose=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "question = \"What are the first names of all the customers?\"\n",
-    "chain.run(question)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "We can customize the prompt."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chains.elasticsearch_database.prompts import DEFAULT_DSL_TEMPLATE\n",
-    "from langchain.prompts.prompt import PromptTemplate\n",
-    "\n",
-    "PROMPT_TEMPLATE = \"\"\"Given an input question, create a syntactically correct Elasticsearch query to run. Unless the user specifies in their question a specific number of examples they wish to obtain, always limit your query to at most {top_k} results. You can order the results by a relevant column to return the most interesting examples in the database.\n",
-    "\n",
-    "Unless told to do not query for all the columns from a specific index, only ask for a the few relevant columns given the question.\n",
-    "\n",
-    "Pay attention to use only the column names that you can see in the mapping description. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which index. Return the query as valid json.\n",
-    "\n",
-    "Use the following format:\n",
-    "\n",
-    "Question: Question here\n",
-    "ESQuery: Elasticsearch Query formatted as json\n",
-    "\"\"\"\n",
-    "\n",
-    "PROMPT = PromptTemplate.from_template(\n",
-    "    PROMPT_TEMPLATE,\n",
-    ")\n",
-    "chain = ElasticsearchDatabaseChain.from_llm(llm=llm, database=db, query_prompt=PROMPT)"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.9.1"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

cookbook/forward_looking_retrieval_augmented_generation.ipynb

@@ -1,497 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "0f0b9afa",
-   "metadata": {},
-   "source": [
-    "# Retrieve as you generate with FLARE\n",
-    "\n",
-    "This notebook is an implementation of Forward-Looking Active REtrieval augmented generation (FLARE).\n",
-    "\n",
-    "Please see the original repo [here](https://github.com/jzbjyb/FLARE/tree/main).\n",
-    "\n",
-    "The basic idea is:\n",
-    "\n",
-    "- Start answering a question\n",
-    "- If you start generating tokens the model is uncertain about, look up relevant documents\n",
-    "- Use those documents to continue generating\n",
-    "- Repeat until finished\n",
-    "\n",
-    "There is a lot of cool detail in how the lookup of relevant documents is done.\n",
-    "Basically, the tokens that model is uncertain about are highlighted, and then an LLM is called to generate a question that would lead to that answer. For example, if the generated text is `Joe Biden went to Harvard`, and the tokens the model was uncertain about was `Harvard`, then a good generated question would be `where did Joe Biden go to college`. This generated question is then used in a retrieval step to fetch relevant documents.\n",
-    "\n",
-    "In order to set up this chain, we will need three things:\n",
-    "\n",
-    "- An LLM to generate the answer\n",
-    "- An LLM to generate hypothetical questions to use in retrieval\n",
-    "- A retriever to use to look up answers for\n",
-    "\n",
-    "The LLM that we use to generate the answer needs to return logprobs so we can identify uncertain tokens. For that reason, we HIGHLY recommend that you use the OpenAI wrapper (NB: not the ChatOpenAI wrapper, as that does not return logprobs).\n",
-    "\n",
-    "The LLM we use to generate hypothetical questions to use in retrieval can be anything. In this notebook we will use ChatOpenAI because it is fast and cheap.\n",
-    "\n",
-    "The retriever can be anything. In this notebook we will use [SERPER](https://serper.dev/) search engine, because it is cheap.\n",
-    "\n",
-    "Other important parameters to understand:\n",
-    "\n",
-    "- `max_generation_len`: The maximum number of tokens to generate before stopping to check if any are uncertain\n",
-    "- `min_prob`: Any tokens generated with probability below this will be considered uncertain"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "a7e4b63d",
-   "metadata": {},
-   "source": [
-    "## Imports"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "042bb161",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "\n",
-    "os.environ[\"SERPER_API_KEY\"] = \"\"os.environ[\"OPENAI_API_KEY\"] = \"\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "a7888f4a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import re\n",
-    "\n",
-    "import numpy as np\n",
-    "\n",
-    "from langchain.schema import BaseRetriever\n",
-    "from langchain.callbacks.manager import (\n",
-    "    AsyncCallbackManagerForRetrieverRun,\n",
-    "    CallbackManagerForRetrieverRun,\n",
-    ")\n",
-    "from langchain.utilities import GoogleSerperAPIWrapper\n",
-    "from langchain.embeddings import OpenAIEmbeddings\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.llms import OpenAI\n",
-    "from langchain.schema import Document\n",
-    "from typing import Any, List"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "5f552dce",
-   "metadata": {},
-   "source": [
-    "## Retriever"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "59c7d875",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "class SerperSearchRetriever(BaseRetriever):\n",
-    "    search: GoogleSerperAPIWrapper = None\n",
-    "\n",
-    "    def _get_relevant_documents(\n",
-    "        self, query: str, *, run_manager: CallbackManagerForRetrieverRun, **kwargs: Any\n",
-    "    ) -> List[Document]:\n",
-    "        return [Document(page_content=self.search.run(query))]\n",
-    "\n",
-    "    async def _aget_relevant_documents(\n",
-    "        self,\n",
-    "        query: str,\n",
-    "        *,\n",
-    "        run_manager: AsyncCallbackManagerForRetrieverRun,\n",
-    "        **kwargs: Any,\n",
-    "    ) -> List[Document]:\n",
-    "        raise NotImplementedError()\n",
-    "\n",
-    "\n",
-    "retriever = SerperSearchRetriever(search=GoogleSerperAPIWrapper())"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "92478194",
-   "metadata": {},
-   "source": [
-    "## FLARE Chain"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "577e7c2c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# We set this so we can see what exactly is going on\n",
-    "from langchain.globals import set_verbose\n",
-    "\n",
-    "set_verbose(True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "300d783e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chains import FlareChain\n",
-    "\n",
-    "flare = FlareChain.from_llm(\n",
-    "    ChatOpenAI(temperature=0),\n",
-    "    retriever=retriever,\n",
-    "    max_generation_len=164,\n",
-    "    min_prob=0.3,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "1f3d5e90",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "query = \"explain in great detail the difference between the langchain framework and baby agi\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "4b1bfa8c",
-   "metadata": {
-    "scrolled": false
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new FlareChain chain...\u001b[0m\n",
-      "\u001b[36;1m\u001b[1;3mCurrent Response: \u001b[0m\n",
-      "Prompt after formatting:\n",
-      "\u001b[32;1m\u001b[1;3mRespond to the user message using any relevant context. If context is provided, you should ground your answer in that context. Once you're done responding return FINISHED.\n",
-      "\n",
-      ">>> CONTEXT: \n",
-      ">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
-      ">>> RESPONSE: \u001b[0m\n",
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new QuestionGeneratorChain chain...\u001b[0m\n",
-      "Prompt after formatting:\n",
-      "\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
-      "\n",
-      ">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
-      ">>> EXISTING PARTIAL RESPONSE:  \n",
-      "The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.\n",
-      "\n",
-      "Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.\n",
-      "\n",
-      "In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for\n",
-      "\n",
-      "The question to which the answer is the term/entity/phrase \" decentralized platform for natural language processing\" is:\u001b[0m\n",
-      "Prompt after formatting:\n",
-      "\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
-      "\n",
-      ">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
-      ">>> EXISTING PARTIAL RESPONSE:  \n",
-      "The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.\n",
-      "\n",
-      "Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.\n",
-      "\n",
-      "In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for\n",
-      "\n",
-      "The question to which the answer is the term/entity/phrase \" uses a blockchain\" is:\u001b[0m\n",
-      "Prompt after formatting:\n",
-      "\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
-      "\n",
-      ">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
-      ">>> EXISTING PARTIAL RESPONSE:  \n",
-      "The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.\n",
-      "\n",
-      "Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.\n",
-      "\n",
-      "In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for\n",
-      "\n",
-      "The question to which the answer is the term/entity/phrase \" distributed ledger to\" is:\u001b[0m\n",
-      "Prompt after formatting:\n",
-      "\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
-      "\n",
-      ">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
-      ">>> EXISTING PARTIAL RESPONSE:  \n",
-      "The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.\n",
-      "\n",
-      "Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.\n",
-      "\n",
-      "In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for\n",
-      "\n",
-      "The question to which the answer is the term/entity/phrase \" process data, allowing for secure and transparent data sharing.\" is:\u001b[0m\n",
-      "Prompt after formatting:\n",
-      "\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
-      "\n",
-      ">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
-      ">>> EXISTING PARTIAL RESPONSE:  \n",
-      "The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.\n",
-      "\n",
-      "Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.\n",
-      "\n",
-      "In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for\n",
-      "\n",
-      "The question to which the answer is the term/entity/phrase \" set of tools\" is:\u001b[0m\n",
-      "Prompt after formatting:\n",
-      "\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
-      "\n",
-      ">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
-      ">>> EXISTING PARTIAL RESPONSE:  \n",
-      "The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.\n",
-      "\n",
-      "Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.\n",
-      "\n",
-      "In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for\n",
-      "\n",
-      "The question to which the answer is the term/entity/phrase \" help developers create\" is:\u001b[0m\n",
-      "Prompt after formatting:\n",
-      "\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
-      "\n",
-      ">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
-      ">>> EXISTING PARTIAL RESPONSE:  \n",
-      "The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.\n",
-      "\n",
-      "Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.\n",
-      "\n",
-      "In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for\n",
-      "\n",
-      "The question to which the answer is the term/entity/phrase \" create an AI system\" is:\u001b[0m\n",
-      "Prompt after formatting:\n",
-      "\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
-      "\n",
-      ">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
-      ">>> EXISTING PARTIAL RESPONSE:  \n",
-      "The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.\n",
-      "\n",
-      "Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.\n",
-      "\n",
-      "In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for\n",
-      "\n",
-      "The question to which the answer is the term/entity/phrase \" NLP applications\" is:\u001b[0m\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n",
-      "\u001b[33;1m\u001b[1;3mGenerated Questions: ['What is the Langchain Framework?', 'What technology does the Langchain Framework use to store and process data for secure and transparent data sharing?', 'What technology does the Langchain Framework use to store and process data?', 'What does the Langchain Framework use a blockchain-based distributed ledger for?', 'What does the Langchain Framework provide in addition to a decentralized platform for natural language processing applications?', 'What set of tools and services does the Langchain Framework provide?', 'What is the purpose of Baby AGI?', 'What type of applications is the Langchain Framework designed for?']\u001b[0m\n",
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new _OpenAIResponseChain chain...\u001b[0m\n",
-      "Prompt after formatting:\n",
-      "\u001b[32;1m\u001b[1;3mRespond to the user message using any relevant context. If context is provided, you should ground your answer in that context. Once you're done responding return FINISHED.\n",
-      "\n",
-      ">>> CONTEXT: LangChain: Software. LangChain is a software development framework designed to simplify the creation of applications using large language models. LangChain Initial release date: October 2022. LangChain Programming languages: Python and JavaScript. LangChain Developer(s): Harrison Chase. LangChain License: MIT License. LangChain is a framework for developing applications powered by language models. We believe that the most powerful and differentiated applications will not only ... Type: Software framework. At its core, LangChain is a framework built around LLMs. We can use it for chatbots, Generative Question-Answering (GQA), summarization, and much more. LangChain is a powerful tool that can be used to work with Large Language Models (LLMs). LLMs are very general in nature, which means that while they can ... LangChain is an intuitive framework created to assist in developing applications driven by a language model, such as OpenAI or Hugging Face. LangChain is a software development framework designed to simplify the creation of applications using large language models (LLMs). Written in: Python and JavaScript. Initial release: October 2022. LangChain - The A.I-native developer toolkit We started LangChain with the intent to build a modular and flexible framework for developing A.I- ... LangChain explained in 3 minutes - LangChain is a ... Duration: 3:03. Posted: Apr 13, 2023. LangChain is a framework built to help you build LLM-powered applications more easily by providing you with the following:. LangChain is a framework that enables quick and easy development of applications that make use of Large Language Models, for example, GPT-3. LangChain is a powerful open-source framework for developing applications powered by language models. It connects to the AI models you want to ...\n",
-      "\n",
-      "LangChain is a framework for including AI from large language models inside data pipelines and applications. This tutorial provides an overview of what you ... Missing: secure | Must include:secure. Blockchain is the best way to secure the data of the shared community. Utilizing the capabilities of the blockchain nobody can read or interfere ... This modern technology consists of a chain of blocks that allows to securely store all committed transactions using shared and distributed ... A Blockchain network is used in the healthcare system to preserve and exchange patient data through hospitals, diagnostic laboratories, pharmacy firms, and ... In this article, I will walk you through the process of using the LangChain.js library with Google Cloud Functions, helping you leverage the ... LangChain is an intuitive framework created to assist in developing applications driven by a language model, such as OpenAI or Hugging Face. Missing: transparent | Must include:transparent. This technology keeps a distributed ledger on each blockchain node, making it more secure and transparent. The blockchain network can operate smart ... blockchain technology can offer a highly secured health data ledger to ... framework can be employed to store encrypted healthcare data in a ... In a simplified way, Blockchain is a data structure that stores transactions in an ordered way and linked to the previous block, serving as a ... Blockchain technology is a decentralized, distributed ledger that stores the record of ownership of digital assets. Missing: Langchain | Must include:Langchain.\n",
-      "\n",
-      "LangChain is a framework for including AI from large language models inside data pipelines and applications. This tutorial provides an overview of what you ... LangChain is an intuitive framework created to assist in developing applications driven by a language model, such as OpenAI or Hugging Face. This documentation covers the steps to integrate Pinecone, a high-performance vector database, with LangChain, a framework for building applications powered ... The ability to connect to any model, ingest any custom database, and build upon a framework that can take action provides numerous use cases for ... With LangChain, developers can use a framework that abstracts the core building blocks of LLM applications. LangChain empowers developers to ... Build a question-answering tool based on financial data with LangChain & Deep Lake's unified & streamable data store. Browse applications built on LangChain technology. Explore PoC and MVP applications created by our community and discover innovative use cases for LangChain ... LangChain is a great framework that can be used for developing applications powered by LLMs. When you intend to enhance your application ... In this blog, we'll introduce you to LangChain and Ray Serve and how to use them to build a search engine using LLM embeddings and a vector ... The LinkChain Framework simplifies embedding creation and storage using Pinecone and Chroma, with code that loads files, splits documents, and creates embedding ... Missing: technology | Must include:technology.\n",
-      "\n",
-      "Blockchain is one type of a distributed ledger. Distributed ledgers use independent computers (referred to as nodes) to record, share and ... Missing: Langchain | Must include:Langchain. Blockchain is used in distributed storage software where huge data is broken down into chunks. This is available in encrypted data across a ... People sometimes use the terms 'Blockchain' and 'Distributed Ledger' interchangeably. This post aims to analyze the features of each. A distributed ledger ... Missing: Framework | Must include:Framework. Think of a “distributed ledger” that uses cryptography to allow each participant in the transaction to add to the ledger in a secure way without ... In this paper, we provide an overview of the history of trade settlement and discuss this nascent technology that may now transform traditional ... Missing: Langchain | Must include:Langchain. LangChain is a blockchain-based language education platform that aims to revolutionize the way people learn languages. Missing: Framework | Must include:Framework. It uses the distributed ledger technology framework and Smart contract engine for building scalable Business Blockchain applications. The fabric ... It looks at the assets the use case is handling, the different parties conducting transactions, and the smart contract, distributed ... Are you curious to know how Blockchain and Distributed ... Duration: 44:31. Posted: May 4, 2021. A blockchain is a distributed and immutable ledger to transfer ownership, record transactions, track assets, and ensure transparency, security, trust and value ... Missing: Langchain | Must include:Langchain.\n",
-      "\n",
-      "LangChain is an intuitive framework created to assist in developing applications driven by a language model, such as OpenAI or Hugging Face. Missing: decentralized | Must include:decentralized. LangChain, created by Harrison Chase, is a Python library that provides out-of-the-box support to build NLP applications using LLMs. Missing: decentralized | Must include:decentralized. LangChain provides a standard interface for chains, enabling developers to create sequences of calls that go beyond a single LLM call. Chains ... Missing: decentralized platform natural. LangChain is a powerful framework that simplifies the process of building advanced language model applications. Missing: platform | Must include:platform. Are your language models ignoring previous instructions ... Duration: 32:23. Posted: Feb 21, 2023. LangChain is a framework that enables quick and easy development of applications ... Prompting is the new way of programming NLP models. Missing: decentralized platform. It then uses natural language processing and machine learning algorithms to search ... Summarization is handled via cohere, QnA is handled via langchain, ... LangChain is a framework for developing applications powered by language models. ... There are several main modules that LangChain provides support for. Missing: decentralized platform. In the healthcare-chain system, blockchain provides an appreciated secure ... The entire process of adding new and previous block data is performed based on ... ChatGPT is a large language model developed by OpenAI, ... tool for a wide range of applications, including natural language processing, ...\n",
-      "\n",
-      "LangChain is a powerful tool that can be used to work with Large Language ... If an API key has been provided, create an OpenAI language model instance At its core, LangChain is a framework built around LLMs. We can use it for chatbots, Generative Question-Answering (GQA), summarization, and much more. A tutorial of the six core modules of the LangChain Python package covering models, prompts, chains, agents, indexes, and memory with OpenAI ... LangChain's collection of tools refers to a set of tools provided by the LangChain framework for developing applications powered by language models. LangChain is a framework for developing applications powered by language models. We believe that the most powerful and differentiated applications will not only ... LangChain is an open-source library that provides developers with the tools to build applications powered by large language models (LLMs). LangChain is a framework for including AI from large language models inside data pipelines and applications. This tutorial provides an overview of what you ... Plan-and-Execute Agents · Feature Stores and LLMs · Structured Tools · Auto-Evaluator Opportunities · Callbacks Improvements · Unleashing the power ... Tool: A function that performs a specific duty. This can be things like: Google Search, Database lookup, Python REPL, other chains. · LLM: The language model ... LangChain provides a standard interface for chains, lots of integrations with other tools, and end-to-end chains for common applications.\n",
-      "\n",
-      "Baby AGI has the ability to complete tasks, generate new tasks based on previous results, and prioritize tasks in real-time. This system is exploring and demonstrating to us the potential of large language models, such as GPT and how it can autonomously perform tasks. Apr 17, 2023\n",
-      "\n",
-      "At its core, LangChain is a framework built around LLMs. We can use it for chatbots, Generative Question-Answering (GQA), summarization, and much more. The core idea of the library is that we can “chain” together different components to create more advanced use cases around LLMs.\n",
-      ">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
-      ">>> RESPONSE: \u001b[0m\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "' LangChain is a framework for developing applications powered by language models. It provides a standard interface for chains, lots of integrations with other tools, and end-to-end chains for common applications. On the other hand, Baby AGI is an AI system that is exploring and demonstrating the potential of large language models, such as GPT, and how it can autonomously perform tasks. Baby AGI has the ability to complete tasks, generate new tasks based on previous results, and prioritize tasks in real-time. '"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "flare.run(query)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "7bed8944",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'\\n\\nThe Langchain framework and Baby AGI are both artificial intelligence (AI) frameworks that are used to create intelligent agents. The Langchain framework is a supervised learning system that is based on the concept of “language chains”. It uses a set of rules to map natural language inputs to specific outputs. It is a general-purpose AI framework and can be used to build applications such as natural language processing (NLP), chatbots, and more.\\n\\nBaby AGI, on the other hand, is an unsupervised learning system that uses neural networks and reinforcement learning to learn from its environment. It is used to create intelligent agents that can adapt to changing environments. It is a more advanced AI system and can be used to build more complex applications such as game playing, robotic vision, and more.\\n\\nThe main difference between the two is that the Langchain framework uses supervised learning while Baby AGI uses unsupervised learning. The Langchain framework is a general-purpose AI framework that can be used for various applications, while Baby AGI is a more advanced AI system that can be used to create more complex applications.'"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "llm = OpenAI()\n",
-    "llm(query)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "8fb76286",
-   "metadata": {
-    "scrolled": false
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new FlareChain chain...\u001b[0m\n",
-      "\u001b[36;1m\u001b[1;3mCurrent Response: \u001b[0m\n",
-      "Prompt after formatting:\n",
-      "\u001b[32;1m\u001b[1;3mRespond to the user message using any relevant context. If context is provided, you should ground your answer in that context. Once you're done responding return FINISHED.\n",
-      "\n",
-      ">>> CONTEXT: \n",
-      ">>> USER INPUT: how are the origin stories of langchain and bitcoin similar or different?\n",
-      ">>> RESPONSE: \u001b[0m\n",
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new QuestionGeneratorChain chain...\u001b[0m\n",
-      "Prompt after formatting:\n",
-      "\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
-      "\n",
-      ">>> USER INPUT: how are the origin stories of langchain and bitcoin similar or different?\n",
-      ">>> EXISTING PARTIAL RESPONSE:  \n",
-      "\n",
-      "Langchain and Bitcoin have very different origin stories. Bitcoin was created by the mysterious Satoshi Nakamoto in 2008 as a decentralized digital currency. Langchain, on the other hand, was created in 2020 by a team of developers as a platform for creating and managing decentralized language learning applications. \n",
-      "\n",
-      "FINISHED\n",
-      "\n",
-      "The question to which the answer is the term/entity/phrase \" very different origin\" is:\u001b[0m\n",
-      "Prompt after formatting:\n",
-      "\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
-      "\n",
-      ">>> USER INPUT: how are the origin stories of langchain and bitcoin similar or different?\n",
-      ">>> EXISTING PARTIAL RESPONSE:  \n",
-      "\n",
-      "Langchain and Bitcoin have very different origin stories. Bitcoin was created by the mysterious Satoshi Nakamoto in 2008 as a decentralized digital currency. Langchain, on the other hand, was created in 2020 by a team of developers as a platform for creating and managing decentralized language learning applications. \n",
-      "\n",
-      "FINISHED\n",
-      "\n",
-      "The question to which the answer is the term/entity/phrase \" 2020 by a\" is:\u001b[0m\n",
-      "Prompt after formatting:\n",
-      "\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
-      "\n",
-      ">>> USER INPUT: how are the origin stories of langchain and bitcoin similar or different?\n",
-      ">>> EXISTING PARTIAL RESPONSE:  \n",
-      "\n",
-      "Langchain and Bitcoin have very different origin stories. Bitcoin was created by the mysterious Satoshi Nakamoto in 2008 as a decentralized digital currency. Langchain, on the other hand, was created in 2020 by a team of developers as a platform for creating and managing decentralized language learning applications. \n",
-      "\n",
-      "FINISHED\n",
-      "\n",
-      "The question to which the answer is the term/entity/phrase \" developers as a platform for creating and managing decentralized language learning applications.\" is:\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n",
-      "\u001b[33;1m\u001b[1;3mGenerated Questions: ['How would you describe the origin stories of Langchain and Bitcoin in terms of their similarities or differences?', 'When was Langchain created and by whom?', 'What was the purpose of creating Langchain?']\u001b[0m\n",
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new _OpenAIResponseChain chain...\u001b[0m\n",
-      "Prompt after formatting:\n",
-      "\u001b[32;1m\u001b[1;3mRespond to the user message using any relevant context. If context is provided, you should ground your answer in that context. Once you're done responding return FINISHED.\n",
-      "\n",
-      ">>> CONTEXT: Bitcoin and Ethereum have many similarities but different long-term visions and limitations. Ethereum changed from proof of work to proof of ... Bitcoin will be around for many years and examining its white paper origins is a great exercise in understanding why. Satoshi Nakamoto's blueprint describes ... Bitcoin is a new currency that was created in 2009 by an unknown person using the alias Satoshi Nakamoto. Transactions are made with no middle men – meaning, no ... Missing: Langchain | Must include:Langchain. By comparison, Bitcoin transaction speeds are tremendously lower. ... learn about its history and its role in the emergence of the Bitcoin ... LangChain is a powerful framework that simplifies the process of ... tasks like document retrieval, clustering, and similarity comparisons. Key terms: Bitcoin System, Blockchain Technology, ... Furthermore, the research paper will discuss and compare the five payment. Blockchain first appeared in Nakamoto's Bitcoin white paper that describes a new decentralized cryptocurrency [1]. Bitcoin takes the blockchain technology ... Missing: stories | Must include:stories. A score of 0 means there were not enough data for this term. Google trends was accessed on 5 November 2018 with searches for bitcoin, euro, gold ... Contracts, transactions, and records of them provide critical structure in our economic system, but they haven't kept up with the world's digital ... Missing: Langchain | Must include:Langchain. Of course, traders try to make a profit on their portfolio in this way.The difference between investing and trading is the regularity with which ...\n",
-      "\n",
-      "After all these giant leaps forward in the LLM space, OpenAI released ChatGPT — thrusting LLMs into the spotlight. LangChain appeared around the same time. Its creator, Harrison Chase, made the first commit in late October 2022. Leaving a short couple of months of development before getting caught in the LLM wave.\n",
-      "\n",
-      "At its core, LangChain is a framework built around LLMs. We can use it for chatbots, Generative Question-Answering (GQA), summarization, and much more. The core idea of the library is that we can “chain” together different components to create more advanced use cases around LLMs.\n",
-      ">>> USER INPUT: how are the origin stories of langchain and bitcoin similar or different?\n",
-      ">>> RESPONSE: \u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "' The origin stories of LangChain and Bitcoin are quite different. Bitcoin was created in 2009 by an unknown person using the alias Satoshi Nakamoto. LangChain was created in late October 2022 by Harrison Chase. Bitcoin is a decentralized cryptocurrency, while LangChain is a framework built around LLMs. '"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "flare.run(\"how are the origin stories of langchain and bitcoin similar or different?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "fbadd022",
-   "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": "3.10.1"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/generative_agents_interactive_simulacra_of_human_behavior.ipynb

@@ -1,994 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "e9732067-71c7-46f7-ad09-381b3bf21a27",
-   "metadata": {},
-   "source": [
-    "# Generative Agents in LangChain\n",
-    "\n",
-    "This notebook implements a generative agent based on the paper [Generative Agents: Interactive Simulacra of Human Behavior](https://arxiv.org/abs/2304.03442) by Park, et. al.\n",
-    "\n",
-    "In it, we leverage a time-weighted Memory object backed by a LangChain Retriever."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "53f81c37-db45-4fdc-843c-aa8fd2a9e99d",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Use termcolor to make it easy to colorize the outputs.\n",
-    "!pip install termcolor > /dev/null"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "3128fc21",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import logging\n",
-    "\n",
-    "logging.basicConfig(level=logging.ERROR)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "8851c370-b395-4b80-a79d-486a38ffc244",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from datetime import datetime, timedelta\n",
-    "from typing import List\n",
-    "from termcolor import colored\n",
-    "\n",
-    "\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.docstore import InMemoryDocstore\n",
-    "from langchain.embeddings import OpenAIEmbeddings\n",
-    "from langchain.retrievers import TimeWeightedVectorStoreRetriever\n",
-    "from langchain.vectorstores import FAISS"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "81824e76",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "USER_NAME = \"Person A\"  # The name you want to use when interviewing the agent.\n",
-    "LLM = ChatOpenAI(max_tokens=1500)  # Can be any LLM you want."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "c3da1649-d88f-4973-b655-7042975cde7e",
-   "metadata": {},
-   "source": [
-    "### Generative Agent Memory Components\n",
-    "\n",
-    "This tutorial highlights the memory of generative agents and its impact on their behavior. The memory varies from standard LangChain Chat memory in two aspects:\n",
-    "\n",
-    "1. **Memory Formation**\n",
-    "\n",
-    "   Generative Agents have extended memories, stored in a single stream:\n",
-    "      1. Observations - from dialogues or interactions with the virtual world, about self or others\n",
-    "      2. Reflections - resurfaced and summarized core memories\n",
-    "\n",
-    "\n",
-    "2. **Memory Recall**\n",
-    "\n",
-    "   Memories are retrieved using a weighted sum of salience, recency, and importance.\n",
-    "\n",
-    "You can review the definitions of the `GenerativeAgent` and `GenerativeAgentMemory` in the [reference documentation](\"https://api.python.langchain.com/en/latest/modules/experimental.html\") for the following imports, focusing on `add_memory` and `summarize_related_memories` methods."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "043e5203-6a41-431c-9efa-3e1743d7d25a",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain_experimental.generative_agents import (\n",
-    "    GenerativeAgent,\n",
-    "    GenerativeAgentMemory,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "361bd49e",
-   "metadata": {
-    "jp-MarkdownHeadingCollapsed": true,
-    "tags": []
-   },
-   "source": [
-    "## Memory Lifecycle\n",
-    "\n",
-    "Summarizing the key methods in the above: `add_memory` and `summarize_related_memories`.\n",
-    "\n",
-    "When an agent makes an observation, it stores the memory:\n",
-    "    \n",
-    "1. Language model scores the memory's importance (1 for mundane, 10 for poignant)\n",
-    "2. Observation and importance are stored within a document by TimeWeightedVectorStoreRetriever, with a `last_accessed_time`.\n",
-    "\n",
-    "When an agent responds to an observation:\n",
-    "\n",
-    "1. Generates query(s) for retriever, which fetches documents based on salience, recency, and importance.\n",
-    "2. Summarizes the retrieved information\n",
-    "3. Updates the `last_accessed_time` for the used documents.\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2fa3ca02",
-   "metadata": {},
-   "source": [
-    "## Create a Generative Character\n",
-    "\n",
-    "\n",
-    "\n",
-    "Now that we've walked through the definition, we will create two characters named \"Tommie\" and \"Eve\"."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "ee9c1a1d-c311-4f1c-8131-75fccd9025b1",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "import math\n",
-    "import faiss\n",
-    "\n",
-    "\n",
-    "def relevance_score_fn(score: float) -> float:\n",
-    "    \"\"\"Return a similarity score on a scale [0, 1].\"\"\"\n",
-    "    # This will differ depending on a few things:\n",
-    "    # - the distance / similarity metric used by the VectorStore\n",
-    "    # - the scale of your embeddings (OpenAI's are unit norm. Many others are not!)\n",
-    "    # This function converts the euclidean norm of normalized embeddings\n",
-    "    # (0 is most similar, sqrt(2) most dissimilar)\n",
-    "    # to a similarity function (0 to 1)\n",
-    "    return 1.0 - score / math.sqrt(2)\n",
-    "\n",
-    "\n",
-    "def create_new_memory_retriever():\n",
-    "    \"\"\"Create a new vector store retriever unique to the agent.\"\"\"\n",
-    "    # Define your embedding model\n",
-    "    embeddings_model = OpenAIEmbeddings()\n",
-    "    # Initialize the vectorstore as empty\n",
-    "    embedding_size = 1536\n",
-    "    index = faiss.IndexFlatL2(embedding_size)\n",
-    "    vectorstore = FAISS(\n",
-    "        embeddings_model.embed_query,\n",
-    "        index,\n",
-    "        InMemoryDocstore({}),\n",
-    "        {},\n",
-    "        relevance_score_fn=relevance_score_fn,\n",
-    "    )\n",
-    "    return TimeWeightedVectorStoreRetriever(\n",
-    "        vectorstore=vectorstore, other_score_keys=[\"importance\"], k=15\n",
-    "    )"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "7884f9dd-c597-4c27-8c77-1402c71bc2f8",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "tommies_memory = GenerativeAgentMemory(\n",
-    "    llm=LLM,\n",
-    "    memory_retriever=create_new_memory_retriever(),\n",
-    "    verbose=False,\n",
-    "    reflection_threshold=8,  # we will give this a relatively low number to show how reflection works\n",
-    ")\n",
-    "\n",
-    "tommie = GenerativeAgent(\n",
-    "    name=\"Tommie\",\n",
-    "    age=25,\n",
-    "    traits=\"anxious, likes design, talkative\",  # You can add more persistent traits here\n",
-    "    status=\"looking for a job\",  # When connected to a virtual world, we can have the characters update their status\n",
-    "    memory_retriever=create_new_memory_retriever(),\n",
-    "    llm=LLM,\n",
-    "    memory=tommies_memory,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "c524d529",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Name: Tommie (age: 25)\n",
-      "Innate traits: anxious, likes design, talkative\n",
-      "No information about Tommie's core characteristics is provided in the given statements.\n"
-     ]
-    }
-   ],
-   "source": [
-    "# The current \"Summary\" of a character can't be made because the agent hasn't made\n",
-    "# any observations yet.\n",
-    "print(tommie.get_summary())"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "4be60979-d56e-4abf-a636-b34ffa8b7fba",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "# We can add memories directly to the memory object\n",
-    "tommie_observations = [\n",
-    "    \"Tommie remembers his dog, Bruno, from when he was a kid\",\n",
-    "    \"Tommie feels tired from driving so far\",\n",
-    "    \"Tommie sees the new home\",\n",
-    "    \"The new neighbors have a cat\",\n",
-    "    \"The road is noisy at night\",\n",
-    "    \"Tommie is hungry\",\n",
-    "    \"Tommie tries to get some rest.\",\n",
-    "]\n",
-    "for observation in tommie_observations:\n",
-    "    tommie.memory.add_memory(observation)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "6992b48b-697f-4973-9560-142ef85357d7",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Name: Tommie (age: 25)\n",
-      "Innate traits: anxious, likes design, talkative\n",
-      "Tommie is a person who is observant of his surroundings, has a sentimental side, and experiences basic human needs such as hunger and the need for rest. He also tends to get tired easily and is affected by external factors such as noise from the road or a neighbor's pet.\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Now that Tommie has 'memories', their self-summary is more descriptive, though still rudimentary.\n",
-    "# We will see how this summary updates after more observations to create a more rich description.\n",
-    "print(tommie.get_summary(force_refresh=True))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "40d39a32-838c-4a03-8b27-a52c76c402e7",
-   "metadata": {
-    "tags": []
-   },
-   "source": [
-    "## Pre-Interview with Character\n",
-    "\n",
-    "Before sending our character on their way, let's ask them a few questions."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "eaf125d8-f54c-4c5f-b6af-32789b1f7d3a",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "def interview_agent(agent: GenerativeAgent, message: str) -> str:\n",
-    "    \"\"\"Help the notebook user interact with the agent.\"\"\"\n",
-    "    new_message = f\"{USER_NAME} says {message}\"\n",
-    "    return agent.generate_dialogue_response(new_message)[1]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "54024d41-6e83-4914-91e5-73140e2dd9c8",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Tommie said \"I really enjoy design and being creative. I\\'ve been working on some personal projects lately. What about you, Person A? What do you like to do?\"'"
-      ]
-     },
-     "execution_count": 11,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "interview_agent(tommie, \"What do you like to do?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "71e2e8cc-921e-4816-82f1-66962b2c1055",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Tommie said \"Well, I\\'m actually looking for a job right now, so hopefully I can find some job postings online and start applying. How about you, Person A? What\\'s on your schedule for today?\"'"
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "interview_agent(tommie, \"What are you looking forward to doing today?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "a2521ffc-7050-4ac3-9a18-4cccfc798c31",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Tommie said \"Honestly, I\\'m feeling pretty anxious about finding a job. It\\'s been a bit of a struggle lately, but I\\'m trying to stay positive and keep searching. How about you, Person A? What worries you?\"'"
-      ]
-     },
-     "execution_count": 13,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "interview_agent(tommie, \"What are you most worried about today?\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e509c468-f7cd-4d72-9f3a-f4aba28b1eea",
-   "metadata": {},
-   "source": [
-    "## Step through the day's observations."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "154dee3d-bfe0-4828-b963-ed7e885799b3",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "# Let's have Tommie start going through a day in the life.\n",
-    "observations = [\n",
-    "    \"Tommie wakes up to the sound of a noisy construction site outside his window.\",\n",
-    "    \"Tommie gets out of bed and heads to the kitchen to make himself some coffee.\",\n",
-    "    \"Tommie realizes he forgot to buy coffee filters and starts rummaging through his moving boxes to find some.\",\n",
-    "    \"Tommie finally finds the filters and makes himself a cup of coffee.\",\n",
-    "    \"The coffee tastes bitter, and Tommie regrets not buying a better brand.\",\n",
-    "    \"Tommie checks his email and sees that he has no job offers yet.\",\n",
-    "    \"Tommie spends some time updating his resume and cover letter.\",\n",
-    "    \"Tommie heads out to explore the city and look for job openings.\",\n",
-    "    \"Tommie sees a sign for a job fair and decides to attend.\",\n",
-    "    \"The line to get in is long, and Tommie has to wait for an hour.\",\n",
-    "    \"Tommie meets several potential employers at the job fair but doesn't receive any offers.\",\n",
-    "    \"Tommie leaves the job fair feeling disappointed.\",\n",
-    "    \"Tommie stops by a local diner to grab some lunch.\",\n",
-    "    \"The service is slow, and Tommie has to wait for 30 minutes to get his food.\",\n",
-    "    \"Tommie overhears a conversation at the next table about a job opening.\",\n",
-    "    \"Tommie asks the diners about the job opening and gets some information about the company.\",\n",
-    "    \"Tommie decides to apply for the job and sends his resume and cover letter.\",\n",
-    "    \"Tommie continues his search for job openings and drops off his resume at several local businesses.\",\n",
-    "    \"Tommie takes a break from his job search to go for a walk in a nearby park.\",\n",
-    "    \"A dog approaches and licks Tommie's feet, and he pets it for a few minutes.\",\n",
-    "    \"Tommie sees a group of people playing frisbee and decides to join in.\",\n",
-    "    \"Tommie has fun playing frisbee but gets hit in the face with the frisbee and hurts his nose.\",\n",
-    "    \"Tommie goes back to his apartment to rest for a bit.\",\n",
-    "    \"A raccoon tore open the trash bag outside his apartment, and the garbage is all over the floor.\",\n",
-    "    \"Tommie starts to feel frustrated with his job search.\",\n",
-    "    \"Tommie calls his best friend to vent about his struggles.\",\n",
-    "    \"Tommie's friend offers some words of encouragement and tells him to keep trying.\",\n",
-    "    \"Tommie feels slightly better after talking to his friend.\",\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "238be49c-edb3-4e26-a2b6-98777ba8de86",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32mTommie wakes up to the sound of a noisy construction site outside his window.\u001b[0m Tommie groans and covers his head with a pillow, trying to block out the noise.\n",
-      "\u001b[32mTommie gets out of bed and heads to the kitchen to make himself some coffee.\u001b[0m Tommie stretches his arms and yawns before starting to make the coffee.\n",
-      "\u001b[32mTommie realizes he forgot to buy coffee filters and starts rummaging through his moving boxes to find some.\u001b[0m Tommie sighs in frustration and continues searching through the boxes.\n",
-      "\u001b[32mTommie finally finds the filters and makes himself a cup of coffee.\u001b[0m Tommie takes a deep breath and enjoys the aroma of the fresh coffee.\n",
-      "\u001b[32mThe coffee tastes bitter, and Tommie regrets not buying a better brand.\u001b[0m Tommie grimaces and sets the coffee mug aside.\n",
-      "\u001b[32mTommie checks his email and sees that he has no job offers yet.\u001b[0m Tommie sighs and closes his laptop, feeling discouraged.\n",
-      "\u001b[32mTommie spends some time updating his resume and cover letter.\u001b[0m Tommie nods, feeling satisfied with his progress.\n",
-      "\u001b[32mTommie heads out to explore the city and look for job openings.\u001b[0m Tommie feels a surge of excitement and anticipation as he steps out into the city.\n",
-      "\u001b[32mTommie sees a sign for a job fair and decides to attend.\u001b[0m Tommie feels hopeful and excited about the possibility of finding job opportunities at the job fair.\n",
-      "\u001b[32mThe line to get in is long, and Tommie has to wait for an hour.\u001b[0m Tommie taps his foot impatiently and checks his phone for the time.\n",
-      "\u001b[32mTommie meets several potential employers at the job fair but doesn't receive any offers.\u001b[0m Tommie feels disappointed and discouraged, but he remains determined to keep searching for job opportunities.\n",
-      "\u001b[32mTommie leaves the job fair feeling disappointed.\u001b[0m Tommie feels disappointed and discouraged, but he remains determined to keep searching for job opportunities.\n",
-      "\u001b[32mTommie stops by a local diner to grab some lunch.\u001b[0m Tommie feels relieved to take a break and satisfy his hunger.\n",
-      "\u001b[32mThe service is slow, and Tommie has to wait for 30 minutes to get his food.\u001b[0m Tommie feels frustrated and impatient due to the slow service.\n",
-      "\u001b[32mTommie overhears a conversation at the next table about a job opening.\u001b[0m Tommie feels a surge of hope and excitement at the possibility of a job opportunity but decides not to interfere with the conversation at the next table.\n",
-      "\u001b[32mTommie asks the diners about the job opening and gets some information about the company.\u001b[0m Tommie said \"Excuse me, I couldn't help but overhear your conversation about the job opening. Could you give me some more information about the company?\"\n",
-      "\u001b[32mTommie decides to apply for the job and sends his resume and cover letter.\u001b[0m Tommie feels hopeful and proud of himself for taking action towards finding a job.\n",
-      "\u001b[32mTommie continues his search for job openings and drops off his resume at several local businesses.\u001b[0m Tommie feels hopeful and determined to keep searching for job opportunities.\n",
-      "\u001b[32mTommie takes a break from his job search to go for a walk in a nearby park.\u001b[0m Tommie feels refreshed and rejuvenated after taking a break in the park.\n",
-      "\u001b[32mA dog approaches and licks Tommie's feet, and he pets it for a few minutes.\u001b[0m Tommie feels happy and enjoys the brief interaction with the dog.\n",
-      "****************************************\n",
-      "\u001b[34mAfter 20 observations, Tommie's summary is:\n",
-      "Name: Tommie (age: 25)\n",
-      "Innate traits: anxious, likes design, talkative\n",
-      "Tommie is determined and hopeful in his search for job opportunities, despite encountering setbacks and disappointments. He is also able to take breaks and care for his physical needs, such as getting rest and satisfying his hunger. Tommie is nostalgic towards his past, as shown by his memory of his childhood dog. Overall, Tommie is a hardworking and resilient individual who remains focused on his goals.\u001b[0m\n",
-      "****************************************\n",
-      "\u001b[32mTommie sees a group of people playing frisbee and decides to join in.\u001b[0m Do nothing.\n",
-      "\u001b[32mTommie has fun playing frisbee but gets hit in the face with the frisbee and hurts his nose.\u001b[0m Tommie feels pain and puts a hand to his nose to check for any injury.\n",
-      "\u001b[32mTommie goes back to his apartment to rest for a bit.\u001b[0m Tommie feels relieved to take a break and rest for a bit.\n",
-      "\u001b[32mA raccoon tore open the trash bag outside his apartment, and the garbage is all over the floor.\u001b[0m Tommie feels annoyed and frustrated at the mess caused by the raccoon.\n",
-      "\u001b[32mTommie starts to feel frustrated with his job search.\u001b[0m Tommie feels discouraged but remains determined to keep searching for job opportunities.\n",
-      "\u001b[32mTommie calls his best friend to vent about his struggles.\u001b[0m Tommie said \"Hey, can I talk to you for a bit? I'm feeling really frustrated with my job search.\"\n",
-      "\u001b[32mTommie's friend offers some words of encouragement and tells him to keep trying.\u001b[0m Tommie said \"Thank you, I really appreciate your support and encouragement.\"\n",
-      "\u001b[32mTommie feels slightly better after talking to his friend.\u001b[0m Tommie feels grateful for his friend's support.\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Let's send Tommie on their way. We'll check in on their summary every few observations to watch it evolve\n",
-    "for i, observation in enumerate(observations):\n",
-    "    _, reaction = tommie.generate_reaction(observation)\n",
-    "    print(colored(observation, \"green\"), reaction)\n",
-    "    if ((i + 1) % 20) == 0:\n",
-    "        print(\"*\" * 40)\n",
-    "        print(\n",
-    "            colored(\n",
-    "                f\"After {i+1} observations, Tommie's summary is:\\n{tommie.get_summary(force_refresh=True)}\",\n",
-    "                \"blue\",\n",
-    "            )\n",
-    "        )\n",
-    "        print(\"*\" * 40)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "dd62a275-7290-43ca-aa0f-504f3a706d09",
-   "metadata": {},
-   "source": [
-    "## Interview after the day"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "6336ab5d-3074-4831-951f-c9e2cba5dfb5",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Tommie said \"It\\'s been a bit of a rollercoaster, to be honest. I\\'ve had some setbacks in my job search, but I also had some good moments today, like sending out a few resumes and meeting some potential employers at a job fair. How about you?\"'"
-      ]
-     },
-     "execution_count": 16,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "interview_agent(tommie, \"Tell me about how your day has been going\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "809ac906-69b7-4326-99ec-af638d32bb20",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Tommie said \"I really enjoy coffee, but sometimes I regret not buying a better brand. How about you?\"'"
-      ]
-     },
-     "execution_count": 17,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "interview_agent(tommie, \"How do you feel about coffee?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "f733a431-19ea-421a-9101-ae2593a8c626",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Tommie said \"Oh, I had a dog named Bruno when I was a kid. He was a golden retriever and my best friend. I have so many fond memories of him.\"'"
-      ]
-     },
-     "execution_count": 18,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "interview_agent(tommie, \"Tell me about your childhood dog!\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "c9261428-778a-4c0b-b725-bc9e91b71391",
-   "metadata": {},
-   "source": [
-    "## Adding Multiple Characters\n",
-    "\n",
-    "Let's add a second character to have a conversation with Tommie. Feel free to configure different traits."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 47,
-   "id": "ec8bbe18-a021-419c-bf1f-23d34732cd99",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "eves_memory = GenerativeAgentMemory(\n",
-    "    llm=LLM,\n",
-    "    memory_retriever=create_new_memory_retriever(),\n",
-    "    verbose=False,\n",
-    "    reflection_threshold=5,\n",
-    ")\n",
-    "\n",
-    "\n",
-    "eve = GenerativeAgent(\n",
-    "    name=\"Eve\",\n",
-    "    age=34,\n",
-    "    traits=\"curious, helpful\",  # You can add more persistent traits here\n",
-    "    status=\"N/A\",  # When connected to a virtual world, we can have the characters update their status\n",
-    "    llm=LLM,\n",
-    "    daily_summaries=[\n",
-    "        (\n",
-    "            \"Eve started her new job as a career counselor last week and received her first assignment, a client named Tommie.\"\n",
-    "        )\n",
-    "    ],\n",
-    "    memory=eves_memory,\n",
-    "    verbose=False,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 48,
-   "id": "1e2745f5-e0da-4abd-98b4-830802ce6698",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "yesterday = (datetime.now() - timedelta(days=1)).strftime(\"%A %B %d\")\n",
-    "eve_observations = [\n",
-    "    \"Eve wakes up and hear's the alarm\",\n",
-    "    \"Eve eats a boal of porridge\",\n",
-    "    \"Eve helps a coworker on a task\",\n",
-    "    \"Eve plays tennis with her friend Xu before going to work\",\n",
-    "    \"Eve overhears her colleague say something about Tommie being hard to work with\",\n",
-    "]\n",
-    "for observation in eve_observations:\n",
-    "    eve.memory.add_memory(observation)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 49,
-   "id": "de4726e3-4bb1-47da-8fd9-f317a036fe0f",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Name: Eve (age: 34)\n",
-      "Innate traits: curious, helpful\n",
-      "Eve is a helpful and active person who enjoys sports and takes care of her physical health. She is attentive to her surroundings, including her colleagues, and has good time management skills.\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(eve.get_summary())"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "837524e9-7f7e-4e9f-b610-f454062f5915",
-   "metadata": {},
-   "source": [
-    "## Pre-conversation interviews\n",
-    "\n",
-    "\n",
-    "Let's \"Interview\" Eve before she speaks with Tommie."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 50,
-   "id": "6cda916d-800c-47bc-a7f9-6a2f19187472",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Eve said \"I\\'m feeling pretty good, thanks for asking! Just trying to stay productive and make the most of the day. How about you?\"'"
-      ]
-     },
-     "execution_count": 50,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "interview_agent(eve, \"How are you feeling about today?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 51,
-   "id": "448ae644-0a66-4eb2-a03a-319f36948b37",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Eve said \"I don\\'t know much about Tommie, but I heard someone mention that they find them difficult to work with. Have you had any experiences working with Tommie?\"'"
-      ]
-     },
-     "execution_count": 51,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "interview_agent(eve, \"What do you know about Tommie?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 52,
-   "id": "493fc5b8-8730-4ef8-9820-0f1769ce1691",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Eve said \"That\\'s interesting. I don\\'t know much about Tommie\\'s work experience, but I would probably ask about his strengths and areas for improvement. What about you?\"'"
-      ]
-     },
-     "execution_count": 52,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "interview_agent(\n",
-    "    eve,\n",
-    "    \"Tommie is looking to find a job. What are are some things you'd like to ask him?\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 53,
-   "id": "4b46452a-6c54-4db2-9d87-18597f70fec8",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Eve said \"Sure, I can keep the conversation going and ask plenty of questions. I want to make sure Tommie feels comfortable and supported. Thanks for letting me know.\"'"
-      ]
-     },
-     "execution_count": 53,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "interview_agent(\n",
-    "    eve,\n",
-    "    \"You'll have to ask him. He may be a bit anxious, so I'd appreciate it if you keep the conversation going and ask as many questions as possible.\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "dd780655-1d73-4fcb-a78d-79fd46a20636",
-   "metadata": {},
-   "source": [
-    "## Dialogue between Generative Agents\n",
-    "\n",
-    "Generative agents are much more complex when they interact with a virtual environment or with each other. Below, we run a simple conversation between Tommie and Eve."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 54,
-   "id": "042ea271-4bf1-4247-9082-239a6fea43b8",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "def run_conversation(agents: List[GenerativeAgent], initial_observation: str) -> None:\n",
-    "    \"\"\"Runs a conversation between agents.\"\"\"\n",
-    "    _, observation = agents[1].generate_reaction(initial_observation)\n",
-    "    print(observation)\n",
-    "    turns = 0\n",
-    "    while True:\n",
-    "        break_dialogue = False\n",
-    "        for agent in agents:\n",
-    "            stay_in_dialogue, observation = agent.generate_dialogue_response(\n",
-    "                observation\n",
-    "            )\n",
-    "            print(observation)\n",
-    "            # observation = f\"{agent.name} said {reaction}\"\n",
-    "            if not stay_in_dialogue:\n",
-    "                break_dialogue = True\n",
-    "        if break_dialogue:\n",
-    "            break\n",
-    "        turns += 1"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 55,
-   "id": "d5462b14-218e-4d85-b035-df57ea8e0f80",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Eve said \"Sure, Tommie. I'd be happy to share about my experience. Where would you like me to start?\"\n",
-      "Tommie said \"That's great, thank you! How about you start by telling me about your previous work experience?\"\n",
-      "Eve said \"Sure, I'd be happy to share my previous work experience with you. I've worked in a few different industries, including marketing and event planning. What specific questions do you have for me?\"\n",
-      "Tommie said \"That's great to hear. Can you tell me more about your experience in event planning? I've always been interested in that field.\"\n",
-      "Eve said \"Sure, I'd be happy to share about my experience in event planning. I've worked on a variety of events, from corporate conferences to weddings. One of the biggest challenges I faced was managing multiple vendors and ensuring everything ran smoothly on the day of the event. What specific questions do you have?\"\n",
-      "Tommie said \"That sounds like a lot of responsibility! Can you tell me more about how you handled the challenges that came up during those events?\"\n",
-      "Eve said \"Sure, Tommie. I'd be happy to share with you how I handled those challenges. One approach that worked well for me was to stay organized and create a detailed timeline for the event. This helped me keep track of all the different tasks that needed to be done and when they needed to be completed. I also made sure to communicate clearly with all the vendors and team members involved in the event to ensure everyone was on the same page. Would you like me to go into more detail?\"\n",
-      "Tommie said \"Thank you for sharing that with me, Eve. That sounds like a great approach to managing events. Can you tell me more about how you handled any unexpected issues that came up during the events?\"\n",
-      "Eve said \"Of course, Tommie. One example of an unexpected issue I faced was when one of the vendors didn't show up on time. To handle this, I quickly contacted a backup vendor and was able to get everything back on track. It's always important to have a backup plan in case things don't go as planned. Do you have any other questions about event planning?\"\n",
-      "Tommie said \"Thank you for sharing that with me, Eve. It's really helpful to hear how you handled unexpected issues like that. Can you give me an example of how you communicated with your team to ensure everyone was on the same page during an event?\"\n",
-      "Eve said \"Sure, Tommie. One thing I did to ensure everyone was on the same page was to have regular check-ins and meetings with the team leading up to the event. This helped us address any issues or concerns early on and make sure everyone was clear on their roles and responsibilities. Have you ever had to manage a team for an event before?\"\n",
-      "Tommie said \"That's a great idea, Eve. I haven't had the opportunity to manage a team for an event yet, but I'll definitely keep that in mind for the future. Thank you for sharing your experience with me.\"\n",
-      "Eve said \"Thanks for the opportunity to share my experience, Tommie. It was great meeting with you today.\"\n"
-     ]
-    }
-   ],
-   "source": [
-    "agents = [tommie, eve]\n",
-    "run_conversation(\n",
-    "    agents,\n",
-    "    \"Tommie said: Hi, Eve. Thanks for agreeing to meet with me today. I have a bunch of questions and am not sure where to start. Maybe you could first share about your experience?\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "1b28fe80-03dc-4399-961d-6e9ee1980216",
-   "metadata": {
-    "tags": []
-   },
-   "source": [
-    "## Let's interview our agents after their conversation\n",
-    "\n",
-    "Since the generative agents retain their memories from the day, we can ask them about their plans, conversations, and other memoreis."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 56,
-   "id": "c4d252f3-fcc1-474c-846e-a7605a6b4ce7",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Name: Tommie (age: 25)\n",
-      "Innate traits: anxious, likes design, talkative\n",
-      "Tommie is determined and hopeful in his job search, but can also feel discouraged and frustrated at times. He has a strong connection to his childhood dog, Bruno. Tommie seeks support from his friends when feeling overwhelmed and is grateful for their help. He also enjoys exploring his new city.\n"
-     ]
-    }
-   ],
-   "source": [
-    "# We can see a current \"Summary\" of a character based on their own perception of self\n",
-    "# has changed\n",
-    "print(tommie.get_summary(force_refresh=True))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 57,
-   "id": "c04db9a4",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Name: Eve (age: 34)\n",
-      "Innate traits: curious, helpful\n",
-      "Eve is a helpful and friendly person who enjoys playing sports and staying productive. She is attentive and responsive to others' needs, actively listening and asking questions to understand their perspectives. Eve has experience in event planning and communication, and is willing to share her knowledge and expertise with others. She values teamwork and collaboration, and strives to create a comfortable and supportive environment for everyone.\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(eve.get_summary(force_refresh=True))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 58,
-   "id": "71762558-8fb6-44d7-8483-f5b47fb2a862",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Tommie said \"It was really helpful actually. Eve shared some great tips on managing events and handling unexpected issues. I feel like I learned a lot from her experience.\"'"
-      ]
-     },
-     "execution_count": 58,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "interview_agent(tommie, \"How was your conversation with Eve?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 59,
-   "id": "085af3d8-ac21-41ea-8f8b-055c56976a67",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Eve said \"It was great, thanks for asking. Tommie was very receptive and had some great questions about event planning. How about you, have you had any interactions with Tommie?\"'"
-      ]
-     },
-     "execution_count": 59,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "interview_agent(eve, \"How was your conversation with Tommie?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 60,
-   "id": "5b439f3c-7849-4432-a697-2bcc85b89dae",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Eve said \"It was great meeting with you, Tommie. If you have any more questions or need any help in the future, don\\'t hesitate to reach out to me. Have a great day!\"'"
-      ]
-     },
-     "execution_count": 60,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "interview_agent(eve, \"What do you wish you would have said to Tommie?\")"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.3"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/hugginggpt.ipynb

@@ -1,135 +0,0 @@
-{
- "cells": [
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# HuggingGPT\n",
-    "Implementation of [HuggingGPT](https://github.com/microsoft/JARVIS). HuggingGPT is a system to connect LLMs (ChatGPT) with ML community (Hugging Face).\n",
-    "\n",
-    "+ 🔥 Paper: https://arxiv.org/abs/2303.17580\n",
-    "+ 🚀 Project: https://github.com/microsoft/JARVIS\n",
-    "+ 🤗 Space: https://huggingface.co/spaces/microsoft/HuggingGPT"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Set up tools\n",
-    "\n",
-    "We set up the tools available from [Transformers Agent](https://huggingface.co/docs/transformers/transformers_agents#tools). It includes a library of tools supported by Transformers and some customized tools such as image generator, video generator, text downloader and other tools."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from transformers import load_tool"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "hf_tools = [\n",
-    "    load_tool(tool_name)\n",
-    "    for tool_name in [\n",
-    "        \"document-question-answering\",\n",
-    "        \"image-captioning\",\n",
-    "        \"image-question-answering\",\n",
-    "        \"image-segmentation\",\n",
-    "        \"speech-to-text\",\n",
-    "        \"summarization\",\n",
-    "        \"text-classification\",\n",
-    "        \"text-question-answering\",\n",
-    "        \"translation\",\n",
-    "        \"huggingface-tools/text-to-image\",\n",
-    "        \"huggingface-tools/text-to-video\",\n",
-    "        \"text-to-speech\",\n",
-    "        \"huggingface-tools/text-download\",\n",
-    "        \"huggingface-tools/image-transformation\",\n",
-    "    ]\n",
-    "]"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup model and HuggingGPT\n",
-    "\n",
-    "We create an instance of HuggingGPT and use ChatGPT as the controller to rule the above tools."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.llms import OpenAI\n",
-    "from langchain_experimental.autonomous_agents import HuggingGPT\n",
-    "# %env OPENAI_API_BASE=http://localhost:8000/v1"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm = OpenAI(model_name=\"gpt-3.5-turbo\")\n",
-    "agent = HuggingGPT(llm, hf_tools)"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Run an example\n",
-    "\n",
-    "Given a text, show a related image and video."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "agent.run(\"please show me a video and an image of 'a boy is running'\")"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "langchain",
-   "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": "3.9.17"
-  },
-  "orig_nbformat": 4
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

cookbook/hypothetical_document_embeddings.ipynb

@@ -1,268 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "ccb74c9b",
-   "metadata": {},
-   "source": [
-    "# Improve document indexing with HyDE\n",
-    "This notebook goes over how to use Hypothetical Document Embeddings (HyDE), as described in [this paper](https://arxiv.org/abs/2212.10496). \n",
-    "\n",
-    "At a high level, HyDE is an embedding technique that takes queries, generates a hypothetical answer, and then embeds that generated document and uses that as the final example. \n",
-    "\n",
-    "In order to use HyDE, we therefore need to provide a base embedding model, as well as an LLMChain that can be used to generate those documents. By default, the HyDE class comes with some default prompts to use (see the paper for more details on them), but we can also create our own."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "546e87ee",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.llms import OpenAI\n",
-    "from langchain.embeddings import OpenAIEmbeddings\n",
-    "from langchain.chains import LLMChain, HypotheticalDocumentEmbedder\n",
-    "from langchain.prompts import PromptTemplate"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "c0ea895f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "base_embeddings = OpenAIEmbeddings()\n",
-    "llm = OpenAI()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "33bd6905",
-   "metadata": {},
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "50729989",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Load with `web_search` prompt\n",
-    "embeddings = HypotheticalDocumentEmbedder.from_llm(llm, base_embeddings, \"web_search\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "3aa573d6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Now we can use it as any embedding class!\n",
-    "result = embeddings.embed_query(\"Where is the Taj Mahal?\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "c7a0b556",
-   "metadata": {},
-   "source": [
-    "## Multiple generations\n",
-    "We can also generate multiple documents and then combine the embeddings for those. By default, we combine those by taking the average. We can do this by changing the LLM we use to generate documents to return multiple things."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "05da7060",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "multi_llm = OpenAI(n=4, best_of=4)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "9b1e12bd",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "embeddings = HypotheticalDocumentEmbedder.from_llm(\n",
-    "    multi_llm, base_embeddings, \"web_search\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "a60cd343",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "result = embeddings.embed_query(\"Where is the Taj Mahal?\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "1da90437",
-   "metadata": {},
-   "source": [
-    "## Using our own prompts\n",
-    "Besides using preconfigured prompts, we can also easily construct our own prompts and use those in the LLMChain that is generating the documents. This can be useful if we know the domain our queries will be in, as we can condition the prompt to generate text more similar to that.\n",
-    "\n",
-    "In the example below, let's condition it to generate text about a state of the union address (because we will use that in the next example)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "0b4a650f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "prompt_template = \"\"\"Please answer the user's question about the most recent state of the union address\n",
-    "Question: {question}\n",
-    "Answer:\"\"\"\n",
-    "prompt = PromptTemplate(input_variables=[\"question\"], template=prompt_template)\n",
-    "llm_chain = LLMChain(llm=llm, prompt=prompt)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "7f7e2b86",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "embeddings = HypotheticalDocumentEmbedder(\n",
-    "    llm_chain=llm_chain, base_embeddings=base_embeddings\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "6dd83424",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "result = embeddings.embed_query(\n",
-    "    \"What did the president say about Ketanji Brown Jackson\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "31388123",
-   "metadata": {},
-   "source": [
-    "## Using HyDE\n",
-    "Now that we have HyDE, we can use it as we would any other embedding class! Here is using it to find similar passages in the state of the union example."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "97719b29",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
-    "from langchain.vectorstores import Chroma\n",
-    "\n",
-    "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)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "bfcfc039",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Running Chroma using direct local API.\n",
-      "Using DuckDB in-memory for database. Data will be transient.\n"
-     ]
-    }
-   ],
-   "source": [
-    "docsearch = Chroma.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": 13,
-   "id": "632af7f2",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. \n",
-      "\n",
-      "We cannot let this happen. \n",
-      "\n",
-      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
-      "\n",
-      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
-      "\n",
-      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
-      "\n",
-      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(docs[0].page_content)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "b9e57b93",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.3"
-  },
-  "vscode": {
-   "interpreter": {
-    "hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
-   }
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/llm_math.ipynb

@@ -1,86 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "e71e720f",
-   "metadata": {},
-   "source": [
-    "# Math chain\n",
-    "\n",
-    "This notebook showcases using LLMs and Python REPLs to do complex word math problems."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "44e9ba31",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
-      "What is 13 raised to the .3432 power?\u001b[32;1m\u001b[1;3m\n",
-      "```text\n",
-      "13 ** .3432\n",
-      "```\n",
-      "...numexpr.evaluate(\"13 ** .3432\")...\n",
-      "\u001b[0m\n",
-      "Answer: \u001b[33;1m\u001b[1;3m2.4116004626599237\u001b[0m\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'Answer: 2.4116004626599237'"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain.llms import OpenAI\nfrom langchain.chains import LLMMathChain\n",
-    "\n",
-    "llm = OpenAI(temperature=0)\n",
-    "llm_math = LLMMathChain.from_llm(llm, verbose=True)\n",
-    "\n",
-    "llm_math.run(\"What is 13 raised to the .3432 power?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "e978bb8e",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.3"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/llm_symbolic_math.ipynb

@@ -1,162 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# LLM Symbolic Math \n",
-    "This notebook showcases using LLMs and Python to Solve Algebraic Equations. Under the hood is makes use of [SymPy](https://www.sympy.org/en/index.html)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.llms import OpenAI\n",
-    "from langchain_experimental.llm_symbolic_math.base import LLMSymbolicMathChain\n",
-    "\n",
-    "llm = OpenAI(temperature=0)\n",
-    "llm_symbolic_math = LLMSymbolicMathChain.from_llm(llm)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Integrals and derivates"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Answer: exp(x)*sin(x) + exp(x)*cos(x)'"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "llm_symbolic_math.run(\"What is the derivative of sin(x)*exp(x) with respect to x?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Answer: exp(x)*sin(x)'"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "llm_symbolic_math.run(\n",
-    "    \"What is the integral of exp(x)*sin(x) + exp(x)*cos(x) with respect to x?\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Solve linear and differential equations"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Answer: Eq(y(t), C2*exp(-t) + (C1 + t/2)*exp(t))'"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "llm_symbolic_math.run('Solve the differential equation y\" - y = e^t')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Answer: {0, -sqrt(3)*I/3, sqrt(3)*I/3}'"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "llm_symbolic_math.run(\"What are the solutions to this equation y^3 + 1/3y?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Answer: (3 - sqrt(7), -sqrt(7) - 2, 1 - sqrt(7)), (sqrt(7) + 3, -2 + sqrt(7), 1 + sqrt(7))'"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "llm_symbolic_math.run(\"x = y + 5, y = z - 3, z = x * y. Solve for x, y, z\")"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.4"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

cookbook/multi_modal_output_agent.ipynb

@@ -1,188 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "cd835d40",
-   "metadata": {},
-   "source": [
-    "# Multi-modal outputs: Image & Text"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "fa88e03a",
-   "metadata": {},
-   "source": [
-    "This notebook shows how non-text producing tools can be used to create multi-modal agents.\n",
-    "\n",
-    "This example is limited to text and image outputs and uses UUIDs to transfer content across tools and agents. \n",
-    "\n",
-    "This example uses Steamship to generate and store generated images. Generated are auth protected by default. \n",
-    "\n",
-    "You can get your Steamship api key here: https://steamship.com/account/api"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "0653da01",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from steamship import Block, Steamship\n",
-    "import re\n",
-    "from IPython.display import Image"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "f6933033",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.llms import OpenAI\n",
-    "from langchain.agents import initialize_agent\n",
-    "from langchain.agents import AgentType\n",
-    "from langchain.tools import SteamshipImageGenerationTool"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "71e51e53",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm = OpenAI(temperature=0)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "a9fc769d",
-   "metadata": {},
-   "source": [
-    "## Dall-E "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "cd177dfe",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "tools = [SteamshipImageGenerationTool(model_name=\"dall-e\")]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "c71b1e46",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "mrkl = initialize_agent(\n",
-    "    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "603aeb9a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "output = mrkl.run(\"How would you visualize a parot playing soccer?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "25eb4efe",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def show_output(output):\n",
-    "    \"\"\"Display the multi-modal output from the agent.\"\"\"\n",
-    "    UUID_PATTERN = re.compile(\n",
-    "        r\"([0-9A-Za-z]{8}-[0-9A-Za-z]{4}-[0-9A-Za-z]{4}-[0-9A-Za-z]{4}-[0-9A-Za-z]{12})\"\n",
-    "    )\n",
-    "\n",
-    "    outputs = UUID_PATTERN.split(output)\n",
-    "    outputs = [\n",
-    "        re.sub(r\"^\\W+\", \"\", el) for el in outputs\n",
-    "    ]  # Clean trailing and leading non-word characters\n",
-    "\n",
-    "    for output in outputs:\n",
-    "        maybe_block_id = UUID_PATTERN.search(output)\n",
-    "        if maybe_block_id:\n",
-    "            display(Image(Block.get(Steamship(), _id=maybe_block_id.group()).raw()))\n",
-    "        else:\n",
-    "            print(output, end=\"\\n\\n\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e247b2c4",
-   "metadata": {},
-   "source": [
-    "## StableDiffusion "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "315025e7",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "tools = [SteamshipImageGenerationTool(model_name=\"stable-diffusion\")]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "7930064a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "mrkl = initialize_agent(\n",
-    "    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "611a833d",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "output = mrkl.run(\"How would you visualize a parot playing soccer?\")"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.3"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/myscale_vector_sql.ipynb

@@ -1,200 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "245065c6",
-   "metadata": {},
-   "source": [
-    "# Vector SQL Retriever with MyScale\n",
-    "\n",
-    ">[MyScale](https://docs.myscale.com/en/) is an integrated vector database. You can access your database in SQL and also from here, LangChain. MyScale can make a use of [various data types and functions for filters](https://blog.myscale.com/2023/06/06/why-integrated-database-solution-can-boost-your-llm-apps/#filter-on-anything-without-constraints). It will boost up your LLM app no matter if you are scaling up your data or expand your system to broader application."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "0246c5bf",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!pip3 install clickhouse-sqlalchemy InstructorEmbedding sentence_transformers openai langchain-experimental"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "7585d2c3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "\n",
-    "from os import environ\n",
-    "import getpass\n",
-    "from typing import Dict, Any\n",
-    "from langchain.llms import OpenAI\nfrom langchain.utilities import SQLDatabase\nfrom langchain.chains import LLMChain\n",
-    "from langchain_experimental.sql.vector_sql import VectorSQLDatabaseChain\n",
-    "from sqlalchemy import create_engine, Column, MetaData\n",
-    "from langchain.prompts import PromptTemplate\n",
-    "\n",
-    "\n",
-    "from sqlalchemy import create_engine\n",
-    "\n",
-    "MYSCALE_HOST = \"msc-1decbcc9.us-east-1.aws.staging.myscale.cloud\"\n",
-    "MYSCALE_PORT = 443\n",
-    "MYSCALE_USER = \"chatdata\"\n",
-    "MYSCALE_PASSWORD = \"myscale_rocks\"\n",
-    "OPENAI_API_KEY = getpass.getpass(\"OpenAI API Key:\")\n",
-    "\n",
-    "engine = create_engine(\n",
-    "    f\"clickhouse://{MYSCALE_USER}:{MYSCALE_PASSWORD}@{MYSCALE_HOST}:{MYSCALE_PORT}/default?protocol=https\"\n",
-    ")\n",
-    "metadata = MetaData(bind=engine)\n",
-    "environ[\"OPENAI_API_KEY\"] = OPENAI_API_KEY"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "e08d9ddc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.embeddings import HuggingFaceInstructEmbeddings\n",
-    "from langchain_experimental.sql.vector_sql import VectorSQLOutputParser\n",
-    "\n",
-    "output_parser = VectorSQLOutputParser.from_embeddings(\n",
-    "    model=HuggingFaceInstructEmbeddings(\n",
-    "        model_name=\"hkunlp/instructor-xl\", model_kwargs={\"device\": \"cpu\"}\n",
-    "    )\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "84b705b2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "\n",
-    "from langchain.llms import OpenAI\n",
-    "from langchain.callbacks import StdOutCallbackHandler\n",
-    "\n",
-    "from langchain.utilities.sql_database import SQLDatabase\n",
-    "from langchain_experimental.sql.prompt import MYSCALE_PROMPT\n",
-    "from langchain_experimental.sql.vector_sql import VectorSQLDatabaseChain\n",
-    "\n",
-    "chain = VectorSQLDatabaseChain(\n",
-    "    llm_chain=LLMChain(\n",
-    "        llm=OpenAI(openai_api_key=OPENAI_API_KEY, temperature=0),\n",
-    "        prompt=MYSCALE_PROMPT,\n",
-    "    ),\n",
-    "    top_k=10,\n",
-    "    return_direct=True,\n",
-    "    sql_cmd_parser=output_parser,\n",
-    "    database=SQLDatabase(engine, None, metadata),\n",
-    ")\n",
-    "\n",
-    "import pandas as pd\n",
-    "\n",
-    "pd.DataFrame(\n",
-    "    chain.run(\n",
-    "        \"Please give me 10 papers to ask what is PageRank?\",\n",
-    "        callbacks=[StdOutCallbackHandler()],\n",
-    "    )\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "6c09cda0",
-   "metadata": {},
-   "source": [
-    "## SQL Database as Retriever"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "734d7ff5",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.chains.qa_with_sources.retrieval import RetrievalQAWithSourcesChain\n",
-    "\n",
-    "from langchain_experimental.sql.vector_sql import VectorSQLDatabaseChain\n",
-    "from langchain_experimental.retrievers.vector_sql_database \\\n",
-    "    import VectorSQLDatabaseChainRetriever\n",
-    "from langchain_experimental.sql.prompt import MYSCALE_PROMPT\n",
-    "from langchain_experimental.sql.vector_sql import VectorSQLRetrieveAllOutputParser\n",
-    "\n",
-    "output_parser_retrieve_all = VectorSQLRetrieveAllOutputParser.from_embeddings(\n",
-    "    output_parser.model\n",
-    ")\n",
-    "\n",
-    "chain = VectorSQLDatabaseChain.from_llm(\n",
-    "    llm=OpenAI(openai_api_key=OPENAI_API_KEY, temperature=0),\n",
-    "    prompt=MYSCALE_PROMPT,\n",
-    "    top_k=10,\n",
-    "    return_direct=True,\n",
-    "    db=SQLDatabase(engine, None, metadata),\n",
-    "    sql_cmd_parser=output_parser_retrieve_all,\n",
-    "    native_format=True,\n",
-    ")\n",
-    "\n",
-    "# You need all those keys to get docs\n",
-    "retriever = VectorSQLDatabaseChainRetriever(sql_db_chain=chain, page_content_key=\"abstract\")\n",
-    "\n",
-    "document_with_metadata_prompt = PromptTemplate(\n",
-    "    input_variables=[\"page_content\", \"id\", \"title\", \"authors\", \"pubdate\", \"categories\"],\n",
-    "    template=\"Content:\\n\\tTitle: {title}\\n\\tAbstract: {page_content}\\n\\tAuthors: {authors}\\n\\tDate of Publication: {pubdate}\\n\\tCategories: {categories}\\nSOURCE: {id}\",\n",
-    ")\n",
-    "\n",
-    "chain = RetrievalQAWithSourcesChain.from_chain_type(\n",
-    "    ChatOpenAI(\n",
-    "        model_name=\"gpt-3.5-turbo-16k\", openai_api_key=OPENAI_API_KEY, temperature=0.6\n",
-    "    ),\n",
-    "    retriever=retriever,\n",
-    "    chain_type=\"stuff\",\n",
-    "    chain_type_kwargs={\n",
-    "        \"document_prompt\": document_with_metadata_prompt,\n",
-    "    },\n",
-    "    return_source_documents=True,\n",
-    ")\n",
-    "ans = chain(\"Please give me 10 papers to ask what is PageRank?\",\n",
-    "            callbacks=[StdOutCallbackHandler()])\n",
-    "print(ans[\"answer\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "4948ff25",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.3"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/plan_and_execute_agent.ipynb

@@ -1,252 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "0ddfef23-3c74-444c-81dd-6753722997fa",
-   "metadata": {},
-   "source": [
-    "# Plan-and-execute\n",
-    "\n",
-    "Plan-and-execute agents accomplish an objective by first planning what to do, then executing the sub tasks. This idea is largely inspired by [BabyAGI](https://github.com/yoheinakajima/babyagi) and then the [\"Plan-and-Solve\" paper](https://arxiv.org/abs/2305.04091).\n",
-    "\n",
-    "The planning is almost always done by an LLM.\n",
-    "\n",
-    "The execution is usually done by a separate agent (equipped with tools)."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "a7ecb22a-7009-48ec-b14e-f0fa5aac1cd0",
-   "metadata": {},
-   "source": [
-    "## Imports"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "5fbbd4ee-bfe8-4a25-afe4-8d1a552a3d2e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.agents.tools import Tool\n",
-    "from langchain.chains import LLMMathChain\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.llms import OpenAI\n",
-    "from langchain.utilities import DuckDuckGoSearchAPIWrapper\n",
-    "from langchain_experimental.plan_and_execute import PlanAndExecute, load_agent_executor, load_chat_planner"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e0e995e5-af9d-4988-bcd0-467a2a2e18cd",
-   "metadata": {},
-   "source": [
-    "## Tools"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "1d789f4e-54e3-4602-891a-f076e0ab9594",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "search = DuckDuckGoSearchAPIWrapper()\n",
-    "llm = OpenAI(temperature=0)\n",
-    "llm_math_chain = LLMMathChain.from_llm(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": "markdown",
-   "id": "04dc6452-a07f-49f9-be12-95be1e2afccc",
-   "metadata": {},
-   "source": [
-    "## Planner, Executor, and Agent\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "d8f49c03-c804-458b-8122-c92b26c7b7dd",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "model = ChatOpenAI(temperature=0)\n",
-    "planner = load_chat_planner(model)\n",
-    "executor = load_agent_executor(model, tools, verbose=True)\n",
-    "agent = PlanAndExecute(planner=planner, executor=executor)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "78ba03dd-0322-4927-b58d-a7e2027fdbb3",
-   "metadata": {},
-   "source": [
-    "## Run example"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "a57f7efe-7866-47a7-bce5-9c7b1047964e",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mAction:\n",
-      "{\n",
-      "  \"action\": \"Search\",\n",
-      "  \"action_input\": \"current prime minister of the UK\"\n",
-      "}\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n",
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mAction:\n",
-      "```\n",
-      "{\n",
-      "  \"action\": \"Search\",\n",
-      "  \"action_input\": \"current prime minister of the UK\"\n",
-      "}\n",
-      "```\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3mBottom right: Rishi Sunak is the current prime minister and the first non-white prime minister. The prime minister of the United Kingdom is the principal minister of the crown of His Majesty's Government, and the head of the British Cabinet. 3 min. British Prime Minister Rishi Sunak asserted his stance on gender identity in a speech Wednesday, stating it was \"common sense\" that \"a man is a man and a woman is a woman\" — a ... The former chancellor Rishi Sunak is the UK's new prime minister. Here's what you need to know about him. He won after running for the second time this year He lost to Liz Truss in September,... Isaeli Prime Minister Benjamin Netanyahu spoke with US President Joe Biden on Wednesday, the prime minister's office said in a statement. Netanyahu \"thanked the President for the powerful words of ... By Yasmeen Serhan/London Updated: October 25, 2022 12:56 PM EDT | Originally published: October 24, 2022 9:17 AM EDT S top me if you've heard this one before: After a tumultuous period of political...\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mThe search results indicate that Rishi Sunak is the current prime minister of the UK. However, it's important to note that this information may not be accurate or up to date.\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n",
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mAction:\n",
-      "```\n",
-      "{\n",
-      "  \"action\": \"Search\",\n",
-      "  \"action_input\": \"current age of the prime minister of the UK\"\n",
-      "}\n",
-      "```\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3mHow old is Rishi Sunak? Mr Sunak was born on 12 May, 1980, making him 42 years old. He first became an MP in 2015, aged 34, and has served the constituency of Richmond in Yorkshire ever since. He... Prime Ministers' ages when they took office From oldest to youngest, the ages of the PMs were as follows: Winston Churchill - 65 years old James Callaghan - 64 years old Clement Attlee - 62 years... Anna Kaufman USA TODAY Just a few days after Liz Truss resigned as prime minister, the UK has a new prime minister. Truss, who lasted a mere 45 days in office, will be replaced by Rishi... Advertisement Rishi Sunak is the youngest British prime minister of modern times. Mr. Sunak is 42 and started out in Parliament in 2015. Rishi Sunak was appointed as chancellor of the Exchequer... The first prime minister of the current United Kingdom of Great Britain and Northern Ireland upon its effective creation in 1922 (when 26 Irish counties seceded and created the Irish Free State) was Bonar Law, [10] although the country was not renamed officially until 1927, when Stanley Baldwin was the serving prime minister. [11]\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mBased on the search results, it seems that Rishi Sunak is the current prime minister of the UK. However, I couldn't find any specific information about his age. Would you like me to search again for the current age of the prime minister?\n",
-      "\n",
-      "Action:\n",
-      "```\n",
-      "{\n",
-      "  \"action\": \"Search\",\n",
-      "  \"action_input\": \"age of Rishi Sunak\"\n",
-      "}\n",
-      "```\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3mRishi Sunak is 42 years old, making him the youngest person to hold the office of prime minister in modern times. How tall is Rishi Sunak? How Old Is Rishi Sunak? Rishi Sunak was born on May 12, 1980, in Southampton, England. Parents and Nationality Sunak's parents were born to Indian-origin families in East Africa before... Born on May 12, 1980, Rishi is currently 42 years old. He has been a member of parliament since 2015 where he was an MP for Richmond and has served in roles including Chief Secretary to the Treasury and the Chancellor of Exchequer while Boris Johnson was PM. Family Murty, 42, is the daughter of the Indian billionaire NR Narayana Murthy, often described as the Bill Gates of India, who founded the software company Infosys. According to reports, his... Sunak became the first non-White person to lead the country and, at age 42, the youngest to take on the role in more than a century. Like most politicians, Sunak is revered by some and...\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mBased on the search results, Rishi Sunak is currently 42 years old. He was born on May 12, 1980.\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n",
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThought: To calculate the age raised to the power of 0.43, I can use the calculator tool.\n",
-      "\n",
-      "Action:\n",
-      "```json\n",
-      "{\n",
-      "  \"action\": \"Calculator\",\n",
-      "  \"action_input\": \"42^0.43\"\n",
-      "}\n",
-      "```\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
-      "42^0.43\u001b[32;1m\u001b[1;3m```text\n",
-      "42**0.43\n",
-      "```\n",
-      "...numexpr.evaluate(\"42**0.43\")...\n",
-      "\u001b[0m\n",
-      "Answer: \u001b[33;1m\u001b[1;3m4.9888126515157\u001b[0m\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n",
-      "\n",
-      "Observation: \u001b[33;1m\u001b[1;3mAnswer: 4.9888126515157\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mThe age raised to the power of 0.43 is approximately 4.9888126515157.\n",
-      "\n",
-      "Final Answer:\n",
-      "```json\n",
-      "{\n",
-      "  \"action\": \"Final Answer\",\n",
-      "  \"action_input\": \"The age raised to the power of 0.43 is approximately 4.9888126515157.\"\n",
-      "}\n",
-      "```\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n",
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mAction:\n",
-      "```\n",
-      "{\n",
-      "  \"action\": \"Final Answer\",\n",
-      "  \"action_input\": \"The current prime minister of the UK is Rishi Sunak. His age raised to the power of 0.43 is approximately 4.9888126515157.\"\n",
-      "}\n",
-      "```\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'The current prime minister of the UK is Rishi Sunak. His age raised to the power of 0.43 is approximately 4.9888126515157.'"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "agent.run(\"Who is the current prime minister of the UK? What is their current age raised to the 0.43 power?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "0ef78a07-1a2a-46f8-9bc9-ae45f9bd706c",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "poetry-venv",
-   "language": "python",
-   "name": "poetry-venv"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.9.1"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/program_aided_language_model.ipynb

@@ -1,292 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "32e022a2",
-   "metadata": {},
-   "source": [
-    "# Program-aided language model (PAL) chain\n",
-    "\n",
-    "Implements Program-Aided Language Models, as in https://arxiv.org/pdf/2211.10435.pdf.\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "1370e40f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_experimental.pal_chain import PALChain\n",
-    "from langchain.llms import OpenAI"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "9a58e15e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm = OpenAI(temperature=0, max_tokens=512)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "095adc76",
-   "metadata": {},
-   "source": [
-    "## Math Prompt"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "beddcac7",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "pal_chain = PALChain.from_math_prompt(llm, verbose=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "e2eab9d4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "question = \"Jan has three times the number of pets as Marcia. Marcia has two more pets than Cindy. If Cindy has four pets, how many total pets do the three have?\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "3ef64b27",
-   "metadata": {
-    "scrolled": true
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new PALChain chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mdef solution():\n",
-      "    \"\"\"Jan has three times the number of pets as Marcia. Marcia has two more pets than Cindy. If Cindy has four pets, how many total pets do the three have?\"\"\"\n",
-      "    cindy_pets = 4\n",
-      "    marcia_pets = cindy_pets + 2\n",
-      "    jan_pets = marcia_pets * 3\n",
-      "    total_pets = cindy_pets + marcia_pets + jan_pets\n",
-      "    result = total_pets\n",
-      "    return result\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'28'"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "pal_chain.run(question)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0269d20a",
-   "metadata": {},
-   "source": [
-    "## Colored Objects"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "e524f81f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "pal_chain = PALChain.from_colored_object_prompt(llm, verbose=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "03a237b8",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "question = \"On the desk, you see two blue booklets, two purple booklets, and two yellow pairs of sunglasses. If I remove all the pairs of sunglasses from the desk, how many purple items remain on it?\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "a84a4352",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new PALChain chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m# Put objects into a list to record ordering\n",
-      "objects = []\n",
-      "objects += [('booklet', 'blue')] * 2\n",
-      "objects += [('booklet', 'purple')] * 2\n",
-      "objects += [('sunglasses', 'yellow')] * 2\n",
-      "\n",
-      "# Remove all pairs of sunglasses\n",
-      "objects = [object for object in objects if object[0] != 'sunglasses']\n",
-      "\n",
-      "# Count number of purple objects\n",
-      "num_purple = len([object for object in objects if object[1] == 'purple'])\n",
-      "answer = num_purple\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished PALChain chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'2'"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "pal_chain.run(question)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "fc3d7f10",
-   "metadata": {},
-   "source": [
-    "## Intermediate Steps\n",
-    "You can also use the intermediate steps flag to return the code executed that generates the answer."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "9d2d9c61",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "pal_chain = PALChain.from_colored_object_prompt(\n",
-    "    llm, verbose=True, return_intermediate_steps=True\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "b29b971b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "question = \"On the desk, you see two blue booklets, two purple booklets, and two yellow pairs of sunglasses. If I remove all the pairs of sunglasses from the desk, how many purple items remain on it?\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "a2c40c28",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new PALChain chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m# Put objects into a list to record ordering\n",
-      "objects = []\n",
-      "objects += [('booklet', 'blue')] * 2\n",
-      "objects += [('booklet', 'purple')] * 2\n",
-      "objects += [('sunglasses', 'yellow')] * 2\n",
-      "\n",
-      "# Remove all pairs of sunglasses\n",
-      "objects = [object for object in objects if object[0] != 'sunglasses']\n",
-      "\n",
-      "# Count number of purple objects\n",
-      "num_purple = len([object for object in objects if object[1] == 'purple'])\n",
-      "answer = num_purple\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    }
-   ],
-   "source": [
-    "result = pal_chain({\"question\": question})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "efddd033",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\"# Put objects into a list to record ordering\\nobjects = []\\nobjects += [('booklet', 'blue')] * 2\\nobjects += [('booklet', 'purple')] * 2\\nobjects += [('sunglasses', 'yellow')] * 2\\n\\n# Remove all pairs of sunglasses\\nobjects = [object for object in objects if object[0] != 'sunglasses']\\n\\n# Count number of purple objects\\nnum_purple = len([object for object in objects if object[1] == 'purple'])\\nanswer = num_purple\""
-      ]
-     },
-     "execution_count": 11,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "result[\"intermediate_steps\"]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "dfd88594",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.3"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/smart_llm.ipynb

@@ -1,281 +0,0 @@
-{
- "cells": [
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "id": "9e9b7651",
-   "metadata": {},
-   "source": [
-    "# How to use a SmartLLMChain\n",
-    "\n",
-    "A SmartLLMChain is a form of self-critique chain that can help you if have particularly complex questions to answer. Instead of doing a single LLM pass, it instead performs these 3 steps:\n",
-    "1. Ideation: Pass the user prompt n times through the LLM to get n output proposals (called \"ideas\"), where n is a parameter you can set \n",
-    "2. Critique: The LLM critiques all ideas to find possible flaws and picks the best one \n",
-    "3. Resolve: The LLM tries to improve upon the best idea (as chosen in the critique step) and outputs it. This is then the final output.\n",
-    "\n",
-    "SmartLLMChains are based on the SmartGPT workflow proposed in https://youtu.be/wVzuvf9D9BU.\n",
-    "\n",
-    "Note that SmartLLMChains\n",
-    "- use more LLM passes (ie n+2 instead of just 1)\n",
-    "- only work then the underlying LLM has the capability for reflection, which smaller models often don't\n",
-    "- only work with underlying models that return exactly 1 output, not multiple\n",
-    "\n",
-    "This notebook demonstrates how to use a SmartLLMChain."
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "id": "714dede0",
-   "metadata": {},
-   "source": [
-    "##### Same LLM for all steps"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "d3f7fb22",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = \"...\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "10e5ece6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.prompts import PromptTemplate\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain_experimental.smart_llm import SmartLLMChain"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "id": "1780da51",
-   "metadata": {},
-   "source": [
-    "As example question, we will use \"I have a 12 liter jug and a 6 liter jug. I want to measure 6 liters. How do I do it?\". This is an example from the original SmartGPT video (https://youtu.be/wVzuvf9D9BU?t=384). While this seems like a very easy question, LLMs struggle do these kinds of questions that involve numbers and physical reasoning.\n",
-    "\n",
-    "As we will see, all 3 initial ideas are completely wrong - even though we're using GPT4! Only when using self-reflection do we get a correct answer. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "054af6b1",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "hard_question = \"I have a 12 liter jug and a 6 liter jug. I want to measure 6 liters. How do I do it?\""
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "id": "8049cecd",
-   "metadata": {},
-   "source": [
-    "So, we first create an LLM and prompt template"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "811ea8e1",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "prompt = PromptTemplate.from_template(hard_question)\n",
-    "llm = ChatOpenAI(temperature=0, model_name=\"gpt-4\")"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "id": "50b602e4",
-   "metadata": {},
-   "source": [
-    "Now we can create a SmartLLMChain"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "8cd49199",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = SmartLLMChain(llm=llm, prompt=prompt, n_ideas=3, verbose=True)"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "id": "6a72f276",
-   "metadata": {},
-   "source": [
-    "Now we can use the SmartLLM as a drop-in replacement for our LLM. E.g.:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "074e5e75",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new SmartLLMChain chain...\u001b[0m\n",
-      "Prompt after formatting:\n",
-      "\u001b[32;1m\u001b[1;3mI have a 12 liter jug and a 6 liter jug. I want to measure 6 liters. How do I do it?\u001b[0m\n",
-      "Idea 1:\n",
-      "\u001b[36;1m\u001b[1;3m1. Fill the 6-liter jug completely.\n",
-      "2. Pour the water from the 6-liter jug into the 12-liter jug.\n",
-      "3. Fill the 6-liter jug again.\n",
-      "4. Carefully pour the water from the 6-liter jug into the 12-liter jug until the 12-liter jug is full.\n",
-      "5. The amount of water left in the 6-liter jug will be exactly 6 liters.\u001b[0m\n",
-      "Idea 2:\n",
-      "\u001b[36;1m\u001b[1;3m1. Fill the 6-liter jug completely.\n",
-      "2. Pour the water from the 6-liter jug into the 12-liter jug.\n",
-      "3. Fill the 6-liter jug again.\n",
-      "4. Carefully pour the water from the 6-liter jug into the 12-liter jug until the 12-liter jug is full.\n",
-      "5. Since the 12-liter jug is now full, there will be 2 liters of water left in the 6-liter jug.\n",
-      "6. Empty the 12-liter jug.\n",
-      "7. Pour the 2 liters of water from the 6-liter jug into the 12-liter jug.\n",
-      "8. Fill the 6-liter jug completely again.\n",
-      "9. Pour the water from the 6-liter jug into the 12-liter jug, which already has 2 liters in it.\n",
-      "10. Now, the 12-liter jug will have exactly 6 liters of water (2 liters from before + 4 liters from the 6-liter jug).\u001b[0m\n",
-      "Idea 3:\n",
-      "\u001b[36;1m\u001b[1;3m1. Fill the 6-liter jug completely.\n",
-      "2. Pour the water from the 6-liter jug into the 12-liter jug.\n",
-      "3. Fill the 6-liter jug again.\n",
-      "4. Carefully pour the water from the 6-liter jug into the 12-liter jug until the 12-liter jug is full.\n",
-      "5. The amount of water left in the 6-liter jug will be exactly 6 liters.\u001b[0m\n",
-      "Critique:\n",
-      "\u001b[33;1m\u001b[1;3mIdea 1:\n",
-      "1. Fill the 6-liter jug completely. (No flaw)\n",
-      "2. Pour the water from the 6-liter jug into the 12-liter jug. (No flaw)\n",
-      "3. Fill the 6-liter jug again. (No flaw)\n",
-      "4. Carefully pour the water from the 6-liter jug into the 12-liter jug until the 12-liter jug is full. (Flaw: The 12-liter jug will never be full in this step, as it can hold 12 liters and we are only pouring 6 liters into it.)\n",
-      "5. The amount of water left in the 6-liter jug will be exactly 6 liters. (Flaw: This statement is incorrect, as there will be no water left in the 6-liter jug after pouring it into the 12-liter jug.)\n",
-      "\n",
-      "Idea 2:\n",
-      "1. Fill the 6-liter jug completely. (No flaw)\n",
-      "2. Pour the water from the 6-liter jug into the 12-liter jug. (No flaw)\n",
-      "3. Fill the 6-liter jug again. (No flaw)\n",
-      "4. Carefully pour the water from the 6-liter jug into the 12-liter jug until the 12-liter jug is full. (Flaw: The 12-liter jug will never be full in this step, as it can hold 12 liters and we are only pouring 6 liters into it.)\n",
-      "5. Since the 12-liter jug is now full, there will be 2 liters of water left in the 6-liter jug. (Flaw: This statement is incorrect, as the 12-liter jug will not be full and there will be no water left in the 6-liter jug.)\n",
-      "6. Empty the 12-liter jug. (No flaw)\n",
-      "7. Pour the 2 liters of water from the 6-liter jug into the 12-liter jug. (Flaw: This step is based on the incorrect assumption that there are 2 liters of water left in the 6-liter jug.)\n",
-      "8. Fill the 6-liter jug completely again. (No flaw)\n",
-      "9. Pour the water from the 6-liter jug into the 12-liter jug, which already has 2 liters in it. (Flaw: This step is based on the incorrect assumption that there are 2 liters of water in the 12-liter jug.)\n",
-      "10. Now, the 12-liter jug will have exactly 6 liters of water (2 liters from before + 4 liters from the 6-liter jug). (Flaw: This conclusion is based on the incorrect assumptions made in the previous steps.)\n",
-      "\n",
-      "Idea 3:\n",
-      "1. Fill the 6-liter jug completely. (No flaw)\n",
-      "2. Pour the water from the 6-liter jug into the 12-liter jug. (No flaw)\n",
-      "3. Fill the 6-liter jug again. (No flaw)\n",
-      "4. Carefully pour the water from the 6-liter jug into the 12-liter jug until the 12-liter jug is full. (Flaw: The 12-liter jug will never be full in this step, as it can hold 12 liters and we are only pouring 6 liters into it.)\n",
-      "5. The amount of water left in the 6-liter jug will be exactly 6 liters. (Flaw: This statement is incorrect, as there will be no water left in the 6-liter jug after pouring it into the 12-liter jug.)\u001b[0m\n",
-      "Resolution:\n",
-      "\u001b[32;1m\u001b[1;3m1. Fill the 12-liter jug completely.\n",
-      "2. Pour the water from the 12-liter jug into the 6-liter jug until the 6-liter jug is full.\n",
-      "3. The amount of water left in the 12-liter jug will be exactly 6 liters.\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'1. Fill the 12-liter jug completely.\\n2. Pour the water from the 12-liter jug into the 6-liter jug until the 6-liter jug is full.\\n3. The amount of water left in the 12-liter jug will be exactly 6 liters.'"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.run({})"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "id": "bbfebea1",
-   "metadata": {},
-   "source": [
-    "##### Different LLM for different steps"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "id": "5be6ec08",
-   "metadata": {},
-   "source": [
-    "You can also use different LLMs for the different steps by passing `ideation_llm`, `critique_llm` and `resolve_llm`. You might want to do this to use a more creative (i.e., high-temperature) model for ideation and a more strict (i.e., low-temperature) model for critique and resolution."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "9c33fa19",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = SmartLLMChain(\n",
-    "    ideation_llm=ChatOpenAI(temperature=0.9, model_name=\"gpt-4\"),\n",
-    "    llm=ChatOpenAI(\n",
-    "        temperature=0, model_name=\"gpt-4\"\n",
-    "    ),  # will be used for critique and resolution as no specific llms are given\n",
-    "    prompt=prompt,\n",
-    "    n_ideas=3,\n",
-    "    verbose=True,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "886c1cc1",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.9.1"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/tree_of_thought.ipynb

@@ -1,239 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Tree of Thought (ToT) example\n",
-    "\n",
-    "The Tree of Thought (ToT) is a chain that allows you to query a Large Language Model (LLM) using the Tree of Thought technique. This is based on the paper [\"Large Language Model Guided Tree-of-Thought\"](https://arxiv.org/pdf/2305.08291.pdf)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/harrisonchase/.pyenv/versions/3.9.1/envs/langchain/lib/python3.9/site-packages/deeplake/util/check_latest_version.py:32: UserWarning: A newer version of deeplake (3.6.13) is available. It's recommended that you update to the latest version using `pip install -U deeplake`.\n",
-      "  warnings.warn(\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain.llms import OpenAI\n",
-    "\n",
-    "llm = OpenAI(temperature=1, max_tokens=512, model=\"text-davinci-003\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "3,*,*,2|1,*,3,*|*,1,*,3|4,*,*,1\n",
-      "\n",
-      "- This is a 4x4 Sudoku puzzle.\n",
-      "- The * represents a cell to be filled.\n",
-      "- The | character separates rows.\n",
-      "- At each step, replace one or more * with digits 1-4.\n",
-      "- There must be no duplicate digits in any row, column or 2x2 subgrid.\n",
-      "- Keep the known digits from previous valid thoughts in place.\n",
-      "- Each thought can be a partial or the final solution.\n"
-     ]
-    }
-   ],
-   "source": [
-    "sudoku_puzzle =   \"3,*,*,2|1,*,3,*|*,1,*,3|4,*,*,1\"\n",
-    "sudoku_solution = \"3,4,1,2|1,2,3,4|2,1,4,3|4,3,2,1\"\n",
-    "problem_description = f\"\"\"\n",
-    "{sudoku_puzzle}\n",
-    "\n",
-    "- This is a 4x4 Sudoku puzzle.\n",
-    "- The * represents a cell to be filled.\n",
-    "- The | character separates rows.\n",
-    "- At each step, replace one or more * with digits 1-4.\n",
-    "- There must be no duplicate digits in any row, column or 2x2 subgrid.\n",
-    "- Keep the known digits from previous valid thoughts in place.\n",
-    "- Each thought can be a partial or the final solution.\n",
-    "\"\"\".strip()\n",
-    "print(problem_description)\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Rules Based Checker\n",
-    "\n",
-    "Each thought is evaluated by the thought checker and is given a validity type: valid, invalid or partial. A simple checker can be rule based. For example, in the case of a sudoku puzzle, the checker can check if the puzzle is valid, invalid or partial.\n",
-    "\n",
-    "In the following code we implement a simple rule based checker for a specific 4x4 sudoku puzzle.\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from typing import Tuple\n",
-    "from langchain_experimental.tot.checker import ToTChecker\n",
-    "from langchain_experimental.tot.thought import ThoughtValidity\n",
-    "import re\n",
-    "\n",
-    "class MyChecker(ToTChecker):\n",
-    "    def evaluate(self, problem_description: str, thoughts: Tuple[str, ...] = ()) -> ThoughtValidity:\n",
-    "        last_thought = thoughts[-1]\n",
-    "        clean_solution = last_thought.replace(\" \", \"\").replace('\"', \"\")\n",
-    "        regex_solution = clean_solution.replace(\"*\", \".\").replace(\"|\", \"\\\\|\")\n",
-    "        if sudoku_solution in clean_solution:\n",
-    "            return ThoughtValidity.VALID_FINAL\n",
-    "        elif re.search(regex_solution, sudoku_solution):\n",
-    "            return ThoughtValidity.VALID_INTERMEDIATE\n",
-    "        else:\n",
-    "            return ThoughtValidity.INVALID"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Just testing the MyChecker class above:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "checker = MyChecker()\n",
-    "assert checker.evaluate(\"\", (\"3,*,*,2|1,*,3,*|*,1,*,3|4,*,*,1\",)) == ThoughtValidity.VALID_INTERMEDIATE\n",
-    "assert checker.evaluate(\"\", (\"3,4,1,2|1,2,3,4|2,1,4,3|4,3,2,1\",)) == ThoughtValidity.VALID_FINAL\n",
-    "assert checker.evaluate(\"\", (\"3,4,1,2|1,2,3,4|2,1,4,3|4,3,*,1\",)) == ThoughtValidity.VALID_INTERMEDIATE\n",
-    "assert checker.evaluate(\"\", (\"3,4,1,2|1,2,3,4|2,1,4,3|4,*,3,1\",)) == ThoughtValidity.INVALID"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Tree of Thought Chain\n",
-    "\n",
-    "Initialize and run the ToT chain, with maximum number of interactions `k` set to `30` and the maximum number child thoughts `c` set to `8`."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new ToTChain chain...\u001b[0m\n",
-      "Starting the ToT solve procedure.\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/harrisonchase/workplace/langchain/libs/langchain/langchain/chains/llm.py:275: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.\n",
-      "  warnings.warn(\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[31;1m\u001b[1;3mThought: 3*,*,2|1*,3,*|*,1,*,3|4,*,*,1\n",
-      "\u001b[0m\u001b[31;1m\u001b[1;3mThought: 3*,1,2|1*,3,*|*,1,*,3|4,*,*,1\n",
-      "\u001b[0m\u001b[31;1m\u001b[1;3mThought: 3*,1,2|1*,3,4|*,1,*,3|4,*,*,1\n",
-      "\u001b[0m\u001b[31;1m\u001b[1;3mThought: 3*,1,2|1*,3,4|*,1,2,3|4,*,*,1\n",
-      "\u001b[0m\u001b[31;1m\u001b[1;3mThought: 3*,1,2|1*,3,4|2,1,*,3|4,*,*,1\n",
-      "\u001b[0m"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Type <enum 'ThoughtValidity'> not serializable\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[31;1m\u001b[1;3mThought: 3,*,*,2|1,*,3,*|*,1,*,3|4,1,*,*\n",
-      "\u001b[0m\u001b[31;1m\u001b[1;3mThought: 3,*,*,2|*,3,2,*|*,1,*,3|4,1,*,*\n",
-      "\u001b[0m\u001b[31;1m\u001b[1;3mThought: 3,2,*,2|1,*,3,*|*,1,*,3|4,1,*,*\n",
-      "\u001b[0m\u001b[31;1m\u001b[1;3mThought: 3,2,*,2|1,*,3,*|1,1,*,3|4,1,*,*\n",
-      "\u001b[0m\u001b[31;1m\u001b[1;3mThought: 3,2,*,2|1,1,3,*|1,1,*,3|4,1,*,*\n",
-      "\u001b[0m\u001b[33;1m\u001b[1;3mThought: 3,*,*,2|1,2,3,*|*,1,*,3|4,*,*,1\n",
-      "\u001b[0m\u001b[31;1m\u001b[1;3m    Thought: 3,1,4,2|1,2,3,4|2,1,4,3|4,3,2,1\n",
-      "\u001b[0m\u001b[32;1m\u001b[1;3m    Thought: 3,4,1,2|1,2,3,4|2,1,4,3|4,3,2,1\n",
-      "\u001b[0m\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'3,4,1,2|1,2,3,4|2,1,4,3|4,3,2,1'"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_experimental.tot.base import ToTChain\n",
-    "\n",
-    "tot_chain = ToTChain(llm=llm, checker=MyChecker(), k=30, c=5, verbose=True, verbose_llm=False)\n",
-    "tot_chain.run(problem_description=problem_description)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.9.1"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

dev.Dockerfile

@@ -35,10 +35,7 @@ FROM langchain-dev-base AS langchain-dev-dependencies
 ARG PYTHON_VIRTUALENV_HOME
 
 # Copy only the dependency files for installation
-COPY libs/langchain/pyproject.toml libs/langchain/poetry.toml ./
-
-# Copy the langchain library for installation
-COPY libs/langchain/ libs/langchain/
+COPY pyproject.toml poetry.toml ./
 
 # Install the Poetry dependencies (this layer will be cached as long as the dependencies don't change)
 RUN poetry install --no-interaction --no-ansi --with dev,test,docs

docker/Dockerfile.base

@@ -1,3 +0,0 @@
-FROM python:3.11
-
-RUN pip install langchain

docs/.local_build.sh

@@ -1,18 +1,12 @@
-#!/usr/bin/env bash
-
-set -o errexit
-set -o nounset
-set -o pipefail
-set -o xtrace
-
-SCRIPT_DIR="$(cd "$(dirname "$0")"; pwd)"
-cd "${SCRIPT_DIR}"
-
-mkdir -p ../_dist
-cp -r . ../_dist
-cd ../_dist
-poetry run python scripts/model_feat_table.py
-poetry run nbdoc_build --srcdir docs
-poetry run python scripts/generate_api_reference_links.py
+mkdir _dist
+cp -r {docs_skeleton,snippets} _dist
+mkdir -p _dist/docs_skeleton/static/api_reference
+cd api_reference
+poetry run make html
+cp -r _build/* ../_dist/docs_skeleton/static/api_reference
+cd ..
+cp -r extras/* _dist/docs_skeleton/docs
+cd _dist/docs_skeleton
+poetry run nbdoc_build
 yarn install
 yarn start

docs/README.md

@@ -1,49 +0,0 @@
-# Website
-
-This website is built using [Docusaurus 2](https://docusaurus.io/), a modern static website generator.
-
-### Installation
-
-```
-$ yarn
-```
-
-### Local Development
-
-```
-$ yarn start
-```
-
-This command starts a local development server and opens up a browser window. Most changes are reflected live without having to restart the server.
-
-### Build
-
-```
-$ yarn build
-```
-
-This command generates static content into the `build` directory and can be served using any static contents hosting service.
-
-### Deployment
-
-Using SSH:
-
-```
-$ USE_SSH=true yarn deploy
-```
-
-Not using SSH:
-
-```
-$ GIT_USER=<Your GitHub username> yarn deploy
-```
-
-If you are using GitHub pages for hosting, this command is a convenient way to build the website and push to the `gh-pages` branch.
-
-### Continuous Integration
-
-Some common defaults for linting/formatting have been set for you. If you integrate your project with an open-source Continuous Integration system (e.g. Travis CI, CircleCI), you may check for issues using the following command.
-
-```
-$ yarn ci
-```

docs/api_reference/Makefile

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

docs/api_reference/conf.py

@@ -7,67 +7,19 @@
 
 # -- Path setup --------------------------------------------------------------
 
-import json
-import os
-import sys
-from pathlib import Path
-
-import toml
-from docutils import nodes
-from sphinx.util.docutils import SphinxDirective
-
 # If extensions (or modules to document with autodoc) are in another directory,
 # add these directories to sys.path here. If the directory is relative to the
 # documentation root, use os.path.abspath to make it absolute, like shown here.
+#
+import os
+import sys
+
+import toml
 
-_DIR = Path(__file__).parent.absolute()
 sys.path.insert(0, os.path.abspath("."))
-sys.path.insert(0, os.path.abspath("../../libs/langchain"))
-sys.path.insert(0, os.path.abspath("../../libs/experimental"))
 
-with (_DIR.parents[1] / "libs" / "langchain" / "pyproject.toml").open("r") as f:
+with open("../../pyproject.toml") as f:
     data = toml.load(f)
-with (_DIR / "guide_imports.json").open("r") as f:
-    imported_classes = json.load(f)
-
-
-class ExampleLinksDirective(SphinxDirective):
-    """Directive to generate a list of links to examples.
-
-    We have a script that extracts links to API reference docs
-    from our notebook examples. This directive uses that information
-    to backlink to the examples from the API reference docs."""
-
-    has_content = False
-    required_arguments = 1
-
-    def run(self):
-        """Run the directive.
-
-        Called any time :example_links:`ClassName` is used
-        in the template *.rst files."""
-        class_or_func_name = self.arguments[0]
-        links = imported_classes.get(class_or_func_name, {})
-        list_node = nodes.bullet_list()
-        for doc_name, link in links.items():
-            item_node = nodes.list_item()
-            para_node = nodes.paragraph()
-            link_node = nodes.reference()
-            link_node["refuri"] = link
-            link_node.append(nodes.Text(doc_name))
-            para_node.append(link_node)
-            item_node.append(para_node)
-            list_node.append(item_node)
-        if list_node.children:
-            title_node = nodes.title()
-            title_node.append(nodes.Text(f"Examples using {class_or_func_name}"))
-            return [title_node, list_node]
-        return [list_node]
-
-
-def setup(app):
-    app.add_directive("example_links", ExampleLinksDirective)
-
 
 # -- Project information -----------------------------------------------------
 
@@ -100,9 +52,6 @@ extensions = [
 ]
 source_suffix = [".rst"]
 
-# some autodoc pydantic options are repeated in the actual template.
-# potentially user error, but there may be bugs in the sphinx extension
-# with options not being passed through correctly (from either the location in the code)
 autodoc_pydantic_model_show_json = False
 autodoc_pydantic_field_list_validators = False
 autodoc_pydantic_config_members = False
@@ -115,6 +64,13 @@ autodoc_member_order = "groupwise"
 autoclass_content = "both"
 autodoc_typehints_format = "short"
 
+autodoc_default_options = {
+    "members": True,
+    "show-inheritance": True,
+    "inherited-members": "BaseModel",
+    "undoc-members": True,
+    "special-members": "__call__",
+}
 # autodoc_typehints = "description"
 # Add any paths that contain templates here, relative to this directory.
 templates_path = ["templates"]
@@ -156,7 +112,7 @@ html_context = {
 html_static_path = ["_static"]
 
 # These paths are either relative to html_static_path
-# or fully qualified paths (e.g. https://...)
+# or fully qualified paths (eg. https://...)
 html_css_files = [
     "css/custom.css",
 ]

docs/api_reference/create_api_rst.py

@@ -1,278 +1,81 @@
-"""Script for auto-generating api_reference.rst."""
-import importlib
-import inspect
-import typing
+"""Script for auto-generating api_reference.rst"""
+import glob
+import re
 from pathlib import Path
-from typing import TypedDict, Sequence, List, Dict, Literal, Union, Optional
-from enum import Enum
-
-from pydantic import BaseModel
 
 ROOT_DIR = Path(__file__).parents[2].absolute()
-HERE = Path(__file__).parent
-
-PKG_DIR = ROOT_DIR / "libs" / "langchain" / "langchain"
-EXP_DIR = ROOT_DIR / "libs" / "experimental" / "langchain_experimental"
-WRITE_FILE = HERE / "api_reference.rst"
-EXP_WRITE_FILE = HERE / "experimental_api_reference.rst"
+PKG_DIR = ROOT_DIR / "langchain"
+WRITE_FILE = Path(__file__).parent / "api_reference.rst"
 
 
-ClassKind = Literal["TypedDict", "Regular", "Pydantic", "enum"]
+def load_members() -> dict:
+    members: dict = {}
+    for py in glob.glob(str(PKG_DIR) + "/**/*.py", recursive=True):
+        module = py[len(str(PKG_DIR)) + 1 :].replace(".py", "").replace("/", ".")
+        top_level = module.split(".")[0]
+        if top_level not in members:
+            members[top_level] = {"classes": [], "functions": []}
+        with open(py, "r") as f:
+            for line in f.readlines():
+                cls = re.findall(r"^class ([^_].*)\(", line)
+                members[top_level]["classes"].extend([module + "." + c for c in cls])
+                func = re.findall(r"^def ([^_].*)\(", line)
+                members[top_level]["functions"].extend([module + "." + f for f in func])
+    return members
 
 
-class ClassInfo(TypedDict):
-    """Information about a class."""
+def construct_doc(members: dict) -> str:
+    full_doc = """\
+.. _api_reference:
 
-    name: str
-    """The name of the class."""
-    qualified_name: str
-    """The fully qualified name of the class."""
-    kind: ClassKind
-    """The kind of the class."""
-    is_public: bool
-    """Whether the class is public or not."""
-
-
-class FunctionInfo(TypedDict):
-    """Information about a function."""
-
-    name: str
-    """The name of the function."""
-    qualified_name: str
-    """The fully qualified name of the function."""
-    is_public: bool
-    """Whether the function is public or not."""
-
-
-class ModuleMembers(TypedDict):
-    """A dictionary of module members."""
-
-    classes_: Sequence[ClassInfo]
-    functions: Sequence[FunctionInfo]
-
-
-def _load_module_members(module_path: str, namespace: str) -> ModuleMembers:
-    """Load all members of a module.
-
-    Args:
-        module_path: Path to the module.
-        namespace: the namespace of the module.
-
-    Returns:
-        list: A list of loaded module objects.
-    """
-    classes_: List[ClassInfo] = []
-    functions: List[FunctionInfo] = []
-    module = importlib.import_module(module_path)
-    for name, type_ in inspect.getmembers(module):
-        if not hasattr(type_, "__module__"):
-            continue
-        if type_.__module__ != module_path:
-            continue
-
-        if inspect.isclass(type_):
-            if type(type_) == typing._TypedDictMeta:  # type: ignore
-                kind: ClassKind = "TypedDict"
-            elif issubclass(type_, Enum):
-                kind = "enum"
-            elif issubclass(type_, BaseModel):
-                kind = "Pydantic"
-            else:
-                kind = "Regular"
-
-            classes_.append(
-                ClassInfo(
-                    name=name,
-                    qualified_name=f"{namespace}.{name}",
-                    kind=kind,
-                    is_public=not name.startswith("_"),
-                )
-            )
-        elif inspect.isfunction(type_):
-            functions.append(
-                FunctionInfo(
-                    name=name,
-                    qualified_name=f"{namespace}.{name}",
-                    is_public=not name.startswith("_"),
-                )
-            )
-        else:
-            continue
-
-    return ModuleMembers(
-        classes_=classes_,
-        functions=functions,
-    )
-
-
-def _merge_module_members(
-    module_members: Sequence[ModuleMembers],
-) -> ModuleMembers:
-    """Merge module members."""
-    classes_: List[ClassInfo] = []
-    functions: List[FunctionInfo] = []
-    for module in module_members:
-        classes_.extend(module["classes_"])
-        functions.extend(module["functions"])
-
-    return ModuleMembers(
-        classes_=classes_,
-        functions=functions,
-    )
-
-
-def _load_package_modules(
-    package_directory: Union[str, Path], submodule: Optional[str] = None
-) -> Dict[str, ModuleMembers]:
-    """Recursively load modules of a package based on the file system.
-
-    Traversal based on the file system makes it easy to determine which
-    of the modules/packages are part of the package vs. 3rd party or built-in.
-
-    Parameters:
-        package_directory: Path to the package directory.
-        submodule: Optional name of submodule to load.
-
-    Returns:
-        list: A list of loaded module objects.
-    """
-    package_path = (
-        Path(package_directory)
-        if isinstance(package_directory, str)
-        else package_directory
-    )
-    modules_by_namespace = {}
-
-    # Get the high level package name
-    package_name = package_path.name
-
-    # If we are loading a submodule, add it in
-    if submodule is not None:
-        package_path = package_path / submodule
-
-    for file_path in package_path.rglob("*.py"):
-        if file_path.name.startswith("_"):
-            continue
-
-        relative_module_name = file_path.relative_to(package_path)
-
-        # Skip if any module part starts with an underscore
-        if any(part.startswith("_") for part in relative_module_name.parts):
-            continue
-
-        # Get the full namespace of the module
-        namespace = str(relative_module_name).replace(".py", "").replace("/", ".")
-        # Keep only the top level namespace
-        top_namespace = namespace.split(".")[0]
-
-        try:
-            # If submodule is present, we need to construct the paths in a slightly
-            # different way
-            if submodule is not None:
-                module_members = _load_module_members(
-                    f"{package_name}.{submodule}.{namespace}",
-                    f"{submodule}.{namespace}",
-                )
-            else:
-                module_members = _load_module_members(
-                    f"{package_name}.{namespace}", namespace
-                )
-            # Merge module members if the namespace already exists
-            if top_namespace in modules_by_namespace:
-                existing_module_members = modules_by_namespace[top_namespace]
-                _module_members = _merge_module_members(
-                    [existing_module_members, module_members]
-                )
-            else:
-                _module_members = module_members
-
-            modules_by_namespace[top_namespace] = _module_members
-
-        except ImportError as e:
-            print(f"Error: Unable to import module '{namespace}' with error: {e}")
-
-    return modules_by_namespace
-
-
-def _construct_doc(pkg: str, members_by_namespace: Dict[str, ModuleMembers]) -> str:
-    """Construct the contents of the reference.rst file for the given package.
-
-    Args:
-        pkg: The package name
-        members_by_namespace: The members of the package, dict organized by top level
-                              module contains a list of classes and functions
-                              inside of the top level namespace.
-
-    Returns:
-        The contents of the reference.rst file.
-    """
-    full_doc = f"""\
-=======================
-``{pkg}`` API Reference
-=======================
+=============
+API Reference
+=============
 
 """
-    namespaces = sorted(members_by_namespace)
-
-    for module in namespaces:
-        _members = members_by_namespace[module]
-        classes = _members["classes_"]
+    for module, _members in sorted(members.items(), key=lambda kv: kv[0]):
+        classes = _members["classes"]
         functions = _members["functions"]
         if not (classes or functions):
             continue
-        section = f":mod:`{pkg}.{module}`"
-        underline = "=" * (len(section) + 1)
+
+        module_title = module.replace("_", " ").title()
+        if module_title == "Llms":
+            module_title = "LLMs"
+        section = f":mod:`langchain.{module}`: {module_title}"
         full_doc += f"""\
 {section}
-{underline}
+{'=' * (len(section) + 1)}
 
-.. automodule:: {pkg}.{module}
+.. automodule:: langchain.{module}
     :no-members:
     :no-inherited-members:
 
 """
 
         if classes:
+            cstring = "\n    ".join(sorted(classes))
             full_doc += f"""\
 Classes
 --------------
-.. currentmodule:: {pkg}
+.. currentmodule:: langchain
 
 .. autosummary::
     :toctree: {module}
+    :template: class.rst
+
+    {cstring}
+
 """
-
-            for class_ in sorted(classes, key=lambda c: c["qualified_name"]):
-                if not class_["is_public"]:
-                    continue
-
-                if class_["kind"] == "TypedDict":
-                    template = "typeddict.rst"
-                elif class_["kind"] == "enum":
-                    template = "enum.rst"
-                elif class_["kind"] == "Pydantic":
-                    template = "pydantic.rst"
-                else:
-                    template = "class.rst"
-
-                full_doc += f"""\
-    :template: {template}
-    
-    {class_["qualified_name"]}
-    
-"""
-
         if functions:
-            _functions = [f["qualified_name"] for f in functions if f["is_public"]]
-            fstring = "\n    ".join(sorted(_functions))
+            fstring = "\n    ".join(sorted(functions))
             full_doc += f"""\
 Functions
 --------------
-.. currentmodule:: {pkg}
+.. currentmodule:: langchain
 
 .. autosummary::
     :toctree: {module}
-    :template: function.rst
 
     {fstring}
 
@@ -280,46 +83,11 @@ Functions
     return full_doc
 
 
-def _document_langchain_experimental() -> None:
-    """Document the langchain_experimental package."""
-    # Generate experimental_api_reference.rst
-    exp_members = _load_package_modules(EXP_DIR)
-    exp_doc = ".. _experimental_api_reference:\n\n" + _construct_doc(
-        "langchain_experimental", exp_members
-    )
-    with open(EXP_WRITE_FILE, "w") as f:
-        f.write(exp_doc)
-
-
-def _document_langchain_core() -> None:
-    """Document the main langchain package."""
-    # load top level module members
-    lc_members = _load_package_modules(PKG_DIR)
-
-    # Add additional packages
-    tools = _load_package_modules(PKG_DIR, "tools")
-    agents = _load_package_modules(PKG_DIR, "agents")
-    schema = _load_package_modules(PKG_DIR, "schema")
-
-    lc_members.update(
-        {
-            "agents.output_parsers": agents["output_parsers"],
-            "agents.format_scratchpad": agents["format_scratchpad"],
-            "tools.render": tools["render"],
-            "schema.runnable": schema["runnable"],
-        }
-    )
-
-    lc_doc = ".. _api_reference:\n\n" + _construct_doc("langchain", lc_members)
-
-    with open(WRITE_FILE, "w") as f:
-        f.write(lc_doc)
-
-
 def main() -> None:
-    """Generate the reference.rst file for each package."""
-    _document_langchain_core()
-    _document_langchain_experimental()
+    members = load_members()
+    full_doc = construct_doc(members)
+    with open(WRITE_FILE, "w") as f:
+        f.write(full_doc)
 
 
 if __name__ == "__main__":

docs/api_reference/templates/class.rst

@@ -5,6 +5,17 @@
 
 .. autoclass:: {{ objname }}
 
+   {% block methods %}
+   {% if methods %}
+   .. rubric:: {{ _('Methods') }}
+
+   .. autosummary::
+   {% for item in methods %}
+      ~{{ name }}.{{ item }}
+   {%- endfor %}
+   {% endif %}
+   {% endblock %}
+
    {% block attributes %}
    {% if attributes %}
    .. rubric:: {{ _('Attributes') }}
@@ -15,22 +26,3 @@
    {%- endfor %}
    {% endif %}
    {% endblock %}
-
-   {% block methods %}
-   {% if methods %}
-   .. rubric:: {{ _('Methods') }}
-
-   .. autosummary::
-   {% for item in methods %}
-      ~{{ name }}.{{ item }}
-   {%- endfor %}
-
-   {% for item in methods %}
-   .. automethod:: {{ name }}.{{ item }}
-   {%- endfor %}
-
-   {% endif %}
-   {% endblock %}
-
-
-.. example_links:: {{ objname }}

docs/api_reference/templates/enum.rst

@@ -1,14 +0,0 @@
-:mod:`{{module}}`.{{objname}}
-{{ underline }}==============
-
-.. currentmodule:: {{ module }}
-
-.. autoclass:: {{ objname }}
-
-    {% block attributes %}
-    {% for item in attributes %}
-    .. autoattribute:: {{ item }}
-    {% endfor %}
-    {% endblock %}
-
-.. example_links:: {{ objname }}

docs/api_reference/templates/function.rst

@@ -1,8 +0,0 @@
-:mod:`{{module}}`.{{objname}}
-{{ underline }}==============
-
-.. currentmodule:: {{ module }}
-
-.. autofunction:: {{ objname }}
-
-.. example_links:: {{ objname }}

docs/api_reference/templates/pydantic.rst

@@ -1,22 +0,0 @@
-:mod:`{{module}}`.{{objname}}
-{{ underline }}==============
-
-.. currentmodule:: {{ module }}
-
-.. autopydantic_model:: {{ objname }}
-    :model-show-json: False
-    :model-show-config-summary: False
-    :model-show-validator-members: False
-    :model-show-field-summary: False
-    :field-signature-prefix: param
-    :members:
-    :undoc-members:
-    :inherited-members:
-    :member-order: groupwise
-    :show-inheritance: True
-    :special-members: __call__
-
-    {% block attributes %}
-    {% endblock %}
-
-.. example_links:: {{ objname }}

docs/api_reference/templates/redirects.html

@@ -5,10 +5,9 @@
     <meta charset="utf-8">
     <meta name="viewport" content="width=device-width, initial-scale=1.0">
     <meta http-equiv="Refresh" content="0; url={{ redirect }}" />
-    <meta name="robots" content="follow, index">
-    <meta name="Description" content="Python API reference for LangChain.">
+    <meta name="Description" content="scikit-learn: machine learning in Python">
     <link rel="canonical" href="{{ redirect }}" />
-    <title>LangChain Python API Reference Documentation.</title>
+    <title>scikit-learn: machine learning in Python</title>
   </head>
   <body>
     <p>You will be automatically redirected to the <a href="{{ redirect }}">new location of this page</a>.</p>

docs/api_reference/templates/typeddict.rst

@@ -1,14 +0,0 @@
-:mod:`{{module}}`.{{objname}}
-{{ underline }}==============
-
-.. currentmodule:: {{ module }}
-
-.. autoclass:: {{ objname }}
-
-    {% block attributes %}
-   {% for item in attributes %}
-  .. autoattribute:: {{ item }}
-   {% endfor %}
-   {% endblock %}
-
-.. example_links:: {{ objname }}

docs/api_reference/themes/scikit-learn-modern/layout.html

@@ -19,7 +19,7 @@
   {% block htmltitle %}
   <title>{{ title|striptags|e }}{{ titlesuffix }}</title>
   {% endblock %}
-  <link rel="canonical" href="https://api.python.langchain.com/en/latest/{{pagename}}.html" />
+  <link rel="canonical" href="http://scikit-learn.org/stable/{{pagename}}.html" />
 
   {% if favicon_url %}
   <link rel="shortcut icon" href="{{ favicon_url|e }}"/>

docs/api_reference/themes/scikit-learn-modern/nav.html

@@ -6,6 +6,33 @@
   {%- set top_container_cls = "sk-landing-container" %}
 {%- endif %}
 
+{% if theme_link_to_live_contributing_page|tobool %}
+{# Link to development page for live builds #}
+  {%- set development_link = "https://scikit-learn.org/dev/developers/index.html" %}
+{# Open on a new development page in new window/tab for live builds #}
+  {%- set development_attrs = 'target="_blank" rel="noopener noreferrer"' %}
+{%- else %}
+  {%- set development_link = pathto('developers/index') %}
+  {%- set development_attrs = '' %}
+{%- endif %}
+
+{# title, link, link_attrs #}
+{%- set drop_down_navigation = [
+  ('Getting Started', pathto('getting_started'), ''),
+  ('Tutorial', pathto('tutorial/index'), ''),
+  ("What's new", pathto('whats_new/v' + version), ''),
+  ('Glossary', pathto('glossary'), ''),
+  ('Development', development_link, development_attrs),
+  ('FAQ', pathto('faq'), ''),
+  ('Support', pathto('support'), ''),
+  ('Related packages', pathto('related_projects'), ''),
+  ('Roadmap', pathto('roadmap'), ''),
+  ('Governance', pathto('governance'), ''),
+  ('About us', pathto('about'), ''),
+  ('GitHub', 'https://github.com/scikit-learn/scikit-learn', ''),
+  ('Other Versions and Download', 'https://scikit-learn.org/dev/versions.html', '')]
+-%}
+
 <nav id="navbar" class="{{ nav_bar_class }} navbar navbar-expand-md navbar-light bg-light py-0">
   <div class="container-fluid {{ top_container_cls }} px-0">
     {%- if logo_url %}
@@ -34,9 +61,6 @@
         <li class="nav-item">
           <a class="sk-nav-link nav-link" href="{{ pathto('api_reference') }}">API</a>
         </li>
-        <li class="nav-item">
-          <a class="sk-nav-link nav-link" href="{{ pathto('experimental_api_reference') }}">Experimental</a>
-        </li>
         <li class="nav-item">
           <a class="sk-nav-link nav-link" target="_blank" rel="noopener noreferrer" href="https://python.langchain.com/">Python Docs</a>
         </li>

docs/api_reference/themes/scikit-learn-modern/static/css/theme.css

@@ -745,11 +745,6 @@ span.descname {
   background-color: transparent;
   padding: 0;
   font-family: monospace;
-  font-size: 1.2rem;
-}
-
-em.property {
-  font-weight: normal;
 }
 
 span.descclassname {

docs/docs/_templates/integration.mdx

@@ -1,60 +0,0 @@
-[comment: Please, a reference example here "docs/integrations/arxiv.md"]::
-[comment: Use this template to create a new .md file in "docs/integrations/"]::
-
-# Title_REPLACE_ME
-
-[comment: Only one Tile/H1 is allowed!]::
-
->
-[comment: Description: After reading this description, a reader should decide if this integration is good enough to try/follow reading OR]::
-[comment: go to read the next integration doc. ]::
-[comment: Description should include a link to the source for follow reading.]::
-
-## Installation and Setup
-
-[comment: Installation and Setup: All necessary additional package installations and setups for Tokens, etc]::
-
-```bash
-pip install package_name_REPLACE_ME
-```
-
-[comment: OR this text:]::
-
-There isn't any special setup for it.
-
-[comment: The next H2/## sections with names of the integration modules, like "LLM", "Text Embedding Models", etc]::
-[comment: see "Modules" in the "index.html" page]::
-[comment: Each H2 section should include a link to an example(s) and a Python code with the import of the integration class]::
-[comment: Below are several example sections. Remove all unnecessary sections. Add all necessary sections not provided here.]::
-
-## LLM
-
-See a [usage example](/docs/integrations/llms/INCLUDE_REAL_NAME).
-
-```python
-from langchain.llms import integration_class_REPLACE_ME
-```
-
-## Text Embedding Models
-
-See a [usage example](/docs/integrations/text_embedding/INCLUDE_REAL_NAME)
-
-```python
-from langchain.embeddings import integration_class_REPLACE_ME
-```
-
-## Chat models
-
-See a [usage example](/docs/integrations/chat/INCLUDE_REAL_NAME)
-
-```python
-from langchain.chat_models import integration_class_REPLACE_ME
-```
-
-## Document Loader
-
-See a [usage example](/docs/integrations/document_loaders/INCLUDE_REAL_NAME).
-
-```python
-from langchain.document_loaders import integration_class_REPLACE_ME
-```

docs/docs/additional_resources/dependents.mdx

@@ -1,465 +0,0 @@
-# Dependents
-
-Dependents stats for `langchain-ai/langchain`
-
-[![](https://img.shields.io/static/v1?label=Used%20by&message=30534&color=informational&logo=slickpic)](https://github.com/langchain-ai/langchain/network/dependents)
-[![](https://img.shields.io/static/v1?label=Used%20by%20(public)&message=451&color=informational&logo=slickpic)](https://github.com/langchain-ai/langchain/network/dependents)
-[![](https://img.shields.io/static/v1?label=Used%20by%20(private)&message=30083&color=informational&logo=slickpic)](https://github.com/langchain-ai/langchain/network/dependents)
-[![](https://img.shields.io/static/v1?label=Used%20by%20(stars)&message=37822&color=informational&logo=slickpic)](https://github.com/langchain-ai/langchain/network/dependents)
-
-
-[update: `2023-10-06`; only dependent repositories with Stars > 100]
-
-
-| Repository | Stars  |
-| :--------  | -----: |
-|[openai/openai-cookbook](https://github.com/openai/openai-cookbook) | 49006 |
-|[AntonOsika/gpt-engineer](https://github.com/AntonOsika/gpt-engineer) | 44368 |
-|[imartinez/privateGPT](https://github.com/imartinez/privateGPT) | 38300 |
-|[LAION-AI/Open-Assistant](https://github.com/LAION-AI/Open-Assistant) | 35327 |
-|[hpcaitech/ColossalAI](https://github.com/hpcaitech/ColossalAI) | 34799 |
-|[microsoft/TaskMatrix](https://github.com/microsoft/TaskMatrix) | 34161 |
-|[streamlit/streamlit](https://github.com/streamlit/streamlit) | 27697 |
-|[geekan/MetaGPT](https://github.com/geekan/MetaGPT) | 27302 |
-|[reworkd/AgentGPT](https://github.com/reworkd/AgentGPT) | 26805 |
-|[OpenBB-finance/OpenBBTerminal](https://github.com/OpenBB-finance/OpenBBTerminal) | 24473 |
-|[StanGirard/quivr](https://github.com/StanGirard/quivr) | 23323 |
-|[run-llama/llama_index](https://github.com/run-llama/llama_index) | 22151 |
-|[openai/chatgpt-retrieval-plugin](https://github.com/openai/chatgpt-retrieval-plugin) | 19741 |
-|[mindsdb/mindsdb](https://github.com/mindsdb/mindsdb) | 18062 |
-|[PromtEngineer/localGPT](https://github.com/PromtEngineer/localGPT) | 16413 |
-|[chatchat-space/Langchain-Chatchat](https://github.com/chatchat-space/Langchain-Chatchat) | 16300 |
-|[cube-js/cube](https://github.com/cube-js/cube) | 16261 |
-|[mlflow/mlflow](https://github.com/mlflow/mlflow) | 15487 |
-|[logspace-ai/langflow](https://github.com/logspace-ai/langflow) | 12599 |
-|[GaiZhenbiao/ChuanhuChatGPT](https://github.com/GaiZhenbiao/ChuanhuChatGPT) | 12501 |
-|[openai/evals](https://github.com/openai/evals) | 12056 |
-|[airbytehq/airbyte](https://github.com/airbytehq/airbyte) | 11919 |
-|[go-skynet/LocalAI](https://github.com/go-skynet/LocalAI) | 11767 |
-|[databrickslabs/dolly](https://github.com/databrickslabs/dolly) | 10609 |
-|[AIGC-Audio/AudioGPT](https://github.com/AIGC-Audio/AudioGPT) | 9240 |
-|[aws/amazon-sagemaker-examples](https://github.com/aws/amazon-sagemaker-examples) | 8892 |
-|[langgenius/dify](https://github.com/langgenius/dify) | 8764 |
-|[gventuri/pandas-ai](https://github.com/gventuri/pandas-ai) | 8687 |
-|[jmorganca/ollama](https://github.com/jmorganca/ollama) | 8628 |
-|[langchain-ai/langchainjs](https://github.com/langchain-ai/langchainjs) | 8392 |
-|[h2oai/h2ogpt](https://github.com/h2oai/h2ogpt) | 7953 |
-|[arc53/DocsGPT](https://github.com/arc53/DocsGPT) | 7730 |
-|[PipedreamHQ/pipedream](https://github.com/PipedreamHQ/pipedream) | 7261 |
-|[joshpxyne/gpt-migrate](https://github.com/joshpxyne/gpt-migrate) | 6349 |
-|[bentoml/OpenLLM](https://github.com/bentoml/OpenLLM) | 6213 |
-|[mage-ai/mage-ai](https://github.com/mage-ai/mage-ai) | 5600 |
-|[zauberzeug/nicegui](https://github.com/zauberzeug/nicegui) | 5499 |
-|[wenda-LLM/wenda](https://github.com/wenda-LLM/wenda) | 5497 |
-|[sweepai/sweep](https://github.com/sweepai/sweep) | 5489 |
-|[embedchain/embedchain](https://github.com/embedchain/embedchain) | 5428 |
-|[zilliztech/GPTCache](https://github.com/zilliztech/GPTCache) | 5311 |
-|[Shaunwei/RealChar](https://github.com/Shaunwei/RealChar) | 5264 |
-|[GreyDGL/PentestGPT](https://github.com/GreyDGL/PentestGPT) | 5146 |
-|[gkamradt/langchain-tutorials](https://github.com/gkamradt/langchain-tutorials) | 5134 |
-|[serge-chat/serge](https://github.com/serge-chat/serge) | 5009 |
-|[assafelovic/gpt-researcher](https://github.com/assafelovic/gpt-researcher) | 4836 |
-|[openchatai/OpenChat](https://github.com/openchatai/OpenChat) | 4697 |
-|[intel-analytics/BigDL](https://github.com/intel-analytics/BigDL) | 4412 |
-|[continuedev/continue](https://github.com/continuedev/continue) | 4324 |
-|[postgresml/postgresml](https://github.com/postgresml/postgresml) | 4267 |
-|[madawei2699/myGPTReader](https://github.com/madawei2699/myGPTReader) | 4214 |
-|[MineDojo/Voyager](https://github.com/MineDojo/Voyager) | 4204 |
-|[danswer-ai/danswer](https://github.com/danswer-ai/danswer) | 3973 |
-|[RayVentura/ShortGPT](https://github.com/RayVentura/ShortGPT) | 3922 |
-|[Azure/azure-sdk-for-python](https://github.com/Azure/azure-sdk-for-python) | 3849 |
-|[khoj-ai/khoj](https://github.com/khoj-ai/khoj) | 3817 |
-|[langchain-ai/chat-langchain](https://github.com/langchain-ai/chat-langchain) | 3742 |
-|[Azure-Samples/azure-search-openai-demo](https://github.com/Azure-Samples/azure-search-openai-demo) | 3731 |
-|[marqo-ai/marqo](https://github.com/marqo-ai/marqo) | 3627 |
-|[kyegomez/tree-of-thoughts](https://github.com/kyegomez/tree-of-thoughts) | 3553 |
-|[llm-workflow-engine/llm-workflow-engine](https://github.com/llm-workflow-engine/llm-workflow-engine) | 3483 |
-|[PrefectHQ/marvin](https://github.com/PrefectHQ/marvin) | 3460 |
-|[aiwaves-cn/agents](https://github.com/aiwaves-cn/agents) | 3413 |
-|[OpenBMB/ToolBench](https://github.com/OpenBMB/ToolBench) | 3388 |
-|[shroominic/codeinterpreter-api](https://github.com/shroominic/codeinterpreter-api) | 3218 |
-|[whitead/paper-qa](https://github.com/whitead/paper-qa) | 3085 |
-|[project-baize/baize-chatbot](https://github.com/project-baize/baize-chatbot) | 3039 |
-|[OpenGVLab/InternGPT](https://github.com/OpenGVLab/InternGPT) | 2911 |
-|[ParisNeo/lollms-webui](https://github.com/ParisNeo/lollms-webui) | 2907 |
-|[Unstructured-IO/unstructured](https://github.com/Unstructured-IO/unstructured) | 2874 |
-|[openchatai/OpenCopilot](https://github.com/openchatai/OpenCopilot) | 2759 |
-|[OpenBMB/BMTools](https://github.com/OpenBMB/BMTools) | 2657 |
-|[homanp/superagent](https://github.com/homanp/superagent) | 2624 |
-|[SamurAIGPT/EmbedAI](https://github.com/SamurAIGPT/EmbedAI) | 2575 |
-|[GerevAI/gerev](https://github.com/GerevAI/gerev) | 2488 |
-|[microsoft/promptflow](https://github.com/microsoft/promptflow) | 2475 |
-|[OpenBMB/AgentVerse](https://github.com/OpenBMB/AgentVerse) | 2445 |
-|[Mintplex-Labs/anything-llm](https://github.com/Mintplex-Labs/anything-llm) | 2434 |
-|[emptycrown/llama-hub](https://github.com/emptycrown/llama-hub) | 2432 |
-|[NVIDIA/NeMo-Guardrails](https://github.com/NVIDIA/NeMo-Guardrails) | 2327 |
-|[ShreyaR/guardrails](https://github.com/ShreyaR/guardrails) | 2307 |
-|[thomas-yanxin/LangChain-ChatGLM-Webui](https://github.com/thomas-yanxin/LangChain-ChatGLM-Webui) | 2305 |
-|[yanqiangmiffy/Chinese-LangChain](https://github.com/yanqiangmiffy/Chinese-LangChain) | 2291 |
-|[keephq/keep](https://github.com/keephq/keep) | 2252 |
-|[OpenGVLab/Ask-Anything](https://github.com/OpenGVLab/Ask-Anything) | 2194 |
-|[IntelligenzaArtificiale/Free-Auto-GPT](https://github.com/IntelligenzaArtificiale/Free-Auto-GPT) | 2169 |
-|[Farama-Foundation/PettingZoo](https://github.com/Farama-Foundation/PettingZoo) | 2031 |
-|[YiVal/YiVal](https://github.com/YiVal/YiVal) | 2014 |
-|[hwchase17/notion-qa](https://github.com/hwchase17/notion-qa) | 2014 |
-|[jupyterlab/jupyter-ai](https://github.com/jupyterlab/jupyter-ai) | 1977 |
-|[paulpierre/RasaGPT](https://github.com/paulpierre/RasaGPT) | 1887 |
-|[dot-agent/dotagent-WIP](https://github.com/dot-agent/dotagent-WIP) | 1812 |
-|[hegelai/prompttools](https://github.com/hegelai/prompttools) | 1775 |
-|[vocodedev/vocode-python](https://github.com/vocodedev/vocode-python) | 1734 |
-|[Vonng/pigsty](https://github.com/Vonng/pigsty) | 1693 |
-|[psychic-api/psychic](https://github.com/psychic-api/psychic) | 1597 |
-|[avinashkranjan/Amazing-Python-Scripts](https://github.com/avinashkranjan/Amazing-Python-Scripts) | 1546 |
-|[pinterest/querybook](https://github.com/pinterest/querybook) | 1539 |
-|[Forethought-Technologies/AutoChain](https://github.com/Forethought-Technologies/AutoChain) | 1531 |
-|[Kav-K/GPTDiscord](https://github.com/Kav-K/GPTDiscord) | 1503 |
-|[jina-ai/langchain-serve](https://github.com/jina-ai/langchain-serve) | 1487 |
-|[noahshinn024/reflexion](https://github.com/noahshinn024/reflexion) | 1481 |
-|[jina-ai/dev-gpt](https://github.com/jina-ai/dev-gpt) | 1436 |
-|[ttengwang/Caption-Anything](https://github.com/ttengwang/Caption-Anything) | 1425 |
-|[milvus-io/bootcamp](https://github.com/milvus-io/bootcamp) | 1420 |
-|[agiresearch/OpenAGI](https://github.com/agiresearch/OpenAGI) | 1401 |
-|[greshake/llm-security](https://github.com/greshake/llm-security) | 1381 |
-|[jina-ai/thinkgpt](https://github.com/jina-ai/thinkgpt) | 1366 |
-|[lunasec-io/lunasec](https://github.com/lunasec-io/lunasec) | 1352 |
-|[101dotxyz/GPTeam](https://github.com/101dotxyz/GPTeam) | 1339 |
-|[refuel-ai/autolabel](https://github.com/refuel-ai/autolabel) | 1320 |
-|[melih-unsal/DemoGPT](https://github.com/melih-unsal/DemoGPT) | 1320 |
-|[mmz-001/knowledge_gpt](https://github.com/mmz-001/knowledge_gpt) | 1320 |
-|[richardyc/Chrome-GPT](https://github.com/richardyc/Chrome-GPT) | 1315 |
-|[run-llama/sec-insights](https://github.com/run-llama/sec-insights) | 1312 |
-|[Azure/azureml-examples](https://github.com/Azure/azureml-examples) | 1305 |
-|[cofactoryai/textbase](https://github.com/cofactoryai/textbase) | 1286 |
-|[dataelement/bisheng](https://github.com/dataelement/bisheng) | 1273 |
-|[eyurtsev/kor](https://github.com/eyurtsev/kor) | 1263 |
-|[pluralsh/plural](https://github.com/pluralsh/plural) | 1188 |
-|[FlagOpen/FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding) | 1184 |
-|[juncongmoo/chatllama](https://github.com/juncongmoo/chatllama) | 1144 |
-|[poe-platform/server-bot-quick-start](https://github.com/poe-platform/server-bot-quick-start) | 1139 |
-|[visual-openllm/visual-openllm](https://github.com/visual-openllm/visual-openllm) | 1137 |
-|[griptape-ai/griptape](https://github.com/griptape-ai/griptape) | 1124 |
-|[microsoft/X-Decoder](https://github.com/microsoft/X-Decoder) | 1119 |
-|[ThousandBirdsInc/chidori](https://github.com/ThousandBirdsInc/chidori) | 1116 |
-|[filip-michalsky/SalesGPT](https://github.com/filip-michalsky/SalesGPT) | 1112 |
-|[psychic-api/rag-stack](https://github.com/psychic-api/rag-stack) | 1110 |
-|[irgolic/AutoPR](https://github.com/irgolic/AutoPR) | 1100 |
-|[promptfoo/promptfoo](https://github.com/promptfoo/promptfoo) | 1099 |
-|[nod-ai/SHARK](https://github.com/nod-ai/SHARK) | 1062 |
-|[SamurAIGPT/Camel-AutoGPT](https://github.com/SamurAIGPT/Camel-AutoGPT) | 1036 |
-|[Farama-Foundation/chatarena](https://github.com/Farama-Foundation/chatarena) | 1020 |
-|[peterw/Chat-with-Github-Repo](https://github.com/peterw/Chat-with-Github-Repo) | 993 |
-|[jiran214/GPT-vup](https://github.com/jiran214/GPT-vup) | 967 |
-|[alejandro-ao/ask-multiple-pdfs](https://github.com/alejandro-ao/ask-multiple-pdfs) | 958 |
-|[run-llama/llama-lab](https://github.com/run-llama/llama-lab) | 953 |
-|[LC1332/Chat-Haruhi-Suzumiya](https://github.com/LC1332/Chat-Haruhi-Suzumiya) | 950 |
-|[rlancemartin/auto-evaluator](https://github.com/rlancemartin/auto-evaluator) | 927 |
-|[cheshire-cat-ai/core](https://github.com/cheshire-cat-ai/core) | 902 |
-|[Anil-matcha/ChatPDF](https://github.com/Anil-matcha/ChatPDF) | 894 |
-|[cirediatpl/FigmaChain](https://github.com/cirediatpl/FigmaChain) | 881 |
-|[seanpixel/Teenage-AGI](https://github.com/seanpixel/Teenage-AGI) | 876 |
-|[xusenlinzy/api-for-open-llm](https://github.com/xusenlinzy/api-for-open-llm) | 865 |
-|[ricklamers/shell-ai](https://github.com/ricklamers/shell-ai) | 864 |
-|[codeacme17/examor](https://github.com/codeacme17/examor) | 856 |
-|[corca-ai/EVAL](https://github.com/corca-ai/EVAL) | 836 |
-|[microsoft/Llama-2-Onnx](https://github.com/microsoft/Llama-2-Onnx) | 835 |
-|[explodinggradients/ragas](https://github.com/explodinggradients/ragas) | 833 |
-|[ajndkr/lanarky](https://github.com/ajndkr/lanarky) | 817 |
-|[kennethleungty/Llama-2-Open-Source-LLM-CPU-Inference](https://github.com/kennethleungty/Llama-2-Open-Source-LLM-CPU-Inference) | 814 |
-|[ray-project/llm-applications](https://github.com/ray-project/llm-applications) | 804 |
-|[hwchase17/chat-your-data](https://github.com/hwchase17/chat-your-data) | 801 |
-|[LambdaLabsML/examples](https://github.com/LambdaLabsML/examples) | 759 |
-|[kreneskyp/ix](https://github.com/kreneskyp/ix) | 758 |
-|[pyspark-ai/pyspark-ai](https://github.com/pyspark-ai/pyspark-ai) | 750 |
-|[billxbf/ReWOO](https://github.com/billxbf/ReWOO) | 746 |
-|[e-johnstonn/BriefGPT](https://github.com/e-johnstonn/BriefGPT) | 738 |
-|[akshata29/entaoai](https://github.com/akshata29/entaoai) | 733 |
-|[getmetal/motorhead](https://github.com/getmetal/motorhead) | 717 |
-|[ruoccofabrizio/azure-open-ai-embeddings-qna](https://github.com/ruoccofabrizio/azure-open-ai-embeddings-qna) | 712 |
-|[msoedov/langcorn](https://github.com/msoedov/langcorn) | 698 |
-|[Dataherald/dataherald](https://github.com/Dataherald/dataherald) | 684 |
-|[jondurbin/airoboros](https://github.com/jondurbin/airoboros) | 657 |
-|[Ikaros-521/AI-Vtuber](https://github.com/Ikaros-521/AI-Vtuber) | 651 |
-|[whyiyhw/chatgpt-wechat](https://github.com/whyiyhw/chatgpt-wechat) | 644 |
-|[langchain-ai/streamlit-agent](https://github.com/langchain-ai/streamlit-agent) | 637 |
-|[SamurAIGPT/ChatGPT-Developer-Plugins](https://github.com/SamurAIGPT/ChatGPT-Developer-Plugins) | 637 |
-|[OpenGenerativeAI/GenossGPT](https://github.com/OpenGenerativeAI/GenossGPT) | 632 |
-|[AILab-CVC/GPT4Tools](https://github.com/AILab-CVC/GPT4Tools) | 629 |
-|[langchain-ai/auto-evaluator](https://github.com/langchain-ai/auto-evaluator) | 614 |
-|[explosion/spacy-llm](https://github.com/explosion/spacy-llm) | 613 |
-|[alexanderatallah/window.ai](https://github.com/alexanderatallah/window.ai) | 607 |
-|[MiuLab/Taiwan-LLaMa](https://github.com/MiuLab/Taiwan-LLaMa) | 601 |
-|[microsoft/PodcastCopilot](https://github.com/microsoft/PodcastCopilot) | 600 |
-|[Dicklesworthstone/swiss_army_llama](https://github.com/Dicklesworthstone/swiss_army_llama) | 596 |
-|[NoDataFound/hackGPT](https://github.com/NoDataFound/hackGPT) | 596 |
-|[namuan/dr-doc-search](https://github.com/namuan/dr-doc-search) | 593 |
-|[amosjyng/langchain-visualizer](https://github.com/amosjyng/langchain-visualizer) | 582 |
-|[microsoft/sample-app-aoai-chatGPT](https://github.com/microsoft/sample-app-aoai-chatGPT) | 581 |
-|[yvann-hub/Robby-chatbot](https://github.com/yvann-hub/Robby-chatbot) | 581 |
-|[yeagerai/yeagerai-agent](https://github.com/yeagerai/yeagerai-agent) | 547 |
-|[tgscan-dev/tgscan](https://github.com/tgscan-dev/tgscan) | 533 |
-|[Azure-Samples/openai](https://github.com/Azure-Samples/openai) | 531 |
-|[plastic-labs/tutor-gpt](https://github.com/plastic-labs/tutor-gpt) | 531 |
-|[xuwenhao/geektime-ai-course](https://github.com/xuwenhao/geektime-ai-course) | 526 |
-|[michaelthwan/searchGPT](https://github.com/michaelthwan/searchGPT) | 526 |
-|[jonra1993/fastapi-alembic-sqlmodel-async](https://github.com/jonra1993/fastapi-alembic-sqlmodel-async) | 522 |
-|[jina-ai/agentchain](https://github.com/jina-ai/agentchain) | 519 |
-|[mckaywrigley/repo-chat](https://github.com/mckaywrigley/repo-chat) | 518 |
-|[modelscope/modelscope-agent](https://github.com/modelscope/modelscope-agent) | 512 |
-|[daveebbelaar/langchain-experiments](https://github.com/daveebbelaar/langchain-experiments) | 504 |
-|[freddyaboulton/gradio-tools](https://github.com/freddyaboulton/gradio-tools) | 497 |
-|[sidhq/Multi-GPT](https://github.com/sidhq/Multi-GPT) | 494 |
-|[continuum-llms/chatgpt-memory](https://github.com/continuum-llms/chatgpt-memory) | 489 |
-|[langchain-ai/langchain-aiplugin](https://github.com/langchain-ai/langchain-aiplugin) | 487 |
-|[mpaepper/content-chatbot](https://github.com/mpaepper/content-chatbot) | 483 |
-|[steamship-core/steamship-langchain](https://github.com/steamship-core/steamship-langchain) | 481 |
-|[alejandro-ao/langchain-ask-pdf](https://github.com/alejandro-ao/langchain-ask-pdf) | 474 |
-|[truera/trulens](https://github.com/truera/trulens) | 464 |
-|[marella/chatdocs](https://github.com/marella/chatdocs) | 459 |
-|[opencopilotdev/opencopilot](https://github.com/opencopilotdev/opencopilot) | 453 |
-|[poe-platform/poe-protocol](https://github.com/poe-platform/poe-protocol) | 444 |
-|[DataDog/dd-trace-py](https://github.com/DataDog/dd-trace-py) | 441 |
-|[logan-markewich/llama_index_starter_pack](https://github.com/logan-markewich/llama_index_starter_pack) | 441 |
-|[opentensor/bittensor](https://github.com/opentensor/bittensor) | 433 |
-|[DjangoPeng/openai-quickstart](https://github.com/DjangoPeng/openai-quickstart) | 425 |
-|[CarperAI/OpenELM](https://github.com/CarperAI/OpenELM) | 424 |
-|[daodao97/chatdoc](https://github.com/daodao97/chatdoc) | 423 |
-|[showlab/VLog](https://github.com/showlab/VLog) | 411 |
-|[Anil-matcha/Chatbase](https://github.com/Anil-matcha/Chatbase) | 402 |
-|[yakami129/VirtualWife](https://github.com/yakami129/VirtualWife) | 399 |
-|[wandb/weave](https://github.com/wandb/weave) | 399 |
-|[mtenenholtz/chat-twitter](https://github.com/mtenenholtz/chat-twitter) | 398 |
-|[LinkSoul-AI/AutoAgents](https://github.com/LinkSoul-AI/AutoAgents) | 397 |
-|[Agenta-AI/agenta](https://github.com/Agenta-AI/agenta) | 389 |
-|[huchenxucs/ChatDB](https://github.com/huchenxucs/ChatDB) | 386 |
-|[mallorbc/Finetune_LLMs](https://github.com/mallorbc/Finetune_LLMs) | 379 |
-|[junruxiong/IncarnaMind](https://github.com/junruxiong/IncarnaMind) | 372 |
-|[MagnivOrg/prompt-layer-library](https://github.com/MagnivOrg/prompt-layer-library) | 368 |
-|[mosaicml/examples](https://github.com/mosaicml/examples) | 366 |
-|[rsaryev/talk-codebase](https://github.com/rsaryev/talk-codebase) | 364 |
-|[morpheuslord/GPT_Vuln-analyzer](https://github.com/morpheuslord/GPT_Vuln-analyzer) | 362 |
-|[monarch-initiative/ontogpt](https://github.com/monarch-initiative/ontogpt) | 362 |
-|[JayZeeDesign/researcher-gpt](https://github.com/JayZeeDesign/researcher-gpt) | 361 |
-|[personoids/personoids-lite](https://github.com/personoids/personoids-lite) | 361 |
-|[intel/intel-extension-for-transformers](https://github.com/intel/intel-extension-for-transformers) | 357 |
-|[jerlendds/osintbuddy](https://github.com/jerlendds/osintbuddy) | 357 |
-|[steamship-packages/langchain-production-starter](https://github.com/steamship-packages/langchain-production-starter) | 356 |
-|[onlyphantom/llm-python](https://github.com/onlyphantom/llm-python) | 354 |
-|[Azure-Samples/miyagi](https://github.com/Azure-Samples/miyagi) | 340 |
-|[mrwadams/attackgen](https://github.com/mrwadams/attackgen) | 338 |
-|[rgomezcasas/dotfiles](https://github.com/rgomezcasas/dotfiles) | 337 |
-|[eosphoros-ai/DB-GPT-Hub](https://github.com/eosphoros-ai/DB-GPT-Hub) | 336 |
-|[andylokandy/gpt-4-search](https://github.com/andylokandy/gpt-4-search) | 335 |
-|[NimbleBoxAI/ChainFury](https://github.com/NimbleBoxAI/ChainFury) | 330 |
-|[momegas/megabots](https://github.com/momegas/megabots) | 329 |
-|[Nuggt-dev/Nuggt](https://github.com/Nuggt-dev/Nuggt) | 315 |
-|[itamargol/openai](https://github.com/itamargol/openai) | 315 |
-|[BlackHC/llm-strategy](https://github.com/BlackHC/llm-strategy) | 315 |
-|[aws-samples/aws-genai-llm-chatbot](https://github.com/aws-samples/aws-genai-llm-chatbot) | 312 |
-|[Cheems-Seminar/grounded-segment-any-parts](https://github.com/Cheems-Seminar/grounded-segment-any-parts) | 312 |
-|[preset-io/promptimize](https://github.com/preset-io/promptimize) | 311 |
-|[dgarnitz/vectorflow](https://github.com/dgarnitz/vectorflow) | 309 |
-|[langchain-ai/langsmith-cookbook](https://github.com/langchain-ai/langsmith-cookbook) | 309 |
-|[CambioML/pykoi](https://github.com/CambioML/pykoi) | 309 |
-|[wandb/edu](https://github.com/wandb/edu) | 301 |
-|[XzaiCloud/luna-ai](https://github.com/XzaiCloud/luna-ai) | 300 |
-|[liangwq/Chatglm_lora_multi-gpu](https://github.com/liangwq/Chatglm_lora_multi-gpu) | 294 |
-|[Haste171/langchain-chatbot](https://github.com/Haste171/langchain-chatbot) | 291 |
-|[sullivan-sean/chat-langchainjs](https://github.com/sullivan-sean/chat-langchainjs) | 286 |
-|[sugarforever/LangChain-Tutorials](https://github.com/sugarforever/LangChain-Tutorials) | 285 |
-|[facebookresearch/personal-timeline](https://github.com/facebookresearch/personal-timeline) | 283 |
-|[hnawaz007/pythondataanalysis](https://github.com/hnawaz007/pythondataanalysis) | 282 |
-|[yuanjie-ai/ChatLLM](https://github.com/yuanjie-ai/ChatLLM) | 280 |
-|[MetaGLM/FinGLM](https://github.com/MetaGLM/FinGLM) | 279 |
-|[JohnSnowLabs/langtest](https://github.com/JohnSnowLabs/langtest) | 277 |
-|[Em1tSan/NeuroGPT](https://github.com/Em1tSan/NeuroGPT) | 274 |
-|[Safiullah-Rahu/CSV-AI](https://github.com/Safiullah-Rahu/CSV-AI) | 274 |
-|[conceptofmind/toolformer](https://github.com/conceptofmind/toolformer) | 274 |
-|[airobotlab/KoChatGPT](https://github.com/airobotlab/KoChatGPT) | 266 |
-|[gia-guar/JARVIS-ChatGPT](https://github.com/gia-guar/JARVIS-ChatGPT) | 263 |
-|[Mintplex-Labs/vector-admin](https://github.com/Mintplex-Labs/vector-admin) | 262 |
-|[artitw/text2text](https://github.com/artitw/text2text) | 262 |
-|[kaarthik108/snowChat](https://github.com/kaarthik108/snowChat) | 261 |
-|[paolorechia/learn-langchain](https://github.com/paolorechia/learn-langchain) | 260 |
-|[shamspias/customizable-gpt-chatbot](https://github.com/shamspias/customizable-gpt-chatbot) | 260 |
-|[ur-whitelab/exmol](https://github.com/ur-whitelab/exmol) | 258 |
-|[hwchase17/chroma-langchain](https://github.com/hwchase17/chroma-langchain) | 257 |
-|[bborn/howdoi.ai](https://github.com/bborn/howdoi.ai) | 255 |
-|[ur-whitelab/chemcrow-public](https://github.com/ur-whitelab/chemcrow-public) | 253 |
-|[pablomarin/GPT-Azure-Search-Engine](https://github.com/pablomarin/GPT-Azure-Search-Engine) | 251 |
-|[gustavz/DataChad](https://github.com/gustavz/DataChad) | 249 |
-|[radi-cho/datasetGPT](https://github.com/radi-cho/datasetGPT) | 249 |
-|[ennucore/clippinator](https://github.com/ennucore/clippinator) | 247 |
-|[recalign/RecAlign](https://github.com/recalign/RecAlign) | 244 |
-|[lilacai/lilac](https://github.com/lilacai/lilac) | 243 |
-|[kaleido-lab/dolphin](https://github.com/kaleido-lab/dolphin) | 236 |
-|[iusztinpaul/hands-on-llms](https://github.com/iusztinpaul/hands-on-llms) | 233 |
-|[PradipNichite/Youtube-Tutorials](https://github.com/PradipNichite/Youtube-Tutorials) | 231 |
-|[shaman-ai/agent-actors](https://github.com/shaman-ai/agent-actors) | 231 |
-|[hwchase17/langchain-streamlit-template](https://github.com/hwchase17/langchain-streamlit-template) | 231 |
-|[yym68686/ChatGPT-Telegram-Bot](https://github.com/yym68686/ChatGPT-Telegram-Bot) | 226 |
-|[grumpyp/aixplora](https://github.com/grumpyp/aixplora) | 222 |
-|[su77ungr/CASALIOY](https://github.com/su77ungr/CASALIOY) | 222 |
-|[alvarosevilla95/autolang](https://github.com/alvarosevilla95/autolang) | 222 |
-|[arthur-ai/bench](https://github.com/arthur-ai/bench) | 220 |
-|[miaoshouai/miaoshouai-assistant](https://github.com/miaoshouai/miaoshouai-assistant) | 219 |
-|[AutoPackAI/beebot](https://github.com/AutoPackAI/beebot) | 217 |
-|[edreisMD/plugnplai](https://github.com/edreisMD/plugnplai) | 216 |
-|[nicknochnack/LangchainDocuments](https://github.com/nicknochnack/LangchainDocuments) | 214 |
-|[AkshitIreddy/Interactive-LLM-Powered-NPCs](https://github.com/AkshitIreddy/Interactive-LLM-Powered-NPCs) | 213 |
-|[SpecterOps/Nemesis](https://github.com/SpecterOps/Nemesis) | 210 |
-|[kyegomez/swarms](https://github.com/kyegomez/swarms) | 210 |
-|[wpydcr/LLM-Kit](https://github.com/wpydcr/LLM-Kit) | 208 |
-|[orgexyz/BlockAGI](https://github.com/orgexyz/BlockAGI) | 204 |
-|[Chainlit/cookbook](https://github.com/Chainlit/cookbook) | 202 |
-|[WongSaang/chatgpt-ui-server](https://github.com/WongSaang/chatgpt-ui-server) | 202 |
-|[jbrukh/gpt-jargon](https://github.com/jbrukh/gpt-jargon) | 202 |
-|[handrew/browserpilot](https://github.com/handrew/browserpilot) | 202 |
-|[langchain-ai/web-explorer](https://github.com/langchain-ai/web-explorer) | 200 |
-|[plchld/InsightFlow](https://github.com/plchld/InsightFlow) | 200 |
-|[alphasecio/langchain-examples](https://github.com/alphasecio/langchain-examples) | 199 |
-|[Gentopia-AI/Gentopia](https://github.com/Gentopia-AI/Gentopia) | 198 |
-|[SamPink/dev-gpt](https://github.com/SamPink/dev-gpt) | 196 |
-|[yasyf/compress-gpt](https://github.com/yasyf/compress-gpt) | 196 |
-|[benthecoder/ClassGPT](https://github.com/benthecoder/ClassGPT) | 195 |
-|[voxel51/voxelgpt](https://github.com/voxel51/voxelgpt) | 193 |
-|[CL-lau/SQL-GPT](https://github.com/CL-lau/SQL-GPT) | 192 |
-|[blob42/Instrukt](https://github.com/blob42/Instrukt) | 191 |
-|[streamlit/llm-examples](https://github.com/streamlit/llm-examples) | 191 |
-|[stepanogil/autonomous-hr-chatbot](https://github.com/stepanogil/autonomous-hr-chatbot) | 190 |
-|[TsinghuaDatabaseGroup/DB-GPT](https://github.com/TsinghuaDatabaseGroup/DB-GPT) | 189 |
-|[PJLab-ADG/DriveLikeAHuman](https://github.com/PJLab-ADG/DriveLikeAHuman) | 187 |
-|[Azure-Samples/azure-search-power-skills](https://github.com/Azure-Samples/azure-search-power-skills) | 187 |
-|[microsoft/azure-openai-in-a-day-workshop](https://github.com/microsoft/azure-openai-in-a-day-workshop) | 187 |
-|[ju-bezdek/langchain-decorators](https://github.com/ju-bezdek/langchain-decorators) | 182 |
-|[hardbyte/qabot](https://github.com/hardbyte/qabot) | 181 |
-|[hongbo-miao/hongbomiao.com](https://github.com/hongbo-miao/hongbomiao.com) | 180 |
-|[QwenLM/Qwen-Agent](https://github.com/QwenLM/Qwen-Agent) | 179 |
-|[showlab/UniVTG](https://github.com/showlab/UniVTG) | 179 |
-|[Azure-Samples/jp-azureopenai-samples](https://github.com/Azure-Samples/jp-azureopenai-samples) | 176 |
-|[afaqueumer/DocQA](https://github.com/afaqueumer/DocQA) | 174 |
-|[ethanyanjiali/minChatGPT](https://github.com/ethanyanjiali/minChatGPT) | 174 |
-|[shauryr/S2QA](https://github.com/shauryr/S2QA) | 174 |
-|[RoboCoachTechnologies/GPT-Synthesizer](https://github.com/RoboCoachTechnologies/GPT-Synthesizer) | 173 |
-|[chakkaradeep/pyCodeAGI](https://github.com/chakkaradeep/pyCodeAGI) | 172 |
-|[vaibkumr/prompt-optimizer](https://github.com/vaibkumr/prompt-optimizer) | 171 |
-|[ccurme/yolopandas](https://github.com/ccurme/yolopandas) | 170 |
-|[anarchy-ai/LLM-VM](https://github.com/anarchy-ai/LLM-VM) | 169 |
-|[ray-project/langchain-ray](https://github.com/ray-project/langchain-ray) | 169 |
-|[fengyuli-dev/multimedia-gpt](https://github.com/fengyuli-dev/multimedia-gpt) | 169 |
-|[ibiscp/LLM-IMDB](https://github.com/ibiscp/LLM-IMDB) | 168 |
-|[mayooear/private-chatbot-mpt30b-langchain](https://github.com/mayooear/private-chatbot-mpt30b-langchain) | 167 |
-|[OpenPluginACI/openplugin](https://github.com/OpenPluginACI/openplugin) | 165 |
-|[jmpaz/promptlib](https://github.com/jmpaz/promptlib) | 165 |
-|[kjappelbaum/gptchem](https://github.com/kjappelbaum/gptchem) | 162 |
-|[JorisdeJong123/7-Days-of-LangChain](https://github.com/JorisdeJong123/7-Days-of-LangChain) | 161 |
-|[retr0reg/Ret2GPT](https://github.com/retr0reg/Ret2GPT) | 161 |
-|[menloparklab/falcon-langchain](https://github.com/menloparklab/falcon-langchain) | 159 |
-|[summarizepaper/summarizepaper](https://github.com/summarizepaper/summarizepaper) | 158 |
-|[emarco177/ice_breaker](https://github.com/emarco177/ice_breaker) | 157 |
-|[AmineDiro/cria](https://github.com/AmineDiro/cria) | 156 |
-|[morpheuslord/HackBot](https://github.com/morpheuslord/HackBot) | 156 |
-|[homanp/vercel-langchain](https://github.com/homanp/vercel-langchain) | 156 |
-|[mlops-for-all/mlops-for-all.github.io](https://github.com/mlops-for-all/mlops-for-all.github.io) | 155 |
-|[positive666/Prompt-Can-Anything](https://github.com/positive666/Prompt-Can-Anything) | 154 |
-|[deeppavlov/dream](https://github.com/deeppavlov/dream) | 153 |
-|[flurb18/AgentOoba](https://github.com/flurb18/AgentOoba) | 151 |
-|[Open-Swarm-Net/GPT-Swarm](https://github.com/Open-Swarm-Net/GPT-Swarm) | 151 |
-|[v7labs/benchllm](https://github.com/v7labs/benchllm) | 150 |
-|[Klingefjord/chatgpt-telegram](https://github.com/Klingefjord/chatgpt-telegram) | 150 |
-|[Aggregate-Intellect/sherpa](https://github.com/Aggregate-Intellect/sherpa) | 148 |
-|[Coding-Crashkurse/Langchain-Full-Course](https://github.com/Coding-Crashkurse/Langchain-Full-Course) | 148 |
-|[SuperDuperDB/superduperdb](https://github.com/SuperDuperDB/superduperdb) | 147 |
-|[defenseunicorns/leapfrogai](https://github.com/defenseunicorns/leapfrogai) | 147 |
-|[menloparklab/langchain-cohere-qdrant-doc-retrieval](https://github.com/menloparklab/langchain-cohere-qdrant-doc-retrieval) | 147 |
-|[Jaseci-Labs/jaseci](https://github.com/Jaseci-Labs/jaseci) | 146 |
-|[realminchoi/babyagi-ui](https://github.com/realminchoi/babyagi-ui) | 146 |
-|[iMagist486/ElasticSearch-Langchain-Chatglm2](https://github.com/iMagist486/ElasticSearch-Langchain-Chatglm2) | 144 |
-|[peterw/StoryStorm](https://github.com/peterw/StoryStorm) | 143 |
-|[kulltc/chatgpt-sql](https://github.com/kulltc/chatgpt-sql) | 142 |
-|[Teahouse-Studios/akari-bot](https://github.com/Teahouse-Studios/akari-bot) | 142 |
-|[hirokidaichi/wanna](https://github.com/hirokidaichi/wanna) | 141 |
-|[yasyf/summ](https://github.com/yasyf/summ) | 141 |
-|[solana-labs/chatgpt-plugin](https://github.com/solana-labs/chatgpt-plugin) | 140 |
-|[ssheng/BentoChain](https://github.com/ssheng/BentoChain) | 139 |
-|[mallahyari/drqa](https://github.com/mallahyari/drqa) | 139 |
-|[petehunt/langchain-github-bot](https://github.com/petehunt/langchain-github-bot) | 139 |
-|[dbpunk-labs/octogen](https://github.com/dbpunk-labs/octogen) | 138 |
-|[RedisVentures/redis-openai-qna](https://github.com/RedisVentures/redis-openai-qna) | 138 |
-|[eunomia-bpf/GPTtrace](https://github.com/eunomia-bpf/GPTtrace) | 138 |
-|[langchain-ai/langsmith-sdk](https://github.com/langchain-ai/langsmith-sdk) | 137 |
-|[jina-ai/fastapi-serve](https://github.com/jina-ai/fastapi-serve) | 137 |
-|[yeagerai/genworlds](https://github.com/yeagerai/genworlds) | 137 |
-|[aurelio-labs/arxiv-bot](https://github.com/aurelio-labs/arxiv-bot) | 137 |
-|[luisroque/large_laguage_models](https://github.com/luisroque/large_laguage_models) | 136 |
-|[ChuloAI/BrainChulo](https://github.com/ChuloAI/BrainChulo) | 136 |
-|[3Alan/DocsMind](https://github.com/3Alan/DocsMind) | 136 |
-|[KylinC/ChatFinance](https://github.com/KylinC/ChatFinance) | 133 |
-|[langchain-ai/text-split-explorer](https://github.com/langchain-ai/text-split-explorer) | 133 |
-|[davila7/file-gpt](https://github.com/davila7/file-gpt) | 133 |
-|[tencentmusic/supersonic](https://github.com/tencentmusic/supersonic) | 132 |
-|[kimtth/azure-openai-llm-vector-langchain](https://github.com/kimtth/azure-openai-llm-vector-langchain) | 131 |
-|[ciare-robotics/world-creator](https://github.com/ciare-robotics/world-creator) | 129 |
-|[zenml-io/zenml-projects](https://github.com/zenml-io/zenml-projects) | 129 |
-|[log1stics/voice-generator-webui](https://github.com/log1stics/voice-generator-webui) | 129 |
-|[snexus/llm-search](https://github.com/snexus/llm-search) | 129 |
-|[fixie-ai/fixie-examples](https://github.com/fixie-ai/fixie-examples) | 128 |
-|[MedalCollector/Orator](https://github.com/MedalCollector/Orator) | 127 |
-|[grumpyp/chroma-langchain-tutorial](https://github.com/grumpyp/chroma-langchain-tutorial) | 127 |
-|[langchain-ai/langchain-aws-template](https://github.com/langchain-ai/langchain-aws-template) | 127 |
-|[prof-frink-lab/slangchain](https://github.com/prof-frink-lab/slangchain) | 126 |
-|[KMnO4-zx/huanhuan-chat](https://github.com/KMnO4-zx/huanhuan-chat) | 124 |
-|[RCGAI/SimplyRetrieve](https://github.com/RCGAI/SimplyRetrieve) | 124 |
-|[Dicklesworthstone/llama2_aided_tesseract](https://github.com/Dicklesworthstone/llama2_aided_tesseract) | 123 |
-|[sdaaron/QueryGPT](https://github.com/sdaaron/QueryGPT) | 122 |
-|[athina-ai/athina-sdk](https://github.com/athina-ai/athina-sdk) | 121 |
-|[AIAnytime/Llama2-Medical-Chatbot](https://github.com/AIAnytime/Llama2-Medical-Chatbot) | 121 |
-|[MuhammadMoinFaisal/LargeLanguageModelsProjects](https://github.com/MuhammadMoinFaisal/LargeLanguageModelsProjects) | 121 |
-|[Azure/business-process-automation](https://github.com/Azure/business-process-automation) | 121 |
-|[definitive-io/code-indexer-loop](https://github.com/definitive-io/code-indexer-loop) | 119 |
-|[nrl-ai/pautobot](https://github.com/nrl-ai/pautobot) | 119 |
-|[Azure/app-service-linux-docs](https://github.com/Azure/app-service-linux-docs) | 118 |
-|[zilliztech/akcio](https://github.com/zilliztech/akcio) | 118 |
-|[CodeAlchemyAI/ViLT-GPT](https://github.com/CodeAlchemyAI/ViLT-GPT) | 117 |
-|[georgesung/llm_qlora](https://github.com/georgesung/llm_qlora) | 117 |
-|[nicknochnack/Nopenai](https://github.com/nicknochnack/Nopenai) | 115 |
-|[nftblackmagic/flask-langchain](https://github.com/nftblackmagic/flask-langchain) | 115 |
-|[mortium91/langchain-assistant](https://github.com/mortium91/langchain-assistant) | 115 |
-|[Ngonie-x/langchain_csv](https://github.com/Ngonie-x/langchain_csv) | 114 |
-|[wombyz/HormoziGPT](https://github.com/wombyz/HormoziGPT) | 114 |
-|[langchain-ai/langchain-teacher](https://github.com/langchain-ai/langchain-teacher) | 113 |
-|[mluogh/eastworld](https://github.com/mluogh/eastworld) | 112 |
-|[mudler/LocalAGI](https://github.com/mudler/LocalAGI) | 112 |
-|[marimo-team/marimo](https://github.com/marimo-team/marimo) | 111 |
-|[trancethehuman/entities-extraction-web-scraper](https://github.com/trancethehuman/entities-extraction-web-scraper) | 111 |
-|[xuwenhao/mactalk-ai-course](https://github.com/xuwenhao/mactalk-ai-course) | 111 |
-|[dcaribou/transfermarkt-datasets](https://github.com/dcaribou/transfermarkt-datasets) | 111 |
-|[rabbitmetrics/langchain-13-min](https://github.com/rabbitmetrics/langchain-13-min) | 111 |
-|[dotvignesh/PDFChat](https://github.com/dotvignesh/PDFChat) | 111 |
-|[aws-samples/cdk-eks-blueprints-patterns](https://github.com/aws-samples/cdk-eks-blueprints-patterns) | 110 |
-|[topoteretes/PromethAI-Backend](https://github.com/topoteretes/PromethAI-Backend) | 110 |
-|[jlonge4/local_llama](https://github.com/jlonge4/local_llama) | 110 |
-|[RUC-GSAI/YuLan-Rec](https://github.com/RUC-GSAI/YuLan-Rec) | 108 |
-|[gh18l/CrawlGPT](https://github.com/gh18l/CrawlGPT) | 107 |
-|[c0sogi/LLMChat](https://github.com/c0sogi/LLMChat) | 107 |
-|[hwchase17/langchain-gradio-template](https://github.com/hwchase17/langchain-gradio-template) | 107 |
-|[ArjanCodes/examples](https://github.com/ArjanCodes/examples) | 106 |
-|[genia-dev/GeniA](https://github.com/genia-dev/GeniA) | 105 |
-|[nexus-stc/stc](https://github.com/nexus-stc/stc) | 105 |
-|[mbchang/data-driven-characters](https://github.com/mbchang/data-driven-characters) | 105 |
-|[ademakdogan/ChatSQL](https://github.com/ademakdogan/ChatSQL) | 104 |
-|[crosleythomas/MirrorGPT](https://github.com/crosleythomas/MirrorGPT) | 104 |
-|[IvanIsCoding/ResuLLMe](https://github.com/IvanIsCoding/ResuLLMe) | 104 |
-|[avrabyt/MemoryBot](https://github.com/avrabyt/MemoryBot) | 104 |
-|[Azure/azure-sdk-tools](https://github.com/Azure/azure-sdk-tools) | 103 |
-|[aniketmaurya/llm-inference](https://github.com/aniketmaurya/llm-inference) | 103 |
-|[Anil-matcha/Youtube-to-chatbot](https://github.com/Anil-matcha/Youtube-to-chatbot) | 103 |
-|[nyanp/chat2plot](https://github.com/nyanp/chat2plot) | 102 |
-|[aws-samples/amazon-kendra-langchain-extensions](https://github.com/aws-samples/amazon-kendra-langchain-extensions) | 101 |
-|[atisharma/llama_farm](https://github.com/atisharma/llama_farm) | 100 |
-|[Xueheng-Li/SynologyChatbotGPT](https://github.com/Xueheng-Li/SynologyChatbotGPT) | 100 |
-
-
-
-_Generated by [github-dependents-info](https://github.com/nvuillam/github-dependents-info)_
-
-`github-dependents-info --repo langchain-ai/langchain --markdownfile dependents.md --minstars 100 --sort stars`

docs/docs/additional_resources/tutorials.mdx

@@ -1,143 +0,0 @@
-# Tutorials
-
-Below are links to tutorials and courses on LangChain. For written guides on common use cases for LangChain, check out the [use cases guides](/docs/use_cases).
-
-⛓ icon marks a new addition [last update 2023-09-21]
-
----------------------
-
-### DeepLearning.AI courses
- by [Harrison Chase](https://github.com/hwchase17) and [Andrew Ng](https://en.wikipedia.org/wiki/Andrew_Ng)
-- [LangChain for LLM Application Development](https://learn.deeplearning.ai/langchain)
-- [LangChain Chat with Your Data](https://learn.deeplearning.ai/langchain-chat-with-your-data)
-
-### Handbook
-[LangChain AI Handbook](https://www.pinecone.io/learn/langchain/) By **James Briggs** and **Francisco Ingham**
-
-### Short Tutorials
-[LangChain Explained in 13 Minutes | QuickStart Tutorial for Beginners](https://youtu.be/aywZrzNaKjs) by [Rabbitmetrics](https://www.youtube.com/@rabbitmetrics)
-
-[LangChain Crash Course: Build an AutoGPT app in 25 minutes](https://youtu.be/MlK6SIjcjE8) by [Nicholas Renotte](https://www.youtube.com/@NicholasRenotte)
-
-[LangChain Crash Course - Build apps with language models](https://youtu.be/LbT1yp6quS8) by [Patrick Loeber](https://www.youtube.com/@patloeber)
-
-##  Tutorials
-
-### [LangChain for Gen AI and LLMs](https://www.youtube.com/playlist?list=PLIUOU7oqGTLieV9uTIFMm6_4PXg-hlN6F) by [James Briggs](https://www.youtube.com/@jamesbriggs)
-- #1 [Getting Started with `GPT-3` vs. Open Source LLMs](https://youtu.be/nE2skSRWTTs)
-- #2 [Prompt Templates for `GPT 3.5` and other LLMs](https://youtu.be/RflBcK0oDH0)
-- #3 [LLM Chains using `GPT 3.5` and other LLMs](https://youtu.be/S8j9Tk0lZHU)
-- [LangChain Data Loaders, Tokenizers, Chunking, and Datasets - Data Prep 101](https://youtu.be/eqOfr4AGLk8)
-- #4 [Chatbot Memory for `Chat-GPT`, `Davinci` + other LLMs](https://youtu.be/X05uK0TZozM)
-- #5 [Chat with OpenAI in LangChain](https://youtu.be/CnAgB3A5OlU)
-- #6 [Fixing LLM Hallucinations with Retrieval Augmentation in LangChain](https://youtu.be/kvdVduIJsc8)
-- #7 [LangChain Agents Deep Dive with `GPT 3.5`](https://youtu.be/jSP-gSEyVeI)
-- #8 [Create Custom Tools for Chatbots in LangChain](https://youtu.be/q-HNphrWsDE)
-- #9 [Build Conversational Agents with Vector DBs](https://youtu.be/H6bCqqw9xyI)
-- [Using NEW `MPT-7B` in Hugging Face and LangChain](https://youtu.be/DXpk9K7DgMo)
-- [`MPT-30B` Chatbot with LangChain](https://youtu.be/pnem-EhT6VI)
-- ⛓ [Fine-tuning OpenAI's `GPT 3.5` for LangChain Agents](https://youtu.be/boHXgQ5eQic?si=OOOfK-GhsgZGBqSr)
-- ⛓ [Chatbots with `RAG`: LangChain Full Walkthrough](https://youtu.be/LhnCsygAvzY?si=N7k6xy4RQksbWwsQ)
-
-
-### [LangChain 101](https://www.youtube.com/playlist?list=PLqZXAkvF1bPNQER9mLmDbntNfSpzdDIU5) by [Greg Kamradt (Data Indy)](https://www.youtube.com/@DataIndependent)
-- [What Is LangChain? - LangChain + `ChatGPT` Overview](https://youtu.be/_v_fgW2SkkQ)
-- [Quickstart Guide](https://youtu.be/kYRB-vJFy38)
-- [Beginner's Guide To 7 Essential Concepts](https://youtu.be/2xxziIWmaSA)
-- [Beginner's Guide To 9 Use Cases](https://youtu.be/vGP4pQdCocw)
-- [Agents Overview + Google Searches](https://youtu.be/Jq9Sf68ozk0)
-- [`OpenAI` + `Wolfram Alpha`](https://youtu.be/UijbzCIJ99g)
-- [Ask Questions On Your Custom (or Private) Files](https://youtu.be/EnT-ZTrcPrg)
-- [Connect `Google Drive Files` To `OpenAI`](https://youtu.be/IqqHqDcXLww)
-- [`YouTube Transcripts` + `OpenAI`](https://youtu.be/pNcQ5XXMgH4)
-- [Question A 300 Page Book (w/ `OpenAI` + `Pinecone`)](https://youtu.be/h0DHDp1FbmQ)
-- [Workaround `OpenAI's` Token Limit With Chain Types](https://youtu.be/f9_BWhCI4Zo)
-- [Build Your Own OpenAI + LangChain Web App in 23 Minutes](https://youtu.be/U_eV8wfMkXU)
-- [Working With The New `ChatGPT API`](https://youtu.be/e9P7FLi5Zy8)
-- [OpenAI + LangChain Wrote Me 100 Custom Sales Emails](https://youtu.be/y1pyAQM-3Bo)
-- [Structured Output From `OpenAI` (Clean Dirty Data)](https://youtu.be/KwAXfey-xQk)
-- [Connect `OpenAI` To +5,000 Tools (LangChain + `Zapier`)](https://youtu.be/7tNm0yiDigU)
-- [Use LLMs To Extract Data From Text (Expert Mode)](https://youtu.be/xZzvwR9jdPA)
-- [Extract Insights From Interview Transcripts Using LLMs](https://youtu.be/shkMOHwJ4SM)
-- [5 Levels Of LLM Summarizing: Novice to Expert](https://youtu.be/qaPMdcCqtWk)
-- [Control Tone & Writing Style Of Your LLM Output](https://youtu.be/miBG-a3FuhU)
-- [Build Your Own `AI Twitter Bot` Using LLMs](https://youtu.be/yLWLDjT01q8)
-- [ChatGPT made my interview questions for me (`Streamlit` + LangChain)](https://youtu.be/zvoAMx0WKkw)
-- [Function Calling via ChatGPT API - First Look With LangChain](https://youtu.be/0-zlUy7VUjg)
-- [Extract Topics From Video/Audio With LLMs (Topic Modeling w/ LangChain)](https://youtu.be/pEkxRQFNAs4)
-
-
-### [LangChain How to and guides](https://www.youtube.com/playlist?list=PL8motc6AQftk1Bs42EW45kwYbyJ4jOdiZ) by [Sam Witteveen](https://www.youtube.com/@samwitteveenai)
-- [LangChain Basics - LLMs & PromptTemplates with Colab](https://youtu.be/J_0qvRt4LNk)
-- [LangChain Basics - Tools and Chains](https://youtu.be/hI2BY7yl_Ac)
-- [`ChatGPT API` Announcement & Code Walkthrough with LangChain](https://youtu.be/phHqvLHCwH4)
-- [Conversations with Memory (explanation & code walkthrough)](https://youtu.be/X550Zbz_ROE)
-- [Chat with `Flan20B`](https://youtu.be/VW5LBavIfY4)
-- [Using `Hugging Face Models` locally (code walkthrough)](https://youtu.be/Kn7SX2Mx_Jk)
-- [`PAL`: Program-aided Language Models with LangChain code](https://youtu.be/dy7-LvDu-3s)
-- [Building a Summarization System with LangChain and `GPT-3` - Part 1](https://youtu.be/LNq_2s_H01Y)
-- [Building a Summarization System with LangChain and `GPT-3` - Part 2](https://youtu.be/d-yeHDLgKHw)
-- [Microsoft's `Visual ChatGPT` using LangChain](https://youtu.be/7YEiEyfPF5U)
-- [LangChain Agents - Joining Tools and Chains with Decisions](https://youtu.be/ziu87EXZVUE)
-- [Comparing LLMs with LangChain](https://youtu.be/rFNG0MIEuW0)
-- [Using `Constitutional AI` in LangChain](https://youtu.be/uoVqNFDwpX4)
-- [Talking to `Alpaca` with LangChain - Creating an Alpaca Chatbot](https://youtu.be/v6sF8Ed3nTE)
-- [Talk to your `CSV` & `Excel` with LangChain](https://youtu.be/xQ3mZhw69bc)
-- [`BabyAGI`: Discover the Power of Task-Driven Autonomous Agents!](https://youtu.be/QBcDLSE2ERA)
-- [Improve your `BabyAGI` with LangChain](https://youtu.be/DRgPyOXZ-oE)
-- [Master `PDF` Chat with LangChain - Your essential guide to queries on documents](https://youtu.be/ZzgUqFtxgXI)
-- [Using LangChain with `DuckDuckGO`, `Wikipedia` & `PythonREPL` Tools](https://youtu.be/KerHlb8nuVc)
-- [Building Custom Tools and Agents with LangChain (gpt-3.5-turbo)](https://youtu.be/biS8G8x8DdA)
-- [LangChain Retrieval QA Over Multiple Files with `ChromaDB`](https://youtu.be/3yPBVii7Ct0)
-- [LangChain Retrieval QA with Instructor Embeddings & `ChromaDB` for PDFs](https://youtu.be/cFCGUjc33aU)
-- [LangChain + Retrieval Local LLMs for Retrieval QA - No OpenAI!!!](https://youtu.be/9ISVjh8mdlA)
-- [`Camel` + LangChain for Synthetic Data & Market Research](https://youtu.be/GldMMK6-_-g)
-- [Information Extraction with LangChain & `Kor`](https://youtu.be/SW1ZdqH0rRQ)
-- [Converting a LangChain App from OpenAI to OpenSource](https://youtu.be/KUDn7bVyIfc)
-- [Using LangChain `Output Parsers` to get what you want out of LLMs](https://youtu.be/UVn2NroKQCw)
-- [Building a LangChain Custom Medical Agent with Memory](https://youtu.be/6UFtRwWnHws)
-- [Understanding `ReACT` with LangChain](https://youtu.be/Eug2clsLtFs)
-- [`OpenAI Functions` + LangChain : Building a Multi Tool Agent](https://youtu.be/4KXK6c6TVXQ)
-- [What can you do with 16K tokens in LangChain?](https://youtu.be/z2aCZBAtWXs)
-- [Tagging and Extraction - Classification using `OpenAI Functions`](https://youtu.be/a8hMgIcUEnE)
-- [HOW to Make Conversational Form with LangChain](https://youtu.be/IT93On2LB5k)
-- ⛓ [`Claude-2` meets LangChain!](https://youtu.be/Hb_D3p0bK2U?si=j96Kc7oJoeRI5-iC)
-- ⛓ [`PaLM 2` Meets LangChain](https://youtu.be/orPwLibLqm4?si=KgJjpEbAD9YBPqT4)
-- ⛓ [`LLaMA2` with LangChain - Basics | LangChain TUTORIAL](https://youtu.be/cIRzwSXB4Rc?si=v3Hwxk1m3fksBIHN)
-- ⛓ [Serving `LLaMA2` with `Replicate`](https://youtu.be/JIF4nNi26DE?si=dSazFyC4UQmaR-rJ)
-- ⛓ [NEW LangChain Expression Language](https://youtu.be/ud7HJ2p3gp0?si=8pJ9O6hGbXrCX5G9)
-- ⛓ [Building a RCI Chain for Agents with LangChain Expression Language](https://youtu.be/QaKM5s0TnsY?si=0miEj-o17AHcGfLG)
-- ⛓ [How to Run `LLaMA-2-70B` on the `Together AI`](https://youtu.be/Tc2DHfzHeYE?si=Xku3S9dlBxWQukpe)
-- ⛓ [`RetrievalQA` with `LLaMA 2 70b` & `Chroma` DB](https://youtu.be/93yueQQnqpM?si=ZMwj-eS_CGLnNMXZ)
-- ⛓ [How to use `BGE Embeddings` for LangChain](https://youtu.be/sWRvSG7vL4g?si=85jnvnmTCF9YIWXI)
-- ⛓ [How to use Custom Prompts for `RetrievalQA` on `LLaMA-2 7B`](https://youtu.be/PDwUKves9GY?si=sMF99TWU0p4eiK80)
-
-
-### [LangChain](https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr) by [Prompt Engineering](https://www.youtube.com/@engineerprompt)
-- [LangChain Crash Course — All You Need to Know to Build Powerful Apps with LLMs](https://youtu.be/5-fc4Tlgmro)
-- [Working with MULTIPLE `PDF` Files in LangChain: `ChatGPT` for your Data](https://youtu.be/s5LhRdh5fu4)
-- [`ChatGPT` for YOUR OWN `PDF` files with LangChain](https://youtu.be/TLf90ipMzfE)
-- [Talk to YOUR DATA without OpenAI APIs: LangChain](https://youtu.be/wrD-fZvT6UI)
-- [LangChain: `PDF` Chat App (GUI) | `ChatGPT` for Your `PDF` FILES](https://youtu.be/RIWbalZ7sTo)
-- [`LangFlow`: Build Chatbots without Writing Code](https://youtu.be/KJ-ux3hre4s)
-- [LangChain: Giving Memory to LLMs](https://youtu.be/dxO6pzlgJiY)
-- [BEST OPEN Alternative to `OPENAI's EMBEDDINGs` for Retrieval QA: LangChain](https://youtu.be/ogEalPMUCSY)
-- [LangChain: Run Language Models Locally - `Hugging Face Models`](https://youtu.be/Xxxuw4_iCzw) 
-- ⛓ [Slash API Costs: Mastering Caching for LLM Applications](https://youtu.be/EQOznhaJWR0?si=AXoI7f3-SVFRvQUl)
-- ⛓ [Avoid PROMPT INJECTION with `Constitutional AI` - LangChain](https://youtu.be/tyKSkPFHVX8?si=9mgcB5Y1kkotkBGB)
-
-
-### LangChain by [Chat with data](https://www.youtube.com/@chatwithdata)
-- [LangChain Beginner's Tutorial for `Typescript`/`Javascript`](https://youtu.be/bH722QgRlhQ)
-- [`GPT-4` Tutorial: How to Chat With Multiple `PDF` Files (~1000 pages of Tesla's 10-K Annual Reports)](https://youtu.be/Ix9WIZpArm0)
-- [`GPT-4` & LangChain Tutorial: How to Chat With A 56-Page `PDF` Document (w/`Pinecone`)](https://youtu.be/ih9PBGVVOO4)
-- [LangChain & `Supabase` Tutorial: How to Build a ChatGPT Chatbot For Your Website](https://youtu.be/R2FMzcsmQY8)
-- [LangChain Agents: Build Personal Assistants For Your Data (Q&A with Harrison Chase and Mayo Oshin)](https://youtu.be/gVkF8cwfBLI)
-
-
-### Codebase Analysis
-- [Codebase Analysis: Langchain Agents](https://carbonated-yacht-2c5.notion.site/Codebase-Analysis-Langchain-Agents-0b0587acd50647ca88aaae7cff5df1f2)
-
-
----------------------
-⛓ icon marks a new addition [last update 2023-09-21]

docs/docs/additional_resources/youtube.mdx

@@ -1,135 +0,0 @@
-# YouTube videos
-
-⛓ icon marks a new addition [last update 2023-09-21]
-
-### [Official LangChain YouTube channel](https://www.youtube.com/@LangChain)
-
-### Introduction to LangChain with Harrison Chase, creator of LangChain
-- [Building the Future with LLMs, `LangChain`, & `Pinecone`](https://youtu.be/nMniwlGyX-c) by [Pinecone](https://www.youtube.com/@pinecone-io)
-- [LangChain and Weaviate with Harrison Chase and Bob van Luijt - Weaviate Podcast #36](https://youtu.be/lhby7Ql7hbk) by [Weaviate • Vector Database](https://www.youtube.com/@Weaviate)
-- [LangChain Demo + Q&A with Harrison Chase](https://youtu.be/zaYTXQFR0_s?t=788) by [Full Stack Deep Learning](https://www.youtube.com/@FullStackDeepLearning)
-- [LangChain Agents: Build Personal Assistants For Your Data (Q&A with Harrison Chase and Mayo Oshin)](https://youtu.be/gVkF8cwfBLI) by [Chat with data](https://www.youtube.com/@chatwithdata)
-
-## Videos (sorted by views)
-
-- [Using `ChatGPT` with YOUR OWN Data. This is magical. (LangChain OpenAI API)](https://youtu.be/9AXP7tCI9PI) by [TechLead](https://www.youtube.com/@TechLead)
-- [First look - `ChatGPT` + `WolframAlpha` (`GPT-3.5` and Wolfram|Alpha via LangChain by James Weaver)](https://youtu.be/wYGbY811oMo) by [Dr Alan D. Thompson](https://www.youtube.com/@DrAlanDThompson) 
-- [LangChain explained - The hottest new Python framework](https://youtu.be/RoR4XJw8wIc) by [AssemblyAI](https://www.youtube.com/@AssemblyAI)
-- [Chatbot with INFINITE MEMORY using `OpenAI` & `Pinecone` - `GPT-3`, `Embeddings`, `ADA`, `Vector DB`, `Semantic`](https://youtu.be/2xNzB7xq8nk) by [David Shapiro ~ AI](https://www.youtube.com/@DavidShapiroAutomator)
-- [LangChain for LLMs is... basically just an Ansible playbook](https://youtu.be/X51N9C-OhlE) by [David Shapiro ~ AI](https://www.youtube.com/@DavidShapiroAutomator)
-- [Build your own LLM Apps with LangChain & `GPT-Index`](https://youtu.be/-75p09zFUJY) by [1littlecoder](https://www.youtube.com/@1littlecoder)
-- [`BabyAGI` - New System of Autonomous AI Agents with LangChain](https://youtu.be/lg3kJvf1kXo) by [1littlecoder](https://www.youtube.com/@1littlecoder)
-- [Run `BabyAGI` with Langchain Agents (with Python Code)](https://youtu.be/WosPGHPObx8) by [1littlecoder](https://www.youtube.com/@1littlecoder)
-- [How to Use Langchain With `Zapier` | Write and Send Email with GPT-3 | OpenAI API Tutorial](https://youtu.be/p9v2-xEa9A0) by [StarMorph AI](https://www.youtube.com/@starmorph)
-- [Use Your Locally Stored Files To Get Response From GPT - `OpenAI` | Langchain | Python](https://youtu.be/NC1Ni9KS-rk) by [Shweta Lodha](https://www.youtube.com/@shweta-lodha)
-- [`Langchain JS` | How to Use GPT-3, GPT-4 to Reference your own Data | `OpenAI Embeddings` Intro](https://youtu.be/veV2I-NEjaM) by [StarMorph AI](https://www.youtube.com/@starmorph)
-- [The easiest way to work with large language models | Learn LangChain in 10min](https://youtu.be/kmbS6FDQh7c) by [Sophia Yang](https://www.youtube.com/@SophiaYangDS)
-- [4 Autonomous AI Agents: “Westworld” simulation `BabyAGI`, `AutoGPT`, `Camel`, `LangChain`](https://youtu.be/yWbnH6inT_U) by [Sophia Yang](https://www.youtube.com/@SophiaYangDS)
-- [AI CAN SEARCH THE INTERNET? Langchain Agents + OpenAI ChatGPT](https://youtu.be/J-GL0htqda8) by [tylerwhatsgood](https://www.youtube.com/@tylerwhatsgood)
-- [Query Your Data with GPT-4 | Embeddings, Vector Databases | Langchain JS Knowledgebase](https://youtu.be/jRnUPUTkZmU) by [StarMorph AI](https://www.youtube.com/@starmorph)
-- [`Weaviate` + LangChain for LLM apps presented by Erika Cardenas](https://youtu.be/7AGj4Td5Lgw) by [`Weaviate` • Vector Database](https://www.youtube.com/@Weaviate)
-- [Langchain Overview — How to Use Langchain & `ChatGPT`](https://youtu.be/oYVYIq0lOtI) by [Python In Office](https://www.youtube.com/@pythoninoffice6568)
-- [Langchain Overview - How to Use Langchain & `ChatGPT`](https://youtu.be/oYVYIq0lOtI) by [Python In Office](https://www.youtube.com/@pythoninoffice6568)
-- [LangChain Tutorials](https://www.youtube.com/watch?v=FuqdVNB_8c0&list=PL9V0lbeJ69brU-ojMpU1Y7Ic58Tap0Cw6) by [Edrick](https://www.youtube.com/@edrickdch):
-  - [LangChain, Chroma DB, OpenAI Beginner Guide | ChatGPT with your PDF](https://youtu.be/FuqdVNB_8c0)
-  - [LangChain 101: The Complete Beginner's Guide](https://youtu.be/P3MAbZ2eMUI)
-- [Custom langchain Agent & Tools with memory. Turn any `Python function` into langchain tool with Gpt 3](https://youtu.be/NIG8lXk0ULg) by [echohive](https://www.youtube.com/@echohive)
-- [Building AI LLM Apps with LangChain (and more?) - LIVE STREAM](https://www.youtube.com/live/M-2Cj_2fzWI?feature=share) by [Nicholas Renotte](https://www.youtube.com/@NicholasRenotte)
-- [`ChatGPT` with any `YouTube` video using langchain and `chromadb`](https://youtu.be/TQZfB2bzVwU) by [echohive](https://www.youtube.com/@echohive)
-- [How to Talk to a `PDF` using LangChain and `ChatGPT`](https://youtu.be/v2i1YDtrIwk) by [Automata Learning Lab](https://www.youtube.com/@automatalearninglab)
-- [Langchain Document Loaders Part 1: Unstructured Files](https://youtu.be/O5C0wfsen98) by [Merk](https://www.youtube.com/@merksworld) 
-- [LangChain - Prompt Templates (what all the best prompt engineers use)](https://youtu.be/1aRu8b0XNOQ) by [Nick Daigler](https://www.youtube.com/@nick_daigs)
-- [LangChain. Crear aplicaciones Python impulsadas por GPT](https://youtu.be/DkW_rDndts8) by [Jesús Conde](https://www.youtube.com/@0utKast)
-- [Easiest Way to Use GPT In Your Products | LangChain Basics Tutorial](https://youtu.be/fLy0VenZyGc) by [Rachel Woods](https://www.youtube.com/@therachelwoods)
-- [`BabyAGI` + `GPT-4` Langchain Agent with Internet Access](https://youtu.be/wx1z_hs5P6E) by [tylerwhatsgood](https://www.youtube.com/@tylerwhatsgood)
-- [Learning LLM Agents. How does it actually work? LangChain, AutoGPT & OpenAI](https://youtu.be/mb_YAABSplk) by [Arnoldas Kemeklis](https://www.youtube.com/@processusAI)
-- [Get Started with LangChain in `Node.js`](https://youtu.be/Wxx1KUWJFv4) by [Developers Digest](https://www.youtube.com/@DevelopersDigest)
-- [LangChain + `OpenAI` tutorial: Building a Q&A system w/ own text data](https://youtu.be/DYOU_Z0hAwo) by [Samuel Chan](https://www.youtube.com/@SamuelChan)
-- [Langchain + `Zapier` Agent](https://youtu.be/yribLAb-pxA) by [Merk](https://www.youtube.com/@merksworld)
-- [Connecting the Internet with `ChatGPT` (LLMs) using Langchain And Answers Your Questions](https://youtu.be/9Y0TBC63yZg) by [Kamalraj M M](https://www.youtube.com/@insightbuilder)
-- [Build More Powerful LLM Applications for Business’s with LangChain (Beginners Guide)](https://youtu.be/sp3-WLKEcBg) by[ No Code Blackbox](https://www.youtube.com/@nocodeblackbox)
-- [LangFlow LLM Agent Demo for 🦜🔗LangChain](https://youtu.be/zJxDHaWt-6o) by [Cobus Greyling](https://www.youtube.com/@CobusGreylingZA)
-- [Chatbot Factory: Streamline Python Chatbot Creation with LLMs and Langchain](https://youtu.be/eYer3uzrcuM) by [Finxter](https://www.youtube.com/@CobusGreylingZA)
-- [LangChain Tutorial - ChatGPT mit eigenen Daten](https://youtu.be/0XDLyY90E2c) by [Coding Crashkurse](https://www.youtube.com/@codingcrashkurse6429)
-- [Chat with a `CSV` | LangChain Agents Tutorial (Beginners)](https://youtu.be/tjeti5vXWOU) by [GoDataProf](https://www.youtube.com/@godataprof)
-- [Introdução ao Langchain - #Cortes - Live DataHackers](https://youtu.be/fw8y5VRei5Y) by [Prof. João Gabriel Lima](https://www.youtube.com/@profjoaogabriellima)
-- [LangChain: Level up `ChatGPT` !? | LangChain Tutorial Part 1](https://youtu.be/vxUGx8aZpDE) by [Code Affinity](https://www.youtube.com/@codeaffinitydev)
-- [KI schreibt krasses Youtube Skript 😲😳 | LangChain Tutorial Deutsch](https://youtu.be/QpTiXyK1jus) by [SimpleKI](https://www.youtube.com/@simpleki)
-- [Chat with Audio: Langchain, `Chroma DB`, OpenAI, and `Assembly AI`](https://youtu.be/Kjy7cx1r75g) by [AI Anytime](https://www.youtube.com/@AIAnytime)
-- [QA over documents with Auto vector index selection with Langchain router chains](https://youtu.be/9G05qybShv8) by [echohive](https://www.youtube.com/@echohive)
-- [Build your own custom LLM application with `Bubble.io` & Langchain (No Code & Beginner friendly)](https://youtu.be/O7NhQGu1m6c) by [No Code Blackbox](https://www.youtube.com/@nocodeblackbox)
-- [Simple App to Question Your Docs: Leveraging `Streamlit`, `Hugging Face Spaces`, LangChain, and `Claude`!](https://youtu.be/X4YbNECRr7o) by [Chris Alexiuk](https://www.youtube.com/@chrisalexiuk)
-- [LANGCHAIN AI- `ConstitutionalChainAI` + Databutton AI ASSISTANT Web App](https://youtu.be/5zIU6_rdJCU) by [Avra](https://www.youtube.com/@Avra_b)
-- [LANGCHAIN AI AUTONOMOUS AGENT WEB APP - 👶 `BABY AGI` 🤖 with EMAIL AUTOMATION using `DATABUTTON`](https://youtu.be/cvAwOGfeHgw) by [Avra](https://www.youtube.com/@Avra_b)
-- [The Future of Data Analysis: Using A.I. Models in Data Analysis (LangChain)](https://youtu.be/v_LIcVyg5dk) by [Absent Data](https://www.youtube.com/@absentdata)
-- [Memory in LangChain | Deep dive (python)](https://youtu.be/70lqvTFh_Yg) by [Eden Marco](https://www.youtube.com/@EdenMarco)
-- [9 LangChain UseCases | Beginner's Guide | 2023](https://youtu.be/zS8_qosHNMw) by [Data Science Basics](https://www.youtube.com/@datasciencebasics)
-- [Use Large Language Models in Jupyter Notebook | LangChain | Agents & Indexes](https://youtu.be/JSe11L1a_QQ) by [Abhinaw Tiwari](https://www.youtube.com/@AbhinawTiwariAT)
-- [How to Talk to Your Langchain Agent | `11 Labs` + `Whisper`](https://youtu.be/N4k459Zw2PU) by [VRSEN](https://www.youtube.com/@vrsen)
-- [LangChain Deep Dive: 5 FUN AI App Ideas To Build Quickly and Easily](https://youtu.be/mPYEPzLkeks) by [James NoCode](https://www.youtube.com/@jamesnocode)
-- [LangChain 101: Models](https://youtu.be/T6c_XsyaNSQ) by [Mckay Wrigley](https://www.youtube.com/@realmckaywrigley)
-- [LangChain with JavaScript Tutorial #1 | Setup & Using LLMs](https://youtu.be/W3AoeMrg27o) by [Leon van Zyl](https://www.youtube.com/@leonvanzyl)
-- [LangChain Overview & Tutorial for Beginners: Build Powerful AI Apps Quickly & Easily (ZERO CODE)](https://youtu.be/iI84yym473Q) by [James NoCode](https://www.youtube.com/@jamesnocode)
-- [LangChain In Action: Real-World Use Case With Step-by-Step Tutorial](https://youtu.be/UO699Szp82M) by [Rabbitmetrics](https://www.youtube.com/@rabbitmetrics)
-- [Summarizing and Querying Multiple Papers with LangChain](https://youtu.be/p_MQRWH5Y6k) by [Automata Learning Lab](https://www.youtube.com/@automatalearninglab)
-- [Using Langchain (and `Replit`) through `Tana`, ask `Google`/`Wikipedia`/`Wolfram Alpha` to fill out a table](https://youtu.be/Webau9lEzoI) by [Stian Håklev](https://www.youtube.com/@StianHaklev)
-- [Langchain PDF App (GUI) | Create a ChatGPT For Your `PDF` in Python](https://youtu.be/wUAUdEw5oxM) by [Alejandro AO - Software & Ai](https://www.youtube.com/@alejandro_ao)
-- [Auto-GPT with LangChain 🔥 | Create Your Own Personal AI Assistant](https://youtu.be/imDfPmMKEjM) by [Data Science Basics](https://www.youtube.com/@datasciencebasics)
-- [Create Your OWN Slack AI Assistant with Python & LangChain](https://youtu.be/3jFXRNn2Bu8) by [Dave Ebbelaar](https://www.youtube.com/@daveebbelaar)
-- [How to Create LOCAL Chatbots with GPT4All and LangChain [Full Guide]](https://youtu.be/4p1Fojur8Zw) by [Liam Ottley](https://www.youtube.com/@LiamOttley)
-- [Build a `Multilingual PDF` Search App with LangChain, `Cohere` and `Bubble`](https://youtu.be/hOrtuumOrv8) by [Menlo Park Lab](https://www.youtube.com/@menloparklab)
-- [Building a LangChain Agent (code-free!) Using `Bubble` and `Flowise`](https://youtu.be/jDJIIVWTZDE) by [Menlo Park Lab](https://www.youtube.com/@menloparklab)
-- [Build a LangChain-based Semantic PDF Search App with No-Code Tools Bubble and Flowise](https://youtu.be/s33v5cIeqA4) by [Menlo Park Lab](https://www.youtube.com/@menloparklab)
-- [LangChain Memory Tutorial | Building a ChatGPT Clone in Python](https://youtu.be/Cwq91cj2Pnc) by [Alejandro AO - Software & Ai](https://www.youtube.com/@alejandro_ao)
-- [ChatGPT For Your DATA | Chat with Multiple Documents Using LangChain](https://youtu.be/TeDgIDqQmzs) by [Data Science Basics](https://www.youtube.com/@datasciencebasics)
-- [`Llama Index`: Chat with Documentation using URL Loader](https://youtu.be/XJRoDEctAwA) by [Merk](https://www.youtube.com/@merksworld)
-- [Using OpenAI, LangChain, and `Gradio` to Build Custom GenAI Applications](https://youtu.be/1MsmqMg3yUc) by [David Hundley](https://www.youtube.com/@dkhundley)
-- [LangChain, Chroma DB, OpenAI Beginner Guide | ChatGPT with your PDF](https://youtu.be/FuqdVNB_8c0)
-- [Build AI chatbot with custom knowledge base using OpenAI API and GPT Index](https://youtu.be/vDZAZuaXf48) by [Irina Nik](https://www.youtube.com/@irina_nik)
-- [Build Your Own Auto-GPT Apps with LangChain (Python Tutorial)](https://youtu.be/NYSWn1ipbgg) by [Dave Ebbelaar](https://www.youtube.com/@daveebbelaar)
-- [Chat with Multiple `PDFs` | LangChain App Tutorial in Python (Free LLMs and Embeddings)](https://youtu.be/dXxQ0LR-3Hg) by [Alejandro AO - Software & Ai](https://www.youtube.com/@alejandro_ao)
-- [Chat with a `CSV` | `LangChain Agents` Tutorial (Beginners)](https://youtu.be/tjeti5vXWOU) by [Alejandro AO - Software & Ai](https://www.youtube.com/@alejandro_ao)
-- [Create Your Own ChatGPT with `PDF` Data in 5 Minutes (LangChain Tutorial)](https://youtu.be/au2WVVGUvc8) by [Liam Ottley](https://www.youtube.com/@LiamOttley)
-- [Build a Custom Chatbot with OpenAI: `GPT-Index` & LangChain | Step-by-Step Tutorial](https://youtu.be/FIDv6nc4CgU) by [Fabrikod](https://www.youtube.com/@fabrikod)
-- [`Flowise` is an open-source no-code UI visual tool to build 🦜🔗LangChain applications](https://youtu.be/CovAPtQPU0k) by [Cobus Greyling](https://www.youtube.com/@CobusGreylingZA)
-- [LangChain & GPT 4 For Data Analysis: The `Pandas` Dataframe Agent](https://youtu.be/rFQ5Kmkd4jc) by [Rabbitmetrics](https://www.youtube.com/@rabbitmetrics)
-- [`GirlfriendGPT` - AI girlfriend with LangChain](https://youtu.be/LiN3D1QZGQw) by [Toolfinder AI](https://www.youtube.com/@toolfinderai)
-- [How to build with Langchain 10x easier | ⛓️ LangFlow & `Flowise`](https://youtu.be/Ya1oGL7ZTvU) by [AI Jason](https://www.youtube.com/@AIJasonZ)
-- [Getting Started With LangChain In 20 Minutes- Build Celebrity Search Application](https://youtu.be/_FpT1cwcSLg) by [Krish Naik](https://www.youtube.com/@krishnaik06)
-- ⛓ [Vector Embeddings Tutorial – Code Your Own AI Assistant with `GPT-4 API` + LangChain + NLP](https://youtu.be/yfHHvmaMkcA?si=5uJhxoh2tvdnOXok) by [FreeCodeCamp.org](https://www.youtube.com/@freecodecamp)
-- ⛓ [Fully LOCAL `Llama 2` Q&A with LangChain](https://youtu.be/wgYctKFnQ74?si=UX1F3W-B3MqF4-K-) by [1littlecoder](https://www.youtube.com/@1littlecoder)
-- ⛓ [Fully LOCAL `Llama 2` Langchain on CPU](https://youtu.be/yhECvKMu8kM?si=IvjxwlA1c09VwHZ4) by [1littlecoder](https://www.youtube.com/@1littlecoder)
-- ⛓ [Build LangChain Audio Apps with Python in 5 Minutes](https://youtu.be/7w7ysaDz2W4?si=BvdMiyHhormr2-vr) by [AssemblyAI](https://www.youtube.com/@AssemblyAI)
-- ⛓ [`Voiceflow` & `Flowise`: Want to Beat Competition? New Tutorial with Real AI Chatbot](https://youtu.be/EZKkmeFwag0?si=-4dETYDHEstiK_bb) by [AI SIMP](https://www.youtube.com/@aisimp)
-- ⛓ [THIS Is How You Build Production-Ready AI Apps (`LangSmith` Tutorial)](https://youtu.be/tFXm5ijih98?si=lfiqpyaivxHFyI94) by [Dave Ebbelaar](https://www.youtube.com/@daveebbelaar)
-- ⛓ [Build POWERFUL LLM Bots EASILY with Your Own Data - `Embedchain` - Langchain 2.0? (Tutorial)](https://youtu.be/jE24Y_GasE8?si=0yEDZt3BK5Q-LIuF) by [WorldofAI](https://www.youtube.com/@intheworldofai)
-- ⛓ [`Code Llama` powered Gradio App for Coding: Runs on CPU](https://youtu.be/AJOhV6Ryy5o?si=ouuQT6IghYlc1NEJ) by [AI Anytime](https://www.youtube.com/@AIAnytime)
-- ⛓ [LangChain Complete Course in One Video | Develop LangChain (AI) Based Solutions for Your Business](https://youtu.be/j9mQd-MyIg8?si=_wlNT3nP2LpDKztZ) by [UBprogrammer](https://www.youtube.com/@UBprogrammer)
-- ⛓ [How to Run `LLaMA` Locally on CPU or GPU | Python & Langchain & CTransformers Guide](https://youtu.be/SvjWDX2NqiM?si=DxFml8XeGhiLTzLV) by [Code With Prince](https://www.youtube.com/@CodeWithPrince)
-- ⛓ [PyData Heidelberg #11 - TimeSeries Forecasting & LLM Langchain](https://www.youtube.com/live/Glbwb5Hxu18?si=PIEY8Raq_C9PCHuW) by [PyData](https://www.youtube.com/@PyDataTV)
-- ⛓ [Prompt Engineering in Web Development | Using LangChain and Templates with OpenAI](https://youtu.be/pK6WzlTOlYw?si=fkcDQsBG2h-DM8uQ) by [Akamai Developer
-](https://www.youtube.com/@AkamaiDeveloper)
-- ⛓ [Retrieval-Augmented Generation (RAG) using LangChain and `Pinecone` - The RAG Special Episode](https://youtu.be/J_tCD_J6w3s?si=60Mnr5VD9UED9bGG) by [Generative AI and Data Science On AWS](https://www.youtube.com/@GenerativeAIDataScienceOnAWS)
-- ⛓ [`LLAMA2 70b-chat` Multiple Documents Chatbot with Langchain & Streamlit |All OPEN SOURCE|Replicate API](https://youtu.be/vhghB81vViM?si=dszzJnArMeac7lyc) by [DataInsightEdge](https://www.youtube.com/@DataInsightEdge01)
-- ⛓ [Chatting with 44K Fashion Products: LangChain Opportunities and Pitfalls](https://youtu.be/Zudgske0F_s?si=8HSshHoEhh0PemJA) by [Rabbitmetrics](https://www.youtube.com/@rabbitmetrics)
-- ⛓ [Structured Data Extraction from `ChatGPT` with LangChain](https://youtu.be/q1lYg8JISpQ?si=0HctzOHYZvq62sve) by [MG](https://www.youtube.com/@MG_cafe)
-- ⛓ [Chat with Multiple PDFs using `Llama 2`, `Pinecone` and LangChain (Free LLMs and Embeddings)](https://youtu.be/TcJ_tVSGS4g?si=FZYnMDJyoFfL3Z2i) by [Muhammad Moin](https://www.youtube.com/@muhammadmoinfaisal)
-- ⛓ [Integrate Audio into `LangChain.js` apps in 5 Minutes](https://youtu.be/hNpUSaYZIzs?si=Gb9h7W9A8lzfvFKi) by [AssemblyAI](https://www.youtube.com/@AssemblyAI)
-- ⛓ [`ChatGPT` for your data with Local LLM](https://youtu.be/bWrjpwhHEMU?si=uM6ZZ18z9og4M90u) by [Jacob Jedryszek](https://www.youtube.com/@jj09)
-- ⛓ [Training `Chatgpt` with your personal data using langchain step by step in detail](https://youtu.be/j3xOMde2v9Y?si=179HsiMU-hEPuSs4) by [NextGen Machines](https://www.youtube.com/@MayankGupta-kb5yc)
-- ⛓ [Use ANY language in `LangSmith` with REST](https://youtu.be/7BL0GEdMmgY?si=iXfOEdBLqXF6hqRM) by [Nerding I/O](https://www.youtube.com/@nerding_io)
-- ⛓ [How to Leverage the Full Potential of LLMs for Your Business with Langchain - Leon Ruddat](https://youtu.be/vZmoEa7oWMg?si=ZhMmydq7RtkZd56Q) by [PyData](https://www.youtube.com/@PyDataTV)
-- ⛓ [`ChatCSV` App: Chat with CSV files using LangChain and `Llama 2`](https://youtu.be/PvsMg6jFs8E?si=Qzg5u5gijxj933Ya) by [Muhammad Moin](https://www.youtube.com/@muhammadmoinfaisal)
-
-
-### [Prompt Engineering and LangChain](https://www.youtube.com/watch?v=muXbPpG_ys4&list=PLEJK-H61Xlwzm5FYLDdKt_6yibO33zoMW) by [Venelin Valkov](https://www.youtube.com/@venelin_valkov)
-- [Getting Started with LangChain: Load Custom Data, Run OpenAI Models, Embeddings and `ChatGPT`](https://www.youtube.com/watch?v=muXbPpG_ys4)
-- [Loaders, Indexes & Vectorstores in LangChain: Question Answering on `PDF` files with `ChatGPT`](https://www.youtube.com/watch?v=FQnvfR8Dmr0)
-- [LangChain Models: `ChatGPT`, `Flan Alpaca`, `OpenAI Embeddings`, Prompt Templates & Streaming](https://www.youtube.com/watch?v=zy6LiK5F5-s)
-- [LangChain Chains: Use `ChatGPT` to Build Conversational Agents, Summaries and Q&A on Text With LLMs](https://www.youtube.com/watch?v=h1tJZQPcimM)
-- [Analyze Custom CSV Data with `GPT-4` using Langchain](https://www.youtube.com/watch?v=Ew3sGdX8at4)
-- [Build ChatGPT Chatbots with LangChain Memory: Understanding and Implementing Memory in Conversations](https://youtu.be/CyuUlf54wTs)
-
-
----------------------
-⛓ icon marks a new addition [last update 2023-09-21]

docs/docs/community.md

@@ -1,53 +0,0 @@
-# Community navigator
-
-Hi! Thanks for being here. We’re lucky to have a community of so many passionate developers building with LangChain–we have so much to teach and learn from each other. Community members contribute code, host meetups, write blog posts, amplify each other’s work, become each other's customers and collaborators, and so much more.
-
-Whether you’re new to LangChain, looking to go deeper, or just want to get more exposure to the world of building with LLMs, this page can point you in the right direction. 
-
-- **🦜 Contribute to LangChain**
-
-- **🌍 Meetups, Events, and Hackathons**
-
-- **📣 Help Us Amplify Your Work**
-
-- **💬 Stay in the loop**
-
-
-# 🦜 Contribute to LangChain
-
-LangChain is the product of over 5,000+ contributions by 1,500+ contributors, and there is ******still****** so much to do together. Here are some ways to get involved:
-
-- **[Open a pull request](https://github.com/langchain-ai/langchain/issues):** We’d appreciate all forms of contributions–new features, infrastructure improvements, better documentation, bug fixes, etc. If you have an improvement or an idea, we’d love to work on it with you.
-- **[Read our contributor guidelines:](https://github.com/langchain-ai/langchain/blob/bbd22b9b761389a5e40fc45b0570e1830aabb707/.github/CONTRIBUTING.md)** We ask contributors to follow a ["fork and pull request"](https://docs.github.com/en/get-started/quickstart/contributing-to-projects) workflow, run a few local checks for formatting, linting, and testing before submitting, and follow certain documentation and testing conventions.
-    - **First time contributor?** [Try one of these PRs with the “good first issue” tag](https://github.com/langchain-ai/langchain/contribute).
-- **Become an expert:** Our experts help the community by answering product questions in Discord. If that’s a role you’d like to play, we’d be so grateful! (And we have some special experts-only goodies/perks we can tell you more about). Send us an email to introduce yourself at hello@langchain.dev and we’ll take it from there!
-- **Integrate with LangChain:** If your product integrates with LangChain–or aspires to–we want to help make sure the experience is as smooth as possible for you and end users. Send us an email at hello@langchain.dev and tell us what you’re working on.
-    - **Become an Integration Maintainer:** Partner with our team to ensure your integration stays up-to-date and talk directly with users (and answer their inquiries) in our Discord. Introduce yourself at hello@langchain.dev if you’d like to explore this role.
-
-
-# 🌍 Meetups, Events, and Hackathons
-
-One of our favorite things about working in AI is how much enthusiasm there is for building together. We want to help make that as easy and impactful for you as possible! 
-- **Find a meetup, hackathon, or webinar:** You can find the one for you on our [global events calendar](https://mirror-feeling-d80.notion.site/0bc81da76a184297b86ca8fc782ee9a3?v=0d80342540df465396546976a50cfb3f).  
-    - **Submit an event to our calendar:** Email us at events@langchain.dev with a link to your event page! We can also help you spread the word with our local communities.
-- **Host a meetup:** If you want to bring a group of builders together, we want to help! We can publicize your event on our event calendar/Twitter, share it with our local communities in Discord, send swag, or potentially hook you up with a sponsor. Email us at events@langchain.dev to tell us about your event!
-- **Become a meetup sponsor:** We often hear from groups of builders that want to get together, but are blocked or limited on some dimension (space to host, budget for snacks, prizes to distribute, etc.). If you’d like to help, send us an email to events@langchain.dev we can share more about how it works!
-- **Speak at an event:** Meetup hosts are always looking for great speakers, presenters, and panelists. If you’d like to do that at an event, send us an email to hello@langchain.dev with more information about yourself, what you want to talk about, and what city you’re based in and we’ll try to match you with an upcoming event!
-- **Tell us about your LLM community:** If you host or participate in a community that would welcome support from LangChain and/or our team, send us an email at hello@langchain.dev and let us know how we can help.
-
-# 📣 Help Us Amplify Your Work
-
-If you’re working on something you’re proud of, and think the LangChain community would benefit from knowing about it, we want to help you show it off.
-
-- **Post about your work and mention us:** We love hanging out on Twitter to see what people in the space are talking about and working on. If you tag [@langchainai](https://twitter.com/LangChainAI), we’ll almost certainly see it and can show you some love.
-- **Publish something on our blog:** If you’re writing about your experience building with LangChain, we’d love to post (or crosspost) it on our blog! E-mail hello@langchain.dev with a draft of your post! Or even an idea for something you want to write about.
-- **Get your product onto our [integrations hub](https://integrations.langchain.com/):** Many developers take advantage of our seamless integrations with other products, and come to our integrations hub to find out who those are. If you want to get your product up there, tell us about it (and how it works with LangChain) at hello@langchain.dev.
-
-# ☀️ Stay in the loop
-
-Here’s where our team hangs out, talks shop, spotlights cool work, and shares what we’re up to. We’d love to see you there too.
-
-- **[Twitter](https://twitter.com/LangChainAI):** We post about what we’re working on and what cool things we’re seeing in the space. If you tag @langchainai in your post, we’ll almost certainly see it, and can show you some love!
-- **[Discord](https://discord.gg/6adMQxSpJS):** connect with over 30,000 developers who are building with LangChain.
-- **[GitHub](https://github.com/langchain-ai/langchain):** Open pull requests, contribute to a discussion, and/or contribute
-- **[Subscribe to our bi-weekly Release Notes](https://6w1pwbss0py.typeform.com/to/KjZB1auB):** a twice/month email roundup of the coolest things going on in our orbit

docs/docs/expression_language/cookbook/agent.ipynb

@@ -1,203 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "e89f490d",
-   "metadata": {},
-   "source": [
-    "# Agents\n",
-    "\n",
-    "You can pass a Runnable into an agent."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "af4381de",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.agents import XMLAgent, tool, AgentExecutor\n",
-    "from langchain.chat_models import ChatAnthropic"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "24cc8134",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "model = ChatAnthropic(model=\"claude-2\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "67c0b0e4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "@tool\n",
-    "def search(query: str) -> str:\n",
-    "    \"\"\"Search things about current events.\"\"\"\n",
-    "    return \"32 degrees\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "7203b101",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "tool_list = [search]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "b68e756d",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Get prompt to use\n",
-    "prompt = XMLAgent.get_default_prompt()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "61ab3e9a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Logic for going from intermediate steps to a string to pass into model\n",
-    "# This is pretty tied to the prompt\n",
-    "def convert_intermediate_steps(intermediate_steps):\n",
-    "    log = \"\"\n",
-    "    for action, observation in intermediate_steps:\n",
-    "        log += (\n",
-    "            f\"<tool>{action.tool}</tool><tool_input>{action.tool_input}\"\n",
-    "            f\"</tool_input><observation>{observation}</observation>\"\n",
-    "        )\n",
-    "    return log\n",
-    "\n",
-    "\n",
-    "# Logic for converting tools to string to go in prompt\n",
-    "def convert_tools(tools):\n",
-    "    return \"\\n\".join([f\"{tool.name}: {tool.description}\" for tool in tools])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "260f5988",
-   "metadata": {},
-   "source": [
-    "Building an agent from a runnable usually involves a few things:\n",
-    "\n",
-    "1. Data processing for the intermediate steps. These need to represented in a way that the language model can recognize them. This should be pretty tightly coupled to the instructions in the prompt\n",
-    "\n",
-    "2. The prompt itself\n",
-    "\n",
-    "3. The model, complete with stop tokens if needed\n",
-    "\n",
-    "4. The output parser - should be in sync with how the prompt specifies things to be formatted."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "e92f1d6f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "agent = (\n",
-    "    {\n",
-    "        \"question\": lambda x: x[\"question\"],\n",
-    "        \"intermediate_steps\": lambda x: convert_intermediate_steps(x[\"intermediate_steps\"])\n",
-    "    }\n",
-    "    | prompt.partial(tools=convert_tools(tool_list))\n",
-    "    | model.bind(stop=[\"</tool_input>\", \"</final_answer>\"])\n",
-    "    | XMLAgent.get_default_output_parser()\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "6ce6ec7a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "agent_executor = AgentExecutor(agent=agent, tools=tool_list, verbose=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "fb5cb2e3",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m <tool>search</tool>\n",
-      "<tool_input>weather in new york\u001b[0m\u001b[36;1m\u001b[1;3m32 degrees\u001b[0m\u001b[32;1m\u001b[1;3m\n",
-      "\n",
-      "<final_answer>The weather in New York is 32 degrees\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "{'question': 'whats the weather in New york?',\n",
-       " 'output': 'The weather in New York is 32 degrees'}"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "agent_executor.invoke({\"question\": \"whats the weather in New york?\"})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "bce86dd8",
-   "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": "3.10.1"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/docs/expression_language/cookbook/code_writing.ipynb

@@ -1,119 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "f09fd305",
-   "metadata": {},
-   "source": [
-    "# Code writing\n",
-    "\n",
-    "Example of how to use LCEL to write Python code."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "bd7c259a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.prompts import ChatPromptTemplate, SystemMessagePromptTemplate, HumanMessagePromptTemplate\n",
-    "from langchain.schema.output_parser import StrOutputParser\n",
-    "from langchain.utilities import PythonREPL"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "73795d2d",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "template = \"\"\"Write some python code to solve the user's problem. \n",
-    "\n",
-    "Return only python code in Markdown format, e.g.:\n",
-    "\n",
-    "```python\n",
-    "....\n",
-    "```\"\"\"\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [(\"system\", template), (\"human\", \"{input}\")]\n",
-    ")\n",
-    "\n",
-    "model = ChatOpenAI()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "42859e8a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def _sanitize_output(text: str):\n",
-    "    _, after = text.split(\"```python\")\n",
-    "    return after.split(\"```\")[0]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "5ded1a86",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = prompt | model | StrOutputParser() | _sanitize_output | PythonREPL().run"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "208c2b75",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Python REPL can execute arbitrary code. Use with caution.\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'4\\n'"
-      ]
-     },
-     "execution_count": 15,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke({\"input\": \"whats 2 plus 2\"})"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.9.1"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/docs/expression_language/cookbook/index.mdx

@@ -1,11 +0,0 @@
----
-sidebar_position: 2
----
-
-# Cookbook
-
-import DocCardList from "@theme/DocCardList";
-
-Example code for accomplishing common tasks with the LangChain Expression Language (LCEL). These examples show how to compose different Runnable (the core LCEL interface) components to achieve various tasks. If you're just getting acquainted with LCEL, the [Prompt + LLM](/docs/expression_language/cookbook/prompt_llm_parser) page is a good place to start.
-
-<DocCardList />

docs/docs/expression_language/cookbook/memory.ipynb

@@ -1,177 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "5062941a",
-   "metadata": {},
-   "source": [
-    "# Adding memory\n",
-    "\n",
-    "This shows how to add memory to an arbitrary chain. Right now, you can use the memory classes but need to hook it up manually"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "7998efd8",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from operator import itemgetter\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.memory import ConversationBufferMemory\n",
-    "from langchain.schema.runnable import RunnablePassthrough, RunnableLambda\n",
-    "from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
-    "\n",
-    "model = ChatOpenAI()\n",
-    "prompt = ChatPromptTemplate.from_messages([\n",
-    "    (\"system\", \"You are a helpful chatbot\"),\n",
-    "    MessagesPlaceholder(variable_name=\"history\"),\n",
-    "    (\"human\", \"{input}\")\n",
-    "])\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "fa0087f3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "memory = ConversationBufferMemory(return_messages=True)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "06b531ae",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'history': []}"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "memory.load_memory_variables({})\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "d9437af6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = RunnablePassthrough.assign(\n",
-    "    memory=RunnableLambda(memory.load_memory_variables) | itemgetter(\"history\")\n",
-    ") | prompt | model\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "bed1e260",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='Hello Bob! How can I assist you today?', additional_kwargs={}, example=False)"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "inputs = {\"input\": \"hi im bob\"}\n",
-    "response = chain.invoke(inputs)\n",
-    "response\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "890475b4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "memory.save_context(inputs, {\"output\": response.content})\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "e8fcb77f",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'history': [HumanMessage(content='hi im bob', additional_kwargs={}, example=False),\n",
-       "  AIMessage(content='Hello Bob! How can I assist you today?', additional_kwargs={}, example=False)]}"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "memory.load_memory_variables({})\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "d837d5c3",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='Your name is Bob.', additional_kwargs={}, example=False)"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "inputs = {\"input\": \"whats my name\"}\n",
-    "response = chain.invoke(inputs)\n",
-    "response\n"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.9.1"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/docs/expression_language/cookbook/moderation.ipynb

@@ -1,133 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "4927a727-b4c8-453c-8c83-bd87b4fcac14",
-   "metadata": {},
-   "source": [
-    "# Adding moderation\n",
-    "\n",
-    "This shows how to add in moderation (or other safeguards) around your LLM application."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 20,
-   "id": "4f5f6449-940a-4f5c-97c0-39b71c3e2a68",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chains import OpenAIModerationChain\n",
-    "from langchain.llms import OpenAI\n",
-    "from langchain.prompts import ChatPromptTemplate"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "fcb8312b-7e7a-424f-a3ec-76738c9a9d21",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "moderate = OpenAIModerationChain()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 21,
-   "id": "b24b9148-f6b0-4091-8ea8-d3fb281bd950",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "model = OpenAI()\n",
-    "prompt = ChatPromptTemplate.from_messages([\n",
-    "    (\"system\", \"repeat after me: {input}\")\n",
-    "])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "id": "1c8ed87c-9ca6-4559-bf60-d40e94a0af08",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = prompt | model"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 23,
-   "id": "5256b9bd-381a-42b0-bfa8-7e6d18f853cb",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'\\n\\nYou are stupid.'"
-      ]
-     },
-     "execution_count": 23,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke({\"input\": \"you are stupid\"})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 24,
-   "id": "fe6e3b33-dc9a-49d5-b194-ba750c58a628",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "moderated_chain = chain | moderate"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 25,
-   "id": "d8ba0cbd-c739-4d23-be9f-6ae092bd5ffb",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'input': '\\n\\nYou are stupid',\n",
-       " 'output': \"Text was found that violates OpenAI's content policy.\"}"
-      ]
-     },
-     "execution_count": 25,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "moderated_chain.invoke({\"input\": \"you are stupid\"})"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.9.1"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/docs/expression_language/cookbook/multiple_chains.ipynb

@@ -1,240 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "raw",
-   "id": "877102d1-02ea-4fa3-8ec7-a08e242b95b3",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "sidebar_position: 2\n",
-    "title: Multiple chains\n",
-    "---"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0f2bf8d3",
-   "metadata": {},
-   "source": [
-    "Runnables can easily be used to string together multiple Chains"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "d65d4e9e",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'El país donde se encuentra la ciudad de Honolulu, donde nació Barack Obama, el 44º Presidente de los Estados Unidos, es Estados Unidos. Honolulu se encuentra en la isla de Oahu, en el estado de Hawái.'"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from operator import itemgetter\n",
-    "\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.prompts import ChatPromptTemplate\n",
-    "from langchain.schema import StrOutputParser\n",
-    "\n",
-    "prompt1 = ChatPromptTemplate.from_template(\"what is the city {person} is from?\")\n",
-    "prompt2 = ChatPromptTemplate.from_template(\"what country is the city {city} in? respond in {language}\")\n",
-    "\n",
-    "model = ChatOpenAI()\n",
-    "\n",
-    "chain1 = prompt1 | model | StrOutputParser()\n",
-    "\n",
-    "chain2 = {\"city\": chain1, \"language\": itemgetter(\"language\")} | prompt2 | model | StrOutputParser()\n",
-    "\n",
-    "chain2.invoke({\"person\": \"obama\", \"language\": \"spanish\"})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "878f8176",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.schema.runnable import RunnableMap, RunnablePassthrough\n",
-    "\n",
-    "prompt1 = ChatPromptTemplate.from_template(\"generate a {attribute} color. Return the name of the color and nothing else:\")\n",
-    "prompt2 = ChatPromptTemplate.from_template(\"what is a fruit of color: {color}. Return the name of the fruit and nothing else:\")\n",
-    "prompt3 = ChatPromptTemplate.from_template(\"what is a country with a flag that has the color: {color}. Return the name of the country and nothing else:\")\n",
-    "prompt4 = ChatPromptTemplate.from_template(\"What is the color of {fruit} and the flag of {country}?\")\n",
-    "\n",
-    "model_parser = model | StrOutputParser()\n",
-    "\n",
-    "color_generator = {\"attribute\": RunnablePassthrough()} | prompt1 | {\"color\": model_parser}\n",
-    "color_to_fruit = prompt2 | model_parser\n",
-    "color_to_country = prompt3 | model_parser\n",
-    "question_generator = color_generator | {\"fruit\": color_to_fruit, \"country\": color_to_country} | prompt4"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "d621a870",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "ChatPromptValue(messages=[HumanMessage(content='What is the color of strawberry and the flag of China?', additional_kwargs={}, example=False)])"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "question_generator.invoke(\"warm\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "b4a9812b-bead-4fd9-ae27-0b8be57e5dc1",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='The color of an apple is typically red or green. The flag of China is predominantly red with a large yellow star in the upper left corner and four smaller yellow stars surrounding it.', additional_kwargs={}, example=False)"
-      ]
-     },
-     "execution_count": 10,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "prompt = question_generator.invoke(\"warm\")\n",
-    "model.invoke(prompt)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "6d75a313-f1c8-4e94-9a17-24e0bf4a2bdc",
-   "metadata": {},
-   "source": [
-    "### Branching and Merging\n",
-    "\n",
-    "You may want the output of one component to be processed by 2 or more other components. [RunnableMaps](https://api.python.langchain.com/en/latest/schema/langchain.schema.runnable.base.RunnableMap.html) let you split or fork the chain so multiple components can process the input in parallel. Later, other components can join or merge the results to synthesize a final response. This type of chain creates a computation graph that looks like the following:\n",
-    "\n",
-    "```text\n",
-    "     Input\n",
-    "      / \\\n",
-    "     /   \\\n",
-    " Branch1 Branch2\n",
-    "     \\   /\n",
-    "      \\ /\n",
-    "      Combine\n",
-    "```"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "247fa0bd-4596-4063-8cb3-1d7fc119d982",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "planner = (\n",
-    "    ChatPromptTemplate.from_template(\n",
-    "        \"Generate an argument about: {input}\"\n",
-    "    )\n",
-    "    | ChatOpenAI()\n",
-    "    | StrOutputParser()\n",
-    "    | {\"base_response\": RunnablePassthrough()}\n",
-    ")\n",
-    "\n",
-    "arguments_for = (\n",
-    "    ChatPromptTemplate.from_template(\n",
-    "        \"List the pros or positive aspects of {base_response}\"\n",
-    "    )\n",
-    "    | ChatOpenAI()\n",
-    "    | StrOutputParser()\n",
-    ")\n",
-    "arguments_against =  (\n",
-    "    ChatPromptTemplate.from_template(\n",
-    "        \"List the cons or negative aspects of {base_response}\"\n",
-    "    )\n",
-    "    | ChatOpenAI()\n",
-    "    | StrOutputParser()\n",
-    ")\n",
-    "\n",
-    "final_responder = (\n",
-    "    ChatPromptTemplate.from_messages(\n",
-    "        [\n",
-    "            (\"ai\", \"{original_response}\"),\n",
-    "            (\"human\", \"Pros:\\n{results_1}\\n\\nCons:\\n{results_2}\"),\n",
-    "            (\"system\", \"Generate a final response given the critique\"),\n",
-    "        ]\n",
-    "    )\n",
-    "    | ChatOpenAI()\n",
-    "    | StrOutputParser()\n",
-    ")\n",
-    "\n",
-    "chain = (\n",
-    "    planner \n",
-    "    | {\n",
-    "        \"results_1\": arguments_for,\n",
-    "        \"results_2\": arguments_against,\n",
-    "        \"original_response\": itemgetter(\"base_response\"),\n",
-    "    }\n",
-    "    | final_responder\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "2564f310-0674-4bb1-9c4e-d7848ca73511",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'While Scrum has its potential cons and challenges, many organizations have successfully embraced and implemented this project management framework to great effect. The cons mentioned above can be mitigated or overcome with proper training, support, and a commitment to continuous improvement. It is also important to note that not all cons may be applicable to every organization or project.\\n\\nFor example, while Scrum may be complex initially, with proper training and guidance, teams can quickly grasp the concepts and practices. The lack of predictability can be mitigated by implementing techniques such as velocity tracking and release planning. The limited documentation can be addressed by maintaining a balance between lightweight documentation and clear communication among team members. The dependency on team collaboration can be improved through effective communication channels and regular team-building activities.\\n\\nScrum can be scaled and adapted to larger projects by using frameworks like Scrum of Scrums or LeSS (Large Scale Scrum). Concerns about speed versus quality can be addressed by incorporating quality assurance practices, such as continuous integration and automated testing, into the Scrum process. Scope creep can be managed by having a well-defined and prioritized product backlog, and a strong product owner can be developed through training and mentorship.\\n\\nResistance to change can be overcome by providing proper education and communication to stakeholders and involving them in the decision-making process. Ultimately, the cons of Scrum can be seen as opportunities for growth and improvement, and with the right mindset and support, they can be effectively managed.\\n\\nIn conclusion, while Scrum may have its challenges and potential cons, the benefits and advantages it offers in terms of collaboration, flexibility, adaptability, transparency, and customer satisfaction make it a widely adopted and successful project management framework. With proper implementation and continuous improvement, organizations can leverage Scrum to drive innovation, efficiency, and project success.'"
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke({\"input\": \"scrum\"})"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "poetry-venv",
-   "language": "python",
-   "name": "poetry-venv"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.9.1"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/docs/expression_language/cookbook/prompt_llm_parser.ipynb

@@ -1,431 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "raw",
-   "id": "abf7263d-3a62-4016-b5d5-b157f92f2070",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "sidebar_position: 0\n",
-    "title: Prompt + LLM\n",
-    "---\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "9a434f2b-9405-468c-9dfd-254d456b57a6",
-   "metadata": {},
-   "source": [
-    "The most common and valuable composition is taking:\n",
-    "\n",
-    "``PromptTemplate`` / ``ChatPromptTemplate`` -> ``LLM`` / ``ChatModel`` -> ``OutputParser``\n",
-    "\n",
-    "Almost any other chains you build will use this building block."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "93aa2c87",
-   "metadata": {},
-   "source": [
-    "## PromptTemplate + LLM\n",
-    "\n",
-    "The simplest composition is just combing a prompt and model to create a chain that takes user input, adds it to a prompt, passes it to a model, and returns the raw model input.\n",
-    "\n",
-    "Note, you can mix and match PromptTemplate/ChatPromptTemplates and LLMs/ChatModels as you like here."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "466b65b3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.prompts import ChatPromptTemplate\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_template(\"tell me a joke about {foo}\")\n",
-    "model = ChatOpenAI()\n",
-    "chain = prompt | model\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "e3d0a6cd",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"Why don't bears wear shoes?\\n\\nBecause they have bear feet!\", additional_kwargs={}, example=False)"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke({\"foo\": \"bears\"})\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "7eb9ef50",
-   "metadata": {},
-   "source": [
-    "Often times we want to attach kwargs that'll be passed to each model call. Here's a few examples of that:"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0b1d8f88",
-   "metadata": {},
-   "source": [
-    "### Attaching Stop Sequences"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "562a06bf",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = prompt | model.bind(stop=[\"\\n\"])\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "43f5d04c",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='Why did the bear never wear shoes?', additional_kwargs={}, example=False)"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke({\"foo\": \"bears\"})\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f3eaf88a",
-   "metadata": {},
-   "source": [
-    "### Attaching Function Call information"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "f94b71b2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "functions = [\n",
-    "    {\n",
-    "      \"name\": \"joke\",\n",
-    "      \"description\": \"A joke\",\n",
-    "      \"parameters\": {\n",
-    "        \"type\": \"object\",\n",
-    "        \"properties\": {\n",
-    "          \"setup\": {\n",
-    "            \"type\": \"string\",\n",
-    "            \"description\": \"The setup for the joke\"\n",
-    "          },\n",
-    "          \"punchline\": {\n",
-    "            \"type\": \"string\",\n",
-    "            \"description\": \"The punchline for the joke\"\n",
-    "          }\n",
-    "        },\n",
-    "        \"required\": [\"setup\", \"punchline\"]\n",
-    "      }\n",
-    "    }\n",
-    "  ]\n",
-    "chain = prompt | model.bind(function_call= {\"name\": \"joke\"}, functions= functions)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "decf7710",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='', additional_kwargs={'function_call': {'name': 'joke', 'arguments': '{\\n  \"setup\": \"Why don\\'t bears wear shoes?\",\\n  \"punchline\": \"Because they have bear feet!\"\\n}'}}, example=False)"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke({\"foo\": \"bears\"}, config={})\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "9098c5ed",
-   "metadata": {},
-   "source": [
-    "## PromptTemplate + LLM + OutputParser\n",
-    "\n",
-    "We can also add in an output parser to easily transform the raw LLM/ChatModel output into a more workable format"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "cc194c78",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.schema.output_parser import StrOutputParser\n",
-    "\n",
-    "chain = prompt | model | StrOutputParser()\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "77acf448",
-   "metadata": {},
-   "source": [
-    "Notice that this now returns a string - a much more workable format for downstream tasks"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "e3d69a18",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\"Why don't bears wear shoes?\\n\\nBecause they have bear feet!\""
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke({\"foo\": \"bears\"})\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "c01864e5",
-   "metadata": {},
-   "source": [
-    "### Functions Output Parser\n",
-    "\n",
-    "When you specify the function to return, you may just want to parse that directly"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "ad0dd88e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.output_parsers.openai_functions import JsonOutputFunctionsParser\n",
-    "\n",
-    "chain = (\n",
-    "    prompt \n",
-    "    | model.bind(function_call= {\"name\": \"joke\"}, functions= functions) \n",
-    "    | JsonOutputFunctionsParser()\n",
-    ")\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "1e7aa8eb",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'setup': \"Why don't bears like fast food?\",\n",
-       " 'punchline': \"Because they can't catch it!\"}"
-      ]
-     },
-     "execution_count": 10,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke({\"foo\": \"bears\"})\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "d4aa1a01",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.output_parsers.openai_functions import JsonKeyOutputFunctionsParser\n",
-    "\n",
-    "chain = (\n",
-    "    prompt \n",
-    "    | model.bind(function_call= {\"name\": \"joke\"}, functions= functions) \n",
-    "    | JsonKeyOutputFunctionsParser(key_name=\"setup\")\n",
-    ")\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "8b6df9ba",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\"Why don't bears wear shoes?\""
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke({\"foo\": \"bears\"})\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "023fbccb-ef7d-489e-a9ba-f98e17283d51",
-   "metadata": {},
-   "source": [
-    "## Simplifying input\n",
-    "\n",
-    "To make invocation even simpler, we can add a `RunnableMap` to take care of creating the prompt input dict for us:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "9601c0f0-71f9-4bd4-a672-7bd04084b018",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.schema.runnable import RunnableMap, RunnablePassthrough\n",
-    "\n",
-    "map_ = RunnableMap(foo=RunnablePassthrough())\n",
-    "chain = (\n",
-    "    map_ \n",
-    "    | prompt\n",
-    "    | model.bind(function_call= {\"name\": \"joke\"}, functions= functions) \n",
-    "    | JsonKeyOutputFunctionsParser(key_name=\"setup\")\n",
-    ")\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "7ec4f154-fda5-4847-9220-41aa902fdc33",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\"Why don't bears wear shoes?\""
-      ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke(\"bears\")\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "def00bfe-0f83-4805-8c8f-8a53f99fa8ea",
-   "metadata": {},
-   "source": [
-    "Since we're composing our map with another Runnable, we can even use some syntactic sugar and just use a dict:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 21,
-   "id": "7bf3846a-02ee-41a3-ba1b-a708827d4f3a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = (\n",
-    "    {\"foo\": RunnablePassthrough()} \n",
-    "    | prompt\n",
-    "    | model.bind(function_call= {\"name\": \"joke\"}, functions= functions) \n",
-    "    | JsonKeyOutputFunctionsParser(key_name=\"setup\")\n",
-    ")\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "id": "e566d6a1-538d-4cb5-a210-a63e082e4c74",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\"Why don't bears like fast food?\""
-      ]
-     },
-     "execution_count": 22,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke(\"bears\")\n"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.9.1"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/docs/expression_language/cookbook/retrieval.ipynb

@@ -1,450 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "raw",
-   "id": "abe47592-909c-4844-bf44-9e55c2fb4bfa",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "sidebar_position: 1\n",
-    "title: RAG\n",
-    "---\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "91c5ef3d",
-   "metadata": {},
-   "source": [
-    "Let's look at adding in a retrieval step to a prompt and LLM, which adds up to a \"retrieval-augmented generation\" chain"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "7f25d9e9-d192-42e9-af50-5660a4bfb0d9",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!pip install langchain openai faiss-cpu tiktoken\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "33be32af",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from operator import itemgetter\n",
-    "\n",
-    "from langchain.prompts import ChatPromptTemplate\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.embeddings import OpenAIEmbeddings\n",
-    "from langchain.schema.output_parser import StrOutputParser\n",
-    "from langchain.schema.runnable import RunnablePassthrough, RunnableLambda\n",
-    "from langchain.vectorstores import FAISS\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "bfc47ec1",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "vectorstore = FAISS.from_texts([\"harrison worked at kensho\"], embedding=OpenAIEmbeddings())\n",
-    "retriever = vectorstore.as_retriever()\n",
-    "\n",
-    "template = \"\"\"Answer the question based only on the following context:\n",
-    "{context}\n",
-    "\n",
-    "Question: {question}\n",
-    "\"\"\"\n",
-    "prompt = ChatPromptTemplate.from_template(template)\n",
-    "\n",
-    "model = ChatOpenAI()\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "eae31755",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = (\n",
-    "    {\"context\": retriever, \"question\": RunnablePassthrough()} \n",
-    "    | prompt \n",
-    "    | model \n",
-    "    | StrOutputParser()\n",
-    ")\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "f3040b0c",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Harrison worked at Kensho.'"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke(\"where did harrison work?\")\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "e1d20c7c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "template = \"\"\"Answer the question based only on the following context:\n",
-    "{context}\n",
-    "\n",
-    "Question: {question}\n",
-    "\n",
-    "Answer in the following language: {language}\n",
-    "\"\"\"\n",
-    "prompt = ChatPromptTemplate.from_template(template)\n",
-    "\n",
-    "chain = {\n",
-    "    \"context\": itemgetter(\"question\") | retriever, \n",
-    "    \"question\": itemgetter(\"question\"), \n",
-    "    \"language\": itemgetter(\"language\")\n",
-    "} | prompt | model | StrOutputParser()\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "7ee8b2d4",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Harrison ha lavorato a Kensho.'"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke({\"question\": \"where did harrison work\", \"language\": \"italian\"})\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f007669c",
-   "metadata": {},
-   "source": [
-    "## Conversational Retrieval Chain\n",
-    "\n",
-    "We can easily add in conversation history. This primarily means adding in chat_message_history"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "3f30c348",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.schema.runnable import RunnableMap\n",
-    "from langchain.schema import format_document\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "64ab1dbf",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.prompts.prompt import PromptTemplate\n",
-    "\n",
-    "_template = \"\"\"Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question, in its original language.\n",
-    "\n",
-    "Chat History:\n",
-    "{chat_history}\n",
-    "Follow Up Input: {question}\n",
-    "Standalone question:\"\"\"\n",
-    "CONDENSE_QUESTION_PROMPT = PromptTemplate.from_template(_template)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "7d628c97",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "template = \"\"\"Answer the question based only on the following context:\n",
-    "{context}\n",
-    "\n",
-    "Question: {question}\n",
-    "\"\"\"\n",
-    "ANSWER_PROMPT = ChatPromptTemplate.from_template(template)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "f60a5d0f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "DEFAULT_DOCUMENT_PROMPT = PromptTemplate.from_template(template=\"{page_content}\")\n",
-    "def _combine_documents(docs, document_prompt = DEFAULT_DOCUMENT_PROMPT, document_separator=\"\\n\\n\"):\n",
-    "    doc_strings = [format_document(doc, document_prompt) for doc in docs]\n",
-    "    return document_separator.join(doc_strings)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "7d007db6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from typing import Tuple, List\n",
-    "def _format_chat_history(chat_history: List[Tuple]) -> str:\n",
-    "    buffer = \"\"\n",
-    "    for dialogue_turn in chat_history:\n",
-    "        human = \"Human: \" + dialogue_turn[0]\n",
-    "        ai = \"Assistant: \" + dialogue_turn[1]\n",
-    "        buffer += \"\\n\" + \"\\n\".join([human, ai])\n",
-    "    return buffer\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "5c32cc89",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "_inputs = RunnableMap(\n",
-    "    standalone_question=RunnablePassthrough.assign(\n",
-    "        chat_history=lambda x: _format_chat_history(x['chat_history'])\n",
-    "    ) | CONDENSE_QUESTION_PROMPT | ChatOpenAI(temperature=0) | StrOutputParser(),\n",
-    ")\n",
-    "_context = {\n",
-    "    \"context\": itemgetter(\"standalone_question\") | retriever | _combine_documents,\n",
-    "    \"question\": lambda x: x[\"standalone_question\"]\n",
-    "}\n",
-    "conversational_qa_chain = _inputs | _context | ANSWER_PROMPT | ChatOpenAI()\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "135c8205",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='Harrison was employed at Kensho.', additional_kwargs={}, example=False)"
-      ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "conversational_qa_chain.invoke({\n",
-    "    \"question\": \"where did harrison work?\",\n",
-    "    \"chat_history\": [],\n",
-    "})\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "424e7e7a",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='Harrison worked at Kensho.', additional_kwargs={}, example=False)"
-      ]
-     },
-     "execution_count": 15,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "conversational_qa_chain.invoke({\n",
-    "    \"question\": \"where did he work?\",\n",
-    "    \"chat_history\": [(\"Who wrote this notebook?\", \"Harrison\")],\n",
-    "})\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "c5543183",
-   "metadata": {},
-   "source": [
-    "### With Memory and returning source documents\n",
-    "\n",
-    "This shows how to use memory with the above. For memory, we need to manage that outside at the memory. For returning the retrieved documents, we just need to pass them through all the way."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "e31dd17c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from operator import itemgetter\n",
-    "from langchain.memory import ConversationBufferMemory\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "d4bffe94",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "memory = ConversationBufferMemory(return_messages=True, output_key=\"answer\", input_key=\"question\")\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "733be985",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# First we add a step to load memory\n",
-    "# This adds a \"memory\" key to the input object\n",
-    "loaded_memory = RunnablePassthrough.assign(\n",
-    "    chat_history=RunnableLambda(memory.load_memory_variables) | itemgetter(\"history\"),\n",
-    ")\n",
-    "# Now we calculate the standalone question\n",
-    "standalone_question = {\n",
-    "    \"standalone_question\": {\n",
-    "        \"question\": lambda x: x[\"question\"],\n",
-    "        \"chat_history\": lambda x: _format_chat_history(x['chat_history'])\n",
-    "    } | CONDENSE_QUESTION_PROMPT | ChatOpenAI(temperature=0) | StrOutputParser(),\n",
-    "}\n",
-    "# Now we retrieve the documents\n",
-    "retrieved_documents = {\n",
-    "    \"docs\": itemgetter(\"standalone_question\") | retriever,\n",
-    "    \"question\": lambda x: x[\"standalone_question\"]\n",
-    "}\n",
-    "# Now we construct the inputs for the final prompt\n",
-    "final_inputs = {\n",
-    "    \"context\": lambda x: _combine_documents(x[\"docs\"]),\n",
-    "    \"question\": itemgetter(\"question\")\n",
-    "}\n",
-    "# And finally, we do the part that returns the answers\n",
-    "answer = {\n",
-    "    \"answer\": final_inputs | ANSWER_PROMPT | ChatOpenAI(),\n",
-    "    \"docs\": itemgetter(\"docs\"),\n",
-    "}\n",
-    "# And now we put it all together!\n",
-    "final_chain = loaded_memory | standalone_question | retrieved_documents | answer\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "id": "806e390c",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'answer': AIMessage(content='Harrison was employed at Kensho.', additional_kwargs={}, example=False),\n",
-       " 'docs': [Document(page_content='harrison worked at kensho', metadata={})]}"
-      ]
-     },
-     "execution_count": 19,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "inputs = {\"question\": \"where did harrison work?\"}\n",
-    "result = final_chain.invoke(inputs)\n",
-    "result\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 20,
-   "id": "977399fd",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Note that the memory does not save automatically\n",
-    "# This will be improved in the future\n",
-    "# For now you need to save it yourself\n",
-    "memory.save_context(inputs, {\"answer\": result[\"answer\"].content})\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 21,
-   "id": "f94f7de4",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'history': [HumanMessage(content='where did harrison work?', additional_kwargs={}, example=False),\n",
-       "  AIMessage(content='Harrison was employed at Kensho.', additional_kwargs={}, example=False)]}"
-      ]
-     },
-     "execution_count": 21,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "memory.load_memory_variables({})\n"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.9.1"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/docs/expression_language/cookbook/sql_db.ipynb

@@ -1,216 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "raw",
-   "id": "c14da114-1a4a-487d-9cff-e0e8c30ba366",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "sidebar_position: 3\n",
-    "title: Querying a SQL DB\n",
-    "---\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "506e9636",
-   "metadata": {},
-   "source": [
-    "We can replicate our SQLDatabaseChain with Runnables."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "7a927516",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.prompts import ChatPromptTemplate\n",
-    "\n",
-    "template = \"\"\"Based on the table schema below, write a SQL query that would answer the user's question:\n",
-    "{schema}\n",
-    "\n",
-    "Question: {question}\n",
-    "SQL Query:\"\"\"\n",
-    "prompt = ChatPromptTemplate.from_template(template)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "3f51f386",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.utilities import SQLDatabase\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "7c3449d6-684b-416e-ba16-90a035835a88",
-   "metadata": {},
-   "source": [
-    "We'll need the Chinook sample DB for this example. There's many places to download it from, e.g. https://database.guide/2-sample-databases-sqlite/"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 20,
-   "id": "2ccca6fc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "db = SQLDatabase.from_uri(\"sqlite:///./Chinook.db\")\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 21,
-   "id": "05ba88ee",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def get_schema(_):\n",
-    "    return db.get_table_info()\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "id": "a4eda902",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def run_query(query):\n",
-    "    return db.run(query)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 23,
-   "id": "5046cb17",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.schema.output_parser import StrOutputParser\n",
-    "from langchain.schema.runnable import RunnablePassthrough\n",
-    "\n",
-    "model = ChatOpenAI()\n",
-    "\n",
-    "sql_response = (\n",
-    "        RunnablePassthrough.assign(schema=get_schema)\n",
-    "        | prompt\n",
-    "        | model.bind(stop=[\"\\nSQLResult:\"])\n",
-    "        | StrOutputParser()\n",
-    "    )\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 24,
-   "id": "a5552039",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'SELECT COUNT(*) FROM Employee'"
-      ]
-     },
-     "execution_count": 24,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "sql_response.invoke({\"question\": \"How many employees are there?\"})\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 25,
-   "id": "d6fee130",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "template = \"\"\"Based on the table schema below, question, sql query, and sql response, write a natural language response:\n",
-    "{schema}\n",
-    "\n",
-    "Question: {question}\n",
-    "SQL Query: {query}\n",
-    "SQL Response: {response}\"\"\"\n",
-    "prompt_response = ChatPromptTemplate.from_template(template)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 26,
-   "id": "923aa634",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "full_chain = (\n",
-    "    RunnablePassthrough.assign(query=sql_response) \n",
-    "    | RunnablePassthrough.assign(\n",
-    "        schema=get_schema,\n",
-    "        response=lambda x: db.run(x[\"query\"]),\n",
-    "    )\n",
-    "    | prompt_response \n",
-    "    | model\n",
-    ")\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 27,
-   "id": "e94963d8",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='There are 8 employees.', additional_kwargs={}, example=False)"
-      ]
-     },
-     "execution_count": 27,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "full_chain.invoke({\"question\": \"How many employees are there?\"})\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "4f358d7b-a721-4db3-9f92-f06913428afc",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.9.1"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/docs/expression_language/cookbook/tools.ipynb

@@ -1,122 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "29781123",
-   "metadata": {},
-   "source": [
-    "# Using tools\n",
-    "\n",
-    "You can use any Tools with Runnables easily."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "a5c579dd-2e22-41b0-a789-346dfdecb5a2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!pip install duckduckgo-search"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "9232d2a9",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.prompts import ChatPromptTemplate\n",
-    "from langchain.schema.output_parser import StrOutputParser\n",
-    "from langchain.tools import DuckDuckGoSearchRun"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "a0c64d2c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "search = DuckDuckGoSearchRun()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "391969b6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "template = \"\"\"turn the following user input into a search query for a search engine:\n",
-    "\n",
-    "{input}\"\"\"\n",
-    "prompt = ChatPromptTemplate.from_template(template)\n",
-    "\n",
-    "model = ChatOpenAI()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "e3d9d20d",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = prompt | model | StrOutputParser() | search"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "55f2967d",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'What sports games are on TV today & tonight? Watch and stream live sports on TV today, tonight, tomorrow. Today\\'s 2023 sports TV schedule includes football, basketball, baseball, hockey, motorsports, soccer and more. Watch on TV or stream online on ESPN, FOX, FS1, CBS, NBC, ABC, Peacock, Paramount+, fuboTV, local channels and many other networks. MLB Games Tonight: How to Watch on TV, Streaming & Odds - Thursday, September 7. Seattle Mariners\\' Julio Rodriguez greets teammates in the dugout after scoring against the Oakland Athletics in a ... Circle - Country Music and Lifestyle. Live coverage of all the MLB action today is available to you, with the information provided below. The Brewers will look to pick up a road win at PNC Park against the Pirates on Wednesday at 12:35 PM ET. Check out the latest odds and with BetMGM Sportsbook. Use bonus code \"GNPLAY\" for special offers! MLB Games Tonight: How to Watch on TV, Streaming & Odds - Tuesday, September 5. Houston Astros\\' Kyle Tucker runs after hitting a double during the fourth inning of a baseball game against the Los Angeles Angels, Sunday, Aug. 13, 2023, in Houston. (AP Photo/Eric Christian Smith) (APMedia) The Houston Astros versus the Texas Rangers is one of ... The second half of tonight\\'s college football schedule still has some good games remaining to watch on your television.. We\\'ve already seen an exciting one when Colorado upset TCU. And we saw some ...'"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke({\"input\": \"I'd like to figure out what games are tonight\"})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "a16949cf-00ea-43c6-a6aa-797ad4f6918d",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "poetry-venv",
-   "language": "python",
-   "name": "poetry-venv"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.9.1"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/docs/expression_language/how_to/binding.ipynb

@@ -1,194 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "711752cb-4f15-42a3-9838-a0c67f397771",
-   "metadata": {},
-   "source": [
-    "# Bind runtime args\n",
-    "\n",
-    "Sometimes we want to invoke a Runnable within a Runnable sequence with constant arguments that are not part of the output of the preceding Runnable in the sequence, and which are not part of the user input. We can use `Runnable.bind()` to easily pass these arguments in.\n",
-    "\n",
-    "Suppose we have a simple prompt + model sequence:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "f3fdf86d-155f-4587-b7cd-52d363970c1d",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "EQUATION: x^3 + 7 = 12\n",
-      "\n",
-      "SOLUTION:\n",
-      "Subtracting 7 from both sides of the equation, we get:\n",
-      "x^3 = 12 - 7\n",
-      "x^3 = 5\n",
-      "\n",
-      "Taking the cube root of both sides, we get:\n",
-      "x = ∛5\n",
-      "\n",
-      "Therefore, the solution to the equation x^3 + 7 = 12 is x = ∛5.\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.prompts import ChatPromptTemplate\n",
-    "from langchain.schema import StrOutputParser\n",
-    "from langchain.schema.runnable import RunnablePassthrough\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", \"Write out the following equation using algebraic symbols then solve it. Use the format\\n\\nEQUATION:...\\nSOLUTION:...\\n\\n\"),\n",
-    "        (\"human\", \"{equation_statement}\")\n",
-    "    ]\n",
-    ")\n",
-    "model = ChatOpenAI(temperature=0)\n",
-    "runnable = {\"equation_statement\": RunnablePassthrough()} | prompt | model | StrOutputParser()\n",
-    "\n",
-    "print(runnable.invoke(\"x raised to the third plus seven equals 12\"))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "929c9aba-a4a0-462c-adac-2cfc2156e117",
-   "metadata": {},
-   "source": [
-    "and want to call the model with certain `stop` words:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "32e0484a-78c5-4570-a00b-20d597245a96",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "EQUATION: x^3 + 7 = 12\n",
-      "\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "runnable = (\n",
-    "    {\"equation_statement\": RunnablePassthrough()} \n",
-    "    | prompt \n",
-    "    | model.bind(stop=\"SOLUTION\") \n",
-    "    | StrOutputParser()\n",
-    ")\n",
-    "print(runnable.invoke(\"x raised to the third plus seven equals 12\"))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f4bd641f-6b58-4ca9-a544-f69095428f16",
-   "metadata": {},
-   "source": [
-    "## Attaching OpenAI functions\n",
-    "\n",
-    "One particularly useful application of binding is to attach OpenAI functions to a compatible OpenAI model:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "f66a0fe4-fde0-4706-8863-d60253f211c7",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "functions = [\n",
-    "    {\n",
-    "      \"name\": \"solver\",\n",
-    "      \"description\": \"Formulates and solves an equation\",\n",
-    "      \"parameters\": {\n",
-    "        \"type\": \"object\",\n",
-    "        \"properties\": {\n",
-    "          \"equation\": {\n",
-    "            \"type\": \"string\",\n",
-    "            \"description\": \"The algebraic expression of the equation\"\n",
-    "          },\n",
-    "          \"solution\": {\n",
-    "            \"type\": \"string\",\n",
-    "            \"description\": \"The solution to the equation\"\n",
-    "          }\n",
-    "        },\n",
-    "        \"required\": [\"equation\", \"solution\"]\n",
-    "      }\n",
-    "    }\n",
-    "  ]\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "id": "f381f969-df8e-48a3-bf5c-d0397cfecde0",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='', additional_kwargs={'function_call': {'name': 'solver', 'arguments': '{\\n\"equation\": \"x^3 + 7 = 12\",\\n\"solution\": \"x = ∛5\"\\n}'}}, example=False)"
-      ]
-     },
-     "execution_count": 22,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Need gpt-4 to solve this one correctly\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", \"Write out the following equation using algebraic symbols then solve it.\"),\n",
-    "        (\"human\", \"{equation_statement}\")\n",
-    "    ]\n",
-    ")\n",
-    "model = ChatOpenAI(model=\"gpt-4\", temperature=0).bind(function_call={\"name\": \"solver\"}, functions=functions)\n",
-    "runnable = (\n",
-    "    {\"equation_statement\": RunnablePassthrough()} \n",
-    "    | prompt \n",
-    "    | model\n",
-    ")\n",
-    "runnable.invoke(\"x raised to the third plus seven equals 12\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "2cdeeb4c-0c1f-43da-bd58-4f591d9e0671",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "poetry-venv",
-   "language": "python",
-   "name": "poetry-venv"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.9.1"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}