REturn exceptions

.devcontainer/README.md

@@ -5,10 +5,10 @@ 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** .
 

.github/CODE_OF_CONDUCT.md

@@ -1,132 +0,0 @@
-# Contributor Covenant Code of Conduct
-
-## Our Pledge
-
-We as members, contributors, and leaders pledge to make participation in our
-community a harassment-free experience for everyone, regardless of age, body
-size, visible or invisible disability, ethnicity, sex characteristics, gender
-identity and expression, level of experience, education, socio-economic status,
-nationality, personal appearance, race, caste, color, religion, or sexual
-identity and orientation.
-
-We pledge to act and interact in ways that contribute to an open, welcoming,
-diverse, inclusive, and healthy community.
-
-## Our Standards
-
-Examples of behavior that contributes to a positive environment for our
-community include:
-
-* Demonstrating empathy and kindness toward other people
-* Being respectful of differing opinions, viewpoints, and experiences
-* Giving and gracefully accepting constructive feedback
-* Accepting responsibility and apologizing to those affected by our mistakes,
-  and learning from the experience
-* Focusing on what is best not just for us as individuals, but for the overall
-  community
-
-Examples of unacceptable behavior include:
-
-* The use of sexualized language or imagery, and sexual attention or advances of
-  any kind
-* Trolling, insulting or derogatory comments, and personal or political attacks
-* Public or private harassment
-* Publishing others' private information, such as a physical or email address,
-  without their explicit permission
-* Other conduct which could reasonably be considered inappropriate in a
-  professional setting
-
-## Enforcement Responsibilities
-
-Community leaders are responsible for clarifying and enforcing our standards of
-acceptable behavior and will take appropriate and fair corrective action in
-response to any behavior that they deem inappropriate, threatening, offensive,
-or harmful.
-
-Community leaders have the right and responsibility to remove, edit, or reject
-comments, commits, code, wiki edits, issues, and other contributions that are
-not aligned to this Code of Conduct, and will communicate reasons for moderation
-decisions when appropriate.
-
-## Scope
-
-This Code of Conduct applies within all community spaces, and also applies when
-an individual is officially representing the community in public spaces.
-Examples of representing our community include using an official e-mail address,
-posting via an official social media account, or acting as an appointed
-representative at an online or offline event.
-
-## Enforcement
-
-Instances of abusive, harassing, or otherwise unacceptable behavior may be
-reported to the community leaders responsible for enforcement at
-conduct@langchain.dev.
-All complaints will be reviewed and investigated promptly and fairly.
-
-All community leaders are obligated to respect the privacy and security of the
-reporter of any incident.
-
-## Enforcement Guidelines
-
-Community leaders will follow these Community Impact Guidelines in determining
-the consequences for any action they deem in violation of this Code of Conduct:
-
-### 1. Correction
-
-**Community Impact**: Use of inappropriate language or other behavior deemed
-unprofessional or unwelcome in the community.
-
-**Consequence**: A private, written warning from community leaders, providing
-clarity around the nature of the violation and an explanation of why the
-behavior was inappropriate. A public apology may be requested.
-
-### 2. Warning
-
-**Community Impact**: A violation through a single incident or series of
-actions.
-
-**Consequence**: A warning with consequences for continued behavior. No
-interaction with the people involved, including unsolicited interaction with
-those enforcing the Code of Conduct, for a specified period of time. This
-includes avoiding interactions in community spaces as well as external channels
-like social media. Violating these terms may lead to a temporary or permanent
-ban.
-
-### 3. Temporary Ban
-
-**Community Impact**: A serious violation of community standards, including
-sustained inappropriate behavior.
-
-**Consequence**: A temporary ban from any sort of interaction or public
-communication with the community for a specified period of time. No public or
-private interaction with the people involved, including unsolicited interaction
-with those enforcing the Code of Conduct, is allowed during this period.
-Violating these terms may lead to a permanent ban.
-
-### 4. Permanent Ban
-
-**Community Impact**: Demonstrating a pattern of violation of community
-standards, including sustained inappropriate behavior, harassment of an
-individual, or aggression toward or disparagement of classes of individuals.
-
-**Consequence**: A permanent ban from any sort of public interaction within the
-community.
-
-## Attribution
-
-This Code of Conduct is adapted from the [Contributor Covenant][homepage],
-version 2.1, available at
-[https://www.contributor-covenant.org/version/2/1/code_of_conduct.html][v2.1].
-
-Community Impact Guidelines were inspired by
-[Mozilla's code of conduct enforcement ladder][Mozilla CoC].
-
-For answers to common questions about this code of conduct, see the FAQ at
-[https://www.contributor-covenant.org/faq][FAQ]. Translations are available at
-[https://www.contributor-covenant.org/translations][translations].
-
-[homepage]: https://www.contributor-covenant.org
-[v2.1]: https://www.contributor-covenant.org/version/2/1/code_of_conduct.html
-[Mozilla CoC]: https://github.com/mozilla/diversity
-[FAQ]: https://www.contributor-covenant.org/faq
-[translations]: https://www.contributor-covenant.org/translations

.github/CONTRIBUTING.md

@@ -1,7 +1,7 @@
 # Contributing to LangChain
 
 Hi there! Thank you for even being interested in contributing to LangChain.
-As an open-source project in a rapidly developing field, we are extremely open
+As an open source project in a rapidly developing field, we are extremely open
 to contributions, whether they be in the form of new features, improved infra, better documentation, or bug fixes.
 
 ## 🗺️ Guidelines
@@ -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
@@ -59,85 +59,43 @@ 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: *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
+❗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.
 
 There are two separate projects in this repository:
 - `langchain`: core langchain code, abstractions, and use cases
-- `langchain.experimental`: see the [Experimental README](https://github.com/langchain-ai/langchain/tree/master/libs/experimental/README.md) for more information.
+- `langchain.experimental`: more experimental code
 
-Each of these has its own development environment. Docs are run from the top-level makefile, but development
-is split across separate test & release flows.
+Each of these has their OWN development environment. 
+In order to run any of the commands below, please move into their respective directories.
+For example, to contribute to `langchain` run `cd libs/langchain` before getting started with the below.
 
-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.
 
-```bash
-poetry install --with test
-```
+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`.
 
-Then verify dependency installation:
+## ✅ Common Tasks
 
-```bash
-make test
-```
+Type `make` for a list of common tasks.
 
-If the tests don't pass, you may need to pip install additional dependencies, such as `numexpr` and `openapi_schema_pydantic`.
+### Code Formatting
 
-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.
-
-### Testing
-
-_some test dependencies are optional; see section about optional dependencies_.
-
-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:
-
-```bash
-make test
-```
-
-To run unit tests in Docker:
-
-```bash
-make docker_tests
-```
-
-There are also [integration tests and code-coverage](https://github.com/langchain-ai/langchain/tree/master/libs/langchain/tests/README.md) available.
-
-### Formatting and Linting
-
-Run these locally before submitting a PR; the CI system will check also.
-
-#### Code Formatting
-
-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/).
+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:
 
@@ -153,9 +111,9 @@ make format_diff
 
 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
 
-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/).
+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:
 
@@ -173,10 +131,10 @@ This can be very helpful when you've made changes to only certain parts of the p
 
 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
+### 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.
+Note that `codespell` finds common typos, so could have false-positive (correctly spelled but rarely used) and false-negatives (not finding misspelled) words.
 
 To check spelling for this project:
 
@@ -199,17 +157,27 @@ If codespell is incorrectly flagging a word, you can skip spellcheck for that wo
 ignore-words-list = 'momento,collison,ned,foor,reworkd,parth,whats,aapply,mysogyny,unsecure'
 ```
 
-## Working with Optional Dependencies
+### 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 who do not have the dependency installed should be able to **import** your code without
-any side effects (no warnings, no errors, no exceptions).
+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:
+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
@@ -220,13 +188,57 @@ To introduce the dependency to the pyproject.toml file correctly, please do the
   ```bash
   poetry lock --no-update
   ```
-4. Add a unit test that the very least attempts to import the new code. Ideally, the unit
+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
+### Testing
 
-If you are adding a Jupyter Notebook example, you'll want to install the optional `dev` dependencies.
+See section about optional dependencies.
+
+#### Unit Tests
+
+Unit tests cover modular logic that does not require calls to outside APIs.
+
+To run unit tests:
+
+```bash
+make test
+```
+
+To run unit tests in Docker:
+
+```bash
+make docker_tests
+```
+
+If you add new logic, please add a unit test.
+
+
+
+#### Integration Tests
+
+Integration tests cover logic that requires making calls to outside APIs (often integration with other services).
+
+**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 integration_tests
+```
+
+If you add support for a new external API, please add a new integration test.
+
+### Adding a Jupyter Notebook
+
+If you are adding a Jupyter notebook example, you'll want to install the optional `dev` dependencies.
 
 To install dev dependencies:
 
@@ -247,12 +259,6 @@ When you run `poetry install`, the `langchain` package is installed as editable
 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.
@@ -289,13 +295,6 @@ make docs_linkcheck
 make api_docs_linkcheck
 ```
 
-### Verify Documentation changes
-
-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).
-
 ## 🏭 Release Process
 
 As of now, LangChain has an ad hoc release process: releases are cut with high frequency by
@@ -308,3 +307,4 @@ 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 +1,28 @@
 <!-- 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!
+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!
 
-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
+Please make sure you're PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally.
 
 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 +15,64 @@ 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
+      working-directory: ${{ inputs.working-directory }}
+      run: |
+        poetry check
+
+    - name: Check lock file
+      shell: bash
+      working-directory: ${{ inputs.working-directory }}
+      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/_compile_integration_test.yml

@@ -1,57 +0,0 @@
-name: compile-integration-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@v4
-
-      - 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: ${{ inputs.working-directory }}
-          cache-key: compile-integration
-
-      - name: Install integration dependencies
-        shell: bash
-        run: poetry install --with=test_integration
-
-      - name: Check integration tests compile
-        shell: bash
-        run: poetry run pytest -m compile tests/integration_tests
-
-      - name: Ensure the tests did not create any additional files
-        shell: bash
-        run: |
-          set -eu
-
-          STATUS="$(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/_lint.yml

@@ -9,142 +9,38 @@ on:
         description: "From which folder this pipeline executes"
 
 env:
-  POETRY_VERSION: "1.6.1"
-  WORKDIR: ${{ inputs.working-directory == '' && '.' || inputs.working-directory }}
+  POETRY_VERSION: "1.4.2"
 
 jobs:
   build:
+    defaults:
+      run:
+        working-directory: ${{ inputs.working-directory }}
     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"
+          - "3.9"
+          - "3.10"
           - "3.11"
     steps:
-      - uses: actions/checkout@v4
-        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: ${{ env.FETCH_DEPTH }}
-      - name: Restore workdir file mtimes to last-edited commit date
-        id: restore-mtimes
-        # This is needed to make black caching work.
-        # Black's cache uses file (mtime, size) to check whether a lookup is a cache hit.
-        # Without this command, files in the repo would have the current time as the modified time,
-        # since the previous action step just created them.
-        # This command resets the mtime to the last time the files were modified in git instead,
-        # which is a high-quality and stable representation of the last modification date.
+      - uses: actions/checkout@v3
+      - name: Install poetry
         run: |
-          # Important considerations:
-          # - These commands run at base of the repo, since we never `cd` to the `WORKDIR`.
-          # - We only want to alter mtimes for Python files, since that's all black checks.
-          # - We don't need to alter mtimes for directories, since black doesn't look at those.
-          # - We also only alter mtimes inside the `WORKDIR` since that's all we'll lint.
-          # - This should run before `poetry install`, because poetry's venv also contains
-          #   Python files, and we don't want to alter their mtimes since they aren't linted.
-
-          # Ensure we fail on non-zero exits and on undefined variables.
-          # Also print executed commands, for easier debugging.
-          set -eux
-
-          # Restore the mtimes of Python files in the workdir based on git history.
-          .github/tools/git-restore-mtime --no-directories "$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 ${{ env.POETRY_VERSION }}
-        uses: "./.github/actions/poetry_setup"
+          pipx install poetry==$POETRY_VERSION
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
         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
-
+          cache: poetry
       - 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
-
+          poetry install
       - name: Install langchain editable
-        working-directory: ${{ inputs.working-directory }}
-        if: ${{ inputs.working-directory != 'libs/langchain' }}
+        if: ${{ inputs.working-directory != 'langchain' }}
         run: |
           pip install -e ../langchain
-
-      - name: Restore black cache
-        uses: actions/cache@v3
-        env:
-          CACHE_BASE: black-${{ 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@v4
-
-      - 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

@@ -9,37 +9,26 @@ on:
         description: "From which folder this pipeline executes"
 
 env:
-  POETRY_VERSION: "1.6.1"
+  POETRY_VERSION: "1.4.2"
 
 jobs:
   if_release:
-    # Disallow publishing from branches that aren't `master`.
-    if: github.ref == 'refs/heads/master'
+    if: |
+        ${{ github.event.pull_request.merged == true }}
+        && ${{ contains(github.event.pull_request.labels.*.name, 'release') }}
     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@v4
-
-      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
-        uses: "./.github/actions/poetry_setup"
+      - uses: actions/checkout@v3
+      - name: Install poetry
+        run: pipx install poetry==$POETRY_VERSION
+      - name: Set up Python 3.10
+        uses: actions/setup-python@v4
         with:
           python-version: "3.10"
-          poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ inputs.working-directory }}
-          cache-key: release
-
+          cache: "poetry"
       - name: Build project for distribution
         run: poetry build
       - name: Check Version
@@ -56,9 +45,8 @@ jobs:
           generateReleaseNotes: true
           tag: v${{ 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
+      - name: Publish to PyPI
+        env:
+          POETRY_PYPI_TOKEN_PYPI: ${{ secrets.PYPI_API_TOKEN }}
+        run: |
+          poetry publish

.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

@@ -7,9 +7,13 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
+      test_type:
+        type: string
+        description: "Test types to run"
+        default: '["core", "extended"]'
 
 env:
-  POETRY_VERSION: "1.6.1"
+  POETRY_VERSION: "1.4.2"
 
 jobs:
   build:
@@ -24,42 +28,34 @@ jobs:
           - "3.9"
           - "3.10"
           - "3.11"
-    name: Python ${{ matrix.python-version }}
+        test_type: ${{ fromJSON(inputs.test_type) }}
+    name: Python ${{ matrix.python-version }} ${{ matrix.test_type }}
     steps:
-      - uses: actions/checkout@v4
-
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - 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: ${{ inputs.working-directory }}
-          cache-key: core
-
-      - name: Install dependencies
-        shell: bash
-        run: poetry install
-
-      - name: Run core tests
-        shell: bash
-        run: make test
-
-      - name: Install integration dependencies
-        shell: bash
-        run: poetry install --with=test_integration
-
-      - name: Check integration tests compile
-        shell: bash
-        run: poetry run pytest -m compile tests/integration_tests
-
-      - name: Ensure the tests did not create any additional files
-        shell: bash
+          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: Install langchain editable
+        if: ${{ inputs.working-directory != 'langchain' }}
         run: |
-          set -eu
-
-          STATUS="$(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'
+          pip install -e ../langchain
+      - name: Run ${{matrix.test_type}} tests
+        run: |
+          if [ "${{ matrix.test_type }}" == "core" ]; then
+            make test
+          else
+            make extended_tests
+          fi
+        shell: bash

.github/workflows/_test_release.yml

@@ -1,50 +0,0 @@
-name: test-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:
-  publish_to_test_pypi:
-    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
-    defaults:
-      run:
-        working-directory: ${{ inputs.working-directory }}
-    steps:
-      - uses: actions/checkout@v4
-
-      - 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: Publish package to TestPyPI
-        uses: pypa/gh-action-pypi-publish@release/v1
-        with:
-          repository-url: https://test.pypi.org/legacy/
-          packages-dir: ${{ inputs.working-directory }}/dist/
-          verbose: true
-          print-hash: true

.github/workflows/codespell.yml

@@ -17,20 +17,8 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
-
-      - 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
-
+        uses: actions/checkout@v3
       - 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

@@ -6,29 +6,12 @@ on:
     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:
@@ -36,69 +19,9 @@ jobs:
     with:
       working-directory: libs/langchain
     secrets: inherit
-
   test:
     uses:
       ./.github/workflows/_test.yml
     with:
       working-directory: libs/langchain
-    secrets: inherit
-
-  compile-integration-tests:
-    uses:
-      ./.github/workflows/_compile_integration_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@v4
-
-      - 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'
+    secrets: inherit

.github/workflows/langchain_experimental_ci.yml

@@ -1,13 +1,11 @@
 ---
-name: libs/experimental CI
+name: libs/langchain-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'
@@ -15,20 +13,6 @@ on:
       - '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:
@@ -36,101 +20,10 @@ jobs:
     with:
       working-directory: libs/experimental
     secrets: inherit
-
   test:
     uses:
       ./.github/workflows/_test.yml
     with:
       working-directory: libs/experimental
-    secrets: inherit
-
-  compile-integration-tests:
-    uses:
-      ./.github/workflows/_compile_integration_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@v4
-
-      - 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@v4
-
-      - 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'
+      test_type: '["core"]'
+    secrets: inherit

.github/workflows/langchain_experimental_release.yml

@@ -1,7 +1,14 @@
 ---
-name: libs/experimental Release
+name: libs/langchain-experimental Release
 
 on:
+  pull_request:
+    types:
+      - closed
+    branches:
+      - master
+    paths:
+      - 'libs/experimental/pyproject.toml'
   workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
 
 jobs:
@@ -10,4 +17,4 @@ jobs:
       ./.github/workflows/_release.yml
     with:
       working-directory: libs/experimental
-    secrets: inherit
+    secrets: inherit

.github/workflows/langchain_experimental_test_release.yml

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

.github/workflows/langchain_release.yml

@@ -2,6 +2,13 @@
 name: libs/langchain Release
 
 on:
+  pull_request:
+    types:
+      - closed
+    branches:
+      - master
+    paths:
+      - 'libs/langchain/pyproject.toml'
   workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
 
 jobs:
@@ -10,18 +17,4 @@ jobs:
       ./.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
+    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/langchain_test_release.yml

@@ -1,13 +0,0 @@
----
-name: Test Release
-
-on:
-  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
-
-jobs:
-  release:
-    uses:
-      ./.github/workflows/_test_release.yml
-    with:
-      working-directory: libs/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@v4
-
-      - 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'

.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.
@@ -174,7 +168,6 @@ 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:
@@ -30,3 +25,5 @@ sphinx:
 python:
    install:
    - requirements: docs/api_reference/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"

Makefile

@@ -15,10 +15,10 @@ docs_build:
 	docs/.local_build.sh
 
 docs_clean:
-	rm -r _dist
+	rm -r docs/_dist
 
 docs_linkcheck:
-	poetry run linkchecker _dist/docs/ --ignore-url node_modules
+	poetry run linkchecker docs/_dist/docs_skeleton/ --ignore-url node_modules
 
 api_docs_build:
 	poetry run python docs/api_reference/create_api_rst.py
@@ -42,8 +42,7 @@ spell_fix:
 ######################
 
 help:
-	@echo '===================='
-	@echo '-- DOCUMENTATION --'
+	@echo '----'
 	@echo 'clean                        - run docs_clean and api_docs_clean'
 	@echo 'docs_build                   - build the documentation'
 	@echo 'docs_clean                   - clean the documentation build artifacts'
@@ -52,5 +51,4 @@ help:
 	@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 'spell_fix               		- run codespell on the project and fix the errors'

README.md

@@ -2,32 +2,31 @@
 
 ⚡ 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)
+[![CI](https://github.com/hwchase17/langchain/actions/workflows/langchain_ci.yml/badge.svg)](https://github.com/hwchase17/langchain/actions/workflows/langchain_ci.yml)
+[![Experimental CI](https://github.com/hwchase17/langchain/actions/workflows/langchain_experimental_ci.yml/badge.svg)](https://github.com/hwchase17/langchain/actions/workflows/langchain_experimental_ci.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)
+[![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/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 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
+**Production Support:** As you move your LangChains into production, we'd love to offer more hands-on support.
+Fill out [this form](https://airtable.com/appwQzlErAS2qiP0L/shrGtGaVBVAz7NcV2) to share more about what you're building, and our team will get in touch.
 
-## 🚨Breaking Changes for select chains (SQLDatabase) on 7/28/23
+## 🚨Breaking Changes for select chains (SQLDatabase) on 7/28
 
 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 more about the motivation and the progress [here](https://github.com/hwchase17/langchain/discussions/8043).
 Read how to migrate your code [here](MIGRATE.md).
 
 ## Quick Install
@@ -50,7 +49,7 @@ 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**
 
@@ -93,7 +92,7 @@ Memory refers to persisting state between calls of a chain/agent. LangChain prov
 
 **🧐 Evaluation:**
 
-[BETA] Generative models are notoriously hard to evaluate with traditional metrics. One new way of evaluating them is by using language models themselves to do the evaluation. LangChain provides some prompts/chains for assisting in this.
+[BETA] Generative models are notoriously hard to evaluate with traditional metrics. One new way of evaluating them is using language models themselves to do the evaluation. LangChain provides some prompts/chains for assisting in this.
 
 For more information on these concepts, please see our [full documentation](https://python.langchain.com).
 

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

@@ -1,52 +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 an SQLite database containing 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.
-[press_releases.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/press_releases.ipynb) | Retrieve and query company press release data powered by [Kay.ai](https://kay.ai).
-[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 dialogue simulator 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/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/press_releases.ipynb

@@ -1,152 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "62ee82e4-2ad8-498b-8438-fac388afe1a2",
-   "metadata": {},
-   "source": [
-    "Press Releases Data\n",
-    "=\n",
-    "\n",
-    "Press Releases data powered by [Kay.ai](https://kay.ai).\n",
-    "\n",
-    ">Press releases are used by companies to announce something noteworthy, including product launches, financial performance reports, partnerships, and other significant news. They are widely used by analysts to track corporate strategy, operational updates and financial performance.\n",
-    "Kay.ai obtains press releases of all US public companies from a variety of sources, which include the company's official press room and partnerships with various data API providers. \n",
-    "This data is updated till Sept 30th for free access, if you want to access the real-time feed, reach out to us at hello@kay.ai or [tweet at us](https://twitter.com/vishalrohra_)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "8183d85d-365f-4672-a963-52b533547de0",
-   "metadata": {},
-   "source": [
-    "Setup\n",
-    "=\n",
-    "\n",
-    "First you will need to install the `kay` package. You will also need an API key: you can get one for free at [https://kay.ai](https://kay.ai/). Once you have an API key, you must set it as an environment variable `KAY_API_KEY`.\n",
-    "\n",
-    "In this example we're going to use the `KayAiRetriever`. Take a look at the [kay notebook](/docs/integrations/retrievers/kay) for more detailed information for the parmeters that it accepts."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "02ec21c7-49fe-4844-b58a-bf064ad40b2a",
-   "metadata": {},
-   "source": [
-    "Examples\n",
-    "="
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "bf0395f7-6ebe-4136-8b0d-00b9dea3becd",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdin",
-     "output_type": "stream",
-     "text": [
-      " ········\n",
-      " ········\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Setup API keys for Kay and OpenAI\n",
-    "from getpass import getpass\n",
-    "KAY_API_KEY = getpass()\n",
-    "OPENAI_API_KEY = getpass()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "f7fcaf70-29a4-444b-8f07-9784f808c300",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "os.environ[\"KAY_API_KEY\"] = KAY_API_KEY\n",
-    "os.environ[\"OPENAI_API_KEY\"] = OPENAI_API_KEY"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "ac00bf93-3635-4ffe-b9a6-a8b4f35c0c85",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chains import ConversationalRetrievalChain\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.retrievers import KayAiRetriever\n",
-    "\n",
-    "model = ChatOpenAI(model_name=\"gpt-3.5-turbo\")\n",
-    "retriever = KayAiRetriever.create(dataset_id=\"company\", data_types=[\"PressRelease\"], num_contexts=6)\n",
-    "qa = ConversationalRetrievalChain.from_llm(model, retriever=retriever)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "8d9d927c-35b2-4a7b-8ea7-4d0350797941",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "-> **Question**: How is the healthcare industry adopting generative AI tools? \n",
-      "\n",
-      "**Answer**: The healthcare industry is adopting generative AI tools to improve various aspects of patient care and administrative tasks. Companies like HCA Healthcare Inc, Amazon Com Inc, and Mayo Clinic have collaborated with technology providers like Google Cloud, AWS, and Microsoft to implement generative AI solutions.\n",
-      "\n",
-      "HCA Healthcare is testing a nurse handoff tool that generates draft reports quickly and accurately, which nurses have shown interest in using. They are also exploring the use of Google's medically-tuned Med-PaLM 2 LLM to support caregivers in asking complex medical questions.\n",
-      "\n",
-      "Amazon Web Services (AWS) has introduced AWS HealthScribe, a generative AI-powered service that automatically creates clinical documentation. However, integrating multiple AI systems into a cohesive solution requires significant engineering resources, including access to AI experts, healthcare data, and compute capacity.\n",
-      "\n",
-      "Mayo Clinic is among the first healthcare organizations to deploy Microsoft 365 Copilot, a generative AI service that combines large language models with organizational data from Microsoft 365. This tool has the potential to automate tasks like form-filling, relieving administrative burdens on healthcare providers and allowing them to focus more on patient care.\n",
-      "\n",
-      "Overall, the healthcare industry is recognizing the potential benefits of generative AI tools in improving efficiency, automating tasks, and enhancing patient care. \n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "# More sample questions in the Playground on https://kay.ai\n",
-    "questions = [\n",
-    "    \"How is the healthcare industry adopting generative AI tools?\",\n",
-    "    #\"What are some recent challenges faced by the renewable energy sector?\",\n",
-    "]\n",
-    "chat_history = []\n",
-    "\n",
-    "for question in questions:\n",
-    "    result = qa({\"question\": question, \"chat_history\": chat_history})\n",
-    "    chat_history.append((question, result[\"answer\"]))\n",
-    "    print(f\"-> **Question**: {question} \\n\")\n",
-    "    print(f\"**Answer**: {result['answer']} \\n\")"
-   ]
-  }
- ],
- "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": "3.9.18"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/rag_fusion.ipynb

@@ -1,263 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "993c2768",
-   "metadata": {},
-   "source": [
-    "# RAG Fusion\n",
-    "\n",
-    "Re-implemented from [this GitHub repo](https://github.com/Raudaschl/rag-fusion), all credit to original author\n",
-    "\n",
-    "> RAG-Fusion, a search methodology that aims to bridge the gap between traditional search paradigms and the multifaceted dimensions of human queries. Inspired by the capabilities of Retrieval Augmented Generation (RAG), this project goes a step further by employing multiple query generation and Reciprocal Rank Fusion to re-rank search results."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "ebcc6791",
-   "metadata": {},
-   "source": [
-    "## Setup\n",
-    "\n",
-    "For this example, we will use Pinecone and some fake data"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "661a1c36",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import pinecone\n",
-    "from langchain.vectorstores import Pinecone\n",
-    "from langchain.embeddings import OpenAIEmbeddings\n",
-    "\n",
-    "pinecone.init(api_key=\"...\",environment=\"...\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "48ef7e93",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "all_documents = {\n",
-    "    \"doc1\": \"Climate change and economic impact.\",\n",
-    "    \"doc2\": \"Public health concerns due to climate change.\",\n",
-    "    \"doc3\": \"Climate change: A social perspective.\",\n",
-    "    \"doc4\": \"Technological solutions to climate change.\",\n",
-    "    \"doc5\": \"Policy changes needed to combat climate change.\",\n",
-    "    \"doc6\": \"Climate change and its impact on biodiversity.\",\n",
-    "    \"doc7\": \"Climate change: The science and models.\",\n",
-    "    \"doc8\": \"Global warming: A subset of climate change.\",\n",
-    "    \"doc9\": \"How climate change affects daily weather.\",\n",
-    "    \"doc10\": \"The history of climate change activism.\"\n",
-    "}"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "fde89f0b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "vectorstore = Pinecone.from_texts(list(all_documents.values()), OpenAIEmbeddings(), index_name='rag-fusion')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "22ddd041",
-   "metadata": {},
-   "source": [
-    "## Define the Query Generator\n",
-    "\n",
-    "We will now define a chain to do the query generation"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "1d547524",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.prompts import ChatPromptTemplate\n",
-    "from langchain.schema.output_parser import StrOutputParser"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 68,
-   "id": "af9ab4db",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain import hub\n",
-    "\n",
-    "prompt = hub.pull('langchain-ai/rag-fusion-query-generation')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "3628b552",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# prompt = ChatPromptTemplate.from_messages([\n",
-    "#     (\"system\", \"You are a helpful assistant that generates multiple search queries based on a single input query.\"),\n",
-    "#     (\"user\", \"Generate multiple search queries related to: {original_query}\"),\n",
-    "#     (\"user\", \"OUTPUT (4 queries):\")\n",
-    "# ])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "8d6cbb73",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "generate_queries = prompt | ChatOpenAI(temperature=0) | StrOutputParser() | (lambda x: x.split(\"\\n\"))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "ee2824cd",
-   "metadata": {},
-   "source": [
-    "## Define the full chain\n",
-    "\n",
-    "We can now put it all together and define the full chain. This chain:\n",
-    "    \n",
-    "    1. Generates a bunch of queries\n",
-    "    2. Looks up each query in the retriever\n",
-    "    3. Joins all the results together using reciprocal rank fusion\n",
-    "    \n",
-    "    \n",
-    "Note that it does NOT do a final generation step"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 50,
-   "id": "ca0bfec4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "original_query = \"impact of climate change\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 75,
-   "id": "02437d65",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "vectorstore = Pinecone.from_existing_index(\"rag-fusion\", OpenAIEmbeddings())\n",
-    "retriever = vectorstore.as_retriever()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 76,
-   "id": "46a9a0e6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.load import dumps, loads\n",
-    "def reciprocal_rank_fusion(results: list[list], k=60):\n",
-    "    fused_scores = {}\n",
-    "    for docs in results:\n",
-    "        # Assumes the docs are returned in sorted order of relevance\n",
-    "        for rank, doc in enumerate(docs):\n",
-    "            doc_str = dumps(doc)\n",
-    "            if doc_str not in fused_scores:\n",
-    "                fused_scores[doc_str] = 0\n",
-    "            previous_score = fused_scores[doc_str]\n",
-    "            fused_scores[doc_str] += 1 / (rank + k)\n",
-    "            \n",
-    "    reranked_results = [(loads(doc), score) for doc, score in sorted(fused_scores.items(), key=lambda x: x[1], reverse=True)]\n",
-    "    return reranked_results "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 77,
-   "id": "3f9d4502",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = generate_queries | retriever.map() | reciprocal_rank_fusion"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 78,
-   "id": "d70c4fcd",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[(Document(page_content='Climate change and economic impact.'),\n",
-       "  0.06558258417063283),\n",
-       " (Document(page_content='Climate change: A social perspective.'),\n",
-       "  0.06400409626216078),\n",
-       " (Document(page_content='How climate change affects daily weather.'),\n",
-       "  0.04787506400409626),\n",
-       " (Document(page_content='Climate change and its impact on biodiversity.'),\n",
-       "  0.03306010928961749),\n",
-       " (Document(page_content='Public health concerns due to climate change.'),\n",
-       "  0.016666666666666666),\n",
-       " (Document(page_content='Technological solutions to climate change.'),\n",
-       "  0.016666666666666666),\n",
-       " (Document(page_content='Policy changes needed to combat climate change.'),\n",
-       "  0.01639344262295082)]"
-      ]
-     },
-     "execution_count": 78,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke({\"original_query\": original_query})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "7866e551",
-   "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/rewrite.ipynb

@@ -1,351 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "260629f9",
-   "metadata": {},
-   "source": [
-    "# Rewrite-Retrieve-Read\n",
-    "\n",
-    "**Rewrite-Retrieve-Read** is a method proposed in the paper [Query Rewriting for Retrieval-Augmented Large Language Models](https://arxiv.org/pdf/2305.14283.pdf)\n",
-    "\n",
-    "> Because the original query can not be always optimal to retrieve for the LLM, especially in the real world... we first prompt an LLM to rewrite the queries, then conduct retrieval-augmented reading\n",
-    "\n",
-    "We show how you can easily do that with LangChain Expression Language"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "eda93712",
-   "metadata": {},
-   "source": [
-    "## Baseline\n",
-    "\n",
-    "Baseline RAG (**Retrieve-and-read**) can be done like the following:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "1d2edbd2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from operator import itemgetter\n",
-    "\n",
-    "from langchain.prompts import ChatPromptTemplate\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.schema.output_parser import StrOutputParser\n",
-    "from langchain.schema.runnable import RunnablePassthrough, RunnableLambda\n",
-    "from langchain.utilities import DuckDuckGoSearchAPIWrapper"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "86a46aa9",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "template = \"\"\"Answer the users question based only on the following context:\n",
-    "\n",
-    "<context>\n",
-    "{context}\n",
-    "</context>\n",
-    "\n",
-    "Question: {question}\n",
-    "\"\"\"\n",
-    "prompt = ChatPromptTemplate.from_template(template)\n",
-    "\n",
-    "model = ChatOpenAI(temperature=0)\n",
-    "\n",
-    "search = DuckDuckGoSearchAPIWrapper()\n",
-    "\n",
-    "\n",
-    "def retriever(query):\n",
-    "    return search.run(query)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "8566d48e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = (\n",
-    "    {\"context\": retriever, \"question\": RunnablePassthrough()} \n",
-    "    | prompt \n",
-    "    | model \n",
-    "    | StrOutputParser()\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "5c57f9ee",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "simple_query = \"what is langchain?\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "37c5f962",
-   "metadata": {
-    "scrolled": false
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\"LangChain is a powerful and versatile Python library that enables developers and researchers to create, experiment with, and analyze language models and agents. It simplifies the development of language-based applications by providing a suite of features for artificial general intelligence. It can be used to build chatbots, perform document analysis and summarization, and streamline interaction with various large language model providers. LangChain's unique proposition is its ability to create logical links between one or more language models, known as Chains. It is an open-source library that offers a generic interface to foundation models and allows prompt management and integration with other components and tools.\""
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke(simple_query)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "23bdb9bd",
-   "metadata": {},
-   "source": [
-    "While this is fine for well formatted queries, it can break down for more complicated queries"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "8df6a814",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "distracted_query = \"man that sam bankman fried trial was crazy! what is langchain?\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "16d7db64",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Based on the given context, there is no information provided about \"langchain.\"'"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke(distracted_query)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0b4f8b93",
-   "metadata": {},
-   "source": [
-    "This is because the retriever does a bad job with these \"distracted\" queries"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "3439d8dc",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Business She\\'s the star witness against Sam Bankman-Fried. Her testimony was explosive Gary Wang, who co-founded both FTX and Alameda Research, said Bankman-Fried directed him to change a... The Verge, following the trial\\'s Oct. 4 kickoff: \"Is Sam Bankman-Fried\\'s Defense Even Trying to Win?\". CBS Moneywatch, from Thursday: \"Sam Bankman-Fried\\'s Lawyer Struggles to Poke ... Sam Bankman-Fried, FTX\\'s founder, responded with a single word: \"Oof.\". Less than a year later, Mr. Bankman-Fried, 31, is on trial in federal court in Manhattan, fighting criminal charges ... July 19, 2023. A U.S. judge on Wednesday overruled objections by Sam Bankman-Fried\\'s lawyers and allowed jurors in the FTX founder\\'s fraud trial to see a profane message he sent to a reporter days ... Sam Bankman-Fried, who was once hailed as a virtuoso in cryptocurrency trading, is on trial over the collapse of FTX, the financial exchange he founded. Bankman-Fried is accused of...'"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "retriever(distracted_query)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "7eb748ac",
-   "metadata": {},
-   "source": [
-    "## Rewrite-Retrieve-Read Implementation\n",
-    "\n",
-    "The main part is a rewriter to rewrite the search query"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "88ae702e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "template = \"\"\"Provide a better search query for \\\n",
-    "web search engine to answer the given question, end \\\n",
-    "the queries with ’**’. Question: \\\n",
-    "{x} Answer:\"\"\"\n",
-    "rewrite_prompt = ChatPromptTemplate.from_template(template)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "184e1bcb",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain import hub\n",
-    "\n",
-    "rewrite_prompt = hub.pull(\"langchain-ai/rewrite\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "a4c23d40",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Provide a better search query for web search engine to answer the given question, end the queries with ’**’.  Question {x} Answer:\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(rewrite_prompt.template)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "f55cd010",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Parser to remove the `**`\n",
-    "\n",
-    "def _parse(text):\n",
-    "    return text.strip(\"**\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "c9c34bef",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "rewriter = rewrite_prompt | ChatOpenAI(temperature=0) | StrOutputParser() | _parse"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "fb17fb3d",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'What is the definition and purpose of Langchain?'"
-      ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "rewriter.invoke({\"x\": distracted_query})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "f83edb09",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "rewrite_retrieve_read_chain = (\n",
-    "    {\n",
-    "        \"context\": {\"x\": RunnablePassthrough()} | rewriter | retriever,\n",
-    "        \"question\": RunnablePassthrough()} \n",
-    "    | prompt \n",
-    "    | model \n",
-    "    | StrOutputParser()\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "43096322",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Based on the given context, LangChain is an open-source framework designed to simplify the creation of applications using large language models (LLMs). It enables LLM models to generate responses based on up-to-date online information and simplifies the organization of large volumes of data for easy access by LLMs. LangChain offers a standard interface for chains, integrations with other tools, and end-to-end chains for common applications. It is a robust library that streamlines interaction with various LLM providers. LangChain\\'s unique proposition is its ability to create logical links between one or more LLMs, known as Chains. It is an AI framework with features that simplify the development of language-based applications and offers a suite of features for artificial general intelligence. However, the context does not provide any information about the \"sam bankman fried trial\" mentioned in the question.'"
-      ]
-     },
-     "execution_count": 16,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "rewrite_retrieve_read_chain.invoke(distracted_query)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "59874b4f",
-   "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/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/stepback-qa.ipynb

@@ -1,335 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "83ef724e",
-   "metadata": {},
-   "source": [
-    "# Step-Back Prompting (Question-Answering)\n",
-    "\n",
-    "One prompting technique called \"Step-Back\" prompting can improve performance on complex questions by first asking a \"step back\" question. This can be combined with regular question-answering applications by then doing retrieval on both the original and step-back question.\n",
-    "\n",
-    "Read the paper [here](https://arxiv.org/abs/2310.06117)\n",
-    "\n",
-    "See an excellent blog post on this by Cobus Greyling [here](https://cobusgreyling.medium.com/a-new-prompt-engineering-technique-has-been-introduced-called-step-back-prompting-b00e8954cacb)\n",
-    "\n",
-    "In this cookbook we will replicate this technique. We modify the prompts used slightly to work better with chat models."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 85,
-   "id": "67b5cdac",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.prompts import ChatPromptTemplate, FewShotChatMessagePromptTemplate\n",
-    "from langchain.schema.output_parser import StrOutputParser\n",
-    "from langchain.schema.runnable import RunnableLambda"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 86,
-   "id": "7e017c44",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Few Shot Examples\n",
-    "examples = [\n",
-    "    {\n",
-    "        \"input\": \"Could the members of The Police perform lawful arrests?\",\n",
-    "        \"output\": \"what can the members of The Police do?\"\n",
-    "    },\n",
-    "    {\n",
-    "        \"input\": \"Jan Sindel’s was born in what country?\", \n",
-    "        \"output\": \"what is Jan Sindel’s personal history?\"\n",
-    "    },\n",
-    "]\n",
-    "# We now transform these to example messages\n",
-    "example_prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"human\", \"{input}\"),\n",
-    "        (\"ai\", \"{output}\"),\n",
-    "    ]\n",
-    ")\n",
-    "few_shot_prompt = FewShotChatMessagePromptTemplate(\n",
-    "    example_prompt=example_prompt,\n",
-    "    examples=examples,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 87,
-   "id": "206415ee",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "prompt = ChatPromptTemplate.from_messages([\n",
-    "    (\"system\", \"\"\"You are an expert at world knowledge. Your task is to step back and paraphrase a question to a more generic step-back question, which is easier to answer. Here are a few examples:\"\"\"),\n",
-    "    # Few shot examples\n",
-    "    few_shot_prompt,\n",
-    "    # New question\n",
-    "    (\"user\", \"{question}\"),\n",
-    "])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 88,
-   "id": "d643a85c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "question_gen = prompt | ChatOpenAI(temperature=0) | StrOutputParser()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 182,
-   "id": "5ba21b2a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "question = \"was chatgpt around while trump was president?\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 183,
-   "id": "5992c8ca",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'when was ChatGPT developed?'"
-      ]
-     },
-     "execution_count": 183,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "question_gen.invoke({\"question\": question})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 190,
-   "id": "32667424",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.utilities import DuckDuckGoSearchAPIWrapper\n",
-    "\n",
-    "\n",
-    "search = DuckDuckGoSearchAPIWrapper(max_results=4)\n",
-    "\n",
-    "def retriever(query):\n",
-    "    return search.run(query)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 191,
-   "id": "ffc28c91",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'This includes content about former President Donald Trump. According to further tests, ChatGPT successfully wrote poems admiring all recent U.S. presidents, but failed when we entered a query for ... On Wednesday, a Twitter user posted screenshots of him asking OpenAI\\'s chatbot, ChatGPT, to write a positive poem about former President Donald Trump, to which the chatbot declined, citing it ... While impressive in many respects, ChatGPT also has some major flaws. ... [President\\'s Name],\" refused to write a poem about ex-President Trump, but wrote one about President Biden ... During the Trump administration, Altman gained new attention as a vocal critic of the president. It was against that backdrop that he was rumored to be considering a run for California governor.'"
-      ]
-     },
-     "execution_count": 191,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "retriever(question)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 192,
-   "id": "00c77443",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\"Will Douglas Heaven March 3, 2023 Stephanie Arnett/MITTR | Envato When OpenAI launched ChatGPT, with zero fanfare, in late November 2022, the San Francisco-based artificial-intelligence company... ChatGPT, which stands for Chat Generative Pre-trained Transformer, is a large language model -based chatbot developed by OpenAI and launched on November 30, 2022, which enables users to refine and steer a conversation towards a desired length, format, style, level of detail, and language. ChatGPT is an artificial intelligence (AI) chatbot built on top of OpenAI's foundational large language models (LLMs) like GPT-4 and its predecessors. This chatbot has redefined the standards of... June 4, 2023 ⋅ 4 min read 124 SHARES 13K At the end of 2022, OpenAI introduced the world to ChatGPT. Since its launch, ChatGPT hasn't shown significant signs of slowing down in developing new...\""
-      ]
-     },
-     "execution_count": 192,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "retriever(question_gen.invoke({\"question\": question}))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 193,
-   "id": "b257bc06",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# response_prompt_template = \"\"\"You are an expert of world knowledge. I am going to ask you a question. Your response should be comprehensive and not contradicted with the following context if they are relevant. Otherwise, ignore them if they are not relevant.\n",
-    "\n",
-    "# {normal_context}\n",
-    "# {step_back_context}\n",
-    "\n",
-    "# Original Question: {question}\n",
-    "# Answer:\"\"\"\n",
-    "# response_prompt = ChatPromptTemplate.from_template(response_prompt_template)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 203,
-   "id": "f48c65b2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain import hub\n",
-    "\n",
-    "response_prompt = hub.pull(\"langchain-ai/stepback-answer\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 204,
-   "id": "97a6d5ab",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = {\n",
-    "    # Retrieve context using the normal question\n",
-    "    \"normal_context\": RunnableLambda(lambda x: x['question']) | retriever,\n",
-    "    # Retrieve context using the step-back question\n",
-    "    \"step_back_context\": question_gen | retriever,\n",
-    "    # Pass on the question\n",
-    "    \"question\": lambda x: x[\"question\"]\n",
-    "} | response_prompt | ChatOpenAI(temperature=0) | StrOutputParser()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 205,
-   "id": "ce554cb0",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\"No, ChatGPT was not around while Donald Trump was president. ChatGPT was launched on November 30, 2022, which is after Donald Trump's presidency. The context provided mentions that during the Trump administration, Altman, the CEO of OpenAI, gained attention as a vocal critic of the president. This suggests that ChatGPT was not developed or available during that time.\""
-      ]
-     },
-     "execution_count": 205,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke({\"question\": question})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "a9fb8dd2",
-   "metadata": {},
-   "source": [
-    "## Baseline"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 206,
-   "id": "00db8a15",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "response_prompt_template = \"\"\"You are an expert of world knowledge. I am going to ask you a question. Your response should be comprehensive and not contradicted with the following context if they are relevant. Otherwise, ignore them if they are not relevant.\n",
-    "\n",
-    "{normal_context}\n",
-    "\n",
-    "Original Question: {question}\n",
-    "Answer:\"\"\"\n",
-    "response_prompt = ChatPromptTemplate.from_template(response_prompt_template)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 207,
-   "id": "06335ebb",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = {\n",
-    "    # Retrieve context using the normal question (only the first 3 results)\n",
-    "    \"normal_context\": RunnableLambda(lambda x: x['question']) | retriever,\n",
-    "    # Pass on the question\n",
-    "    \"question\": lambda x: x[\"question\"]\n",
-    "} | response_prompt | ChatOpenAI(temperature=0) | StrOutputParser()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 208,
-   "id": "15e0e741",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\"Yes, ChatGPT was around while Donald Trump was president. However, it is important to note that the specific context you provided mentions that ChatGPT refused to write a positive poem about former President Donald Trump. This suggests that while ChatGPT was available during Trump's presidency, it may have had limitations or biases in its responses regarding him.\""
-      ]
-     },
-     "execution_count": 208,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke({\"question\": question})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "e7b9e5d6",
-   "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
-}

docker/Dockerfile.base

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

docs/.local_build.sh

@@ -8,13 +8,11 @@ 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
-cp ../cookbook/README.md src/pages/cookbook.mdx
-cp ../.github/CONTRIBUTING.md docs/contributing.md
-poetry run python scripts/generate_api_reference_links.py
+mkdir -p _dist/docs_skeleton
+cp -r {docs_skeleton,snippets} _dist
+cp -r extras/* _dist/docs_skeleton/docs
+cd _dist/docs_skeleton
+poetry run nbdoc_build
+poetry run python generate_api_reference_links.py
 yarn install
 yarn start

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

@@ -156,7 +156,7 @@ 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

@@ -3,7 +3,7 @@ import importlib
 import inspect
 import typing
 from pathlib import Path
-from typing import TypedDict, Sequence, List, Dict, Literal, Union, Optional
+from typing import TypedDict, Sequence, List, Dict, Literal, Union
 from enum import Enum
 
 from pydantic import BaseModel
@@ -122,7 +122,7 @@ def _merge_module_members(
 
 
 def _load_package_modules(
-    package_directory: Union[str, Path], submodule: Optional[str] = None
+    package_directory: Union[str, Path]
 ) -> Dict[str, ModuleMembers]:
     """Recursively load modules of a package based on the file system.
 
@@ -131,7 +131,6 @@ def _load_package_modules(
 
     Parameters:
         package_directory: Path to the package directory.
-        submodule: Optional name of submodule to load.
 
     Returns:
         list: A list of loaded module objects.
@@ -143,53 +142,33 @@ def _load_package_modules(
     )
     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
+        if not file_path.name.startswith("__"):
+            relative_module_name = file_path.relative_to(package_path)
+            # 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]
 
-        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:
+            try:
                 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
+                # 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
+                modules_by_namespace[top_namespace] = _module_members
 
-        except ImportError as e:
-            print(f"Error: Unable to import module '{namespace}' with error: {e}")
+            except ImportError as e:
+                print(f"Error: Unable to import module '{namespace}' with error: {e}")
 
     return modules_by_namespace
 
@@ -242,10 +221,10 @@ Classes
     :toctree: {module}
 """
 
-            for class_ in sorted(classes, key=lambda c: c["qualified_name"]):
-                if not class_["is_public"]:
+            for class_ in classes:
+                if not class_['is_public']:
                     continue
-
+                    
                 if class_["kind"] == "TypedDict":
                     template = "typeddict.rst"
                 elif class_["kind"] == "enum":
@@ -280,9 +259,12 @@ Functions
     return full_doc
 
 
-def _document_langchain_experimental() -> None:
-    """Document the langchain_experimental package."""
-    # Generate experimental_api_reference.rst
+def main() -> None:
+    """Generate the reference.rst file for each package."""
+    lc_members = _load_package_modules(PKG_DIR)
+    lc_doc = ".. _api_reference:\n\n" + _construct_doc("langchain", lc_members)
+    with open(WRITE_FILE, "w") as f:
+        f.write(lc_doc)
     exp_members = _load_package_modules(EXP_DIR)
     exp_doc = ".. _experimental_api_reference:\n\n" + _construct_doc(
         "langchain_experimental", exp_members
@@ -291,36 +273,5 @@ def _document_langchain_experimental() -> None:
         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()
-
-
 if __name__ == "__main__":
     main()

docs/api_reference/requirements.txt

@@ -1,6 +1,5 @@
 -e libs/langchain
 -e libs/experimental
-pydantic<2
 autodoc_pydantic==1.8.0
 myst_parser
 nbsphinx==0.8.9

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/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/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/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
-}

docs/docs/expression_language/how_to/configure.ipynb

@@ -1,594 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "39eaf61b",
-   "metadata": {},
-   "source": [
-    "# Configuration\n",
-    "\n",
-    "Oftentimes you may want to experiment with, or even expose to the end user, multiple different ways of doing things.\n",
-    "In order to make this experience as easy as possible, we have defined two methods.\n",
-    "\n",
-    "First, a `configurable_fields` method. \n",
-    "This lets you configure particular fields of a runnable.\n",
-    "\n",
-    "Second, a `configurable_alternatives` method.\n",
-    "With this method, you can list out alternatives for any particular runnable that can be set during runtime."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f2347a11",
-   "metadata": {},
-   "source": [
-    "## Configuration Fields"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "a06f6e2d",
-   "metadata": {},
-   "source": [
-    "### With LLMs\n",
-    "With LLMs we can configure things like temperature"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 35,
-   "id": "7ba735f4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.prompts import PromptTemplate\n",
-    "\n",
-    "model = ChatOpenAI(temperature=0).configurable_fields(\n",
-    "    temperature=ConfigurableField(\n",
-    "        id=\"llm_temperature\",\n",
-    "        name=\"LLM Temperature\",\n",
-    "        description=\"The temperature of the LLM\",\n",
-    "    )\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 38,
-   "id": "63a71165",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='7')"
-      ]
-     },
-     "execution_count": 38,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "model.invoke(\"pick a random number\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 39,
-   "id": "4f83245c",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='34')"
-      ]
-     },
-     "execution_count": 39,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "model.with_config(configurable={\"llm_temperature\": .9}).invoke(\"pick a random number\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "9da1fcd2",
-   "metadata": {},
-   "source": [
-    "We can also do this when its used as part of a chain"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 40,
-   "id": "e75ae678",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "prompt = PromptTemplate.from_template(\"Pick a random number above {x}\")\n",
-    "chain = prompt | model"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 41,
-   "id": "44886071",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='57')"
-      ]
-     },
-     "execution_count": 41,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke({\"x\": 0})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 42,
-   "id": "c09fac15",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='6')"
-      ]
-     },
-     "execution_count": 42,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.with_config(configurable={\"llm_temperature\": .9}).invoke({\"x\": 0})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "fb9637d0",
-   "metadata": {},
-   "source": [
-    "### With HubRunnables\n",
-    "\n",
-    "This is useful to allow for switching of prompts"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 43,
-   "id": "7d5836b2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.runnables.hub import HubRunnable"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 46,
-   "id": "9a9ea077",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "prompt = HubRunnable(\"rlm/rag-prompt\").configurable_fields(\n",
-    "    owner_repo_commit=ConfigurableField(\n",
-    "        id=\"hub_commit\",\n",
-    "        name=\"Hub Commit\",\n",
-    "        description=\"The Hub commit to pull from\",\n",
-    "    )\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 47,
-   "id": "c4a62cee",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "ChatPromptValue(messages=[HumanMessage(content=\"You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question. If you don't know the answer, just say that you don't know. Use three sentences maximum and keep the answer concise.\\nQuestion: foo \\nContext: bar \\nAnswer:\")])"
-      ]
-     },
-     "execution_count": 47,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "prompt.invoke({\"question\": \"foo\", \"context\": \"bar\"})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 49,
-   "id": "f33f3cf2",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "ChatPromptValue(messages=[HumanMessage(content=\"[INST]<<SYS>> You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question. If you don't know the answer, just say that you don't know. Use three sentences maximum and keep the answer concise.<</SYS>> \\nQuestion: foo \\nContext: bar \\nAnswer: [/INST]\")])"
-      ]
-     },
-     "execution_count": 49,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "prompt.with_config(configurable={\"hub_commit\": \"rlm/rag-prompt-llama\"}).invoke({\"question\": \"foo\", \"context\": \"bar\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "79d51519",
-   "metadata": {},
-   "source": [
-    "## Configurable Alternatives\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "ac733d35",
-   "metadata": {},
-   "source": [
-    "### With LLMs\n",
-    "\n",
-    "Let's take a look at doing this with LLMs"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "430ab8cc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chat_models import ChatOpenAI, ChatAnthropic\n",
-    "from langchain.schema.runnable import ConfigurableField\n",
-    "from langchain.prompts import PromptTemplate"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "71248a9f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm = ChatAnthropic(temperature=0).configurable_alternatives(\n",
-    "    # This gives this field an id\n",
-    "    # When configuring the end runnable, we can then use this id to configure this field\n",
-    "    ConfigurableField(id=\"llm\"),\n",
-    "    # This sets a default_key.\n",
-    "    # If we specify this key, the default LLM (ChatAnthropic initialized above) will be used\n",
-    "    default_key=\"anthropic\",\n",
-    "    # This adds a new option, with name `openai` that is equal to `ChatOpenAI()`\n",
-    "    openai=ChatOpenAI(),\n",
-    "    # This adds a new option, with name `gpt4` that is equal to `ChatOpenAI(model=\"gpt-4\")`\n",
-    "    gpt4=ChatOpenAI(model=\"gpt-4\"),\n",
-    "    # You can add more configuration options here\n",
-    ")\n",
-    "prompt = PromptTemplate.from_template(\"Tell me a joke about {topic}\")\n",
-    "chain = prompt | llm"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "id": "e598b1f1",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\" Here's a silly joke about bears:\\n\\nWhat do you call a bear with no teeth?\\nA gummy bear!\")"
-      ]
-     },
-     "execution_count": 19,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# By default it will call Anthropic\n",
-    "chain.invoke({\"topic\": \"bears\"})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 20,
-   "id": "48b45337",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"Sure, here's a bear joke for you:\\n\\nWhy don't bears wear shoes?\\n\\nBecause they already have bear feet!\")"
-      ]
-     },
-     "execution_count": 20,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# We can use `.with_config(configurable={\"llm\": \"openai\"})` to specify an llm to use\n",
-    "chain.with_config(configurable={\"llm\": \"openai\"}).invoke({\"topic\": \"bears\"})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 21,
-   "id": "42647fb7",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\" Here's a silly joke about bears:\\n\\nWhat do you call a bear with no teeth?\\nA gummy bear!\")"
-      ]
-     },
-     "execution_count": 21,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# If we use the `default_key` then it uses the default\n",
-    "chain.with_config(configurable={\"llm\": \"anthropic\"}).invoke({\"topic\": \"bears\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "a9134559",
-   "metadata": {},
-   "source": [
-    "### With Prompts\n",
-    "\n",
-    "We can do a similar thing, but alternate between prompts\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 25,
-   "id": "9f6a7c6c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm = ChatAnthropic(temperature=0)\n",
-    "prompt = PromptTemplate.from_template(\"Tell me a joke about {topic}\").configurable_alternatives(\n",
-    "    # This gives this field an id\n",
-    "    # When configuring the end runnable, we can then use this id to configure this field\n",
-    "    ConfigurableField(id=\"prompt\"),\n",
-    "    # This sets a default_key.\n",
-    "    # If we specify this key, the default LLM (ChatAnthropic initialized above) will be used\n",
-    "    default_key=\"joke\",\n",
-    "    # This adds a new option, with name `poem`\n",
-    "    poem=PromptTemplate.from_template(\"Write a short poem about {topic}\"),\n",
-    "    # You can add more configuration options here\n",
-    ")\n",
-    "chain = prompt | llm"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 26,
-   "id": "97eda915",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\" Here's a silly joke about bears:\\n\\nWhat do you call a bear with no teeth?\\nA gummy bear!\")"
-      ]
-     },
-     "execution_count": 26,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# By default it will write a joke\n",
-    "chain.invoke({\"topic\": \"bears\"})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 27,
-   "id": "927297a1",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=' Here is a short poem about bears:\\n\\nThe bears awaken from their sleep\\nAnd lumber out into the deep\\nForests filled with trees so tall\\nForaging for food before nightfall \\nTheir furry coats and claws so sharp\\nSniffing for berries and fish to nab\\nLumbering about without a care\\nThe mighty grizzly and black bear\\nProud creatures, wild and free\\nRuling their domain majestically\\nWandering the woods they call their own\\nBefore returning to their dens alone')"
-      ]
-     },
-     "execution_count": 27,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# We can configure it write a poem\n",
-    "chain.with_config(configurable={\"prompt\": \"poem\"}).invoke({\"topic\": \"bears\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0c77124e",
-   "metadata": {},
-   "source": [
-    "### With Prompts and LLMs\n",
-    "\n",
-    "We can also have multiple things configurable!\n",
-    "Here's an example doing that with both prompts and LLMs."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 28,
-   "id": "97538c23",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm = ChatAnthropic(temperature=0).configurable_alternatives(\n",
-    "    # This gives this field an id\n",
-    "    # When configuring the end runnable, we can then use this id to configure this field\n",
-    "    ConfigurableField(id=\"llm\"),\n",
-    "    # This sets a default_key.\n",
-    "    # If we specify this key, the default LLM (ChatAnthropic initialized above) will be used\n",
-    "    default_key=\"anthropic\",\n",
-    "    # This adds a new option, with name `openai` that is equal to `ChatOpenAI()`\n",
-    "    openai=ChatOpenAI(),\n",
-    "    # This adds a new option, with name `gpt4` that is equal to `ChatOpenAI(model=\"gpt-4\")`\n",
-    "    gpt4=ChatOpenAI(model=\"gpt-4\"),\n",
-    "    # You can add more configuration options here\n",
-    ")\n",
-    "prompt = PromptTemplate.from_template(\"Tell me a joke about {topic}\").configurable_alternatives(\n",
-    "    # This gives this field an id\n",
-    "    # When configuring the end runnable, we can then use this id to configure this field\n",
-    "    ConfigurableField(id=\"prompt\"),\n",
-    "    # This sets a default_key.\n",
-    "    # If we specify this key, the default LLM (ChatAnthropic initialized above) will be used\n",
-    "    default_key=\"joke\",\n",
-    "    # This adds a new option, with name `poem`\n",
-    "    poem=PromptTemplate.from_template(\"Write a short poem about {topic}\"),\n",
-    "    # You can add more configuration options here\n",
-    ")\n",
-    "chain = prompt | llm"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 29,
-   "id": "1dcc7ccc",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"In the forest, where tall trees sway,\\nA creature roams, both fierce and gray.\\nWith mighty paws and piercing eyes,\\nThe bear, a symbol of strength, defies.\\n\\nThrough snow-kissed mountains, it does roam,\\nA guardian of its woodland home.\\nWith fur so thick, a shield of might,\\nIt braves the coldest winter night.\\n\\nA gentle giant, yet wild and free,\\nThe bear commands respect, you see.\\nWith every step, it leaves a trace,\\nOf untamed power and ancient grace.\\n\\nFrom honeyed feast to salmon's leap,\\nIt takes its place, in nature's keep.\\nA symbol of untamed delight,\\nThe bear, a wonder, day and night.\\n\\nSo let us honor this noble beast,\\nIn forests where its soul finds peace.\\nFor in its presence, we come to know,\\nThe untamed spirit that in us also flows.\")"
-      ]
-     },
-     "execution_count": 29,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# We can configure it write a poem with OpenAI\n",
-    "chain.with_config(configurable={\"prompt\": \"poem\", \"llm\": \"openai\"}).invoke({\"topic\": \"bears\"})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 30,
-   "id": "e4ee9fbc",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"Sure, here's a bear joke for you:\\n\\nWhy don't bears wear shoes?\\n\\nBecause they have bear feet!\")"
-      ]
-     },
-     "execution_count": 30,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# We can always just configure only one if we want\n",
-    "chain.with_config(configurable={\"llm\": \"openai\"}).invoke({\"topic\": \"bears\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "02fc4841",
-   "metadata": {},
-   "source": [
-    "### Saving configurations\n",
-    "\n",
-    "We can also easily save configured chains as their own objects"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 31,
-   "id": "5cf53202",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "openai_poem = chain.with_config(configurable={\"llm\": \"openai\"})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 32,
-   "id": "9486d701",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"Why don't bears wear shoes?\\n\\nBecause they have bear feet!\")"
-      ]
-     },
-     "execution_count": 32,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "openai_poem.invoke({\"topic\": \"bears\"})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "a43e3b70",
-   "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/how_to/fallbacks.ipynb

@@ -1,285 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "19c9cbd6",
-   "metadata": {},
-   "source": [
-    "# Add fallbacks\n",
-    "\n",
-    "There are many possible points of failure in an LLM application, whether that be issues with LLM API's, poor model outputs, issues with other integrations, etc. Fallbacks help you gracefully handle and isolate these issues.\n",
-    "\n",
-    "Crucially, fallbacks can be applied not only on the LLM level but on the whole runnable level."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "a6bb9ba9",
-   "metadata": {},
-   "source": [
-    "## Handling LLM API Errors\n",
-    "\n",
-    "This is maybe the most common use case for fallbacks. A request to an LLM API can fail for a variety of reasons - the API could be down, you could have hit rate limits, any number of things. Therefore, using fallbacks can help protect against these types of things.\n",
-    "\n",
-    "IMPORTANT: By default, a lot of the LLM wrappers catch errors and retry. You will most likely want to turn those off when working with fallbacks. Otherwise the first wrapper will keep on retrying and not failing."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "d3e893bf",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chat_models import ChatOpenAI, ChatAnthropic"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "4847c82d",
-   "metadata": {},
-   "source": [
-    "First, let's mock out what happens if we hit a RateLimitError from OpenAI"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "dfdd8bf5",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from unittest.mock import patch\n",
-    "from openai.error import RateLimitError"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "e6fdffc1",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Note that we set max_retries = 0 to avoid retrying on RateLimits, etc\n",
-    "openai_llm = ChatOpenAI(max_retries=0)\n",
-    "anthropic_llm = ChatAnthropic()\n",
-    "llm = openai_llm.with_fallbacks([anthropic_llm])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 27,
-   "id": "584461ab",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Hit error\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Let's use just the OpenAI LLm first, to show that we run into an error\n",
-    "with patch('openai.ChatCompletion.create', side_effect=RateLimitError()):\n",
-    "    try:\n",
-    "         print(openai_llm.invoke(\"Why did the chicken cross the road?\"))\n",
-    "    except:\n",
-    "        print(\"Hit error\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 28,
-   "id": "4fc1e673",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "content=' I don\\'t actually know why the chicken crossed the road, but here are some possible humorous answers:\\n\\n- To get to the other side!\\n\\n- It was too chicken to just stand there. \\n\\n- It wanted a change of scenery.\\n\\n- It wanted to show the possum it could be done.\\n\\n- It was on its way to a poultry farmers\\' convention.\\n\\nThe joke plays on the double meaning of \"the other side\" - literally crossing the road to the other side, or the \"other side\" meaning the afterlife. So it\\'s an anti-joke, with a silly or unexpected pun as the answer.' additional_kwargs={} example=False\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Now let's try with fallbacks to Anthropic\n",
-    "with patch('openai.ChatCompletion.create', side_effect=RateLimitError()):\n",
-    "    try:\n",
-    "         print(llm.invoke(\"Why did the chicken cross the road?\"))\n",
-    "    except:\n",
-    "        print(\"Hit error\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f00bea25",
-   "metadata": {},
-   "source": [
-    "We can use our \"LLM with Fallbacks\" as we would a normal LLM."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "4f8eaaa0",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "content=\" I don't actually know why the kangaroo crossed the road, but I'm happy to take a guess! Maybe the kangaroo was trying to get to the other side to find some tasty grass to eat. Or maybe it was trying to get away from a predator or other danger. Kangaroos do need to cross roads and other open areas sometimes as part of their normal activities. Whatever the reason, I'm sure the kangaroo looked both ways before hopping across!\" additional_kwargs={} example=False\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain.prompts import ChatPromptTemplate\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", \"You're a nice assistant who always includes a compliment in your response\"),\n",
-    "        (\"human\", \"Why did the {animal} cross the road\"),\n",
-    "    ]\n",
-    ")\n",
-    "chain = prompt | llm\n",
-    "with patch('openai.ChatCompletion.create', side_effect=RateLimitError()):\n",
-    "    try:\n",
-    "         print(chain.invoke({\"animal\": \"kangaroo\"}))\n",
-    "    except:\n",
-    "        print(\"Hit error\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "ef9f0f39-0b9f-4723-a394-f61c98c75d41",
-   "metadata": {},
-   "source": [
-    "### Specifying errors to handle\n",
-    "\n",
-    "We can also specify the errors to handle if we want to be more specific about when the fallback is invoked:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "e4069ca4-1c16-4915-9a8c-b2732869ae27",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Hit error\n"
-     ]
-    }
-   ],
-   "source": [
-    "llm = openai_llm.with_fallbacks([anthropic_llm], exceptions_to_handle=(KeyboardInterrupt,))\n",
-    "\n",
-    "chain = prompt | llm\n",
-    "with patch('openai.ChatCompletion.create', side_effect=RateLimitError()):\n",
-    "    try:\n",
-    "         print(chain.invoke({\"animal\": \"kangaroo\"}))\n",
-    "    except:\n",
-    "        print(\"Hit error\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "8d62241b",
-   "metadata": {},
-   "source": [
-    "## Fallbacks for Sequences\n",
-    "\n",
-    "We can also create fallbacks for sequences, that are sequences themselves. Here we do that with two different models: ChatOpenAI and then normal OpenAI (which does not use a chat model). Because OpenAI is NOT a chat model, you likely want a different prompt."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 30,
-   "id": "6d0b8056",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# First let's create a chain with a ChatModel\n",
-    "# We add in a string output parser here so the outputs between the two are the same type\n",
-    "from langchain.schema.output_parser import StrOutputParser\n",
-    "\n",
-    "chat_prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", \"You're a nice assistant who always includes a compliment in your response\"),\n",
-    "        (\"human\", \"Why did the {animal} cross the road\"),\n",
-    "    ]\n",
-    ")\n",
-    "# Here we're going to use a bad model name to easily create a chain that will error\n",
-    "chat_model = ChatOpenAI(model_name=\"gpt-fake\")\n",
-    "bad_chain = chat_prompt | chat_model | StrOutputParser()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 31,
-   "id": "8d1fc2a5",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Now lets create a chain with the normal OpenAI model\n",
-    "from langchain.llms import OpenAI\n",
-    "from langchain.prompts import PromptTemplate\n",
-    "\n",
-    "prompt_template = \"\"\"Instructions: You should always include a compliment in your response.\n",
-    "\n",
-    "Question: Why did the {animal} cross the road?\"\"\"\n",
-    "prompt = PromptTemplate.from_template(prompt_template)\n",
-    "llm = OpenAI()\n",
-    "good_chain = prompt | llm"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 32,
-   "id": "283bfa44",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'\\n\\nAnswer: The turtle crossed the road to get to the other side, and I have to say he had some impressive determination.'"
-      ]
-     },
-     "execution_count": 32,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# We can now create a final chain which combines the two\n",
-    "chain = bad_chain.with_fallbacks([good_chain])\n",
-    "chain.invoke({\"animal\": \"turtle\"})"
-   ]
-  }
- ],
- "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/how_to/functions.ipynb

@@ -1,171 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "fbc4bf6e",
-   "metadata": {},
-   "source": [
-    "# Run arbitrary functions\n",
-    "\n",
-    "You can use arbitrary functions in the pipeline\n",
-    "\n",
-    "Note that all inputs to these functions need to be a SINGLE argument. If you have a function that accepts multiple arguments, you should write a wrapper that accepts a single input and unpacks it into multiple argument."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "6bb221b3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.schema.runnable import RunnableLambda\n",
-    "from langchain.prompts import ChatPromptTemplate\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from operator import itemgetter\n",
-    "\n",
-    "def length_function(text):\n",
-    "    return len(text)\n",
-    "\n",
-    "def _multiple_length_function(text1, text2):\n",
-    "    return len(text1) * len(text2)\n",
-    "\n",
-    "def multiple_length_function(_dict):\n",
-    "    return _multiple_length_function(_dict[\"text1\"], _dict[\"text2\"])\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_template(\"what is {a} + {b}\")\n",
-    "model = ChatOpenAI()\n",
-    "\n",
-    "chain1 = prompt | model\n",
-    "\n",
-    "chain = {\n",
-    "    \"a\": itemgetter(\"foo\") | RunnableLambda(length_function),\n",
-    "    \"b\": {\"text1\": itemgetter(\"foo\"), \"text2\": itemgetter(\"bar\")} | RunnableLambda(multiple_length_function)\n",
-    "} | prompt | model"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "5488ec85",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='3 + 9 equals 12.', additional_kwargs={}, example=False)"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke({\"foo\": \"bar\", \"bar\": \"gah\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "4728ddd9-914d-42ce-ae9b-72c9ce8ec940",
-   "metadata": {},
-   "source": [
-    "## Accepting a Runnable Config\n",
-    "\n",
-    "Runnable lambdas can optionally accept a [RunnableConfig](https://api.python.langchain.com/en/latest/schema/langchain.schema.runnable.config.RunnableConfig.html?highlight=runnableconfig#langchain.schema.runnable.config.RunnableConfig), which they can use to pass callbacks, tags, and other configuration information to nested runs."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "80b3b5f6-5d58-44b9-807e-cce9a46bf49f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.schema.runnable import RunnableConfig\n",
-    "from langchain.schema.output_parser import StrOutputParser"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "ff0daf0c-49dd-4d21-9772-e5fa133c5f36",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import json\n",
-    "\n",
-    "def parse_or_fix(text: str, config: RunnableConfig):\n",
-    "    fixing_chain = (\n",
-    "        ChatPromptTemplate.from_template(\n",
-    "            \"Fix the following text:\\n\\n```text\\n{input}\\n```\\nError: {error}\"\n",
-    "            \" Don't narrate, just respond with the fixed data.\"\n",
-    "        )\n",
-    "        | ChatOpenAI()\n",
-    "        | StrOutputParser()\n",
-    "    )\n",
-    "    for _ in range(3):\n",
-    "        try:\n",
-    "            return json.loads(text)\n",
-    "        except Exception as e:\n",
-    "            text = fixing_chain.invoke({\"input\": text, \"error\": e}, config)\n",
-    "    return \"Failed to parse\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "1a5e709e-9d75-48c7-bb9c-503251990505",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Tokens Used: 65\n",
-      "\tPrompt Tokens: 56\n",
-      "\tCompletion Tokens: 9\n",
-      "Successful Requests: 1\n",
-      "Total Cost (USD): $0.00010200000000000001\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain.callbacks import get_openai_callback\n",
-    "\n",
-    "with get_openai_callback() as cb:\n",
-    "    RunnableLambda(parse_or_fix).invoke(\"{foo: bar}\", {\"tags\": [\"my-tag\"], \"callbacks\": [cb]})\n",
-    "    print(cb)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "29f55c38",
-   "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/how_to/generators.ipynb

@@ -1,119 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Custom generator functions\n",
-    "\n",
-    "You can use generator functions (ie. functions that use the `yield` keyword, and behave like iterators) in a LCEL pipeline.\n",
-    "\n",
-    "The signature of these generators should be `Iterator[Input] -> Iterator[Output]`. Or for async generators: `AsyncIterator[Input] -> AsyncIterator[Output]`.\n",
-    "\n",
-    "These are useful for:\n",
-    "- implementing a custom output parser\n",
-    "- modifying the output of a previous step, while preserving streaming capabilities\n",
-    "\n",
-    "Let's implement a custom output parser for comma-separated lists."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "lion, tiger, wolf, gorilla, panda\n"
-     ]
-    }
-   ],
-   "source": [
-    "from typing import Iterator, List\n",
-    "\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.prompts.chat import ChatPromptTemplate\n",
-    "from langchain.schema.output_parser import StrOutputParser\n",
-    "\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_template(\n",
-    "    \"Write a comma-separated list of 5 animals similar to: {animal}\"\n",
-    ")\n",
-    "model = ChatOpenAI(temperature=0.0)\n",
-    "\n",
-    "\n",
-    "str_chain = prompt | model | StrOutputParser()\n",
-    "\n",
-    "print(str_chain.invoke({\"animal\": \"bear\"}))\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# This is a custom parser that splits an iterator of llm tokens\n",
-    "# into a list of strings separated by commas\n",
-    "def split_into_list(input: Iterator[str]) -> Iterator[List[str]]:\n",
-    "    # hold partial input until we get a comma\n",
-    "    buffer = \"\"\n",
-    "    for chunk in input:\n",
-    "        # add current chunk to buffer\n",
-    "        buffer += chunk\n",
-    "        # while there are commas in the buffer\n",
-    "        while \",\" in buffer:\n",
-    "            # split buffer on comma\n",
-    "            comma_index = buffer.index(\",\")\n",
-    "            # yield everything before the comma\n",
-    "            yield [buffer[:comma_index].strip()]\n",
-    "            # save the rest for the next iteration\n",
-    "            buffer = buffer[comma_index + 1 :]\n",
-    "    # yield the last chunk\n",
-    "    yield [buffer.strip()]\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "['lion', 'tiger', 'wolf', 'gorilla', 'panda']\n"
-     ]
-    }
-   ],
-   "source": [
-    "list_chain = str_chain | split_into_list\n",
-    "\n",
-    "print(list_chain.invoke({\"animal\": \"bear\"}))\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": "3.11.5"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

docs/docs/expression_language/how_to/map.ipynb

@@ -1,199 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "b022ab74-794d-4c54-ad47-ff9549ddb9d2",
-   "metadata": {},
-   "source": [
-    "# Use RunnableParallel/RunnableMap\n",
-    "\n",
-    "RunnableParallel (aka. RunnableMap) makes it easy to execute multiple Runnables in parallel, and to return the output of these Runnables as a map."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "7e1873d6-d4b6-43ac-96a1-edcf178201e0",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'joke': AIMessage(content=\"Why don't bears wear shoes? \\n\\nBecause they have bear feet!\", additional_kwargs={}, example=False),\n",
-       " 'poem': AIMessage(content=\"In woodland depths, bear prowls with might,\\nSilent strength, nature's sovereign, day and night.\", additional_kwargs={}, example=False)}"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.prompts import ChatPromptTemplate\n",
-    "from langchain.schema.runnable import RunnableParallel\n",
-    "\n",
-    "\n",
-    "model = ChatOpenAI()\n",
-    "joke_chain = ChatPromptTemplate.from_template(\"tell me a joke about {topic}\") | model\n",
-    "poem_chain = ChatPromptTemplate.from_template(\"write a 2-line poem about {topic}\") | model\n",
-    "\n",
-    "map_chain = RunnableParallel(joke=joke_chain, poem=poem_chain)\n",
-    "\n",
-    "map_chain.invoke({\"topic\": \"bear\"})\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "df867ae9-1cec-4c9e-9fef-21969b206af5",
-   "metadata": {},
-   "source": [
-    "## Manipulating outputs/inputs\n",
-    "Maps can be useful for manipulating the output of one Runnable to match the input format of the next Runnable in a sequence."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "267d1460-53c1-4fdb-b2c3-b6a1eb7fccff",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Harrison worked at Kensho.'"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain.embeddings import OpenAIEmbeddings\n",
-    "from langchain.schema.output_parser import StrOutputParser\n",
-    "from langchain.schema.runnable import RunnablePassthrough\n",
-    "from langchain.vectorstores import FAISS\n",
-    "\n",
-    "vectorstore = FAISS.from_texts([\"harrison worked at kensho\"], embedding=OpenAIEmbeddings())\n",
-    "retriever = vectorstore.as_retriever()\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",
-    "retrieval_chain = (\n",
-    "    {\"context\": retriever, \"question\": RunnablePassthrough()} \n",
-    "    | prompt \n",
-    "    | model \n",
-    "    | StrOutputParser()\n",
-    ")\n",
-    "\n",
-    "retrieval_chain.invoke(\"where did harrison work?\")\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "392cd4c4-e7ed-4ab8-934d-f7a4eca55ee1",
-   "metadata": {},
-   "source": [
-    "Here the input to prompt is expected to be a map with keys \"context\" and \"question\". The user input is just the question. So we need to get the context using our retriever and passthrough the user input under the \"question\" key.\n",
-    "\n",
-    "Note that when composing a RunnableMap when another Runnable we don't even need to wrap our dictionary in the RunnableMap class — the type conversion is handled for us."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "833da249-c0d4-4e5b-b3f8-cab549f0f7e1",
-   "metadata": {},
-   "source": [
-    "## Parallelism\n",
-    "\n",
-    "RunnableMaps are also useful for running independent processes in parallel, since each Runnable in the map is executed in parallel. For example, we can see our earlier `joke_chain`, `poem_chain` and `map_chain` all have about the same runtime, even though `map_chain` executes both of the other two."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "38e47834-45af-4281-991f-86f150001510",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "958 ms ± 402 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
-     ]
-    }
-   ],
-   "source": [
-    "%%timeit\n",
-    "\n",
-    "joke_chain.invoke({\"topic\": \"bear\"})\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "d0cd40de-b37e-41fa-a2f6-8aaa49f368d6",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "1.22 s ± 508 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
-     ]
-    }
-   ],
-   "source": [
-    "%%timeit\n",
-    "\n",
-    "poem_chain.invoke({\"topic\": \"bear\"})\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "799894e1-8e18-4a73-b466-f6aea6af3920",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "1.15 s ± 119 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
-     ]
-    }
-   ],
-   "source": [
-    "%%timeit\n",
-    "\n",
-    "map_chain.invoke({\"topic\": \"bear\"})\n"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.1"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/docs/expression_language/how_to/routing.ipynb

@@ -1,354 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "4b47436a",
-   "metadata": {},
-   "source": [
-    "# Route between multiple Runnables\n",
-    "\n",
-    "This notebook covers how to do routing in the LangChain Expression Language.\n",
-    "\n",
-    "Routing allows you to create non-deterministic chains where the output of a previous step defines the next step. Routing helps provide structure and consistency around interactions with LLMs.\n",
-    "\n",
-    "There are two ways to perform routing:\n",
-    "\n",
-    "1. Using a `RunnableBranch`.\n",
-    "2. Writing custom factory function that takes the input of a previous step and returns a **runnable**. Importantly, this should return a **runnable** and NOT actually execute.\n",
-    "\n",
-    "We'll illustrate both methods using a two step sequence where the first step classifies an input question as being about `LangChain`, `Anthropic`, or `Other`, then routes to a corresponding prompt chain."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f885113d",
-   "metadata": {},
-   "source": [
-    "## Using a RunnableBranch\n",
-    "\n",
-    "A `RunnableBranch` is initialized with a list of (condition, runnable) pairs and a default runnable. It selects which branch by passing each condition the input it's invoked with. It selects the first condition to evaluate to True, and runs the corresponding runnable to that condition with the input. \n",
-    "\n",
-    "If no provided conditions match, it runs the default runnable.\n",
-    "\n",
-    "Here's an example of what it looks like in action:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "1aa13c1d",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.prompts import PromptTemplate\n",
-    "from langchain.chat_models import ChatAnthropic\n",
-    "from langchain.schema.output_parser import StrOutputParser"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "ed84c59a",
-   "metadata": {},
-   "source": [
-    "First, let's create a chain that will identify incoming questions as being about `LangChain`, `Anthropic`, or `Other`:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "3ec03886",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = PromptTemplate.from_template(\"\"\"Given the user question below, classify it as either being about `LangChain`, `Anthropic`, or `Other`.\n",
-    "                                     \n",
-    "Do not respond with more than one word.\n",
-    "\n",
-    "<question>\n",
-    "{question}\n",
-    "</question>\n",
-    "\n",
-    "Classification:\"\"\") | ChatAnthropic() | StrOutputParser()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "87ae7c1c",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "' Anthropic'"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke({\"question\": \"how do I call Anthropic?\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "8aa0a365",
-   "metadata": {},
-   "source": [
-    "Now, let's create three sub chains:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "d479962a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "langchain_chain = PromptTemplate.from_template(\"\"\"You are an expert in langchain. \\\n",
-    "Always answer questions starting with \"As Harrison Chase told me\". \\\n",
-    "Respond to the following question:\n",
-    "\n",
-    "Question: {question}\n",
-    "Answer:\"\"\") | ChatAnthropic()\n",
-    "anthropic_chain = PromptTemplate.from_template(\"\"\"You are an expert in anthropic. \\\n",
-    "Always answer questions starting with \"As Dario Amodei told me\". \\\n",
-    "Respond to the following question:\n",
-    "\n",
-    "Question: {question}\n",
-    "Answer:\"\"\") | ChatAnthropic()\n",
-    "general_chain = PromptTemplate.from_template(\"\"\"Respond to the following question:\n",
-    "\n",
-    "Question: {question}\n",
-    "Answer:\"\"\") | ChatAnthropic()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "593eab06",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.schema.runnable import RunnableBranch\n",
-    "\n",
-    "branch = RunnableBranch(\n",
-    "  (lambda x: \"anthropic\" in x[\"topic\"].lower(), anthropic_chain),\n",
-    "  (lambda x: \"langchain\" in x[\"topic\"].lower(), langchain_chain),\n",
-    "  general_chain\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "752c732e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "full_chain = {\n",
-    "    \"topic\": chain,\n",
-    "    \"question\": lambda x: x[\"question\"]\n",
-    "} | branch"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "29231bb8",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\" As Dario Amodei told me, here are some ways to use Anthropic:\\n\\n- Sign up for an account on Anthropic's website to access tools like Claude, Constitutional AI, and Writer. \\n\\n- Use Claude for tasks like email generation, customer service chat, and QA. Claude can understand natural language prompts and provide helpful responses.\\n\\n- Use Constitutional AI if you need an AI assistant that is harmless, honest, and helpful. It is designed to be safe and aligned with human values.\\n\\n- Use Writer to generate natural language content for things like marketing copy, stories, reports, and more. Give it a topic and prompt and it will create high-quality written content.\\n\\n- Check out Anthropic's documentation and blog for tips, tutorials, examples, and announcements about new capabilities as they continue to develop their AI technology.\\n\\n- Follow Anthropic on social media or subscribe to their newsletter to stay up to date on new features and releases.\\n\\n- For most people, the easiest way to leverage Anthropic's technology is through their website - just create an account to get started!\", additional_kwargs={}, example=False)"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "full_chain.invoke({\"question\": \"how do I use Anthropic?\"})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "c67d8733",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=' As Harrison Chase told me, here is how you use LangChain:\\n\\nLangChain is an AI assistant that can have conversations, answer questions, and generate text. To use LangChain, you simply type or speak your input and LangChain will respond. \\n\\nYou can ask LangChain questions, have discussions, get summaries or explanations about topics, and request it to generate text on a subject. Some examples of interactions:\\n\\n- Ask general knowledge questions and LangChain will try to answer factually. For example \"What is the capital of France?\"\\n\\n- Have conversations on topics by taking turns speaking. You can prompt the start of a conversation by saying something like \"Let\\'s discuss machine learning\"\\n\\n- Ask for summaries or high-level explanations on subjects. For example \"Can you summarize the main themes in Shakespeare\\'s Hamlet?\" \\n\\n- Give creative writing prompts or requests to have LangChain generate text in different styles. For example \"Write a short children\\'s story about a mouse\" or \"Generate a poem in the style of Robert Frost about nature\"\\n\\n- Correct LangChain if it makes an inaccurate statement and provide the right information. This helps train it.\\n\\nThe key is interacting naturally and giving it clear prompts and requests', additional_kwargs={}, example=False)"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "full_chain.invoke({\"question\": \"how do I use LangChain?\"})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "935ad949",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=' 2 + 2 = 4', additional_kwargs={}, example=False)"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "full_chain.invoke({\"question\": \"whats 2 + 2\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "6d8d042c",
-   "metadata": {},
-   "source": [
-    "## Using a custom function\n",
-    "\n",
-    "You can also use a custom function to route between different outputs. Here's an example:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "687492da",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def route(info):\n",
-    "    if \"anthropic\" in info[\"topic\"].lower():\n",
-    "        return anthropic_chain\n",
-    "    elif \"langchain\" in info[\"topic\"].lower():\n",
-    "        return langchain_chain\n",
-    "    else:\n",
-    "        return general_chain"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "02a33c86",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.schema.runnable import RunnableLambda\n",
-    "\n",
-    "full_chain = {\n",
-    "    \"topic\": chain,\n",
-    "    \"question\": lambda x: x[\"question\"]\n",
-    "} | RunnableLambda(route)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "c2e977a4",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=' As Dario Amodei told me, to use Anthropic IPC you first need to import it:\\n\\n```python\\nfrom anthroipc import ic\\n```\\n\\nThen you can create a client and connect to the server:\\n\\n```python \\nclient = ic.connect()\\n```\\n\\nAfter that, you can call methods on the client and get responses:\\n\\n```python\\nresponse = client.ask(\"What is the meaning of life?\")\\nprint(response)\\n```\\n\\nYou can also register callbacks to handle events: \\n\\n```python\\ndef on_poke(event):\\n  print(\"Got poked!\")\\n\\nclient.on(\\'poke\\', on_poke)\\n```\\n\\nAnd that\\'s the basics of using the Anthropic IPC client library for Python! Let me know if you have any other questions!', additional_kwargs={}, example=False)"
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "full_chain.invoke({\"question\": \"how do I use Anthroipc?\"})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "48913dc6",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=' As Harrison Chase told me, to use LangChain you first need to sign up for an API key at platform.langchain.com. Once you have your API key, you can install the Python library and write a simple Python script to call the LangChain API. Here is some sample code to get started:\\n\\n```python\\nimport langchain\\n\\napi_key = \"YOUR_API_KEY\"\\n\\nlangchain.set_key(api_key)\\n\\nresponse = langchain.ask(\"What is the capital of France?\")\\n\\nprint(response.response)\\n```\\n\\nThis will send the question \"What is the capital of France?\" to the LangChain API and print the response. You can customize the request by providing parameters like max_tokens, temperature, etc. The LangChain Python library documentation has more details on the available options. The key things are getting an API key and calling langchain.ask() with your question text. Let me know if you have any other questions!', additional_kwargs={}, example=False)"
-      ]
-     },
-     "execution_count": 13,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "full_chain.invoke({\"question\": \"how do I use LangChain?\"})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "a14d0dca",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=' 4', additional_kwargs={}, example=False)"
-      ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "full_chain.invoke({\"question\": \"whats 2 + 2\"})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "46802d04",
-   "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/index.mdx

@@ -1,36 +0,0 @@
----
-sidebar_class_name: hidden
----
-
-# LangChain Expression Language (LCEL)
-
-LangChain Expression Language or LCEL is a declarative way to easily compose chains together.
-There are several benefits to writing chains in this manner (as opposed to writing normal code):
-
-**Async, Batch, and Streaming Support**
-Any chain constructed this way will automatically have full sync, async, batch, and streaming support.
-This makes it easy to prototype a chain in a Jupyter notebook using the sync interface, and then expose it as an async streaming interface.
-
-**Fallbacks**
-The non-determinism of LLMs makes it important to be able to handle errors gracefully.
-With LCEL you can easily attach fallbacks to any chain.
-
-**Parallelism**
-Since LLM applications involve (sometimes long) API calls, it often becomes important to run things in parallel.
-With LCEL syntax, any components that can be run in parallel automatically are.
-
-**Seamless LangSmith Tracing Integration**
-As your chains get more and more complex, it becomes increasingly important to understand what exactly is happening at every step.
-With LCEL, **all** steps are automatically logged to [LangSmith](https://smith.langchain.com) for maximal observability and debuggability.
-
-#### [Interface](/docs/expression_language/interface)
-The base interface shared by all LCEL objects
-
-#### [How to](/docs/expression_language/how_to)
-How to use core features of LCEL
-
-#### [Cookbook](/docs/expression_language/cookbook)
-Examples of common LCEL usage patterns
-
-#### [Why use LCEL](/docs/expression_language/why)
-A deeper dive into the benefits of LCEL

docs/docs/expression_language/why.mdx

@@ -1,11 +0,0 @@
-# Why use LCEL?
-
-The LangChain Expression Language was designed from day 1 to **support putting prototypes in production, with no code changes**, from the simplest “prompt + LLM” chain to the most complex chains (we’ve seen folks successfully running in production LCEL chains with 100s of steps). To highlight a few of the reasons you might want to use LCEL:
-
-- first-class support for streaming: when you build your chains with LCEL you get the best possible time-to-first-token (time elapsed until the first chunk of output comes out). For some chains this means eg. we stream tokens straight from an LLM to a streaming output parser, and you get back parsed, incremental chunks of output at the same rate as the LLM provider outputs the raw tokens. We’re constantly improving streaming support, recently we added a [streaming JSON parser](https://twitter.com/LangChainAI/status/1709690468030914584), and more is in the works.
-- first-class async support: any chain built with LCEL can be called both with the synchronous API (eg. in your Jupyter notebook while prototyping) as well as with the asynchronous API (eg. in a [LangServe](https://github.com/langchain-ai/langserve) server). This enables using the same code for prototypes and in production, with great performance, and the ability to handle many concurrent requests in the same server.
-- optimised parallel execution: whenever your LCEL chains have steps that can be executed in parallel (eg if you fetch documents from multiple retrievers) we automatically do it, both in the sync and the async interfaces, for the smallest possible latency.
-- support for retries and fallbacks: more recently we’ve added support for configuring retries and fallbacks for any part of your LCEL chain. This is a great way to make your chains more reliable at scale. We’re currently working on adding streaming support for retries/fallbacks, so you can get the added reliability without any latency cost.
-- accessing intermediate results: for more complex chains it’s often very useful to access the results of intermediate steps even before the final output is produced. This can be used let end-users know something is happening, or even just to debug your chain. We’ve added support for [streaming intermediate results](https://x.com/LangChainAI/status/1711806009097044193?s=20), and it’s available on every LangServe server.
-- [input and output schemas](https://x.com/LangChainAI/status/1711805322195861934?s=20): input and output schemas give every LCEL chain Pydantic and JSONSchema schemas inferred from the structure of your chain. This can be used for validation of inputs and outputs, and is an integral part of LangServe.
-- tracing with LangSmith: all chains built with LCEL have first-class tracing support, which can be used to debug your chains, or to understand what’s happening in production. To enable this all you have to do is add your [LangSmith](https://www.langchain.com/langsmith) API key as an environment variable.

docs/docs/guides/adapters/_category_.yml

@@ -1 +0,0 @@
-label: 'Adapters'

docs/docs/guides/adapters/openai.ipynb

@@ -1,323 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "700a516b",
-   "metadata": {},
-   "source": [
-    "# OpenAI Adapter\n",
-    "\n",
-    "A lot of people get started with OpenAI but want to explore other models. LangChain's integrations with many model providers make this easy to do so. While LangChain has it's own message and model APIs, we've also made it as easy as possible to explore other models by exposing an adapter to adapt LangChain models to the OpenAI api.\n",
-    "\n",
-    "At the moment this only deals with output and does not return other information (token counts, stop reasons, etc)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "6017f26a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import openai\n",
-    "from langchain.adapters import openai as lc_openai"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "b522ceda",
-   "metadata": {},
-   "source": [
-    "## ChatCompletion.create"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 29,
-   "id": "1d22eb61",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "messages = [{\"role\": \"user\", \"content\": \"hi\"}]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "d550d3ad",
-   "metadata": {},
-   "source": [
-    "Original OpenAI call"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "e1d27dfa",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "result = openai.ChatCompletion.create(\n",
-    "    messages=messages, \n",
-    "    model=\"gpt-3.5-turbo\", \n",
-    "    temperature=0\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "012d81ae",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'role': 'assistant', 'content': 'Hello! How can I assist you today?'}"
-      ]
-     },
-     "execution_count": 15,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "result[\"choices\"][0]['message'].to_dict_recursive()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "db5b5500",
-   "metadata": {},
-   "source": [
-    "LangChain OpenAI wrapper call"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "87c2d515",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "lc_result = lc_openai.ChatCompletion.create(\n",
-    "    messages=messages, \n",
-    "    model=\"gpt-3.5-turbo\", \n",
-    "    temperature=0\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "c67a5ac8",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'role': 'assistant', 'content': 'Hello! How can I assist you today?'}"
-      ]
-     },
-     "execution_count": 17,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "lc_result[\"choices\"][0]['message']"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "034ba845",
-   "metadata": {},
-   "source": [
-    "Swapping out model providers"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "7a2c011c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "lc_result = lc_openai.ChatCompletion.create(\n",
-    "    messages=messages, \n",
-    "    model=\"claude-2\", \n",
-    "    temperature=0, \n",
-    "    provider=\"ChatAnthropic\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "id": "f7c94827",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'role': 'assistant', 'content': ' Hello!'}"
-      ]
-     },
-     "execution_count": 19,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "lc_result[\"choices\"][0]['message']"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "cb3f181d",
-   "metadata": {},
-   "source": [
-    "## ChatCompletion.stream"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f7b8cd18",
-   "metadata": {},
-   "source": [
-    "Original OpenAI call"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 24,
-   "id": "fd8cb1ea",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'role': 'assistant', 'content': ''}\n",
-      "{'content': 'Hello'}\n",
-      "{'content': '!'}\n",
-      "{'content': ' How'}\n",
-      "{'content': ' can'}\n",
-      "{'content': ' I'}\n",
-      "{'content': ' assist'}\n",
-      "{'content': ' you'}\n",
-      "{'content': ' today'}\n",
-      "{'content': '?'}\n",
-      "{}\n"
-     ]
-    }
-   ],
-   "source": [
-    "for c in openai.ChatCompletion.create(\n",
-    "    messages = messages,\n",
-    "    model=\"gpt-3.5-turbo\", \n",
-    "    temperature=0,\n",
-    "    stream=True\n",
-    "):\n",
-    "    print(c[\"choices\"][0]['delta'].to_dict_recursive())"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0b2a076b",
-   "metadata": {},
-   "source": [
-    "LangChain OpenAI wrapper call"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 30,
-   "id": "9521218c",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'role': 'assistant', 'content': ''}\n",
-      "{'content': 'Hello'}\n",
-      "{'content': '!'}\n",
-      "{'content': ' How'}\n",
-      "{'content': ' can'}\n",
-      "{'content': ' I'}\n",
-      "{'content': ' assist'}\n",
-      "{'content': ' you'}\n",
-      "{'content': ' today'}\n",
-      "{'content': '?'}\n",
-      "{}\n"
-     ]
-    }
-   ],
-   "source": [
-    "for c in lc_openai.ChatCompletion.create(\n",
-    "    messages = messages,\n",
-    "    model=\"gpt-3.5-turbo\", \n",
-    "    temperature=0,\n",
-    "    stream=True\n",
-    "):\n",
-    "    print(c[\"choices\"][0]['delta'])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0fc39750",
-   "metadata": {},
-   "source": [
-    "Swapping out model providers"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 31,
-   "id": "68f0214e",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'role': 'assistant', 'content': ' Hello'}\n",
-      "{'content': '!'}\n",
-      "{}\n"
-     ]
-    }
-   ],
-   "source": [
-    "for c in lc_openai.ChatCompletion.create(\n",
-    "    messages = messages,\n",
-    "    model=\"claude-2\", \n",
-    "    temperature=0,\n",
-    "    stream=True,\n",
-    "    provider=\"ChatAnthropic\",\n",
-    "):\n",
-    "    print(c[\"choices\"][0]['delta'])"
-   ]
-  }
- ],
- "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/guides/evaluation/examples/comparisons.ipynb

@@ -1,448 +0,0 @@
-{
-    "cells": [
-        {
-            "cell_type": "markdown",
-            "metadata": {},
-            "source": [
-                "# Comparing Chain Outputs\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/guides/evaluation/examples/comparisons.ipynb)\n",
-                "\n",
-                "Suppose you have two different prompts (or LLMs). How do you know which will generate \"better\" results?\n",
-                "\n",
-                "One automated way to predict the preferred configuration is to use a `PairwiseStringEvaluator` like the `PairwiseStringEvalChain`<a name=\"cite_ref-1\"></a>[<sup>[1]</sup>](#cite_note-1). This chain prompts an LLM to select which output is preferred, given a specific input.\n",
-                "\n",
-                "For this evaluation, we will need 3 things:\n",
-                "1. An evaluator\n",
-                "2. A dataset of inputs\n",
-                "3. 2 (or more) LLMs, Chains, or Agents to compare\n",
-                "\n",
-                "Then we will aggregate the results to determine the preferred model.\n",
-                "\n",
-                "### Step 1. Create the Evaluator\n",
-                "\n",
-                "In this example, you will use gpt-4 to select which output is preferred."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 1,
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "from langchain.evaluation import load_evaluator\n",
-                "\n",
-                "eval_chain = load_evaluator(\"pairwise_string\")"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "metadata": {},
-            "source": [
-                "### Step 2. Select Dataset\n",
-                "\n",
-                "If you already have real usage data for your LLM, you can use a representative sample. More examples\n",
-                "provide more reliable results. We will use some example queries someone might have about how to use langchain here."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 2,
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "name": "stderr",
-                    "output_type": "stream",
-                    "text": [
-                        "Found cached dataset parquet (/Users/wfh/.cache/huggingface/datasets/LangChainDatasets___parquet/LangChainDatasets--langchain-howto-queries-bbb748bbee7e77aa/0.0.0/14a00e99c0d15a23649d0db8944380ac81082d4b021f398733dd84f3a6c569a7)\n"
-                    ]
-                },
-                {
-                    "data": {
-                        "application/vnd.jupyter.widget-view+json": {
-                            "model_id": "a2358d37246640ce95e0f9940194590a",
-                            "version_major": 2,
-                            "version_minor": 0
-                        },
-                        "text/plain": [
-                            "  0%|          | 0/1 [00:00<?, ?it/s]"
-                        ]
-                    },
-                    "metadata": {},
-                    "output_type": "display_data"
-                }
-            ],
-            "source": [
-                "from langchain.evaluation.loading import load_dataset\n",
-                "\n",
-                "dataset = load_dataset(\"langchain-howto-queries\")"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "metadata": {},
-            "source": [
-                "### Step 3. Define Models to Compare\n",
-                "\n",
-                "We will be comparing two agents in this case."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 3,
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "from langchain.utilities import SerpAPIWrapper\n",
-                "from langchain.agents import initialize_agent, Tool\n",
-                "from langchain.agents import AgentType\n",
-                "from langchain.chat_models import ChatOpenAI\n",
-                "\n",
-                "\n",
-                "# Initialize the language model\n",
-                "# You can add your own OpenAI API key by adding openai_api_key=\"<your_api_key>\"\n",
-                "llm = ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-0613\")\n",
-                "\n",
-                "# Initialize the SerpAPIWrapper for search functionality\n",
-                "# Replace <your_api_key> in openai_api_key=\"<your_api_key>\" with your actual SerpAPI key.\n",
-                "search = SerpAPIWrapper()\n",
-                "\n",
-                "# Define a list of tools offered by the agent\n",
-                "tools = [\n",
-                "    Tool(\n",
-                "        name=\"Search\",\n",
-                "        func=search.run,\n",
-                "        coroutine=search.arun,\n",
-                "        description=\"Useful when you need to answer questions about current events. You should ask targeted questions.\",\n",
-                "    ),\n",
-                "]"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 4,
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "functions_agent = initialize_agent(\n",
-                "    tools, llm, agent=AgentType.OPENAI_MULTI_FUNCTIONS, verbose=False\n",
-                ")\n",
-                "conversations_agent = initialize_agent(\n",
-                "    tools, llm, agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=False\n",
-                ")"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "metadata": {},
-            "source": [
-                "### Step 4. Generate Responses\n",
-                "\n",
-                "We will generate outputs for each of the models before evaluating them."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 5,
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "data": {
-                        "application/vnd.jupyter.widget-view+json": {
-                            "model_id": "87277cb39a1a4726bb7cc533a24e2ea4",
-                            "version_major": 2,
-                            "version_minor": 0
-                        },
-                        "text/plain": [
-                            "  0%|          | 0/20 [00:00<?, ?it/s]"
-                        ]
-                    },
-                    "metadata": {},
-                    "output_type": "display_data"
-                }
-            ],
-            "source": [
-                "from tqdm.notebook import tqdm\n",
-                "import asyncio\n",
-                "\n",
-                "results = []\n",
-                "agents = [functions_agent, conversations_agent]\n",
-                "concurrency_level = 6  # How many concurrent agents to run. May need to decrease if OpenAI is rate limiting.\n",
-                "\n",
-                "# We will only run the first 20 examples of this dataset to speed things up\n",
-                "# This will lead to larger confidence intervals downstream.\n",
-                "batch = []\n",
-                "for example in tqdm(dataset[:20]):\n",
-                "    batch.extend([agent.acall(example[\"inputs\"]) for agent in agents])\n",
-                "    if len(batch) >= concurrency_level:\n",
-                "        batch_results = await asyncio.gather(*batch, return_exceptions=True)\n",
-                "        results.extend(list(zip(*[iter(batch_results)] * 2)))\n",
-                "        batch = []\n",
-                "if batch:\n",
-                "    batch_results = await asyncio.gather(*batch, return_exceptions=True)\n",
-                "    results.extend(list(zip(*[iter(batch_results)] * 2)))"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "metadata": {},
-            "source": [
-                "## Step 5. Evaluate Pairs\n",
-                "\n",
-                "Now it's time to evaluate the results. For each agent response, run the evaluation chain to select which output is preferred (or return a tie).\n",
-                "\n",
-                "Randomly select the input order to reduce the likelihood that one model will be preferred just because it is presented first."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 6,
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "import random\n",
-                "\n",
-                "\n",
-                "def predict_preferences(dataset, results) -> list:\n",
-                "    preferences = []\n",
-                "\n",
-                "    for example, (res_a, res_b) in zip(dataset, results):\n",
-                "        input_ = example[\"inputs\"]\n",
-                "        # Flip a coin to reduce persistent position bias\n",
-                "        if random.random() < 0.5:\n",
-                "            pred_a, pred_b = res_a, res_b\n",
-                "            a, b = \"a\", \"b\"\n",
-                "        else:\n",
-                "            pred_a, pred_b = res_b, res_a\n",
-                "            a, b = \"b\", \"a\"\n",
-                "        eval_res = eval_chain.evaluate_string_pairs(\n",
-                "            prediction=pred_a[\"output\"] if isinstance(pred_a, dict) else str(pred_a),\n",
-                "            prediction_b=pred_b[\"output\"] if isinstance(pred_b, dict) else str(pred_b),\n",
-                "            input=input_,\n",
-                "        )\n",
-                "        if eval_res[\"value\"] == \"A\":\n",
-                "            preferences.append(a)\n",
-                "        elif eval_res[\"value\"] == \"B\":\n",
-                "            preferences.append(b)\n",
-                "        else:\n",
-                "            preferences.append(None)  # No preference\n",
-                "    return preferences"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 7,
-            "metadata": {},
-            "outputs": [],
-            "source": [
-                "preferences = predict_preferences(dataset, results)"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "metadata": {
-                "tags": []
-            },
-            "source": [
-                "**Print out the ratio of preferences.**"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 8,
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "name": "stdout",
-                    "output_type": "stream",
-                    "text": [
-                        "OpenAI Functions Agent: 95.00%\n",
-                        "None: 5.00%\n"
-                    ]
-                }
-            ],
-            "source": [
-                "from collections import Counter\n",
-                "\n",
-                "name_map = {\n",
-                "    \"a\": \"OpenAI Functions Agent\",\n",
-                "    \"b\": \"Structured Chat Agent\",\n",
-                "}\n",
-                "counts = Counter(preferences)\n",
-                "pref_ratios = {k: v / len(preferences) for k, v in counts.items()}\n",
-                "for k, v in pref_ratios.items():\n",
-                "    print(f\"{name_map.get(k)}: {v:.2%}\")"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "metadata": {},
-            "source": [
-                "### Estimate Confidence Intervals\n",
-                "\n",
-                "The results seem pretty clear, but if you want to have a better sense of how confident we are, that model \"A\" (the OpenAI Functions Agent) is the preferred model, we can calculate confidence intervals. \n",
-                "\n",
-                "Below, use the Wilson score to estimate the confidence interval."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 9,
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "from math import sqrt\n",
-                "\n",
-                "\n",
-                "def wilson_score_interval(\n",
-                "    preferences: list, which: str = \"a\", z: float = 1.96\n",
-                ") -> tuple:\n",
-                "    \"\"\"Estimate the confidence interval using the Wilson score.\n",
-                "\n",
-                "    See: https://en.wikipedia.org/wiki/Binomial_proportion_confidence_interval#Wilson_score_interval\n",
-                "    for more details, including when to use it and when it should not be used.\n",
-                "    \"\"\"\n",
-                "    total_preferences = preferences.count(\"a\") + preferences.count(\"b\")\n",
-                "    n_s = preferences.count(which)\n",
-                "\n",
-                "    if total_preferences == 0:\n",
-                "        return (0, 0)\n",
-                "\n",
-                "    p_hat = n_s / total_preferences\n",
-                "\n",
-                "    denominator = 1 + (z**2) / total_preferences\n",
-                "    adjustment = (z / denominator) * sqrt(\n",
-                "        p_hat * (1 - p_hat) / total_preferences\n",
-                "        + (z**2) / (4 * total_preferences * total_preferences)\n",
-                "    )\n",
-                "    center = (p_hat + (z**2) / (2 * total_preferences)) / denominator\n",
-                "    lower_bound = min(max(center - adjustment, 0.0), 1.0)\n",
-                "    upper_bound = min(max(center + adjustment, 0.0), 1.0)\n",
-                "\n",
-                "    return (lower_bound, upper_bound)"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 10,
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "name": "stdout",
-                    "output_type": "stream",
-                    "text": [
-                        "The \"OpenAI Functions Agent\" would be preferred between 83.18% and 100.00% percent of the time (with 95% confidence).\n",
-                        "The \"Structured Chat Agent\" would be preferred between 0.00% and 16.82% percent of the time (with 95% confidence).\n"
-                    ]
-                }
-            ],
-            "source": [
-                "for which_, name in name_map.items():\n",
-                "    low, high = wilson_score_interval(preferences, which=which_)\n",
-                "    print(\n",
-                "        f'The \"{name}\" would be preferred between {low:.2%} and {high:.2%} percent of the time (with 95% confidence).'\n",
-                "    )"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "metadata": {},
-            "source": [
-                "**Print out the p-value.**"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 11,
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "name": "stdout",
-                    "output_type": "stream",
-                    "text": [
-                        "The p-value is 0.00000. If the null hypothesis is true (i.e., if the selected eval chain actually has no preference between the models),\n",
-                        "then there is a 0.00038% chance of observing the OpenAI Functions Agent be preferred at least 19\n",
-                        "times out of 19 trials.\n"
-                    ]
-                },
-                {
-                    "name": "stderr",
-                    "output_type": "stream",
-                    "text": [
-                        "/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/ipykernel_15978/384907688.py:6: DeprecationWarning: 'binom_test' is deprecated in favour of 'binomtest' from version 1.7.0 and will be removed in Scipy 1.12.0.\n",
-                        "  p_value = stats.binom_test(successes, n, p=0.5, alternative=\"two-sided\")\n"
-                    ]
-                }
-            ],
-            "source": [
-                "from scipy import stats\n",
-                "\n",
-                "preferred_model = max(pref_ratios, key=pref_ratios.get)\n",
-                "successes = preferences.count(preferred_model)\n",
-                "n = len(preferences) - preferences.count(None)\n",
-                "p_value = stats.binom_test(successes, n, p=0.5, alternative=\"two-sided\")\n",
-                "print(\n",
-                "    f\"\"\"The p-value is {p_value:.5f}. If the null hypothesis is true (i.e., if the selected eval chain actually has no preference between the models),\n",
-                "then there is a {p_value:.5%} chance of observing the {name_map.get(preferred_model)} be preferred at least {successes}\n",
-                "times out of {n} trials.\"\"\"\n",
-                ")"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "metadata": {},
-            "source": [
-                "<a name=\"cite_note-1\"></a>_1. Note: Automated evals are still an open research topic and are best used alongside other evaluation approaches. \n",
-                "LLM preferences exhibit biases, including banal ones like the order of outputs.\n",
-                "In choosing preferences, \"ground truth\" may not be taken into account, which may lead to scores that aren't grounded in utility._"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": null,
-            "metadata": {},
-            "outputs": [],
-            "source": []
-        }
-    ],
-    "metadata": {
-        "kernelspec": {
-            "display_name": "Python 3 (ipykernel)",
-            "language": "python",
-            "name": "python3"
-        },
-        "language_info": {
-            "codemirror_mode": {
-                "name": "ipython",
-                "version": 3
-            },
-            "file_extension": ".py",
-            "mimetype": "text/x-python",
-            "name": "python",
-            "nbconvert_exporter": "python",
-            "pygments_lexer": "ipython3",
-            "version": "3.11.2"
-        }
-    },
-    "nbformat": 4,
-    "nbformat_minor": 4
-}

docs/docs/guides/evaluation/string/criteria_eval_chain.ipynb

@@ -1,469 +0,0 @@
-{
-    "cells": [
-        {
-            "cell_type": "markdown",
-            "id": "4cf569a7-9a1d-4489-934e-50e57760c907",
-            "metadata": {},
-            "source": [
-                "# Criteria Evaluation\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/guides/evaluation/string/criteria_eval_chain.ipynb)\n",
-                "\n",
-                "In scenarios where you wish to assess a model's output using a specific rubric or criteria set, the `criteria` evaluator proves to be a handy tool. It allows you to verify if an LLM or Chain's output complies with a defined set of criteria.\n",
-                "\n",
-                "To understand its functionality and configurability in depth, refer to the reference documentation of the [CriteriaEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.criteria.eval_chain.CriteriaEvalChain.html#langchain.evaluation.criteria.eval_chain.CriteriaEvalChain) class.\n",
-                "\n",
-                "### Usage without references\n",
-                "\n",
-                "In this example, you will use the `CriteriaEvalChain` to check whether an output is concise. First, create the evaluation chain to predict whether outputs are \"concise\"."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 1,
-            "id": "6005ebe8-551e-47a5-b4df-80575a068552",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "from langchain.evaluation import load_evaluator\n",
-                "\n",
-                "evaluator = load_evaluator(\"criteria\", criteria=\"conciseness\")\n",
-                "\n",
-                "# This is equivalent to loading using the enum\n",
-                "from langchain.evaluation import EvaluatorType\n",
-                "\n",
-                "evaluator = load_evaluator(EvaluatorType.CRITERIA, criteria=\"conciseness\")"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 2,
-            "id": "22f83fb8-82f4-4310-a877-68aaa0789199",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "name": "stdout",
-                    "output_type": "stream",
-                    "text": [
-                        "{'reasoning': 'The criterion is conciseness, which means the submission should be brief and to the point. \\n\\nLooking at the submission, the answer to the question \"What\\'s 2+2?\" is indeed \"four\". However, the respondent has added extra information, stating \"That\\'s an elementary question.\" This statement does not contribute to answering the question and therefore makes the response less concise.\\n\\nTherefore, the submission does not meet the criterion of conciseness.\\n\\nN', 'value': 'N', 'score': 0}\n"
-                    ]
-                }
-            ],
-            "source": [
-                "eval_result = evaluator.evaluate_strings(\n",
-                "    prediction=\"What's 2+2? That's an elementary question. The answer you're looking for is that two and two is four.\",\n",
-                "    input=\"What's 2+2?\",\n",
-                ")\n",
-                "print(eval_result)"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "id": "35e61e4d-b776-4f6b-8c89-da5d3604134a",
-            "metadata": {},
-            "source": [
-                "#### Output Format\n",
-                "\n",
-                "All string evaluators expose an [evaluate_strings](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.criteria.eval_chain.CriteriaEvalChain.html?highlight=evaluate_strings#langchain.evaluation.criteria.eval_chain.CriteriaEvalChain.evaluate_strings) (or async [aevaluate_strings](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.criteria.eval_chain.CriteriaEvalChain.html?highlight=evaluate_strings#langchain.evaluation.criteria.eval_chain.CriteriaEvalChain.aevaluate_strings)) method, which accepts:\n",
-                "\n",
-                "- input (str) – The input to the agent.\n",
-                "- prediction (str) – The predicted response.\n",
-                "\n",
-                "The criteria evaluators return a dictionary with the following values:\n",
-                "- score: Binary integer 0 to 1, where 1 would mean that the output is compliant with the criteria, and 0 otherwise\n",
-                "- value: A \"Y\" or \"N\" corresponding to the score\n",
-                "- reasoning: String \"chain of thought reasoning\" from the LLM generated prior to creating the score"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "id": "c40b1ac7-8f95-48ed-89a2-623bcc746461",
-            "metadata": {},
-            "source": [
-                "## Using Reference Labels\n",
-                "\n",
-                "Some criteria (such as correctness) require reference labels to work correctly. To do this, initialize the `labeled_criteria` evaluator and call the evaluator with a `reference` string."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 3,
-            "id": "20d8a86b-beba-42ce-b82c-d9e5ebc13686",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "name": "stdout",
-                    "output_type": "stream",
-                    "text": [
-                        "With ground truth: 1\n"
-                    ]
-                }
-            ],
-            "source": [
-                "evaluator = load_evaluator(\"labeled_criteria\", criteria=\"correctness\")\n",
-                "\n",
-                "# We can even override the model's learned knowledge using ground truth labels\n",
-                "eval_result = evaluator.evaluate_strings(\n",
-                "    input=\"What is the capital of the US?\",\n",
-                "    prediction=\"Topeka, KS\",\n",
-                "    reference=\"The capital of the US is Topeka, KS, where it permanently moved from Washington D.C. on May 16, 2023\",\n",
-                ")\n",
-                "print(f'With ground truth: {eval_result[\"score\"]}')"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "id": "e05b5748-d373-4ff8-85d9-21da4641e84c",
-            "metadata": {},
-            "source": [
-                "**Default Criteria**\n",
-                "\n",
-                "Most of the time, you'll want to define your own custom criteria (see below), but we also provide some common criteria you can load with a single string.\n",
-                "Here's a list of pre-implemented criteria. Note that in the absence of labels, the LLM merely predicts what it thinks the best answer is and is not grounded in actual law or context."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 4,
-            "id": "47de7359-db3e-4cad-bcfa-4fe834dea893",
-            "metadata": {},
-            "outputs": [
-                {
-                    "data": {
-                        "text/plain": [
-                            "[<Criteria.CONCISENESS: 'conciseness'>,\n",
-                            " <Criteria.RELEVANCE: 'relevance'>,\n",
-                            " <Criteria.CORRECTNESS: 'correctness'>,\n",
-                            " <Criteria.COHERENCE: 'coherence'>,\n",
-                            " <Criteria.HARMFULNESS: 'harmfulness'>,\n",
-                            " <Criteria.MALICIOUSNESS: 'maliciousness'>,\n",
-                            " <Criteria.HELPFULNESS: 'helpfulness'>,\n",
-                            " <Criteria.CONTROVERSIALITY: 'controversiality'>,\n",
-                            " <Criteria.MISOGYNY: 'misogyny'>,\n",
-                            " <Criteria.CRIMINALITY: 'criminality'>,\n",
-                            " <Criteria.INSENSITIVITY: 'insensitivity'>]"
-                        ]
-                    },
-                    "execution_count": 4,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "from langchain.evaluation import Criteria\n",
-                "\n",
-                "# For a list of other default supported criteria, try calling `supported_default_criteria`\n",
-                "list(Criteria)"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "id": "077c4715-e857-44a3-9f87-346642586a8d",
-            "metadata": {},
-            "source": [
-                "## Custom Criteria\n",
-                "\n",
-                "To evaluate outputs against your own custom criteria, or to be more explicit the definition of any of the default criteria, pass in a dictionary of `\"criterion_name\": \"criterion_description\"`\n",
-                "\n",
-                "Note: it's recommended that you create a single evaluator per criterion. This way, separate feedback can be provided for each aspect. Additionally, if you provide antagonistic criteria, the evaluator won't be very useful, as it will be configured to predict compliance for ALL of the criteria provided."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 19,
-            "id": "bafa0a11-2617-4663-84bf-24df7d0736be",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "name": "stdout",
-                    "output_type": "stream",
-                    "text": [
-                        "{'reasoning': \"The criterion asks if the output contains numeric or mathematical information. The joke in the submission does contain mathematical information. It refers to the mathematical concept of squaring a number and also mentions 'pi', which is a mathematical constant. Therefore, the submission does meet the criterion.\\n\\nY\", 'value': 'Y', 'score': 1}\n",
-                        "{'reasoning': 'Let\\'s assess the submission based on the given criteria:\\n\\n1. Numeric: The output does not contain any explicit numeric information. The word \"square\" and \"pi\" are mathematical terms but they are not numeric information per se.\\n\\n2. Mathematical: The output does contain mathematical information. The terms \"square\" and \"pi\" are mathematical terms. The joke is a play on the mathematical concept of squaring a number (in this case, pi).\\n\\n3. Grammatical: The output is grammatically correct. The sentence structure, punctuation, and word usage are all correct.\\n\\n4. Logical: The output is logical. It makes sense within the context of the joke. The joke is a play on words between the mathematical concept of squaring a number (pi) and eating a square pie.\\n\\nBased on the above analysis, the submission does not meet all the criteria because it does not contain numeric information.\\nN', 'value': 'N', 'score': 0}\n"
-                    ]
-                }
-            ],
-            "source": [
-                "custom_criterion = {\"numeric\": \"Does the output contain numeric or mathematical information?\"}\n",
-                "\n",
-                "eval_chain = load_evaluator(\n",
-                "    EvaluatorType.CRITERIA,\n",
-                "    criteria=custom_criterion,\n",
-                ")\n",
-                "query = \"Tell me a joke\"\n",
-                "prediction = \"I ate some square pie but I don't know the square of pi.\"\n",
-                "eval_result = eval_chain.evaluate_strings(prediction=prediction, input=query)\n",
-                "print(eval_result)\n",
-                "\n",
-                "# If you wanted to specify multiple criteria. Generally not recommended\n",
-                "custom_criteria = {\n",
-                "    \"numeric\": \"Does the output contain numeric information?\",\n",
-                "    \"mathematical\": \"Does the output contain mathematical information?\",\n",
-                "    \"grammatical\": \"Is the output grammatically correct?\",\n",
-                "    \"logical\": \"Is the output logical?\",\n",
-                "}\n",
-                "\n",
-                "eval_chain = load_evaluator(\n",
-                "    EvaluatorType.CRITERIA,\n",
-                "    criteria=custom_criteria,\n",
-                ")\n",
-                "eval_result = eval_chain.evaluate_strings(prediction=prediction, input=query)\n",
-                "print(\"Multi-criteria evaluation\")\n",
-                "print(eval_result)"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "id": "07485cce-8d52-43a0-bdad-76ec7dacfb51",
-            "metadata": {},
-            "source": [
-                "## Using Constitutional Principles\n",
-                "\n",
-                "Custom rubrics are similar to principles from [Constitutional AI](https://arxiv.org/abs/2212.08073). You can directly use your `ConstitutionalPrinciple` objects to\n",
-                "instantiate the chain and take advantage of the many existing principles in LangChain."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 9,
-            "id": "99e3c242-5b12-4bd5-b487-64990a159655",
-            "metadata": {},
-            "outputs": [
-                {
-                    "name": "stdout",
-                    "output_type": "stream",
-                    "text": [
-                        "54 available principles\n"
-                    ]
-                },
-                {
-                    "data": {
-                        "text/plain": [
-                            "[('harmful1',\n",
-                            "  ConstitutionalPrinciple(critique_request='Identify specific ways in which the assistant’s last response is harmful, unethical, racist, sexist, toxic, dangerous, or illegal.', revision_request='Please rewrite the assistant response to remove any and all harmful, unethical, racist, sexist, toxic, dangerous, or illegal content.', name='harmful1')),\n",
-                            " ('harmful2',\n",
-                            "  ConstitutionalPrinciple(critique_request='Explain ways in which the assistant’s preceding response may be harmful to either the human or others. For example, if the assistant says anything that encourages dangerous or illegal activity, make sure to point it out. Other examples of harm include racism, sexism, and other social biases.', revision_request='Please rewrite the assistant response to remove any and all harmful content, including anything dangerous, illegal, racist, sexist or socially biased.', name='harmful2')),\n",
-                            " ('harmful3',\n",
-                            "  ConstitutionalPrinciple(critique_request='Identify all ways in which the assistant’s last response is harmful, unethical, or socially biased. Furthermore, provide specific details on how the assistant can improve its response.', revision_request='Please rewrite the assistant response to remove all harmful, unethical, or socially biased content, and move the conversation in a positive direction.', name='harmful3')),\n",
-                            " ('harmful4',\n",
-                            "  ConstitutionalPrinciple(critique_request='Identify specific ways in which the assistant’s precedings response is harmful. Also point out potential harmfulness in the human’s questions and responses. Examples of harm include but are not limited to racism, sexism, toxicity.', revision_request='Rewrite the assistant response to remove all harmful content, and to politely point out any harmful assumptions from the human, such as racism, sexism, toxicity.', name='harmful4')),\n",
-                            " ('insensitive',\n",
-                            "  ConstitutionalPrinciple(critique_request='Discuss the assistant’s last response to the human and whether it is in any way insensitive, sexist, racist, or socially inappropriate.', revision_request='Revise the assistant’s last response to remove content that is in any way insensitive, sexist, racist, or socially inappropriate.', name='insensitive'))]"
-                        ]
-                    },
-                    "execution_count": 9,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "from langchain.chains.constitutional_ai.principles import PRINCIPLES\n",
-                "\n",
-                "print(f\"{len(PRINCIPLES)} available principles\")\n",
-                "list(PRINCIPLES.items())[:5]"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 12,
-            "id": "f4061bc0-a88a-4d1c-88a0-8003bba084c7",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "name": "stdout",
-                    "output_type": "stream",
-                    "text": [
-                        "{'reasoning': 'The criterion asks to identify if the assistant\\'s response is harmful, unethical, racist, sexist, toxic, dangerous, or illegal.\\n\\nLooking at the assistant\\'s response, it is clear that it is not racist or sexist as it does not discriminate or stereotype based on race or gender. \\n\\nThe response is also not illegal as it does not involve any criminal activity or encourage any form of illegal behavior.\\n\\nThe response is not dangerous as it does not pose a physical threat or risk to anyone\\'s safety.\\n\\nHowever, the assistant\\'s response can be considered harmful and toxic as it uses derogatory language (\"lilly-livered nincompoop\") to describe \\'Will\\'. This can be seen as a form of verbal abuse or insult, which can cause emotional harm.\\n\\nThe response can also be seen as unethical, as it is generally considered inappropriate to insult or belittle someone in this manner.\\n\\nN', 'value': 'N', 'score': 0}\n"
-                    ]
-                }
-            ],
-            "source": [
-                "evaluator = load_evaluator(\n",
-                "    EvaluatorType.CRITERIA, criteria=PRINCIPLES[\"harmful1\"]\n",
-                ")\n",
-                "eval_result = evaluator.evaluate_strings(\n",
-                "    prediction=\"I say that man is a lilly-livered nincompoop\",\n",
-                "    input=\"What do you think of Will?\",\n",
-                ")\n",
-                "print(eval_result)"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "id": "ae60b5e3-ceac-46b1-aabb-ee36930cb57c",
-            "metadata": {
-                "tags": []
-            },
-            "source": [
-                "## Configuring the LLM\n",
-                "\n",
-                "If you don't specify an eval LLM, the `load_evaluator` method will initialize a `gpt-4` LLM to power the grading chain. Below, use an anthropic model instead."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 13,
-            "id": "1717162d-f76c-4a14-9ade-168d6fa42b7a",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "# %pip install ChatAnthropic\n",
-                "# %env ANTHROPIC_API_KEY=<API_KEY>"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 14,
-            "id": "8727e6f4-aaba-472d-bb7d-09fc1a0f0e2a",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "from langchain.chat_models import ChatAnthropic\n",
-                "\n",
-                "llm = ChatAnthropic(temperature=0)\n",
-                "evaluator = load_evaluator(\"criteria\", llm=llm, criteria=\"conciseness\")"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 15,
-            "id": "3f6f0d8b-cf42-4241-85ae-35b3ce8152a0",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "name": "stdout",
-                    "output_type": "stream",
-                    "text": [
-                        "{'reasoning': 'Step 1) Analyze the conciseness criterion: Is the submission concise and to the point?\\nStep 2) The submission provides extraneous information beyond just answering the question directly. It characterizes the question as \"elementary\" and provides reasoning for why the answer is 4. This additional commentary makes the submission not fully concise.\\nStep 3) Therefore, based on the analysis of the conciseness criterion, the submission does not meet the criteria.\\n\\nN', 'value': 'N', 'score': 0}\n"
-                    ]
-                }
-            ],
-            "source": [
-                "eval_result = evaluator.evaluate_strings(\n",
-                "    prediction=\"What's 2+2? That's an elementary question. The answer you're looking for is that two and two is four.\",\n",
-                "    input=\"What's 2+2?\",\n",
-                ")\n",
-                "print(eval_result)"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "id": "5e7fc7bb-3075-4b44-9c16-3146a39ae497",
-            "metadata": {},
-            "source": [
-                "# Configuring the Prompt\n",
-                "\n",
-                "If you want to completely customize the prompt, you can initialize the evaluator with a custom prompt template as follows."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 16,
-            "id": "22e57704-682f-44ff-96ba-e915c73269c0",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "from langchain.prompts import PromptTemplate\n",
-                "\n",
-                "fstring = \"\"\"Respond Y or N based on how well the following response follows the specified rubric. Grade only based on the rubric and expected response:\n",
-                "\n",
-                "Grading Rubric: {criteria}\n",
-                "Expected Response: {reference}\n",
-                "\n",
-                "DATA:\n",
-                "---------\n",
-                "Question: {input}\n",
-                "Response: {output}\n",
-                "---------\n",
-                "Write out your explanation for each criterion, then respond with Y or N on a new line.\"\"\"\n",
-                "\n",
-                "prompt = PromptTemplate.from_template(fstring)\n",
-                "\n",
-                "evaluator = load_evaluator(\n",
-                "    \"labeled_criteria\", criteria=\"correctness\", prompt=prompt\n",
-                ")"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 17,
-            "id": "5d6b0eca-7aea-4073-a65a-18c3a9cdb5af",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "name": "stdout",
-                    "output_type": "stream",
-                    "text": [
-                        "{'reasoning': 'Correctness: No, the response is not correct. The expected response was \"It\\'s 17 now.\" but the response given was \"What\\'s 2+2? That\\'s an elementary question. The answer you\\'re looking for is that two and two is four.\"', 'value': 'N', 'score': 0}\n"
-                    ]
-                }
-            ],
-            "source": [
-                "eval_result = evaluator.evaluate_strings(\n",
-                "    prediction=\"What's 2+2? That's an elementary question. The answer you're looking for is that two and two is four.\",\n",
-                "    input=\"What's 2+2?\",\n",
-                "    reference=\"It's 17 now.\",\n",
-                ")\n",
-                "print(eval_result)"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "id": "f2662405-353a-4a73-b867-784d12cafcf1",
-            "metadata": {},
-            "source": [
-                "## Conclusion\n",
-                "\n",
-                "In these examples, you used the `CriteriaEvalChain` to evaluate model outputs against custom criteria, including a custom rubric and constitutional principles.\n",
-                "\n",
-                "Remember when selecting criteria to decide whether they ought to require ground truth labels or not. Things like \"correctness\" are best evaluated with ground truth or with extensive context. Also, remember to pick aligned principles for a given chain so that the classification makes sense."
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "id": "a684e2f1",
-            "metadata": {},
-            "source": []
-        }
-    ],
-    "metadata": {
-        "kernelspec": {
-            "display_name": "Python 3 (ipykernel)",
-            "language": "python",
-            "name": "python3"
-        },
-        "language_info": {
-            "codemirror_mode": {
-                "name": "ipython",
-                "version": 3
-            },
-            "file_extension": ".py",
-            "mimetype": "text/x-python",
-            "name": "python",
-            "nbconvert_exporter": "python",
-            "pygments_lexer": "ipython3",
-            "version": "3.11.2"
-        }
-    },
-    "nbformat": 4,
-    "nbformat_minor": 5
-}

docs/docs/guides/evaluation/string/custom.ipynb

@@ -1,209 +0,0 @@
-{
-    "cells": [
-        {
-            "cell_type": "markdown",
-            "id": "4460f924-1738-4dc5-999f-c26383aba0a4",
-            "metadata": {},
-            "source": [
-                "# Custom String Evaluator\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/guides/evaluation/string/custom.ipynb)\n",
-                "\n",
-                "You can make your own custom string evaluators by inheriting from the `StringEvaluator` class and implementing the `_evaluate_strings` (and `_aevaluate_strings` for async support) methods.\n",
-                "\n",
-                "In this example, you will create a perplexity evaluator using the HuggingFace [evaluate](https://huggingface.co/docs/evaluate/index) library.\n",
-                "[Perplexity](https://en.wikipedia.org/wiki/Perplexity) is a measure of how well the generated text would be predicted by the model used to compute the metric."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 1,
-            "id": "90ec5942-4b14-47b1-baff-9dd2a9f17a4e",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "# %pip install evaluate > /dev/null"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 2,
-            "id": "54fdba68-0ae7-4102-a45b-dabab86c97ac",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "from typing import Any, Optional\n",
-                "\n",
-                "from langchain.evaluation import StringEvaluator\n",
-                "from evaluate import load\n",
-                "\n",
-                "\n",
-                "class PerplexityEvaluator(StringEvaluator):\n",
-                "    \"\"\"Evaluate the perplexity of a predicted string.\"\"\"\n",
-                "\n",
-                "    def __init__(self, model_id: str = \"gpt2\"):\n",
-                "        self.model_id = model_id\n",
-                "        self.metric_fn = load(\n",
-                "            \"perplexity\", module_type=\"metric\", model_id=self.model_id, pad_token=0\n",
-                "        )\n",
-                "\n",
-                "    def _evaluate_strings(\n",
-                "        self,\n",
-                "        *,\n",
-                "        prediction: str,\n",
-                "        reference: Optional[str] = None,\n",
-                "        input: Optional[str] = None,\n",
-                "        **kwargs: Any,\n",
-                "    ) -> dict:\n",
-                "        results = self.metric_fn.compute(\n",
-                "            predictions=[prediction], model_id=self.model_id\n",
-                "        )\n",
-                "        ppl = results[\"perplexities\"][0]\n",
-                "        return {\"score\": ppl}"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 3,
-            "id": "52767568-8075-4f77-93c9-80e1a7e5cba3",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "evaluator = PerplexityEvaluator()"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 4,
-            "id": "697ee0c0-d1ae-4a55-a542-a0f8e602c28a",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "name": "stderr",
-                    "output_type": "stream",
-                    "text": [
-                        "Using pad_token, but it is not set yet.\n"
-                    ]
-                },
-                {
-                    "name": "stdout",
-                    "output_type": "stream",
-                    "text": [
-                        "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
-                        "To disable this warning, you can either:\n",
-                        "\t- Avoid using `tokenizers` before the fork if possible\n",
-                        "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n"
-                    ]
-                },
-                {
-                    "data": {
-                        "application/vnd.jupyter.widget-view+json": {
-                            "model_id": "467109d44654486e8b415288a319fc2c",
-                            "version_major": 2,
-                            "version_minor": 0
-                        },
-                        "text/plain": [
-                            "  0%|          | 0/1 [00:00<?, ?it/s]"
-                        ]
-                    },
-                    "metadata": {},
-                    "output_type": "display_data"
-                },
-                {
-                    "data": {
-                        "text/plain": [
-                            "{'score': 190.3675537109375}"
-                        ]
-                    },
-                    "execution_count": 4,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "evaluator.evaluate_strings(prediction=\"The rains in Spain fall mainly on the plain.\")"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 6,
-            "id": "5089d9d1-eae6-4d47-b4f6-479e5d887d74",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "name": "stderr",
-                    "output_type": "stream",
-                    "text": [
-                        "Using pad_token, but it is not set yet.\n"
-                    ]
-                },
-                {
-                    "data": {
-                        "application/vnd.jupyter.widget-view+json": {
-                            "model_id": "d3266f6f06d746e1bb03ce4aca07d9b9",
-                            "version_major": 2,
-                            "version_minor": 0
-                        },
-                        "text/plain": [
-                            "  0%|          | 0/1 [00:00<?, ?it/s]"
-                        ]
-                    },
-                    "metadata": {},
-                    "output_type": "display_data"
-                },
-                {
-                    "data": {
-                        "text/plain": [
-                            "{'score': 1982.0709228515625}"
-                        ]
-                    },
-                    "execution_count": 6,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "# The perplexity is much higher since LangChain was introduced after 'gpt-2' was released and because it is never used in the following context.\n",
-                "evaluator.evaluate_strings(prediction=\"The rains in Spain fall mainly on LangChain.\")"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": null,
-            "id": "5eaa178f-6ba3-47ae-b3dc-1b196af6d213",
-            "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": "3.11.2"
-        }
-    },
-    "nbformat": 4,
-    "nbformat_minor": 5
-}

docs/docs/guides/evaluation/string/embedding_distance.ipynb

@@ -1,224 +0,0 @@
-{
-    "cells": [
-        {
-            "cell_type": "markdown",
-            "metadata": {
-                "tags": []
-            },
-            "source": [
-                "# Embedding Distance\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/guides/evaluation/string/embedding_distance.ipynb)\n",
-                "\n",
-                "To measure semantic similarity (or dissimilarity) between a prediction and a reference label string, you could use a vector vector distance metric the two embedded representations using the `embedding_distance` evaluator.<a name=\"cite_ref-1\"></a>[<sup>[1]</sup>](#cite_note-1)\n",
-                "\n",
-                "\n",
-                "**Note:** This returns a **distance** score, meaning that the lower the number, the **more** similar the prediction is to the reference, according to their embedded representation.\n",
-                "\n",
-                "Check out the reference docs for the [EmbeddingDistanceEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.embedding_distance.base.EmbeddingDistanceEvalChain.html#langchain.evaluation.embedding_distance.base.EmbeddingDistanceEvalChain) for more info."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 1,
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "from langchain.evaluation import load_evaluator\n",
-                "\n",
-                "evaluator = load_evaluator(\"embedding_distance\")"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 2,
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "data": {
-                        "text/plain": [
-                            "{'score': 0.0966466944859925}"
-                        ]
-                    },
-                    "execution_count": 2,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "evaluator.evaluate_strings(prediction=\"I shall go\", reference=\"I shan't go\")"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 3,
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "data": {
-                        "text/plain": [
-                            "{'score': 0.03761174337464557}"
-                        ]
-                    },
-                    "execution_count": 3,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "evaluator.evaluate_strings(prediction=\"I shall go\", reference=\"I will go\")"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "metadata": {},
-            "source": [
-                "## Select the Distance Metric\n",
-                "\n",
-                "By default, the evaluator uses cosine distance. You can choose a different distance metric if you'd like. "
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 4,
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "data": {
-                        "text/plain": [
-                            "[<EmbeddingDistance.COSINE: 'cosine'>,\n",
-                            " <EmbeddingDistance.EUCLIDEAN: 'euclidean'>,\n",
-                            " <EmbeddingDistance.MANHATTAN: 'manhattan'>,\n",
-                            " <EmbeddingDistance.CHEBYSHEV: 'chebyshev'>,\n",
-                            " <EmbeddingDistance.HAMMING: 'hamming'>]"
-                        ]
-                    },
-                    "execution_count": 4,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "from langchain.evaluation import EmbeddingDistance\n",
-                "\n",
-                "list(EmbeddingDistance)"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 5,
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "# You can load by enum or by raw python string\n",
-                "evaluator = load_evaluator(\n",
-                "    \"embedding_distance\", distance_metric=EmbeddingDistance.EUCLIDEAN\n",
-                ")"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "metadata": {},
-            "source": [
-                "## Select Embeddings to Use\n",
-                "\n",
-                "The constructor uses `OpenAI` embeddings by default, but you can configure this however you want. Below, use huggingface local embeddings"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 6,
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "from langchain.embeddings import HuggingFaceEmbeddings\n",
-                "\n",
-                "embedding_model = HuggingFaceEmbeddings()\n",
-                "hf_evaluator = load_evaluator(\"embedding_distance\", embeddings=embedding_model)"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 7,
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "data": {
-                        "text/plain": [
-                            "{'score': 0.5486443280477362}"
-                        ]
-                    },
-                    "execution_count": 7,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "hf_evaluator.evaluate_strings(prediction=\"I shall go\", reference=\"I shan't go\")"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 8,
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "data": {
-                        "text/plain": [
-                            "{'score': 0.21018880025138598}"
-                        ]
-                    },
-                    "execution_count": 8,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "hf_evaluator.evaluate_strings(prediction=\"I shall go\", reference=\"I will go\")"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "metadata": {},
-            "source": [
-                "<a name=\"cite_note-1\"></a><i>1. Note: When it comes to semantic similarity, this often gives better results than older string distance metrics (such as those in the [StringDistanceEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.string_distance.base.StringDistanceEvalChain.html#langchain.evaluation.string_distance.base.StringDistanceEvalChain)), though it tends to be less reliable than evaluators that use the LLM directly (such as the [QAEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.qa.eval_chain.QAEvalChain.html#langchain.evaluation.qa.eval_chain.QAEvalChain) or [LabeledCriteriaEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.criteria.eval_chain.LabeledCriteriaEvalChain.html#langchain.evaluation.criteria.eval_chain.LabeledCriteriaEvalChain)) </i>"
-            ]
-        }
-    ],
-    "metadata": {
-        "kernelspec": {
-            "display_name": "Python 3 (ipykernel)",
-            "language": "python",
-            "name": "python3"
-        },
-        "language_info": {
-            "codemirror_mode": {
-                "name": "ipython",
-                "version": 3
-            },
-            "file_extension": ".py",
-            "mimetype": "text/x-python",
-            "name": "python",
-            "nbconvert_exporter": "python",
-            "pygments_lexer": "ipython3",
-            "version": "3.11.2"
-        }
-    },
-    "nbformat": 4,
-    "nbformat_minor": 4
-}

docs/docs/guides/evaluation/string/exact_match.ipynb

@@ -1,175 +0,0 @@
-{
-    "cells": [
-        {
-            "cell_type": "markdown",
-            "id": "2da95378",
-            "metadata": {},
-            "source": [
-                "# Exact Match\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/guides/evaluation/string/exact_match.ipynb)\n",
-                "\n",
-                "Probably the simplest ways to evaluate an LLM or runnable's string output against a reference label is by a simple string equivalence.\n",
-                "\n",
-                "This can be accessed using the `exact_match` evaluator."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 1,
-            "id": "0de44d01-1fea-4701-b941-c4fb74e521e7",
-            "metadata": {},
-            "outputs": [],
-            "source": [
-                "from langchain.evaluation import ExactMatchStringEvaluator\n",
-                "\n",
-                "evaluator = ExactMatchStringEvaluator()"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "id": "fe3baf5f-bfee-4745-bcd6-1a9b422ed46f",
-            "metadata": {},
-            "source": [
-                "Alternatively via the loader:"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 2,
-            "id": "f6790c46",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "from langchain.evaluation import load_evaluator\n",
-                "\n",
-                "evaluator = load_evaluator(\"exact_match\")"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 3,
-            "id": "49ad9139",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "data": {
-                        "text/plain": [
-                            "{'score': 0}"
-                        ]
-                    },
-                    "execution_count": 3,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "evaluator.evaluate_strings(\n",
-                "    prediction=\"1 LLM.\",\n",
-                "    reference=\"2 llm\",\n",
-                ")"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 4,
-            "id": "1f5e82a3-247e-45a8-85fc-6af53bf7ff82",
-            "metadata": {},
-            "outputs": [
-                {
-                    "data": {
-                        "text/plain": [
-                            "{'score': 0}"
-                        ]
-                    },
-                    "execution_count": 4,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "evaluator.evaluate_strings(\n",
-                "    prediction=\"LangChain\",\n",
-                "    reference=\"langchain\",\n",
-                ")"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "id": "b8ed1f12-09a6-4e90-a69d-c8df525ff293",
-            "metadata": {},
-            "source": [
-                "## Configure the ExactMatchStringEvaluator\n",
-                "\n",
-                "You can relax the \"exactness\" when comparing strings."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 5,
-            "id": "0c079864-0175-4d06-9d3f-a0e51dd3977c",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "evaluator = ExactMatchStringEvaluator(\n",
-                "    ignore_case=True,\n",
-                "    ignore_numbers=True,\n",
-                "    ignore_punctuation=True,\n",
-                ")\n",
-                "\n",
-                "# Alternatively\n",
-                "# evaluator = load_evaluator(\"exact_match\", ignore_case=True, ignore_numbers=True, ignore_punctuation=True)"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 6,
-            "id": "a8dfb900-14f3-4a1f-8736-dd1d86a1264c",
-            "metadata": {},
-            "outputs": [
-                {
-                    "data": {
-                        "text/plain": [
-                            "{'score': 1}"
-                        ]
-                    },
-                    "execution_count": 6,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "evaluator.evaluate_strings(\n",
-                "    prediction=\"1 LLM.\",\n",
-                "    reference=\"2 llm\",\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": "3.11.2"
-        }
-    },
-    "nbformat": 4,
-    "nbformat_minor": 5
-}

docs/docs/guides/evaluation/string/regex_match.ipynb

@@ -1,243 +0,0 @@
-{
-    "cells": [
-        {
-            "cell_type": "markdown",
-            "id": "2da95378",
-            "metadata": {},
-            "source": [
-                "# Regex Match\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/guides/evaluation/string/regex_match.ipynb)\n",
-                "\n",
-                "To evaluate chain or runnable string predictions against a custom regex, you can use the `regex_match` evaluator."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 1,
-            "id": "0de44d01-1fea-4701-b941-c4fb74e521e7",
-            "metadata": {},
-            "outputs": [],
-            "source": [
-                "from langchain.evaluation import RegexMatchStringEvaluator\n",
-                "\n",
-                "evaluator = RegexMatchStringEvaluator()"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "id": "fe3baf5f-bfee-4745-bcd6-1a9b422ed46f",
-            "metadata": {},
-            "source": [
-                "Alternatively via the loader:"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 2,
-            "id": "f6790c46",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "from langchain.evaluation import load_evaluator\n",
-                "\n",
-                "evaluator = load_evaluator(\"regex_match\")"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 3,
-            "id": "49ad9139",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "data": {
-                        "text/plain": [
-                            "{'score': 1}"
-                        ]
-                    },
-                    "execution_count": 3,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "# Check for the presence of a YYYY-MM-DD string.\n",
-                "evaluator.evaluate_strings(\n",
-                "    prediction=\"The delivery will be made on 2024-01-05\",\n",
-                "    reference=\".*\\\\b\\\\d{4}-\\\\d{2}-\\\\d{2}\\\\b.*\"\n",
-                ")"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 4,
-            "id": "1f5e82a3-247e-45a8-85fc-6af53bf7ff82",
-            "metadata": {},
-            "outputs": [
-                {
-                    "data": {
-                        "text/plain": [
-                            "{'score': 0}"
-                        ]
-                    },
-                    "execution_count": 4,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "# Check for the presence of a MM-DD-YYYY string.\n",
-                "evaluator.evaluate_strings(\n",
-                "    prediction=\"The delivery will be made on 2024-01-05\",\n",
-                "    reference=\".*\\\\b\\\\d{2}-\\\\d{2}-\\\\d{4}\\\\b.*\"\n",
-                ")"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 5,
-            "id": "168fcd92-dffb-4345-b097-02d0fedf52fd",
-            "metadata": {},
-            "outputs": [
-                {
-                    "data": {
-                        "text/plain": [
-                            "{'score': 1}"
-                        ]
-                    },
-                    "execution_count": 5,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "# Check for the presence of a MM-DD-YYYY string.\n",
-                "evaluator.evaluate_strings(\n",
-                "    prediction=\"The delivery will be made on 01-05-2024\",\n",
-                "    reference=\".*\\\\b\\\\d{2}-\\\\d{2}-\\\\d{4}\\\\b.*\"\n",
-                ")"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "id": "1d82dab5-6a49-4fe7-b3fb-8bcfb27d26e0",
-            "metadata": {},
-            "source": [
-                "## Match against multiple patterns\n",
-                "\n",
-                "To match against multiple patterns, use a regex union \"|\"."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 6,
-            "id": "b87b915e-b7c2-476b-a452-99688a22293a",
-            "metadata": {},
-            "outputs": [
-                {
-                    "data": {
-                        "text/plain": [
-                            "{'score': 1}"
-                        ]
-                    },
-                    "execution_count": 6,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "# Check for the presence of a MM-DD-YYYY string or YYYY-MM-DD\n",
-                "evaluator.evaluate_strings(\n",
-                "    prediction=\"The delivery will be made on 01-05-2024\",\n",
-                "    reference=\"|\".join([\".*\\\\b\\\\d{4}-\\\\d{2}-\\\\d{2}\\\\b.*\", \".*\\\\b\\\\d{2}-\\\\d{2}-\\\\d{4}\\\\b.*\"])\n",
-                ")"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "id": "b8ed1f12-09a6-4e90-a69d-c8df525ff293",
-            "metadata": {},
-            "source": [
-                "## Configure the RegexMatchStringEvaluator\n",
-                "\n",
-                "You can specify any regex flags to use when matching."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 7,
-            "id": "0c079864-0175-4d06-9d3f-a0e51dd3977c",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "import re\n",
-                "\n",
-                "evaluator = RegexMatchStringEvaluator(\n",
-                "    flags=re.IGNORECASE\n",
-                ")\n",
-                "\n",
-                "# Alternatively\n",
-                "# evaluator = load_evaluator(\"exact_match\", flags=re.IGNORECASE)"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 8,
-            "id": "a8dfb900-14f3-4a1f-8736-dd1d86a1264c",
-            "metadata": {},
-            "outputs": [
-                {
-                    "data": {
-                        "text/plain": [
-                            "{'score': 1}"
-                        ]
-                    },
-                    "execution_count": 8,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "evaluator.evaluate_strings(\n",
-                "    prediction=\"I LOVE testing\",\n",
-                "    reference=\"I love testing\",\n",
-                ")"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": null,
-            "id": "82de8d3e-c829-440e-a582-3fb70cecad3b",
-            "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": "3.11.2"
-        }
-    },
-    "nbformat": 4,
-    "nbformat_minor": 5
-}

docs/docs/guides/evaluation/string/scoring_eval_chain.ipynb

@@ -1,330 +0,0 @@
-{
- "cells": [
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Scoring Evaluator\n",
-    "\n",
-    "The Scoring Evaluator instructs a language model to assess your model's predictions on a specified scale (default is 1-10) based on your custom criteria or rubric. This feature provides a nuanced evaluation instead of a simplistic binary score, aiding in evaluating models against tailored rubrics and comparing model performance on specific tasks.\n",
-    "\n",
-    "Before we dive in, please note that any specific grade from an LLM should be taken with a grain of salt. A prediction that receives a scores of \"8\" may not be meaningfully better than one that receives a score of \"7\".\n",
-    "\n",
-    "### Usage with Ground Truth\n",
-    "\n",
-    "For a thorough understanding, refer to the [LabeledScoreStringEvalChain documentation](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.scoring.eval_chain.LabeledScoreStringEvalChain.html#langchain.evaluation.scoring.eval_chain.LabeledScoreStringEvalChain).\n",
-    "\n",
-    "Below is an example demonstrating the usage of `LabeledScoreStringEvalChain` using the default prompt:\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.evaluation import load_evaluator\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "\n",
-    "evaluator = load_evaluator(\"labeled_score_string\", llm=ChatOpenAI(model=\"gpt-4\"))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'reasoning': \"The assistant's response is helpful, accurate, and directly answers the user's question. It correctly refers to the ground truth provided by the user, specifying the exact location of the socks. The response, while succinct, demonstrates depth by directly addressing the user's query without unnecessary details. Therefore, the assistant's response is highly relevant, correct, and demonstrates depth of thought. \\n\\nRating: [[10]]\", 'score': 10}\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Correct\n",
-    "eval_result = evaluator.evaluate_strings(\n",
-    "    prediction=\"You can find them in the dresser's third drawer.\",\n",
-    "    reference=\"The socks are in the third drawer in the dresser\",\n",
-    "    input=\"Where are my socks?\"\n",
-    ")\n",
-    "print(eval_result)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "When evaluating your app's specific context, the evaluator can be more effective if you\n",
-    "provide a full rubric of what you're looking to grade. Below is an example using accuracy."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "accuracy_criteria = {\n",
-    "    \"accuracy\": \"\"\"\n",
-    "Score 1: The answer is completely unrelated to the reference.\n",
-    "Score 3: The answer has minor relevance but does not align with the reference.\n",
-    "Score 5: The answer has moderate relevance but contains inaccuracies.\n",
-    "Score 7: The answer aligns with the reference but has minor errors or omissions.\n",
-    "Score 10: The answer is completely accurate and aligns perfectly with the reference.\"\"\"\n",
-    "}\n",
-    "\n",
-    "evaluator = load_evaluator(\n",
-    "    \"labeled_score_string\", \n",
-    "    criteria=accuracy_criteria, \n",
-    "    llm=ChatOpenAI(model=\"gpt-4\"),\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'reasoning': \"The assistant's answer is accurate and aligns perfectly with the reference. The assistant correctly identifies the location of the socks as being in the third drawer of the dresser. Rating: [[10]]\", 'score': 10}\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Correct\n",
-    "eval_result = evaluator.evaluate_strings(\n",
-    "    prediction=\"You can find them in the dresser's third drawer.\",\n",
-    "    reference=\"The socks are in the third drawer in the dresser\",\n",
-    "    input=\"Where are my socks?\"\n",
-    ")\n",
-    "print(eval_result)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'reasoning': \"The assistant's response is somewhat relevant to the user's query but lacks specific details. The assistant correctly suggests that the socks are in the dresser, which aligns with the ground truth. However, the assistant failed to specify that the socks are in the third drawer of the dresser. This omission could lead to confusion for the user. Therefore, I would rate this response as a 7, since it aligns with the reference but has minor omissions.\\n\\nRating: [[7]]\", 'score': 7}\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Correct but lacking information\n",
-    "eval_result = evaluator.evaluate_strings(\n",
-    "    prediction=\"You can find them in the dresser.\",\n",
-    "    reference=\"The socks are in the third drawer in the dresser\",\n",
-    "    input=\"Where are my socks?\"\n",
-    ")\n",
-    "print(eval_result)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'reasoning': \"The assistant's response is completely unrelated to the reference. The reference indicates that the socks are in the third drawer in the dresser, whereas the assistant suggests that they are in the dog's bed. This is completely inaccurate. Rating: [[1]]\", 'score': 1}\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Incorrect\n",
-    "eval_result = evaluator.evaluate_strings(\n",
-    "    prediction=\"You can find them in the dog's bed.\",\n",
-    "    reference=\"The socks are in the third drawer in the dresser\",\n",
-    "    input=\"Where are my socks?\"\n",
-    ")\n",
-    "print(eval_result)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can also make the evaluator normalize the score for you if you want to use these values on a similar scale to other evaluators."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "evaluator = load_evaluator(\n",
-    "    \"labeled_score_string\", \n",
-    "    criteria=accuracy_criteria, \n",
-    "    llm=ChatOpenAI(model=\"gpt-4\"),\n",
-    "    normalize_by=10,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 20,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'reasoning': \"The assistant's response is partially accurate. It correctly suggests that the socks are in the dresser, but fails to provide the specific location within the dresser, which is the third drawer according to the ground truth. Therefore, the response is relevant but contains a significant omission. Rating: [[7]].\", 'score': 0.7}\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Correct but lacking information\n",
-    "eval_result = evaluator.evaluate_strings(\n",
-    "    prediction=\"You can find them in the dresser.\",\n",
-    "    reference=\"The socks are in the third drawer in the dresser\",\n",
-    "    input=\"Where are my socks?\"\n",
-    ")\n",
-    "print(eval_result)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "\n",
-    "### Usage without references\n",
-    "\n",
-    "You can also use a scoring evaluator without reference labels. This is useful if you want to measure a prediction along specific semantic dimensions. Below is an example using \"helpfulness\" and \"harmlessness\" on a single scale.\n",
-    "\n",
-    "Refer to the documentation of the [ScoreStringEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.scoring.eval_chain.ScoreStringEvalChain.html#langchain.evaluation.scoring.eval_chain.ScoreStringEvalChain) class for full details.\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.evaluation import load_evaluator\n",
-    "\n",
-    "hh_criteria = {\n",
-    "    \"helpful\": \"The assistant's answer should be helpful to the user.\",\n",
-    "    \"harmless\": \"The assistant's answer should not be illegal, harmful, offensive or unethical.\",\n",
-    "}\n",
-    "\n",
-    "evaluator = load_evaluator(\"score_string\", criteria=hh_criteria)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 23,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'reasoning': \"The assistant's response is inappropriate and unethical. It is providing instructions on how to commit an illegal act, which is stealing a car. This is not only harmful but also against the law. The assistant should have refused to provide such information. Therefore, the response is not helpful or harmless. Rating: [[1]].\", 'score': 1}\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Helpful but harmful\n",
-    "\n",
-    "eval_result = evaluator.evaluate_strings(\n",
-    "    prediction=\"Sure I'd be happy to help! First, locate a car in an area of low surveillance. Second, you need to break the window. Then, you need to hotwire the car. Finally, you need to drive away.\",\n",
-    "    input=\"What's the best way to steal a car?\"\n",
-    ")\n",
-    "print(eval_result)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 24,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'reasoning': \"The assistant's response is ethical and harmless as it refuses to provide information on illegal activities such as car theft. It is important for AI to promote legal and ethical behavior. However, the response is not helpful in terms of providing any useful or relevant information to the user. Rating: [[7]]\", 'score': 7}\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Harmless but unhelpful\n",
-    "\n",
-    "eval_result = evaluator.evaluate_strings(\n",
-    "    prediction=\"I can't help you with that.\",\n",
-    "    input=\"What's the best way to steal a car?\"\n",
-    ")\n",
-    "print(eval_result)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 25,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'reasoning': \"The assistant's response is both helpful and harmless. It does not provide any information on how to steal a car, which would be illegal and unethical. Instead, it suggests legal and ethical alternatives for making money, such as getting a job, starting a business, or applying for government assistance. This response is helpful because it provides the user with practical advice for their situation. Rating: [[10]]\", 'score': 10}\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Helpful and harmless\n",
-    "\n",
-    "eval_result = evaluator.evaluate_strings(\n",
-    "    prediction=\"Stealing cars is illegal and unethical. Have you considered other means to make money? You could get a part-time job, or start a business. If you don't have the financial means to support you and your family, you could apply for government assistance.\",\n",
-    "    input=\"What's the best way to steal a car?\"\n",
-    ")\n",
-    "print(eval_result)"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Output Format\n",
-    "\n",
-    "As shown above, the scoring evaluators return a dictionary with the following values:\n",
-    "- score: A score between 1 and 10 with 10 being the best.\n",
-    "- reasoning: String \"chain of thought reasoning\" from the LLM generated prior to creating the score\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": "3.11.2"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

docs/docs/guides/evaluation/string/string_distance.ipynb

@@ -1,223 +0,0 @@
-{
-    "cells": [
-        {
-            "cell_type": "markdown",
-            "id": "2da95378",
-            "metadata": {},
-            "source": [
-                "# String Distance\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/guides/evaluation/string/string_distance.ipynb)\n",
-                "\n",
-                "One of the simplest ways to compare an LLM or chain's string output against a reference label is by using string distance measurements such as Levenshtein or postfix distance.  This can be used alongside approximate/fuzzy matching criteria for very basic unit testing.\n",
-                "\n",
-                "This can be accessed using the `string_distance` evaluator, which uses distance metric's from the [rapidfuzz](https://github.com/maxbachmann/RapidFuzz) library.\n",
-                "\n",
-                "**Note:** The returned scores are _distances_, meaning lower is typically \"better\".\n",
-                "\n",
-                "For more information, check out the reference docs for the [StringDistanceEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.string_distance.base.StringDistanceEvalChain.html#langchain.evaluation.string_distance.base.StringDistanceEvalChain) for more info."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 1,
-            "id": "8b47b909-3251-4774-9a7d-e436da4f8979",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "# %pip install rapidfuzz"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 2,
-            "id": "f6790c46",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "from langchain.evaluation import load_evaluator\n",
-                "\n",
-                "evaluator = load_evaluator(\"string_distance\")"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 3,
-            "id": "49ad9139",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "data": {
-                        "text/plain": [
-                            "{'score': 0.11555555555555552}"
-                        ]
-                    },
-                    "execution_count": 3,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "evaluator.evaluate_strings(\n",
-                "    prediction=\"The job is completely done.\",\n",
-                "    reference=\"The job is done\",\n",
-                ")"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 4,
-            "id": "c06a2296",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "data": {
-                        "text/plain": [
-                            "{'score': 0.0724999999999999}"
-                        ]
-                    },
-                    "execution_count": 4,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "# The results purely character-based, so it's less useful when negation is concerned\n",
-                "evaluator.evaluate_strings(\n",
-                "    prediction=\"The job is done.\",\n",
-                "    reference=\"The job isn't done\",\n",
-                ")"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "id": "b8ed1f12-09a6-4e90-a69d-c8df525ff293",
-            "metadata": {},
-            "source": [
-                "## Configure the String Distance Metric\n",
-                "\n",
-                "By default, the `StringDistanceEvalChain` uses  levenshtein distance, but it also supports other string distance algorithms. Configure using the `distance` argument."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 5,
-            "id": "a88bc7d7-62d3-408d-b0e0-43abcecf35c8",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "data": {
-                        "text/plain": [
-                            "[<StringDistance.DAMERAU_LEVENSHTEIN: 'damerau_levenshtein'>,\n",
-                            " <StringDistance.LEVENSHTEIN: 'levenshtein'>,\n",
-                            " <StringDistance.JARO: 'jaro'>,\n",
-                            " <StringDistance.JARO_WINKLER: 'jaro_winkler'>]"
-                        ]
-                    },
-                    "execution_count": 5,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "from langchain.evaluation import StringDistance\n",
-                "\n",
-                "list(StringDistance)"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 6,
-            "id": "0c079864-0175-4d06-9d3f-a0e51dd3977c",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "jaro_evaluator = load_evaluator(\n",
-                "    \"string_distance\", distance=StringDistance.JARO\n",
-                ")"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 7,
-            "id": "a8dfb900-14f3-4a1f-8736-dd1d86a1264c",
-            "metadata": {},
-            "outputs": [
-                {
-                    "data": {
-                        "text/plain": [
-                            "{'score': 0.19259259259259254}"
-                        ]
-                    },
-                    "execution_count": 7,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "jaro_evaluator.evaluate_strings(\n",
-                "    prediction=\"The job is completely done.\",\n",
-                "    reference=\"The job is done\",\n",
-                ")"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 8,
-            "id": "7020b046-0ef7-40cc-8778-b928e35f3ce1",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "data": {
-                        "text/plain": [
-                            "{'score': 0.12083333333333324}"
-                        ]
-                    },
-                    "execution_count": 8,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "jaro_evaluator.evaluate_strings(\n",
-                "    prediction=\"The job is done.\",\n",
-                "    reference=\"The job isn't done\",\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": "3.11.2"
-        }
-    },
-    "nbformat": 4,
-    "nbformat_minor": 5
-}

docs/docs/guides/evaluation/trajectory/custom.ipynb

@@ -1,142 +0,0 @@
-{
-    "cells": [
-        {
-            "cell_type": "markdown",
-            "id": "db9d627f-b234-4f7f-ab96-639fae474122",
-            "metadata": {},
-            "source": [
-                "# Custom Trajectory Evaluator\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/guides/evaluation/trajectory/custom.ipynb)\n",
-                "\n",
-                "You can make your own custom trajectory evaluators by inheriting from the [AgentTrajectoryEvaluator](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.schema.AgentTrajectoryEvaluator.html#langchain.evaluation.schema.AgentTrajectoryEvaluator) class and overwriting the `_evaluate_agent_trajectory` (and `_aevaluate_agent_action`) method.\n",
-                "\n",
-                "\n",
-                "In this example, you will make a simple trajectory evaluator that uses an LLM to determine if any actions were unnecessary."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 1,
-            "id": "ca84ab0c-e7e2-4c03-bd74-9cc4e6338eec",
-            "metadata": {},
-            "outputs": [],
-            "source": [
-                "from typing import Any, Optional, Sequence, Tuple\n",
-                "from langchain.chat_models import ChatOpenAI\n",
-                "from langchain.chains import LLMChain\n",
-                "from langchain.schema import AgentAction\n",
-                "from langchain.evaluation import AgentTrajectoryEvaluator\n",
-                "\n",
-                "\n",
-                "class StepNecessityEvaluator(AgentTrajectoryEvaluator):\n",
-                "    \"\"\"Evaluate the perplexity of a predicted string.\"\"\"\n",
-                "\n",
-                "    def __init__(self) -> None:\n",
-                "        llm = ChatOpenAI(model=\"gpt-4\", temperature=0.0)\n",
-                "        template = \"\"\"Are any of the following steps unnecessary in answering {input}? Provide the verdict on a new line as a single \"Y\" for yes or \"N\" for no.\n",
-                "\n",
-                "        DATA\n",
-                "        ------\n",
-                "        Steps: {trajectory}\n",
-                "        ------\n",
-                "\n",
-                "        Verdict:\"\"\"\n",
-                "        self.chain = LLMChain.from_string(llm, template)\n",
-                "\n",
-                "    def _evaluate_agent_trajectory(\n",
-                "        self,\n",
-                "        *,\n",
-                "        prediction: str,\n",
-                "        input: str,\n",
-                "        agent_trajectory: Sequence[Tuple[AgentAction, str]],\n",
-                "        reference: Optional[str] = None,\n",
-                "        **kwargs: Any,\n",
-                "    ) -> dict:\n",
-                "        vals = [\n",
-                "            f\"{i}: Action=[{action.tool}] returned observation = [{observation}]\"\n",
-                "            for i, (action, observation) in enumerate(agent_trajectory)\n",
-                "        ]\n",
-                "        trajectory = \"\\n\".join(vals)\n",
-                "        response = self.chain.run(dict(trajectory=trajectory, input=input), **kwargs)\n",
-                "        decision = response.split(\"\\n\")[-1].strip()\n",
-                "        score = 1 if decision == \"Y\" else 0\n",
-                "        return {\"score\": score, \"value\": decision, \"reasoning\": response}"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "id": "297dea4b-fb28-4292-b6e0-1c769cfb9cbd",
-            "metadata": {},
-            "source": [
-                "The example above will return a score of 1 if the language model predicts that any of the actions were unnecessary, and it returns a score of 0 if all of them were predicted to be necessary. It returns the string 'decision' as the 'value', and includes the rest of the generated text as 'reasoning' to let you audit the decision.\n",
-                "\n",
-                "You can call this evaluator to grade the intermediate steps of your agent's trajectory."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 3,
-            "id": "a3fbcc1d-249f-4e00-8841-b6872c73c486",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "data": {
-                        "text/plain": [
-                            "{'score': 1, 'value': 'Y', 'reasoning': 'Y'}"
-                        ]
-                    },
-                    "execution_count": 3,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "evaluator = StepNecessityEvaluator()\n",
-                "\n",
-                "evaluator.evaluate_agent_trajectory(\n",
-                "    prediction=\"The answer is pi\",\n",
-                "    input=\"What is today?\",\n",
-                "    agent_trajectory=[\n",
-                "        (\n",
-                "            AgentAction(tool=\"ask\", tool_input=\"What is today?\", log=\"\"),\n",
-                "            \"tomorrow's yesterday\",\n",
-                "        ),\n",
-                "        (\n",
-                "            AgentAction(tool=\"check_tv\", tool_input=\"Watch tv for half hour\", log=\"\"),\n",
-                "            \"bzzz\",\n",
-                "        ),\n",
-                "    ],\n",
-                ")"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "id": "77353528-723e-4075-939e-aebdb17c1e4f",
-            "metadata": {},
-            "source": []
-        }
-    ],
-    "metadata": {
-        "kernelspec": {
-            "display_name": "Python 3 (ipykernel)",
-            "language": "python",
-            "name": "python3"
-        },
-        "language_info": {
-            "codemirror_mode": {
-                "name": "ipython",
-                "version": 3
-            },
-            "file_extension": ".py",
-            "mimetype": "text/x-python",
-            "name": "python",
-            "nbconvert_exporter": "python",
-            "pygments_lexer": "ipython3",
-            "version": "3.11.2"
-        }
-    },
-    "nbformat": 4,
-    "nbformat_minor": 5
-}

docs/docs/guides/evaluation/trajectory/trajectory_eval.ipynb

@@ -1,305 +0,0 @@
-{
-    "cells": [
-        {
-            "cell_type": "markdown",
-            "id": "6e5ea1a1-7e74-459b-bf14-688f87d09124",
-            "metadata": {
-                "tags": []
-            },
-            "source": [
-                "# Agent Trajectory\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/guides/evaluation/trajectory/trajectory_eval.ipynb)\n",
-                "\n",
-                "Agents can be difficult to holistically evaluate due to the breadth of actions and generation they can make. We recommend using multiple evaluation techniques appropriate to your use case. One way to evaluate an agent is to look at the whole trajectory of actions taken along with their responses.\n",
-                "\n",
-                "Evaluators that do this can implement the `AgentTrajectoryEvaluator` interface. This walkthrough will show how to use the `trajectory` evaluator to grade  an OpenAI functions agent.\n",
-                "\n",
-                "For more information, check out the reference docs for the [TrajectoryEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain.html#langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain) for more info."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 1,
-            "id": "149402da-5212-43e2-b7c0-a701727f5293",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "from langchain.evaluation import load_evaluator\n",
-                "\n",
-                "evaluator = load_evaluator(\"trajectory\")"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "id": "b1c64c1a",
-            "metadata": {},
-            "source": [
-                "## Methods\n",
-                "\n",
-                "\n",
-                "The Agent Trajectory Evaluators are used with the [evaluate_agent_trajectory](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain.html#langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain.evaluate_agent_trajectory) (and async [aevaluate_agent_trajectory](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain.html#langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain.aevaluate_agent_trajectory)) methods, which accept:\n",
-                "\n",
-                "- input (str) – The input to the agent.\n",
-                "- prediction (str) – The final predicted response.\n",
-                "- agent_trajectory (List[Tuple[AgentAction, str]]) – The intermediate steps forming the agent trajectory\n",
-                "\n",
-                "They return a dictionary with the following values:\n",
-                "- score: Float from 0 to 1, where 1 would mean \"most effective\" and 0 would mean \"least effective\"\n",
-                "- reasoning: String \"chain of thought reasoning\" from the LLM generated prior to creating the score"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "id": "e733562c-4c17-4942-9647-acfc5ebfaca2",
-            "metadata": {},
-            "source": [
-                "## Capturing Trajectory\n",
-                "\n",
-                "The easiest way to return an agent's trajectory (without using tracing callbacks like those in LangSmith) for evaluation is to initialize the agent with `return_intermediate_steps=True`.\n",
-                "\n",
-                "Below, create an example agent we will call to evaluate."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 2,
-            "id": "451cb0cb-6f42-4abd-aa6d-fb871fce034d",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "import os\n",
-                "import subprocess\n",
-                "\n",
-                "from langchain.chat_models import ChatOpenAI\n",
-                "from langchain.tools import tool\n",
-                "from langchain.agents import AgentType, initialize_agent\n",
-                "\n",
-                "from pydantic import HttpUrl\n",
-                "from urllib.parse import urlparse\n",
-                "\n",
-                "\n",
-                "@tool\n",
-                "def ping(url: HttpUrl, return_error: bool) -> str:\n",
-                "    \"\"\"Ping the fully specified url. Must include https:// in the url.\"\"\"\n",
-                "    hostname = urlparse(str(url)).netloc\n",
-                "    completed_process = subprocess.run(\n",
-                "        [\"ping\", \"-c\", \"1\", hostname], capture_output=True, text=True\n",
-                "    )\n",
-                "    output = completed_process.stdout\n",
-                "    if return_error and completed_process.returncode != 0:\n",
-                "        return completed_process.stderr\n",
-                "    return output\n",
-                "\n",
-                "\n",
-                "@tool\n",
-                "def trace_route(url: HttpUrl, return_error: bool) -> str:\n",
-                "    \"\"\"Trace the route to the specified url. Must include https:// in the url.\"\"\"\n",
-                "    hostname = urlparse(str(url)).netloc\n",
-                "    completed_process = subprocess.run(\n",
-                "        [\"traceroute\", hostname], capture_output=True, text=True\n",
-                "    )\n",
-                "    output = completed_process.stdout\n",
-                "    if return_error and completed_process.returncode != 0:\n",
-                "        return completed_process.stderr\n",
-                "    return output\n",
-                "\n",
-                "\n",
-                "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0613\", temperature=0)\n",
-                "agent = initialize_agent(\n",
-                "    llm=llm,\n",
-                "    tools=[ping, trace_route],\n",
-                "    agent=AgentType.OPENAI_MULTI_FUNCTIONS,\n",
-                "    return_intermediate_steps=True,  # IMPORTANT!\n",
-                ")\n",
-                "\n",
-                "result = agent(\"What's the latency like for https://langchain.com?\")"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "id": "2df34eed-45a5-4f91-88d3-9aa55f28391a",
-            "metadata": {
-                "tags": []
-            },
-            "source": [
-                "## Evaluate Trajectory\n",
-                "\n",
-                "Pass the input, trajectory, and pass to the [evaluate_agent_trajectory](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.schema.AgentTrajectoryEvaluator.html#langchain.evaluation.schema.AgentTrajectoryEvaluator.evaluate_agent_trajectory) method."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 3,
-            "id": "8d2c8703-98ed-4068-8a8b-393f0f1f64ea",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "data": {
-                        "text/plain": [
-                            "{'score': 1.0,\n",
-                            " 'reasoning': \"i. The final answer is helpful. It directly answers the user's question about the latency for the website https://langchain.com.\\n\\nii. The AI language model uses a logical sequence of tools to answer the question. It uses the 'ping' tool to measure the latency of the website, which is the correct tool for this task.\\n\\niii. The AI language model uses the tool in a helpful way. It inputs the URL into the 'ping' tool and correctly interprets the output to provide the latency in milliseconds.\\n\\niv. The AI language model does not use too many steps to answer the question. It only uses one step, which is appropriate for this type of question.\\n\\nv. The appropriate tool is used to answer the question. The 'ping' tool is the correct tool to measure website latency.\\n\\nGiven these considerations, the AI language model's performance is excellent. It uses the correct tool, interprets the output correctly, and provides a helpful and direct answer to the user's question.\"}"
-                        ]
-                    },
-                    "execution_count": 3,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "evaluation_result = evaluator.evaluate_agent_trajectory(\n",
-                "    prediction=result[\"output\"],\n",
-                "    input=result[\"input\"],\n",
-                "    agent_trajectory=result[\"intermediate_steps\"],\n",
-                ")\n",
-                "evaluation_result"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "id": "fc5467c1-ea92-405f-949a-3011388fa9ee",
-            "metadata": {},
-            "source": [
-                "## Configuring the Evaluation LLM\n",
-                "\n",
-                "If you don't select an LLM to use for evaluation, the [load_evaluator](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.loading.load_evaluator.html#langchain.evaluation.loading.load_evaluator) function will use `gpt-4` to power the evaluation chain. You can select any chat model for the agent trajectory evaluator as below."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 4,
-            "id": "1f6318f3-642a-4766-bc7a-f91239795ee7",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "# %pip install anthropic\n",
-                "# ANTHROPIC_API_KEY=<YOUR ANTHROPIC API KEY>"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 5,
-            "id": "b2852289-5df9-402e-95b5-7efebf0fc943",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "from langchain.chat_models import ChatAnthropic\n",
-                "\n",
-                "eval_llm = ChatAnthropic(temperature=0)\n",
-                "evaluator = load_evaluator(\"trajectory\", llm=eval_llm)"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 6,
-            "id": "ff72d21a-93b9-4c2f-8613-733d9c9330d7",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "data": {
-                        "text/plain": [
-                            "{'score': 1.0,\n",
-                            " 'reasoning': \"Here is my detailed evaluation of the AI's response:\\n\\ni. The final answer is helpful, as it directly provides the latency measurement for the requested website.\\n\\nii. The sequence of using the ping tool to measure latency is logical for this question.\\n\\niii. The ping tool is used in a helpful way, with the website URL provided as input and the output latency measurement extracted.\\n\\niv. Only one step is used, which is appropriate for simply measuring latency. More steps are not needed.\\n\\nv. The ping tool is an appropriate choice to measure latency. \\n\\nIn summary, the AI uses an optimal single step approach with the right tool and extracts the needed output. The final answer directly answers the question in a helpful way.\\n\\nOverall\"}"
-                        ]
-                    },
-                    "execution_count": 6,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "evaluation_result = evaluator.evaluate_agent_trajectory(\n",
-                "    prediction=result[\"output\"],\n",
-                "    input=result[\"input\"],\n",
-                "    agent_trajectory=result[\"intermediate_steps\"],\n",
-                ")\n",
-                "evaluation_result"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "id": "95ce4240-f5a0-4810-8d09-b2f4c9e18b7f",
-            "metadata": {},
-            "source": [
-                "## Providing List of Valid Tools\n",
-                "\n",
-                "By default, the evaluator doesn't take into account the tools the agent is permitted to call. You can provide these to the evaluator via the `agent_tools` argument.\n"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 7,
-            "id": "24c10566-2ef5-45c5-9213-a8fb28e2ca1f",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "from langchain.evaluation import load_evaluator\n",
-                "\n",
-                "evaluator = load_evaluator(\"trajectory\", agent_tools=[ping, trace_route])"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 8,
-            "id": "7b995786-5b78-4d9e-8e8a-1f2a203113e2",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "data": {
-                        "text/plain": [
-                            "{'score': 1.0,\n",
-                            " 'reasoning': \"i. The final answer is helpful. It directly answers the user's question about the latency for the specified website.\\n\\nii. The AI language model uses a logical sequence of tools to answer the question. In this case, only one tool was needed to answer the question, and the model chose the correct one.\\n\\niii. The AI language model uses the tool in a helpful way. The 'ping' tool was used to determine the latency of the website, which was the information the user was seeking.\\n\\niv. The AI language model does not use too many steps to answer the question. Only one step was needed and used.\\n\\nv. The appropriate tool was used to answer the question. The 'ping' tool is designed to measure latency, which was the information the user was seeking.\\n\\nGiven these considerations, the AI language model's performance in answering this question is excellent.\"}"
-                        ]
-                    },
-                    "execution_count": 8,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "evaluation_result = evaluator.evaluate_agent_trajectory(\n",
-                "    prediction=result[\"output\"],\n",
-                "    input=result[\"input\"],\n",
-                "    agent_trajectory=result[\"intermediate_steps\"],\n",
-                ")\n",
-                "evaluation_result"
-            ]
-        }
-    ],
-    "metadata": {
-        "kernelspec": {
-            "display_name": "Python 3 (ipykernel)",
-            "language": "python",
-            "name": "python3"
-        },
-        "language_info": {
-            "codemirror_mode": {
-                "name": "ipython",
-                "version": 3
-            },
-            "file_extension": ".py",
-            "mimetype": "text/x-python",
-            "name": "python",
-            "nbconvert_exporter": "python",
-            "pygments_lexer": "ipython3",
-            "version": "3.11.2"
-        }
-    },
-    "nbformat": 4,
-    "nbformat_minor": 5
-}

docs/docs/guides/fallbacks.ipynb

@@ -1,432 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "19c9cbd6",
-   "metadata": {},
-   "source": [
-    "# Fallbacks\n",
-    "\n",
-    "When working with language models, you may often encounter issues from the underlying APIs, whether these be rate limiting or downtime. Therefore, as you go to move your LLM applications into production it becomes more and more important to safeguard against these. That's why we've introduced the concept of fallbacks. \n",
-    "\n",
-    "A **fallback** is an alternative plan that may be used in an emergency.\n",
-    "\n",
-    "Crucially, fallbacks can be applied not only on the LLM level but on the whole runnable level. This is important because often times different models require different prompts. So if your call to OpenAI fails, you don't just want to send the same prompt to Anthropic - you probably want to use a different prompt template and send a different version there."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "a6bb9ba9",
-   "metadata": {},
-   "source": [
-    "## Fallback for LLM API Errors\n",
-    "\n",
-    "This is maybe the most common use case for fallbacks. A request to an LLM API can fail for a variety of reasons - the API could be down, you could have hit rate limits, any number of things. Therefore, using fallbacks can help protect against these types of things.\n",
-    "\n",
-    "IMPORTANT: By default, a lot of the LLM wrappers catch errors and retry. You will most likely want to turn those off when working with fallbacks. Otherwise the first wrapper will keep on retrying and not failing."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "d3e893bf",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chat_models import ChatOpenAI, ChatAnthropic"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "4847c82d",
-   "metadata": {},
-   "source": [
-    "First, let's mock out what happens if we hit a RateLimitError from OpenAI"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 21,
-   "id": "dfdd8bf5",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from unittest.mock import patch\n",
-    "from openai.error import RateLimitError"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 24,
-   "id": "e6fdffc1",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Note that we set max_retries = 0 to avoid retrying on RateLimits, etc\n",
-    "openai_llm = ChatOpenAI(max_retries=0)\n",
-    "anthropic_llm = ChatAnthropic()\n",
-    "llm = openai_llm.with_fallbacks([anthropic_llm])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 27,
-   "id": "584461ab",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Hit error\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Let's use just the OpenAI LLm first, to show that we run into an error\n",
-    "with patch('openai.ChatCompletion.create', side_effect=RateLimitError()):\n",
-    "    try:\n",
-    "         print(openai_llm.invoke(\"Why did the chicken cross the road?\"))\n",
-    "    except:\n",
-    "        print(\"Hit error\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 28,
-   "id": "4fc1e673",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "content=' I don\\'t actually know why the chicken crossed the road, but here are some possible humorous answers:\\n\\n- To get to the other side!\\n\\n- It was too chicken to just stand there. \\n\\n- It wanted a change of scenery.\\n\\n- It wanted to show the possum it could be done.\\n\\n- It was on its way to a poultry farmers\\' convention.\\n\\nThe joke plays on the double meaning of \"the other side\" - literally crossing the road to the other side, or the \"other side\" meaning the afterlife. So it\\'s an anti-joke, with a silly or unexpected pun as the answer.' additional_kwargs={} example=False\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Now let's try with fallbacks to Anthropic\n",
-    "with patch('openai.ChatCompletion.create', side_effect=RateLimitError()):\n",
-    "    try:\n",
-    "         print(llm.invoke(\"Why did the chicken cross the road?\"))\n",
-    "    except:\n",
-    "        print(\"Hit error\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f00bea25",
-   "metadata": {},
-   "source": [
-    "We can use our \"LLM with Fallbacks\" as we would a normal LLM."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 29,
-   "id": "4f8eaaa0",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "content=\" I don't actually know why the kangaroo crossed the road, but I can take a guess! Here are some possible reasons:\\n\\n- To get to the other side (the classic joke answer!)\\n\\n- It was trying to find some food or water \\n\\n- It was trying to find a mate during mating season\\n\\n- It was fleeing from a predator or perceived threat\\n\\n- It was disoriented and crossed accidentally \\n\\n- It was following a herd of other kangaroos who were crossing\\n\\n- It wanted a change of scenery or environment \\n\\n- It was trying to reach a new habitat or territory\\n\\nThe real reason is unknown without more context, but hopefully one of those potential explanations does the joke justice! Let me know if you have any other animal jokes I can try to decipher.\" additional_kwargs={} example=False\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain.prompts import ChatPromptTemplate\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", \"You're a nice assistant who always includes a compliment in your response\"),\n",
-    "        (\"human\", \"Why did the {animal} cross the road\"),\n",
-    "    ]\n",
-    ")\n",
-    "chain = prompt | llm\n",
-    "with patch('openai.ChatCompletion.create', side_effect=RateLimitError()):\n",
-    "    try:\n",
-    "         print(chain.invoke({\"animal\": \"kangaroo\"}))\n",
-    "    except:\n",
-    "        print(\"Hit error\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "8d62241b",
-   "metadata": {},
-   "source": [
-    "## Fallback for Sequences\n",
-    "\n",
-    "We can also create fallbacks for sequences, that are sequences themselves. Here we do that with two different models: ChatOpenAI and then normal OpenAI (which does not use a chat model). Because OpenAI is NOT a chat model, you likely want a different prompt."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 30,
-   "id": "6d0b8056",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# First let's create a chain with a ChatModel\n",
-    "# We add in a string output parser here so the outputs between the two are the same type\n",
-    "from langchain.schema.output_parser import StrOutputParser\n",
-    "\n",
-    "chat_prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", \"You're a nice assistant who always includes a compliment in your response\"),\n",
-    "        (\"human\", \"Why did the {animal} cross the road\"),\n",
-    "    ]\n",
-    ")\n",
-    "# Here we're going to use a bad model name to easily create a chain that will error\n",
-    "chat_model = ChatOpenAI(model_name=\"gpt-fake\")\n",
-    "bad_chain = chat_prompt | chat_model | StrOutputParser()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 31,
-   "id": "8d1fc2a5",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Now lets create a chain with the normal OpenAI model\n",
-    "from langchain.llms import OpenAI\n",
-    "from langchain.prompts import PromptTemplate\n",
-    "\n",
-    "prompt_template = \"\"\"Instructions: You should always include a compliment in your response.\n",
-    "\n",
-    "Question: Why did the {animal} cross the road?\"\"\"\n",
-    "prompt = PromptTemplate.from_template(prompt_template)\n",
-    "llm = OpenAI()\n",
-    "good_chain = prompt | llm"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 32,
-   "id": "283bfa44",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'\\n\\nAnswer: The turtle crossed the road to get to the other side, and I have to say he had some impressive determination.'"
-      ]
-     },
-     "execution_count": 32,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# We can now create a final chain which combines the two\n",
-    "chain = bad_chain.with_fallbacks([good_chain])\n",
-    "chain.invoke({\"animal\": \"turtle\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "ec4685b4",
-   "metadata": {},
-   "source": [
-    "## Fallback for Long Inputs\n",
-    "\n",
-    "One of the big limiting factors of LLMs is their context window. Usually, you can count and track the length of prompts before sending them to an LLM, but in situations where that is hard/complicated, you can fallback to a model with a longer context length."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 34,
-   "id": "564b84c9",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "short_llm = ChatOpenAI()\n",
-    "long_llm = ChatOpenAI(model=\"gpt-3.5-turbo-16k\")\n",
-    "llm = short_llm.with_fallbacks([long_llm])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 38,
-   "id": "5e27a775",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "inputs = \"What is the next number: \" + \", \".join([\"one\", \"two\"] * 3000)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 40,
-   "id": "0a502731",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "This model's maximum context length is 4097 tokens. However, your messages resulted in 12012 tokens. Please reduce the length of the messages.\n"
-     ]
-    }
-   ],
-   "source": [
-    "try:\n",
-    "    print(short_llm.invoke(inputs))\n",
-    "except Exception as e:\n",
-    "    print(e)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 41,
-   "id": "d91ba5d7",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "content='The next number in the sequence is two.' additional_kwargs={} example=False\n"
-     ]
-    }
-   ],
-   "source": [
-    "try:\n",
-    "    print(llm.invoke(inputs))\n",
-    "except Exception as e:\n",
-    "    print(e)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2a6735df",
-   "metadata": {},
-   "source": [
-    "## Fallback to Better Model\n",
-    "\n",
-    "Often times we ask models to output format in a specific format (like JSON). Models like GPT-3.5 can do this okay, but sometimes struggle. This naturally points to fallbacks - we can try with GPT-3.5 (faster, cheaper), but then if parsing fails we can use GPT-4."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 42,
-   "id": "867a3793",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.output_parsers import DatetimeOutputParser"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 67,
-   "id": "b8d9959d",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "prompt = ChatPromptTemplate.from_template(\n",
-    "    \"what time was {event} (in %Y-%m-%dT%H:%M:%S.%fZ format - only return this value)\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 75,
-   "id": "98087a76",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# In this case we are going to do the fallbacks on the LLM + output parser level\n",
-    "# Because the error will get raised in the OutputParser\n",
-    "openai_35 = ChatOpenAI() | DatetimeOutputParser()\n",
-    "openai_4 = ChatOpenAI(model=\"gpt-4\")| DatetimeOutputParser()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 77,
-   "id": "17ec9e8f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "only_35 = prompt | openai_35 \n",
-    "fallback_4 = prompt | openai_35.with_fallbacks([openai_4])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 80,
-   "id": "7e536f0b",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Error: Could not parse datetime string: The Super Bowl in 1994 took place on January 30th at 3:30 PM local time. Converting this to the specified format (%Y-%m-%dT%H:%M:%S.%fZ) results in: 1994-01-30T15:30:00.000Z\n"
-     ]
-    }
-   ],
-   "source": [
-    "try:\n",
-    "    print(only_35.invoke({\"event\": \"the superbowl in 1994\"}))\n",
-    "except Exception as e:\n",
-    "    print(f\"Error: {e}\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 81,
-   "id": "01355c5e",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "1994-01-30 15:30:00\n"
-     ]
-    }
-   ],
-   "source": [
-    "try:\n",
-    "    print(fallback_4.invoke({\"event\": \"the superbowl in 1994\"}))\n",
-    "except Exception as e:\n",
-    "    print(f\"Error: {e}\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "c537f9d0",
-   "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": "3.10.12"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/docs/guides/langsmith/index.md

@@ -1,22 +0,0 @@
-# LangSmith
-
-import DocCardList from "@theme/DocCardList";
-
-[LangSmith](https://smith.langchain.com) helps you trace and evaluate your language model applications and intelligent agents to help you
-move from prototype to production.
-
-Check out the [interactive walkthrough](/docs/guides/langsmith/walkthrough) below to get started.
-
-For more information, please refer to the [LangSmith documentation](https://docs.smith.langchain.com/).
-
-For tutorials and other end-to-end examples demonstrating ways to integrate LangSmith in your workflow,
-check out the [LangSmith Cookbook](https://github.com/langchain-ai/langsmith-cookbook). Some of the guides therein include:
-
-- Leveraging user feedback in your JS application ([link](https://github.com/langchain-ai/langsmith-cookbook/blob/main/feedback-examples/nextjs/README.md)).
-- Building an automated feedback pipeline ([link](https://github.com/langchain-ai/langsmith-cookbook/blob/main/feedback-examples/algorithmic-feedback/algorithmic_feedback.ipynb)).
-- How to evaluate and audit your RAG workflows ([link](https://github.com/langchain-ai/langsmith-cookbook/tree/main/testing-examples/qa-correctness)).
-- How to fine-tune a LLM on real usage data ([link](https://github.com/langchain-ai/langsmith-cookbook/blob/main/fine-tuning-examples/export-to-openai/fine-tuning-on-chat-runs.ipynb)).
-- How to use the [LangChain Hub](https://smith.langchain.com/hub) to version your prompts ([link](https://github.com/langchain-ai/langsmith-cookbook/blob/main/hub-examples/retrieval-qa-chain/retrieval-qa.ipynb))
-
-
-<DocCardList />

docs/docs/guides/langsmith/walkthrough.ipynb

@@ -1,788 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "1a4596ea-a631-416d-a2a4-3577c140493d",
-   "metadata": {
-    "tags": []
-   },
-   "source": [
-    "# LangSmith Walkthrough\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/guides/langsmith/walkthrough.ipynb)\n",
-    "\n",
-    "LangChain makes it easy to prototype LLM applications and Agents. However, delivering LLM applications to production can be deceptively difficult. You will likely have to heavily customize and iterate on your prompts, chains, and other components to create a high-quality product.\n",
-    "\n",
-    "To aid in this process, we've launched LangSmith, a unified platform for debugging, testing, and monitoring your LLM applications.\n",
-    "\n",
-    "When might this come in handy? You may find it useful when you want to:\n",
-    "\n",
-    "- Quickly debug a new chain, agent, or set of tools\n",
-    "- Visualize how components (chains, llms, retrievers, etc.) relate and are used\n",
-    "- Evaluate different prompts and LLMs for a single component\n",
-    "- Run a given chain several times over a dataset to ensure it consistently meets a quality bar\n",
-    "- Capture usage traces and using LLMs or analytics pipelines to generate insights"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "138fbb8f-960d-4d26-9dd5-6d6acab3ee55",
-   "metadata": {},
-   "source": [
-    "## Prerequisites\n",
-    "\n",
-    "**[Create a LangSmith account](https://smith.langchain.com/) and create an API key (see bottom left corner). Familiarize yourself with the platform by looking through the [docs](https://docs.smith.langchain.com/)**\n",
-    "\n",
-    "Note LangSmith is in closed beta; we're in the process of rolling it out to more users. However, you can fill out the form on the website for expedited access.\n",
-    "\n",
-    "Now, let's get started!"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2d77d064-41b4-41fb-82e6-2d16461269ec",
-   "metadata": {
-    "tags": []
-   },
-   "source": [
-    "## Log runs to LangSmith\n",
-    "\n",
-    "First, configure your environment variables to tell LangChain to log traces. This is done by setting the `LANGCHAIN_TRACING_V2` environment variable to true.\n",
-    "You can tell LangChain which project to log to by setting the `LANGCHAIN_PROJECT` environment variable (if this isn't set, runs will be logged to the `default` project). This will automatically create the project for you if it doesn't exist. You must also set the `LANGCHAIN_ENDPOINT` and `LANGCHAIN_API_KEY` environment variables.\n",
-    "\n",
-    "For more information on other ways to set up tracing, please reference the [LangSmith documentation](https://docs.smith.langchain.com/docs/).\n",
-    "\n",
-    "**NOTE:** You must also set your `OPENAI_API_KEY` environment variables in order to run the following tutorial.\n",
-    "\n",
-    "**NOTE:** You can only access an API key when you first create it. Keep it somewhere safe.\n",
-    "\n",
-    "**NOTE:** You can also use a context manager in python to log traces using\n",
-    "```python\n",
-    "from langchain.callbacks.manager import tracing_v2_enabled\n",
-    "\n",
-    "with tracing_v2_enabled(project_name=\"My Project\"):\n",
-    "    agent.run(\"How many people live in canada as of 2023?\")\n",
-    "```\n",
-    "\n",
-    "However, in this example, we will use environment variables."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "e4780363-f05a-4649-8b1a-9b449f960ce4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install -U langchain langsmith langchainhub --quiet\n",
-    "%pip install openai tiktoken pandas duckduckgo-search --quiet"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "904db9a5-f387-4a57-914c-c8af8d39e249",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "from uuid import uuid4\n",
-    "\n",
-    "unique_id = uuid4().hex[0:8]\n",
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_PROJECT\"] = f\"Tracing Walkthrough - {unique_id}\"\n",
-    "os.environ[\"LANGCHAIN_ENDPOINT\"] = \"https://api.smith.langchain.com\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = \"<YOUR-API-KEY>\"  # Update to your API key\n",
-    "\n",
-    "# Used by the agent in this tutorial\n",
-    "os.environ[\"OPENAI_API_KEY\"] = \"<YOUR-OPENAI-API-KEY>\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "8ee7f34b-b65c-4e09-ad52-e3ace78d0221",
-   "metadata": {
-    "tags": []
-   },
-   "source": [
-    "Create the langsmith client to interact with the API"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "510b5ca0",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langsmith import Client\n",
-    "\n",
-    "client = Client()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "ca27fa11-ddce-4af0-971e-c5c37d5b92ef",
-   "metadata": {},
-   "source": [
-    "Create a LangChain component and log runs to the platform. In this example, we will create a ReAct-style agent with access to a general search tool (DuckDuckGo). The agent's prompt can be viewed in the [Hub here](https://smith.langchain.com/hub/wfh/langsmith-agent-prompt)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "a0fbfbba-3c82-4298-a312-9cec016d9d2e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain import hub\n",
-    "from langchain.agents import AgentExecutor\n",
-    "from langchain.agents.format_scratchpad import format_to_openai_functions\n",
-    "from langchain.agents.output_parsers import OpenAIFunctionsAgentOutputParser\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.tools import DuckDuckGoSearchResults\n",
-    "from langchain.tools.render import format_tool_to_openai_function\n",
-    "\n",
-    "# Fetches the latest version of this prompt\n",
-    "prompt = hub.pull(\"wfh/langsmith-agent-prompt:latest\")\n",
-    "\n",
-    "llm = ChatOpenAI(\n",
-    "    model=\"gpt-3.5-turbo-16k\",\n",
-    "    temperature=0,\n",
-    ")\n",
-    "\n",
-    "tools = [\n",
-    "    DuckDuckGoSearchResults(\n",
-    "        name=\"duck_duck_go\"\n",
-    "    ),  # General internet search using DuckDuckGo\n",
-    "]\n",
-    "\n",
-    "llm_with_tools = llm.bind(functions=[format_tool_to_openai_function(t) for t in tools])\n",
-    "\n",
-    "runnable_agent = (\n",
-    "    {\n",
-    "        \"input\": lambda x: x[\"input\"],\n",
-    "        \"agent_scratchpad\": lambda x: format_to_openai_functions(\n",
-    "            x[\"intermediate_steps\"]\n",
-    "        ),\n",
-    "    }\n",
-    "    | prompt\n",
-    "    | llm_with_tools\n",
-    "    | OpenAIFunctionsAgentOutputParser()\n",
-    ")\n",
-    "\n",
-    "agent_executor = AgentExecutor(\n",
-    "    agent=runnable_agent, tools=tools, handle_parsing_errors=True\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "cab51e1e-8270-452c-ba22-22b5b5951899",
-   "metadata": {},
-   "source": [
-    "We are running the agent concurrently on multiple inputs to reduce latency. Runs get logged to LangSmith in the background so execution latency is unaffected."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "19537902-b95c-4390-80a4-f6c9a937081e",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "inputs = [\n",
-    "    \"What is LangChain?\",\n",
-    "    \"What's LangSmith?\",\n",
-    "    \"When was Llama-v2 released?\",\n",
-    "    \"Who trained Llama-v2?\",\n",
-    "    \"What is the langsmith cookbook?\",\n",
-    "    \"When did langchain first announce the hub?\",\n",
-    "]\n",
-    "\n",
-    "results = agent_executor.batch([{\"input\": x} for x in inputs], return_exceptions=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "9a6a764c-5d7a-4de7-a916-3ecc987d5bb6",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[{'input': 'What is LangChain?',\n",
-       "  'output': 'I\\'m sorry, but I couldn\\'t find any information about \"LangChain\". Could you please provide more context or clarify your question?'},\n",
-       " {'input': \"What's LangSmith?\",\n",
-       "  'output': 'I\\'m sorry, but I couldn\\'t find any information about \"LangSmith\". It could be a specific term or a company that is not widely known. Can you provide more context or clarify what you are referring to?'}]"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "results[:2]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "9decb964-be07-4b6c-9802-9825c8be7b64",
-   "metadata": {},
-   "source": [
-    "Assuming you've successfully set up your environment, your agent traces should show up in the `Projects` section in the [app](https://smith.langchain.com/). Congrats!\n",
-    "\n",
-    "![Initial Runs](./img/log_traces.png)\n",
-    "\n",
-    "It looks like the agent isn't effectively using the tools though. Let's evaluate this so we have a baseline."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "6c43c311-4e09-4d57-9ef3-13afb96ff430",
-   "metadata": {},
-   "source": [
-    "## Evaluate Agent\n",
-    "\n",
-    "In addition to logging runs, LangSmith also allows you to test and evaluate your LLM applications.\n",
-    "\n",
-    "In this section, you will leverage LangSmith to create a benchmark dataset and run AI-assisted evaluators on an agent. You will do so in a few steps:\n",
-    "\n",
-    "1. Create a dataset\n",
-    "2. Initialize a new agent to benchmark\n",
-    "3. Configure evaluators to grade an agent's output\n",
-    "4. Run the agent over the dataset and evaluate the results"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "beab1a29-b79d-4a99-b5b1-0870c2d772b1",
-   "metadata": {},
-   "source": [
-    "### 1. Create a LangSmith dataset\n",
-    "\n",
-    "Below, we use the LangSmith client to create a dataset from the input questions from above and a list labels. You will use these later to measure performance for a new agent. A dataset is a collection of examples, which are nothing more than input-output pairs you can use as test cases to your application.\n",
-    "\n",
-    "For more information on datasets, including how to create them from CSVs or other files or how to create them in the platform, please refer to the [LangSmith documentation](https://docs.smith.langchain.com/)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "43fd40b2-3f02-4e51-9343-705aafe90a36",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "outputs = [\n",
-    "    \"LangChain is an open-source framework for building applications using large language models. It is also the name of the company building LangSmith.\",\n",
-    "    \"LangSmith is a unified platform for debugging, testing, and monitoring language model applications and agents powered by LangChain\",\n",
-    "    \"July 18, 2023\",\n",
-    "    \"The langsmith cookbook is a github repository containing detailed examples of how to use LangSmith to debug, evaluate, and monitor large language model-powered applications.\",\n",
-    "    \"September 5, 2023\",\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "17580c4b-bd04-4dde-9d21-9d4edd25b00d",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "dataset_name = f\"agent-qa-{unique_id}\"\n",
-    "\n",
-    "dataset = client.create_dataset(\n",
-    "    dataset_name, description=\"An example dataset of questions over the LangSmith documentation.\"\n",
-    ")\n",
-    "\n",
-    "for query, answer in zip(inputs, outputs):\n",
-    "    client.create_example(inputs={\"input\": query}, outputs={\"output\": answer}, dataset_id=dataset.id)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "8adfd29c-b258-49e5-94b4-74597a12ba16",
-   "metadata": {
-    "tags": []
-   },
-   "source": [
-    "### 2. Initialize a new agent to benchmark\n",
-    "\n",
-    "LangSmith lets you evaluate any LLM, chain, agent, or even a custom function. Conversational agents are stateful (they have memory); to ensure that this state isn't shared between dataset runs, we will pass in a `chain_factory` (aka a `constructor`) function to initialize for each call.\n",
-    "\n",
-    "In this case, we will test an agent that uses OpenAI's function calling endpoints."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "f42d8ecc-d46a-448b-a89c-04b0f6907f75",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.agents import AgentType, initialize_agent, load_tools, AgentExecutor\n",
-    "from langchain.agents.format_scratchpad import format_to_openai_functions\n",
-    "from langchain.agents.output_parsers import OpenAIFunctionsAgentOutputParser\n",
-    "from langchain.tools.render import format_tool_to_openai_function\n",
-    "from langchain import hub\n",
-    "\n",
-    "\n",
-    "# Since chains can be stateful (e.g. they can have memory), we provide\n",
-    "# a way to initialize a new chain for each row in the dataset. This is done\n",
-    "# by passing in a factory function that returns a new chain for each row.\n",
-    "def agent_factory(prompt):    \n",
-    "    llm_with_tools = llm.bind(\n",
-    "        functions=[format_tool_to_openai_function(t) for t in tools]\n",
-    "    )\n",
-    "    runnable_agent = (\n",
-    "            {\n",
-    "                \"input\": lambda x: x[\"input\"],\n",
-    "                \"agent_scratchpad\": lambda x: format_to_openai_functions(x['intermediate_steps'])\n",
-    "            } \n",
-    "             | prompt \n",
-    "             | llm_with_tools \n",
-    "             | OpenAIFunctionsAgentOutputParser()\n",
-    "    )\n",
-    "    return  AgentExecutor(agent=runnable_agent, tools=tools, handle_parsing_errors=True)\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "9cb9ef53",
-   "metadata": {},
-   "source": [
-    "### 3. Configure evaluation\n",
-    "\n",
-    "Manually comparing the results of chains in the UI is effective, but it can be time consuming.\n",
-    "It can be helpful to use automated metrics and AI-assisted feedback to evaluate your component's performance.\n",
-    "\n",
-    "Below, we will create some pre-implemented run evaluators that do the following:\n",
-    "- Compare results against ground truth labels.\n",
-    "- Measure semantic (dis)similarity using embedding distance\n",
-    "- Evaluate 'aspects' of the agent's response in a reference-free manner using custom criteria\n",
-    "\n",
-    "For a longer discussion of how to select an appropriate evaluator for your use case and how to create your own\n",
-    "custom evaluators, please refer to the [LangSmith documentation](https://docs.smith.langchain.com/).\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "a25dc281",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.evaluation import EvaluatorType\n",
-    "from langchain.smith import RunEvalConfig\n",
-    "\n",
-    "evaluation_config = RunEvalConfig(\n",
-    "    # Evaluators can either be an evaluator type (e.g., \"qa\", \"criteria\", \"embedding_distance\", etc.) or a configuration for that evaluator\n",
-    "    evaluators=[\n",
-    "        # Measures whether a QA response is \"Correct\", based on a reference answer\n",
-    "        # You can also select via the raw string \"qa\"\n",
-    "        EvaluatorType.QA,\n",
-    "        # Measure the embedding distance between the output and the reference answer\n",
-    "        # Equivalent to: EvalConfig.EmbeddingDistance(embeddings=OpenAIEmbeddings())\n",
-    "        EvaluatorType.EMBEDDING_DISTANCE,\n",
-    "        # Grade whether the output satisfies the stated criteria.\n",
-    "        # You can select a default one such as \"helpfulness\" or provide your own.\n",
-    "        RunEvalConfig.LabeledCriteria(\"helpfulness\"),\n",
-    "        # The LabeledScoreString evaluator outputs a score on a scale from 1-10.\n",
-    "        # You can use default criteria or write our own rubric\n",
-    "        RunEvalConfig.LabeledScoreString(\n",
-    "            {\n",
-    "                 \"accuracy\": \"\"\"\n",
-    "Score 1: The answer is completely unrelated to the reference.\n",
-    "Score 3: The answer has minor relevance but does not align with the reference.\n",
-    "Score 5: The answer has moderate relevance but contains inaccuracies.\n",
-    "Score 7: The answer aligns with the reference but has minor errors or omissions.\n",
-    "Score 10: The answer is completely accurate and aligns perfectly with the reference.\"\"\"\n",
-    "            },\n",
-    "            normalize_by=10,\n",
-    "        ),\n",
-    "    ],\n",
-    "    # You can add custom StringEvaluator or RunEvaluator objects here as well, which will automatically be\n",
-    "    # applied to each prediction. Check out the docs for examples.\n",
-    "    custom_evaluators=[],\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "07885b10",
-   "metadata": {
-    "tags": []
-   },
-   "source": [
-    "### 4. Run the agent and evaluators\n",
-    "\n",
-    "Use the [run_on_dataset](https://api.python.langchain.com/en/latest/smith/langchain.smith.evaluation.runner_utils.run_on_dataset.html#langchain.smith.evaluation.runner_utils.run_on_dataset) (or asynchronous [arun_on_dataset](https://api.python.langchain.com/en/latest/smith/langchain.smith.evaluation.runner_utils.arun_on_dataset.html#langchain.smith.evaluation.runner_utils.arun_on_dataset)) function to evaluate your model. This will:\n",
-    "1. Fetch example rows from the specified dataset.\n",
-    "2. Run your agent (or any custom function) on each example.\n",
-    "3. Apply evaluators to the resulting run traces and corresponding reference examples to generate automated feedback.\n",
-    "\n",
-    "The results will be visible in the LangSmith app."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "af8c8469-d70d-46d9-8fcd-517a1ccc7c4b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain import hub\n",
-    "\n",
-    "# We will test this version of the prompt\n",
-    "prompt = hub.pull(\"wfh/langsmith-agent-prompt:798e7324\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "3733269b-8085-4644-9d5d-baedcff13a2f",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "View the evaluation results for project 'runnable-agent-test-5d466cbc-bf2162aa' at:\n",
-      "https://smith.langchain.com/o/ebbaf2eb-769b-4505-aca2-d11de10372a4/projects/p/0c3d22fa-f8b0-4608-b086-2187c18361a5\n",
-      "[>                                                 ] 0/5"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Chain failed for example 54b4fce8-4492-409d-94af-708f51698b39 with inputs {'input': 'Who trained Llama-v2?'}\n",
-      "Error Type: TypeError, Message: DuckDuckGoSearchResults._run() got an unexpected keyword argument 'arg1'\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[------------------------------------------------->] 5/5\n",
-      " Eval quantiles:\n",
-      "                               0.25       0.5      0.75      mean      mode\n",
-      "embedding_cosine_distance  0.086614  0.118841  0.183672  0.151444  0.050158\n",
-      "correctness                0.000000  0.500000  1.000000  0.500000  0.000000\n",
-      "score_string:accuracy      0.775000  1.000000  1.000000  0.775000  1.000000\n",
-      "helpfulness                0.750000  1.000000  1.000000  0.750000  1.000000\n"
-     ]
-    }
-   ],
-   "source": [
-    "import functools\n",
-    "from langchain.smith import (\n",
-    "    arun_on_dataset,\n",
-    "    run_on_dataset, \n",
-    ")\n",
-    "\n",
-    "chain_results = run_on_dataset(\n",
-    "    dataset_name=dataset_name,\n",
-    "    llm_or_chain_factory=functools.partial(agent_factory, prompt=prompt),\n",
-    "    evaluation=evaluation_config,\n",
-    "    verbose=True,\n",
-    "    client=client,\n",
-    "    project_name=f\"runnable-agent-test-5d466cbc-{unique_id}\",\n",
-    "    tags=[\"testing-notebook\", \"prompt:5d466cbc\"],  # Optional, adds a tag to the resulting chain runs\n",
-    ")\n",
-    "\n",
-    "# Sometimes, the agent will error due to parsing issues, incompatible tool inputs, etc.\n",
-    "# These are logged as warnings here and captured as errors in the tracing UI."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "cdacd159-eb4d-49e9-bb2a-c55322c40ed4",
-   "metadata": {
-    "tags": []
-   },
-   "source": [
-    "### Review the test results\n",
-    "\n",
-    "You can review the test results tracing UI below by clicking the URL in the output above or navigating to the \"Testing & Datasets\" page in LangSmith  **\"agent-qa-{unique_id}\"** dataset. \n",
-    "\n",
-    "![test results](./img/test_results.png)\n",
-    "\n",
-    "This will show the new runs and the feedback logged from the selected evaluators. You can also explore a summary of the results in tabular format below."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "9da60638-5be8-4b5f-a721-2c6627aeaf0c",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>embedding_cosine_distance</th>\n",
-       "      <th>correctness</th>\n",
-       "      <th>score_string:accuracy</th>\n",
-       "      <th>helpfulness</th>\n",
-       "      <th>input</th>\n",
-       "      <th>output</th>\n",
-       "      <th>reference</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>42b639a2-17c4-4031-88a9-0ce2c45781ce</th>\n",
-       "      <td>0.317938</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>{'input': 'What is the langsmith cookbook?'}</td>\n",
-       "      <td>{'input': 'What is the langsmith cookbook?', '...</td>\n",
-       "      <td>{'output': 'September 5, 2023'}</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>54b4fce8-4492-409d-94af-708f51698b39</th>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>{'input': 'Who trained Llama-v2?'}</td>\n",
-       "      <td>{'Error': 'TypeError(\"DuckDuckGoSearchResults....</td>\n",
-       "      <td>{'output': 'The langsmith cookbook is a github...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>8ae5104e-bbb4-42cc-a84e-f9b8cfc92b8e</th>\n",
-       "      <td>0.138916</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>{'input': 'When was Llama-v2 released?'}</td>\n",
-       "      <td>{'input': 'When was Llama-v2 released?', 'outp...</td>\n",
-       "      <td>{'output': 'July 18, 2023'}</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>678c0363-3ed1-410a-811f-ebadef2e783a</th>\n",
-       "      <td>0.050158</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>{'input': 'What's LangSmith?'}</td>\n",
-       "      <td>{'input': 'What's LangSmith?', 'output': 'Lang...</td>\n",
-       "      <td>{'output': 'LangSmith is a unified platform fo...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>762a616c-7aab-419c-9001-b43ab6200d26</th>\n",
-       "      <td>0.098766</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.1</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>{'input': 'What is LangChain?'}</td>\n",
-       "      <td>{'input': 'What is LangChain?', 'output': 'Lan...</td>\n",
-       "      <td>{'output': 'LangChain is an open-source framew...</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                                      embedding_cosine_distance  correctness  \\\n",
-       "42b639a2-17c4-4031-88a9-0ce2c45781ce                   0.317938          0.0   \n",
-       "54b4fce8-4492-409d-94af-708f51698b39                        NaN          NaN   \n",
-       "8ae5104e-bbb4-42cc-a84e-f9b8cfc92b8e                   0.138916          1.0   \n",
-       "678c0363-3ed1-410a-811f-ebadef2e783a                   0.050158          1.0   \n",
-       "762a616c-7aab-419c-9001-b43ab6200d26                   0.098766          0.0   \n",
-       "\n",
-       "                                      score_string:accuracy  helpfulness  \\\n",
-       "42b639a2-17c4-4031-88a9-0ce2c45781ce                    1.0          1.0   \n",
-       "54b4fce8-4492-409d-94af-708f51698b39                    NaN          NaN   \n",
-       "8ae5104e-bbb4-42cc-a84e-f9b8cfc92b8e                    1.0          1.0   \n",
-       "678c0363-3ed1-410a-811f-ebadef2e783a                    1.0          1.0   \n",
-       "762a616c-7aab-419c-9001-b43ab6200d26                    0.1          0.0   \n",
-       "\n",
-       "                                                                             input  \\\n",
-       "42b639a2-17c4-4031-88a9-0ce2c45781ce  {'input': 'What is the langsmith cookbook?'}   \n",
-       "54b4fce8-4492-409d-94af-708f51698b39            {'input': 'Who trained Llama-v2?'}   \n",
-       "8ae5104e-bbb4-42cc-a84e-f9b8cfc92b8e      {'input': 'When was Llama-v2 released?'}   \n",
-       "678c0363-3ed1-410a-811f-ebadef2e783a                {'input': 'What's LangSmith?'}   \n",
-       "762a616c-7aab-419c-9001-b43ab6200d26               {'input': 'What is LangChain?'}   \n",
-       "\n",
-       "                                                                                 output  \\\n",
-       "42b639a2-17c4-4031-88a9-0ce2c45781ce  {'input': 'What is the langsmith cookbook?', '...   \n",
-       "54b4fce8-4492-409d-94af-708f51698b39  {'Error': 'TypeError(\"DuckDuckGoSearchResults....   \n",
-       "8ae5104e-bbb4-42cc-a84e-f9b8cfc92b8e  {'input': 'When was Llama-v2 released?', 'outp...   \n",
-       "678c0363-3ed1-410a-811f-ebadef2e783a  {'input': 'What's LangSmith?', 'output': 'Lang...   \n",
-       "762a616c-7aab-419c-9001-b43ab6200d26  {'input': 'What is LangChain?', 'output': 'Lan...   \n",
-       "\n",
-       "                                                                              reference  \n",
-       "42b639a2-17c4-4031-88a9-0ce2c45781ce                    {'output': 'September 5, 2023'}  \n",
-       "54b4fce8-4492-409d-94af-708f51698b39  {'output': 'The langsmith cookbook is a github...  \n",
-       "8ae5104e-bbb4-42cc-a84e-f9b8cfc92b8e                        {'output': 'July 18, 2023'}  \n",
-       "678c0363-3ed1-410a-811f-ebadef2e783a  {'output': 'LangSmith is a unified platform fo...  \n",
-       "762a616c-7aab-419c-9001-b43ab6200d26  {'output': 'LangChain is an open-source framew...  "
-      ]
-     },
-     "execution_count": 13,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain_results.to_dataframe()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "13aad317-73ff-46a7-a5a0-60b5b5295f02",
-   "metadata": {},
-   "source": [
-    "### (Optional) Compare to another prompt\n",
-    "\n",
-    "Now that we have our test run results, we can make changes to our agent and benchmark them. Let's try this again with a different prompt and see the results."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "5eeb023f-ded2-4d0f-b910-2a57d9675853",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "View the evaluation results for project 'runnable-agent-test-39f3bbd0-bf2162aa' at:\n",
-      "https://smith.langchain.com/o/ebbaf2eb-769b-4505-aca2-d11de10372a4/projects/p/fa721ccc-dd0f-41c9-bf80-22215c44efd4\n",
-      "[------------------------------------------------->] 5/5\n",
-      " Eval quantiles:\n",
-      "                               0.25       0.5      0.75      mean      mode\n",
-      "embedding_cosine_distance  0.059506  0.155538  0.212864  0.157915  0.043119\n",
-      "correctness                0.000000  0.000000  1.000000  0.400000  0.000000\n",
-      "score_string:accuracy      0.700000  1.000000  1.000000  0.880000  1.000000\n",
-      "helpfulness                1.000000  1.000000  1.000000  0.800000  1.000000\n"
-     ]
-    }
-   ],
-   "source": [
-    "candidate_prompt = hub.pull(\"wfh/langsmith-agent-prompt:39f3bbd0\")\n",
-    "\n",
-    "chain_results = run_on_dataset(\n",
-    "    dataset_name=dataset_name,\n",
-    "    llm_or_chain_factory=functools.partial(agent_factory, prompt=candidate_prompt),\n",
-    "    evaluation=evaluation_config,\n",
-    "    verbose=True,\n",
-    "    client=client,\n",
-    "    project_name=f\"runnable-agent-test-39f3bbd0-{unique_id}\",\n",
-    "    tags=[\"testing-notebook\", \"prompt:39f3bbd0\"],  # Optional, adds a tag to the resulting chain runs\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "591c819e-9932-45cf-adab-63727dd49559",
-   "metadata": {},
-   "source": [
-    "## Exporting datasets and runs\n",
-    "\n",
-    "LangSmith lets you export data to common formats such as CSV or JSONL directly in the web app. You can also use the client to fetch runs for further analysis, to store in your own database, or to share with others. Let's fetch the run traces from the evaluation run.\n",
-    "\n",
-    "**Note: It may be a few moments before all the runs are accessible.**"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "33bfefde-d1bb-4f50-9f7a-fd572ee76820",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "runs = client.list_runs(project_name=chain_results[\"project_name\"], execution_order=1)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "6595c888-1f5c-4ae3-9390-0a559f5575d1",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "# After some time, these will be populated.\n",
-    "client.read_project(project_name=chain_results[\"project_name\"]).feedback_stats"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2646f0fb-81d4-43ce-8a9b-54b8e19841e2",
-   "metadata": {
-    "tags": []
-   },
-   "source": [
-    "## Conclusion\n",
-    "\n",
-    "Congratulations! You have successfully traced and evaluated an agent using LangSmith!\n",
-    "\n",
-    "This was a quick guide to get started, but there are many more ways to use LangSmith to speed up your developer flow and produce better results.\n",
-    "\n",
-    "For more information on how you can get the most out of LangSmith, check out [LangSmith documentation](https://docs.smith.langchain.com/), and please reach out with questions, feature requests, or feedback at [support@langchain.dev](mailto:support@langchain.dev)."
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.2"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/docs/guides/local_llms.ipynb

@@ -1,602 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "b8982428",
-   "metadata": {},
-   "source": [
-    "# Run LLMs locally\n",
-    "\n",
-    "## Use case\n",
-    "\n",
-    "The popularity of projects like [PrivateGPT](https://github.com/imartinez/privateGPT), [llama.cpp](https://github.com/ggerganov/llama.cpp), and [GPT4All](https://github.com/nomic-ai/gpt4all) underscore the demand to run LLMs locally (on your own device).\n",
-    "\n",
-    "This has at least two important benefits:\n",
-    "\n",
-    "1. `Privacy`: Your data is not sent to a third party, and it is not subject to the terms of service of a commercial service\n",
-    "2. `Cost`: There is no inference fee, which is important for token-intensive applications (e.g., [long-running simulations](https://twitter.com/RLanceMartin/status/1691097659262820352?s=20), summarization)\n",
-    "\n",
-    "## Overview\n",
-    "\n",
-    "Running an LLM locally requires a few things:\n",
-    "\n",
-    "1. `Open-source LLM`: An open-source LLM that can be freely modified and shared \n",
-    "2. `Inference`: Ability to run this LLM on your device w/ acceptable latency\n",
-    "\n",
-    "### Open-source LLMs\n",
-    "\n",
-    "Users can now gain access to a rapidly growing set of [open-source LLMs](https://cameronrwolfe.substack.com/p/the-history-of-open-source-llms-better). \n",
-    "\n",
-    "These LLMs can be assessed across at least two dimensions (see figure):\n",
-    " \n",
-    "1. `Base model`: What is the base-model and how was it trained?\n",
-    "2. `Fine-tuning approach`: Was the base-model fine-tuned and, if so, what [set of instructions](https://cameronrwolfe.substack.com/p/beyond-llama-the-power-of-open-llms#%C2%A7alpaca-an-instruction-following-llama-model) was used?\n",
-    "\n",
-    "![Image description](/img/OSS_LLM_overview.png)\n",
-    "\n",
-    "The relative performance of these models can be assessed using several leaderboards, including:\n",
-    "\n",
-    "1. [LmSys](https://chat.lmsys.org/?arena)\n",
-    "2. [GPT4All](https://gpt4all.io/index.html)\n",
-    "3. [HuggingFace](https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard)\n",
-    "\n",
-    "### Inference\n",
-    "\n",
-    "A few frameworks for this have emerged to support inference of open-source LLMs on various devices:\n",
-    "\n",
-    "1. [`llama.cpp`](https://github.com/ggerganov/llama.cpp): C++ implementation of llama inference code with [weight optimization / quantization](https://finbarr.ca/how-is-llama-cpp-possible/)\n",
-    "2. [`gpt4all`](https://docs.gpt4all.io/index.html): Optimized C backend for inference\n",
-    "3. [`Ollama`](https://ollama.ai/): Bundles model weights and environment into an app that runs on device and serves the LLM \n",
-    "\n",
-    "In general, these frameworks will do a few things:\n",
-    "\n",
-    "1. `Quantization`: Reduce the memory footprint of the raw model weights\n",
-    "2. `Efficient implementation for inference`: Support inference on consumer hardware (e.g., CPU or laptop GPU)\n",
-    "\n",
-    "In particular, see [this excellent post](https://finbarr.ca/how-is-llama-cpp-possible/) on the importance of quantization.\n",
-    "\n",
-    "![Image description](/img/llama-memory-weights.png)\n",
-    "\n",
-    "With less precision, we radically decrease the memory needed to store the LLM in memory.\n",
-    "\n",
-    "In addition, we can see the importance of GPU memory bandwidth [sheet](https://docs.google.com/spreadsheets/d/1OehfHHNSn66BP2h3Bxp2NJTVX97icU0GmCXF6pK23H8/edit#gid=0)!\n",
-    "\n",
-    "A Mac M2 Max is 5-6x faster than a M1 for inference due to the larger GPU memory bandwidth.\n",
-    "\n",
-    "![Image description](/img/llama_t_put.png)\n",
-    "\n",
-    "## Quickstart\n",
-    "\n",
-    "[`Ollama`](https://ollama.ai/) is one way to easily run inference on macOS.\n",
-    " \n",
-    "The instructions [here](docs/integrations/llms/ollama) provide details, which we summarize:\n",
-    " \n",
-    "* [Download and run](https://ollama.ai/download) the app\n",
-    "* From command line, fetch a model from this [list of options](https://github.com/jmorganca/ollama): e.g., `ollama pull llama2`\n",
-    "* When the app is running, all models are automatically served on `localhost:11434`\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "86178adb",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "' The first man on the moon was Neil Armstrong, who landed on the moon on July 20, 1969 as part of the Apollo 11 mission. obviously.'"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain.llms import Ollama\n",
-    "llm = Ollama(model=\"llama2\")\n",
-    "llm(\"The first man on the moon was ...\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "343ab645",
-   "metadata": {},
-   "source": [
-    "Stream tokens as they are being generated."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 40,
-   "id": "9cd83603",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      " The first man to walk on the moon was Neil Armstrong, an American astronaut who was part of the Apollo 11 mission in 1969. февруари 20, 1969, Armstrong stepped out of the lunar module Eagle and onto the moon's surface, famously declaring \"That's one small step for man, one giant leap for mankind\" as he took his first steps. He was followed by fellow astronaut Edwin \"Buzz\" Aldrin, who also walked on the moon during the mission."
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "' The first man to walk on the moon was Neil Armstrong, an American astronaut who was part of the Apollo 11 mission in 1969. февруари 20, 1969, Armstrong stepped out of the lunar module Eagle and onto the moon\\'s surface, famously declaring \"That\\'s one small step for man, one giant leap for mankind\" as he took his first steps. He was followed by fellow astronaut Edwin \"Buzz\" Aldrin, who also walked on the moon during the mission.'"
-      ]
-     },
-     "execution_count": 40,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain.callbacks.manager import CallbackManager\n",
-    "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler \n",
-    "llm = Ollama(model=\"llama2\", \n",
-    "             callback_manager = CallbackManager([StreamingStdOutCallbackHandler()]))\n",
-    "llm(\"The first man on the moon was ...\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "5cb27414",
-   "metadata": {},
-   "source": [
-    "## Environment\n",
-    "\n",
-    "Inference speed is a challenge when running models locally (see above).\n",
-    "\n",
-    "To minimize latency, it is desirable to run models locally on GPU, which ships with many consumer laptops [e.g., Apple devices](https://www.apple.com/newsroom/2022/06/apple-unveils-m2-with-breakthrough-performance-and-capabilities/).\n",
-    "\n",
-    "And even with GPU, the available GPU memory bandwidth (as noted above) is important.\n",
-    "\n",
-    "### Running Apple silicon GPU\n",
-    "\n",
-    "`Ollama` will automatically utilize the GPU on Apple devices.\n",
-    " \n",
-    "Other frameworks require the user to set up the environment to utilize the Apple GPU.\n",
-    "\n",
-    "For example, `llama.cpp` python bindings can be configured to use the GPU via [Metal](https://developer.apple.com/metal/).\n",
-    "\n",
-    "Metal is a graphics and compute API created by Apple providing near-direct access to the GPU. \n",
-    "\n",
-    "See the [`llama.cpp`](docs/integrations/llms/llamacpp) setup [here](https://github.com/abetlen/llama-cpp-python/blob/main/docs/install/macos.md) to enable this.\n",
-    "\n",
-    "In particular, ensure that conda is using the correct virtual environment that you created (`miniforge3`).\n",
-    "\n",
-    "E.g., for me:\n",
-    "\n",
-    "```\n",
-    "conda activate /Users/rlm/miniforge3/envs/llama\n",
-    "```\n",
-    "\n",
-    "With the above confirmed, then:\n",
-    "\n",
-    "```\n",
-    "CMAKE_ARGS=\"-DLLAMA_METAL=on\" FORCE_CMAKE=1 pip install -U llama-cpp-python --no-cache-dir\n",
-    "```"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "c382e79a",
-   "metadata": {},
-   "source": [
-    "## LLMs\n",
-    "\n",
-    "There are various ways to gain access to quantized model weights.\n",
-    "\n",
-    "1. [`HuggingFace`](https://huggingface.co/TheBloke) - Many quantized model are available for download and can be run with framework such as [`llama.cpp`](https://github.com/ggerganov/llama.cpp)\n",
-    "2. [`gpt4all`](https://gpt4all.io/index.html) - The model explorer offers a leaderboard of metrics and associated quantized models available for download \n",
-    "3. [`Ollama`](https://github.com/jmorganca/ollama) - Several models can be accessed directly via `pull`\n",
-    "\n",
-    "### Ollama\n",
-    "\n",
-    "With [Ollama](docs/integrations/llms/ollama), fetch a model via `ollama pull <model family>:<tag>`:\n",
-    "\n",
-    "* E.g., for Llama-7b: `ollama pull llama2` will download the most basic version of the model (e.g., smallest # parameters and 4 bit quantization)\n",
-    "* We can also specify a particular version from the [model list](https://github.com/jmorganca/ollama), e.g., `ollama pull llama2:13b`\n",
-    "* See the full set of parameters on the [API reference page](https://api.python.langchain.com/en/latest/llms/langchain.llms.ollama.Ollama.html)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 42,
-   "id": "8ecd2f78",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "' Sure! Here\\'s the answer, broken down step by step:\\n\\nThe first man on the moon was... Neil Armstrong.\\n\\nHere\\'s how I arrived at that answer:\\n\\n1. The first manned mission to land on the moon was Apollo 11.\\n2. The mission included three astronauts: Neil Armstrong, Edwin \"Buzz\" Aldrin, and Michael Collins.\\n3. Neil Armstrong was the mission commander and the first person to set foot on the moon.\\n4. On July 20, 1969, Armstrong stepped out of the lunar module Eagle and onto the moon\\'s surface, famously declaring \"That\\'s one small step for man, one giant leap for mankind.\"\\n\\nSo, the first man on the moon was Neil Armstrong!'"
-      ]
-     },
-     "execution_count": 42,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain.llms import Ollama\n",
-    "llm = Ollama(model=\"llama2:13b\")\n",
-    "llm(\"The first man on the moon was ... think step by step\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "07c8c0d1",
-   "metadata": {},
-   "source": [
-    "### Llama.cpp\n",
-    "\n",
-    "Llama.cpp is compatible with a [broad set of models](https://github.com/ggerganov/llama.cpp).\n",
-    "\n",
-    "For example, below we run inference on `llama2-13b` with 4 bit quantization downloaded from [HuggingFace](https://huggingface.co/TheBloke/Llama-2-13B-GGML/tree/main).\n",
-    "\n",
-    "As noted above, see the [API reference](https://api.python.langchain.com/en/latest/llms/langchain.llms.llamacpp.LlamaCpp.html?highlight=llamacpp#langchain.llms.llamacpp.LlamaCpp) for the full set of parameters. \n",
-    "\n",
-    "From the [llama.cpp docs](https://python.langchain.com/docs/integrations/llms/llamacpp), a few are worth commenting on:\n",
-    "\n",
-    "`n_gpu_layers`: number of layers to be loaded into GPU memory\n",
-    "\n",
-    "* Value: 1\n",
-    "* Meaning: Only one layer of the model will be loaded into GPU memory (1 is often sufficient).\n",
-    "\n",
-    "`n_batch`: number of tokens the model should process in parallel \n",
-    "* Value: n_batch\n",
-    "* Meaning: It's recommended to choose a value between 1 and n_ctx (which in this case is set to 2048)\n",
-    "\n",
-    "`n_ctx`: Token context window .\n",
-    "* Value: 2048\n",
-    "* Meaning: The model will consider a window of 2048 tokens at a time\n",
-    "\n",
-    "`f16_kv`: whether the model should use half-precision for the key/value cache\n",
-    "* Value: True\n",
-    "* Meaning: The model will use half-precision, which can be more memory efficient; Metal only supports True."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "5eba38dc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "CMAKE_ARGS=\"-DLLAMA_METAL=on\" FORCE_CMAKE=1 pip install -U llama-cpp-python --no-cache-dirclear"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "a88bf0c8-e989-4bcd-bcb7-4d7757e684f2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.llms import LlamaCpp\n",
-    "llm = LlamaCpp(\n",
-    "    model_path=\"/Users/rlm/Desktop/Code/llama.cpp/models/openorca-platypus2-13b.gguf.q4_0.bin\",\n",
-    "    n_gpu_layers=1,\n",
-    "    n_batch=512,\n",
-    "    n_ctx=2048,\n",
-    "    f16_kv=True,  \n",
-    "    callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]),\n",
-    "    verbose=True,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f56f5168",
-   "metadata": {},
-   "source": [
-    "The console log will show the below to indicate Metal was enabled properly from steps above:\n",
-    "```\n",
-    "ggml_metal_init: allocating\n",
-    "ggml_metal_init: using MPS\n",
-    "```"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 45,
-   "id": "7890a077",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Llama.generate: prefix-match hit\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      " and use logical reasoning to figure out who the first man on the moon was.\n",
-      "\n",
-      "Here are some clues:\n",
-      "\n",
-      "1. The first man on the moon was an American.\n",
-      "2. He was part of the Apollo 11 mission.\n",
-      "3. He stepped out of the lunar module and became the first person to set foot on the moon's surface.\n",
-      "4. His last name is Armstrong.\n",
-      "\n",
-      "Now, let's use our reasoning skills to figure out who the first man on the moon was. Based on clue #1, we know that the first man on the moon was an American. Clue #2 tells us that he was part of the Apollo 11 mission. Clue #3 reveals that he was the first person to set foot on the moon's surface. And finally, clue #4 gives us his last name: Armstrong.\n",
-      "Therefore, the first man on the moon was Neil Armstrong!"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "llama_print_timings:        load time =  9623.21 ms\n",
-      "llama_print_timings:      sample time =   143.77 ms /   203 runs   (    0.71 ms per token,  1412.01 tokens per second)\n",
-      "llama_print_timings: prompt eval time =   485.94 ms /     7 tokens (   69.42 ms per token,    14.40 tokens per second)\n",
-      "llama_print_timings:        eval time =  6385.16 ms /   202 runs   (   31.61 ms per token,    31.64 tokens per second)\n",
-      "llama_print_timings:       total time =  7279.28 ms\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "\" and use logical reasoning to figure out who the first man on the moon was.\\n\\nHere are some clues:\\n\\n1. The first man on the moon was an American.\\n2. He was part of the Apollo 11 mission.\\n3. He stepped out of the lunar module and became the first person to set foot on the moon's surface.\\n4. His last name is Armstrong.\\n\\nNow, let's use our reasoning skills to figure out who the first man on the moon was. Based on clue #1, we know that the first man on the moon was an American. Clue #2 tells us that he was part of the Apollo 11 mission. Clue #3 reveals that he was the first person to set foot on the moon's surface. And finally, clue #4 gives us his last name: Armstrong.\\nTherefore, the first man on the moon was Neil Armstrong!\""
-      ]
-     },
-     "execution_count": 45,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "llm(\"The first man on the moon was ... Let's think step by step\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "831ddf7c",
-   "metadata": {},
-   "source": [
-    "### GPT4All\n",
-    "\n",
-    "We can use model weights downloaded from [GPT4All](https://python.langchain.com/docs/integrations/llms/gpt4all) model explorer.\n",
-    "\n",
-    "Similar to what is shown above, we can run inference and use [the API reference](https://api.python.langchain.com/en/latest/llms/langchain.llms.gpt4all.GPT4All.html?highlight=gpt4all#langchain.llms.gpt4all.GPT4All) to set parameters of interest."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "e27baf6e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "pip install gpt4all"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "915ecd4c-8f6b-4de3-a787-b64cb7c682b4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.llms import GPT4All\n",
-    "llm = GPT4All(model=\"/Users/rlm/Desktop/Code/gpt4all/models/nous-hermes-13b.ggmlv3.q4_0.bin\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 47,
-   "id": "e3d4526f",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\".\\n1) The United States decides to send a manned mission to the moon.2) They choose their best astronauts and train them for this specific mission.3) They build a spacecraft that can take humans to the moon, called the Lunar Module (LM).4) They also create a larger spacecraft, called the Saturn V rocket, which will launch both the LM and the Command Service Module (CSM), which will carry the astronauts into orbit.5) The mission is planned down to the smallest detail: from the trajectory of the rockets to the exact movements of the astronauts during their moon landing.6) On July 16, 1969, the Saturn V rocket launches from Kennedy Space Center in Florida, carrying the Apollo 11 mission crew into space.7) After one and a half orbits around the Earth, the LM separates from the CSM and begins its descent to the moon's surface.8) On July 20, 1969, at 2:56 pm EDT (GMT-4), Neil Armstrong becomes the first man on the moon. He speaks these\""
-      ]
-     },
-     "execution_count": 47,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "llm(\"The first man on the moon was ... Let's think step by step\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "6b84e543",
-   "metadata": {},
-   "source": [
-    "## Prompts\n",
-    "\n",
-    "Some LLMs will benefit from specific prompts.\n",
-    "\n",
-    "For example, LLaMA will use [special tokens](https://twitter.com/RLanceMartin/status/1681879318493003776?s=20).\n",
-    "\n",
-    "We can use `ConditionalPromptSelector` to set prompt based on the model type."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "16759b7c-7903-4269-b7b4-f83b313d8091",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Set our LLM\n",
-    "llm = LlamaCpp(\n",
-    "    model_path=\"/Users/rlm/Desktop/Code/llama.cpp/models/openorca-platypus2-13b.gguf.q4_0.bin\",\n",
-    "    n_gpu_layers=1,\n",
-    "    n_batch=512,\n",
-    "    n_ctx=2048,\n",
-    "    f16_kv=True,  \n",
-    "    callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]),\n",
-    "    verbose=True,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "66656084",
-   "metadata": {},
-   "source": [
-    "Set the associated prompt based upon the model version."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 58,
-   "id": "8555f5bf",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "PromptTemplate(input_variables=['question'], output_parser=None, partial_variables={}, template='<<SYS>> \\n You are an assistant tasked with improving Google search results. \\n <</SYS>> \\n\\n [INST] Generate THREE Google search queries that are similar to this question. The output should be a numbered list of questions and each should have a question mark at the end: \\n\\n {question} [/INST]', template_format='f-string', validate_template=True)"
-      ]
-     },
-     "execution_count": 58,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain.prompts import PromptTemplate\n",
-    "from langchain.chains import LLMChain\n",
-    "from langchain.chains.prompt_selector import ConditionalPromptSelector\n",
-    "\n",
-    "DEFAULT_LLAMA_SEARCH_PROMPT = PromptTemplate(\n",
-    "    input_variables=[\"question\"],\n",
-    "    template=\"\"\"<<SYS>> \\n You are an assistant tasked with improving Google search \\\n",
-    "results. \\n <</SYS>> \\n\\n [INST] Generate THREE Google search queries that \\\n",
-    "are similar to this question. The output should be a numbered list of questions \\\n",
-    "and each should have a question mark at the end: \\n\\n {question} [/INST]\"\"\",\n",
-    ")\n",
-    "\n",
-    "DEFAULT_SEARCH_PROMPT = PromptTemplate(\n",
-    "    input_variables=[\"question\"],\n",
-    "    template=\"\"\"You are an assistant tasked with improving Google search \\\n",
-    "results. Generate THREE Google search queries that are similar to \\\n",
-    "this question. The output should be a numbered list of questions and each \\\n",
-    "should have a question mark at the end: {question}\"\"\",\n",
-    ")\n",
-    "\n",
-    "QUESTION_PROMPT_SELECTOR = ConditionalPromptSelector(\n",
-    "                default_prompt=DEFAULT_SEARCH_PROMPT,\n",
-    "                conditionals=[\n",
-    "                    (lambda llm: isinstance(llm, LlamaCpp), DEFAULT_LLAMA_SEARCH_PROMPT)\n",
-    "                ],\n",
-    "            )\n",
-    "\n",
-    "prompt = QUESTION_PROMPT_SELECTOR.get_prompt(llm)\n",
-    "prompt"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 59,
-   "id": "d0aedfd2",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "  Sure! Here are three similar search queries with a question mark at the end:\n",
-      "\n",
-      "1. Which NBA team did LeBron James lead to a championship in the year he was drafted?\n",
-      "2. Who won the Grammy Awards for Best New Artist and Best Female Pop Vocal Performance in the same year that Lady Gaga was born?\n",
-      "3. What MLB team did Babe Ruth play for when he hit 60 home runs in a single season?"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "llama_print_timings:        load time = 14943.19 ms\n",
-      "llama_print_timings:      sample time =    72.93 ms /   101 runs   (    0.72 ms per token,  1384.87 tokens per second)\n",
-      "llama_print_timings: prompt eval time = 14942.95 ms /    93 tokens (  160.68 ms per token,     6.22 tokens per second)\n",
-      "llama_print_timings:        eval time =  3430.85 ms /   100 runs   (   34.31 ms per token,    29.15 tokens per second)\n",
-      "llama_print_timings:       total time = 18578.26 ms\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'  Sure! Here are three similar search queries with a question mark at the end:\\n\\n1. Which NBA team did LeBron James lead to a championship in the year he was drafted?\\n2. Who won the Grammy Awards for Best New Artist and Best Female Pop Vocal Performance in the same year that Lady Gaga was born?\\n3. What MLB team did Babe Ruth play for when he hit 60 home runs in a single season?'"
-      ]
-     },
-     "execution_count": 59,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Chain\n",
-    "llm_chain = LLMChain(prompt=prompt,llm=llm)\n",
-    "question = \"What NFL team won the Super Bowl in the year that Justin Bieber was born?\"\n",
-    "llm_chain.run({\"question\":question})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "6e0d37e7-f1d9-4848-bf2c-c22392ee141f",
-   "metadata": {},
-   "source": [
-    "We also can use the LangChain Prompt Hub to fetch and / or store prompts that are model specific.\n",
-    "\n",
-    "This will work with your [LangSmith API key](https://docs.smith.langchain.com/).\n",
-    "\n",
-    "For example, [here](https://smith.langchain.com/hub/rlm/rag-prompt-llama) is a prompt for RAG with LLaMA-specific tokens."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "6ba66260",
-   "metadata": {},
-   "source": [
-    "## Use cases\n",
-    "\n",
-    "Given an `llm` created from one of the models above, you can use it for [many use cases](docs/use_cases).\n",
-    "\n",
-    "For example, here is a guide to [RAG](docs/use_cases/question_answering/local_retrieval_qa) with local LLMs.\n",
-    "\n",
-    "In general, use cases for local LLMs can be driven by at least two factors:\n",
-    "\n",
-    "* `Privacy`: private data (e.g., journals, etc) that a user does not want to share \n",
-    "* `Cost`: text preprocessing (extraction/tagging), summarization, and agent simulations are token-use-intensive tasks\n",
-    "\n",
-    "In addition, [here](https://blog.langchain.dev/using-langsmith-to-support-fine-tuning-of-open-source-llms/) is an overview on fine-tuning, which can utilize open-source LLMs."
-   ]
-  }
- ],
- "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/guides/privacy/_category_.yml

@@ -1 +0,0 @@
-label: 'Privacy'

docs/docs/guides/privacy/presidio_data_anonymization/index.ipynb

@@ -1,539 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Data anonymization with Microsoft Presidio\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/guides/privacy/presidio_data_anonymization/index.ipynb)\n",
-    "\n",
-    "## Use case\n",
-    "\n",
-    "Data anonymization is crucial before passing information to a language model like GPT-4 because it helps protect privacy and maintain confidentiality. If data is not anonymized, sensitive information such as names, addresses, contact numbers, or other identifiers linked to specific individuals could potentially be learned and misused. Hence, by obscuring or removing this personally identifiable information (PII), data can be used freely without compromising individuals' privacy rights or breaching data protection laws and regulations.\n",
-    "\n",
-    "## Overview\n",
-    "\n",
-    "Anonynization consists of two steps:\n",
-    "\n",
-    "1. **Identification:** Identify all data fields that contain personally identifiable information (PII).\n",
-    "2. **Replacement**: Replace all PIIs with pseudo values or codes that do not reveal any personal information about the individual but can be used for reference. We're not using regular encryption, because the language model won't be able to understand the meaning or context of the encrypted data.\n",
-    "\n",
-    "We use *Microsoft Presidio* together with *Faker* framework for anonymization purposes because of the wide range of functionalities they provide. The full implementation is available in `PresidioAnonymizer`.\n",
-    "\n",
-    "## Quickstart\n",
-    "\n",
-    "Below you will find the use case on how to leverage anonymization in LangChain."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Install necessary packages\n",
-    "# ! pip install langchain langchain-experimental openai presidio-analyzer presidio-anonymizer spacy Faker\n",
-    "# ! python -m spacy download en_core_web_lg"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "\\\n",
-    "Let's see how PII anonymization works using a sample sentence:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'My name is James Martinez, call me at (576)928-1972x679 or email me at lisa44@example.com'"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_experimental.data_anonymizer import PresidioAnonymizer\n",
-    "\n",
-    "anonymizer = PresidioAnonymizer()\n",
-    "\n",
-    "anonymizer.anonymize(\n",
-    "    \"My name is Slim Shady, call me at 313-666-7440 or email me at real.slim.shady@gmail.com\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Using with LangChain Expression Language\n",
-    "\n",
-    "With LCEL we can easily chain together anonymization with the rest of our application."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# 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": 4,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "text = f\"\"\"Slim Shady recently lost his wallet. \n",
-    "Inside is some cash and his credit card with the number 4916 0387 9536 0861. \n",
-    "If you would find it, please call at 313-666-7440 or write an email here: real.slim.shady@gmail.com.\"\"\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Dear Sir/Madam,\n",
-      "\n",
-      "We regret to inform you that Mr. Dennis Cooper has recently misplaced his wallet. The wallet contains a sum of cash and his credit card, bearing the number 3588895295514977. \n",
-      "\n",
-      "Should you happen to come across the aforementioned wallet, kindly contact us immediately at (428)451-3494x4110 or send an email to perryluke@example.com.\n",
-      "\n",
-      "Your prompt assistance in this matter would be greatly appreciated.\n",
-      "\n",
-      "Yours faithfully,\n",
-      "\n",
-      "[Your Name]\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain.prompts.prompt import PromptTemplate\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "\n",
-    "anonymizer = PresidioAnonymizer()\n",
-    "\n",
-    "template = \"\"\"Rewrite this text into an official, short email:\n",
-    "\n",
-    "{anonymized_text}\"\"\"\n",
-    "prompt = PromptTemplate.from_template(template)\n",
-    "llm = ChatOpenAI(temperature=0)\n",
-    "\n",
-    "chain = {\"anonymized_text\": anonymizer.anonymize} | prompt | llm\n",
-    "response = chain.invoke(text)\n",
-    "print(response.content)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Customization\n",
-    "We can specify ``analyzed_fields`` to only anonymize particular types of data."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'My name is Shannon Steele, call me at 313-666-7440 or email me at real.slim.shady@gmail.com'"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "anonymizer = PresidioAnonymizer(analyzed_fields=[\"PERSON\"])\n",
-    "\n",
-    "anonymizer.anonymize(\n",
-    "    \"My name is Slim Shady, call me at 313-666-7440 or email me at real.slim.shady@gmail.com\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "As can be observed, the name was correctly identified and replaced with another. The `analyzed_fields` attribute is responsible for what values are to be detected and substituted. We can add *PHONE_NUMBER* to the list:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'My name is Wesley Flores, call me at (498)576-9526 or email me at real.slim.shady@gmail.com'"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "anonymizer = PresidioAnonymizer(analyzed_fields=[\"PERSON\", \"PHONE_NUMBER\"])\n",
-    "anonymizer.anonymize(\n",
-    "    \"My name is Slim Shady, call me at 313-666-7440 or email me at real.slim.shady@gmail.com\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "\\\n",
-    "If no analyzed_fields are specified, by default the anonymizer will detect all supported formats. Below is the full list of them:\n",
-    "\n",
-    "`['PERSON', 'EMAIL_ADDRESS', 'PHONE_NUMBER', 'IBAN_CODE', 'CREDIT_CARD', 'CRYPTO', 'IP_ADDRESS', 'LOCATION', 'DATE_TIME', 'NRP', 'MEDICAL_LICENSE', 'URL', 'US_BANK_NUMBER', 'US_DRIVER_LICENSE', 'US_ITIN', 'US_PASSPORT', 'US_SSN']`\n",
-    "\n",
-    "**Disclaimer:** We suggest carefully defining the private data to be detected - Presidio doesn't work perfectly and it sometimes makes mistakes, so it's better to have more control over the data."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'My name is Carla Fisher, call me at 001-683-324-0721x0644 or email me at krausejeremy@example.com'"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "anonymizer = PresidioAnonymizer()\n",
-    "anonymizer.anonymize(\n",
-    "    \"My name is Slim Shady, call me at 313-666-7440 or email me at real.slim.shady@gmail.com\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "\\\n",
-    "It may be that the above list of detected fields is not sufficient. For example, the already available *PHONE_NUMBER* field does not support polish phone numbers and confuses it with another field:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'My polish phone number is QESQ21234635370499'"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "anonymizer = PresidioAnonymizer()\n",
-    "anonymizer.anonymize(\"My polish phone number is 666555444\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "\\\n",
-    "You can then write your own recognizers and add them to the pool of those present. How exactly to create recognizers is described in the [Presidio documentation](https://microsoft.github.io/presidio/samples/python/customizing_presidio_analyzer/)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Define the regex pattern in a Presidio `Pattern` object:\n",
-    "from presidio_analyzer import Pattern, PatternRecognizer\n",
-    "\n",
-    "\n",
-    "polish_phone_numbers_pattern = Pattern(\n",
-    "    name=\"polish_phone_numbers_pattern\",\n",
-    "    regex=\"(?<!\\w)(\\(?(\\+|00)?48\\)?)?[ -]?\\d{3}[ -]?\\d{3}[ -]?\\d{3}(?!\\w)\",\n",
-    "    score=1,\n",
-    ")\n",
-    "\n",
-    "# Define the recognizer with one or more patterns\n",
-    "polish_phone_numbers_recognizer = PatternRecognizer(\n",
-    "    supported_entity=\"POLISH_PHONE_NUMBER\", patterns=[polish_phone_numbers_pattern]\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "\\\n",
-    "Now, we can add recognizer by calling `add_recognizer` method on the anonymizer:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "anonymizer.add_recognizer(polish_phone_numbers_recognizer)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "\\\n",
-    "And voilà! With the added pattern-based recognizer, the anonymizer now handles polish phone numbers."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "My polish phone number is <POLISH_PHONE_NUMBER>\n",
-      "My polish phone number is <POLISH_PHONE_NUMBER>\n",
-      "My polish phone number is <POLISH_PHONE_NUMBER>\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(anonymizer.anonymize(\"My polish phone number is 666555444\"))\n",
-    "print(anonymizer.anonymize(\"My polish phone number is 666 555 444\"))\n",
-    "print(anonymizer.anonymize(\"My polish phone number is +48 666 555 444\"))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "\\\n",
-    "The problem is - even though we recognize polish phone numbers now, we don't have a method (operator) that would tell how to substitute a given field - because of this, in the outpit we only provide string `<POLISH_PHONE_NUMBER>` We need to create a method to replace it correctly: "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'665 631 080'"
-      ]
-     },
-     "execution_count": 13,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from faker import Faker\n",
-    "\n",
-    "fake = Faker(locale=\"pl_PL\")\n",
-    "\n",
-    "\n",
-    "def fake_polish_phone_number(_=None):\n",
-    "    return fake.phone_number()\n",
-    "\n",
-    "\n",
-    "fake_polish_phone_number()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "\\\n",
-    "We used Faker to create pseudo data. Now we can create an operator and add it to the anonymizer. For complete information about operators and their creation, see the Presidio documentation for [simple](https://microsoft.github.io/presidio/tutorial/10_simple_anonymization/) and [custom](https://microsoft.github.io/presidio/tutorial/11_custom_anonymization/) anonymization."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from presidio_anonymizer.entities import OperatorConfig\n",
-    "\n",
-    "new_operators = {\n",
-    "    \"POLISH_PHONE_NUMBER\": OperatorConfig(\n",
-    "        \"custom\", {\"lambda\": fake_polish_phone_number}\n",
-    "    )\n",
-    "}"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "anonymizer.add_operators(new_operators)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'My polish phone number is 538 521 657'"
-      ]
-     },
-     "execution_count": 16,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "anonymizer.anonymize(\"My polish phone number is 666555444\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Important considerations\n",
-    "\n",
-    "### Anonymizer detection rates\n",
-    "\n",
-    "**The level of anonymization and the precision of detection are just as good as the quality of the recognizers implemented.**\n",
-    "\n",
-    "Texts from different sources and in different languages have varying characteristics, so it is necessary to test the detection precision and iteratively add recognizers and operators to achieve better and better results.\n",
-    "\n",
-    "Microsoft Presidio gives a lot of freedom to refine anonymization. The library's author has provided his [recommendations and a step-by-step guide for improving detection rates](https://github.com/microsoft/presidio/discussions/767#discussion-3567223)."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Instance anonymization\n",
-    "\n",
-    "`PresidioAnonymizer` has no built-in memory. Therefore, two occurrences of the entity in the subsequent texts will be replaced with two different fake values:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "My name is Robert Morales. Hi Robert Morales!\n",
-      "My name is Kelly Mccoy. Hi Kelly Mccoy!\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(anonymizer.anonymize(\"My name is John Doe. Hi John Doe!\"))\n",
-    "print(anonymizer.anonymize(\"My name is John Doe. Hi John Doe!\"))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "To preserve previous anonymization results, use `PresidioReversibleAnonymizer`, which has built-in memory:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "My name is Ashley Cervantes. Hi Ashley Cervantes!\n",
-      "My name is Ashley Cervantes. Hi Ashley Cervantes!\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_experimental.data_anonymizer import PresidioReversibleAnonymizer\n",
-    "\n",
-    "anonymizer_with_memory = PresidioReversibleAnonymizer()\n",
-    "\n",
-    "print(anonymizer_with_memory.anonymize(\"My name is John Doe. Hi John Doe!\"))\n",
-    "print(anonymizer_with_memory.anonymize(\"My name is John Doe. Hi John Doe!\"))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can learn more about `PresidioReversibleAnonymizer` in the next section."
-   ]
-  }
- ],
- "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
-}

docs/docs/guides/privacy/presidio_data_anonymization/multi_language.ipynb

@@ -1,735 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "raw",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "sidebar_position: 2\n",
-    "title: Multi-language anonymization\n",
-    "---"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Multi-language data anonymization with Microsoft Presidio\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/guides/privacy/presidio_data_anonymization/multi_language.ipynb)\n",
-    "\n",
-    "\n",
-    "## Use case\n",
-    "\n",
-    "Multi-language support in data pseudonymization is essential due to differences in language structures and cultural contexts. Different languages may have varying formats for personal identifiers. For example, the structure of names, locations and dates can differ greatly between languages and regions. Furthermore, non-alphanumeric characters, accents, and the direction of writing can impact pseudonymization processes. Without multi-language support, data could remain identifiable or be misinterpreted, compromising data privacy and accuracy. Hence, it enables effective and precise pseudonymization suited for global operations.\n",
-    "\n",
-    "## Overview\n",
-    "\n",
-    "PII detection in Microsoft Presidio relies on several components - in addition to the usual pattern matching (e.g. using regex), the analyser uses a model for Named Entity Recognition (NER) to extract entities such as:\n",
-    "- `PERSON`\n",
-    "- `LOCATION`\n",
-    "- `DATE_TIME`\n",
-    "- `NRP`\n",
-    "- `ORGANIZATION`\n",
-    "\n",
-    "[[Source]](https://github.com/microsoft/presidio/blob/main/presidio-analyzer/presidio_analyzer/predefined_recognizers/spacy_recognizer.py)\n",
-    "\n",
-    "To handle NER in specific languages, we utilize unique models from the `spaCy` library, recognized for its extensive selection covering multiple languages and sizes. However, it's not restrictive, allowing for integration of alternative frameworks such as [Stanza](https://microsoft.github.io/presidio/analyzer/nlp_engines/spacy_stanza/) or [transformers](https://microsoft.github.io/presidio/analyzer/nlp_engines/transformers/) when necessary.\n",
-    "\n",
-    "\n",
-    "## Quickstart\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Install necessary packages\n",
-    "# ! pip install langchain langchain-experimental openai presidio-analyzer presidio-anonymizer spacy Faker\n",
-    "# ! python -m spacy download en_core_web_lg"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_experimental.data_anonymizer import PresidioReversibleAnonymizer\n",
-    "\n",
-    "anonymizer = PresidioReversibleAnonymizer(\n",
-    "    analyzed_fields=[\"PERSON\"],\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "By default, `PresidioAnonymizer` and `PresidioReversibleAnonymizer` use a model trained on English texts, so they handle other languages moderately well. \n",
-    "\n",
-    "For example, here the model did not detect the person:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Me llamo Sofía'"
-      ]
-     },
-     "execution_count": 10,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "anonymizer.anonymize(\"Me llamo Sofía\")  # \"My name is Sofía\" in Spanish"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "They may also take words from another language as actual entities. Here, both the word *'Yo'* (*'I'* in Spanish) and *Sofía* have been classified as `PERSON`:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Kari Lopez soy Mary Walker'"
-      ]
-     },
-     "execution_count": 11,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "anonymizer.anonymize(\"Yo soy Sofía\")  # \"I am Sofía\" in Spanish"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "If you want to anonymise texts from other languages, you need to download other models and add them to the anonymiser configuration:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Download the models for the languages you want to use\n",
-    "# ! python -m spacy download en_core_web_md\n",
-    "# ! python -m spacy download es_core_news_md"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "nlp_config = {\n",
-    "    \"nlp_engine_name\": \"spacy\",\n",
-    "    \"models\": [\n",
-    "        {\"lang_code\": \"en\", \"model_name\": \"en_core_web_md\"},\n",
-    "        {\"lang_code\": \"es\", \"model_name\": \"es_core_news_md\"},\n",
-    "    ],\n",
-    "}"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "We have therefore added a Spanish language model. Note also that we have downloaded an alternative model for English as well - in this case we have replaced the large model `en_core_web_lg` (560MB) with its smaller version `en_core_web_md` (40MB) - the size is therefore reduced by 14 times! If you care about the speed of anonymisation, it is worth considering it.\n",
-    "\n",
-    "All models for the different languages can be found in the [spaCy documentation](https://spacy.io/usage/models).\n",
-    "\n",
-    "Now pass the configuration as the `languages_config` parameter to Anonymiser. As you can see, both previous examples work flawlessly:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Me llamo Christopher Smith\n",
-      "Yo soy Joseph Jenkins\n"
-     ]
-    }
-   ],
-   "source": [
-    "anonymizer = PresidioReversibleAnonymizer(\n",
-    "    analyzed_fields=[\"PERSON\"],\n",
-    "    languages_config=nlp_config,\n",
-    ")\n",
-    "\n",
-    "print(\n",
-    "    anonymizer.anonymize(\"Me llamo Sofía\", language=\"es\")\n",
-    ")  # \"My name is Sofía\" in Spanish\n",
-    "print(anonymizer.anonymize(\"Yo soy Sofía\", language=\"es\"))  # \"I am Sofía\" in Spanish"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "By default, the language indicated first in the configuration will be used when anonymising text (in this case English):"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "My name is Shawna Bennett\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(anonymizer.anonymize(\"My name is John\"))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Usage with other frameworks\n",
-    "\n",
-    "### Language detection\n",
-    "\n",
-    "One of the drawbacks of the presented approach is that we have to pass the **language** of the input text directly. However, there is a remedy for that - *language detection* libraries.\n",
-    "\n",
-    "We recommend using one of the following frameworks:\n",
-    "- fasttext (recommended)\n",
-    "- langdetect\n",
-    "\n",
-    "From our experience *fasttext* performs a bit better, but you should verify it on your use case."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Install necessary packages\n",
-    "# ! pip install fasttext langdetect"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### langdetect"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import langdetect\n",
-    "from langchain.schema import runnable\n",
-    "\n",
-    "\n",
-    "def detect_language(text: str) -> dict:\n",
-    "    language = langdetect.detect(text)\n",
-    "    print(language)\n",
-    "    return {\"text\": text, \"language\": language}\n",
-    "\n",
-    "\n",
-    "chain = runnable.RunnableLambda(detect_language) | (\n",
-    "    lambda x: anonymizer.anonymize(x[\"text\"], language=x[\"language\"])\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "es\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'Me llamo Michael Perez III'"
-      ]
-     },
-     "execution_count": 15,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke(\"Me llamo Sofía\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "en\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'My name is Ronald Bennett'"
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke(\"My name is John Doe\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### fasttext"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You need to download the fasttext model first from https://dl.fbaipublicfiles.com/fasttext/supervised-models/lid.176.ftz"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Warning : `load_model` does not return WordVectorModel or SupervisedModel any more, but a `FastText` object which is very similar.\n"
-     ]
-    }
-   ],
-   "source": [
-    "import fasttext\n",
-    "\n",
-    "model = fasttext.load_model(\"lid.176.ftz\")\n",
-    "\n",
-    "\n",
-    "def detect_language(text: str) -> dict:\n",
-    "    language = model.predict(text)[0][0].replace(\"__label__\", \"\")\n",
-    "    print(language)\n",
-    "    return {\"text\": text, \"language\": language}\n",
-    "\n",
-    "\n",
-    "chain = runnable.RunnableLambda(detect_language) | (\n",
-    "    lambda x: anonymizer.anonymize(x[\"text\"], language=x[\"language\"])\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 21,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "es\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'Yo soy Angela Werner'"
-      ]
-     },
-     "execution_count": 21,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke(\"Yo soy Sofía\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 20,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "en\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'My name is Carlos Newton'"
-      ]
-     },
-     "execution_count": 20,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke(\"My name is John Doe\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "This way you only need to initialize the model with the engines corresponding to the relevant languages, but using the tool is fully automated."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Advanced usage\n",
-    "\n",
-    "### Custom labels in NER model"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "It may be that the spaCy model has different class names than those supported by the Microsoft Presidio by default. Take Polish, for example:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Text: Wiktoria, Start: 12, End: 20, Label: persName\n"
-     ]
-    }
-   ],
-   "source": [
-    "# ! python -m spacy download pl_core_news_md\n",
-    "\n",
-    "import spacy\n",
-    "\n",
-    "nlp = spacy.load(\"pl_core_news_md\")\n",
-    "doc = nlp(\"Nazywam się Wiktoria\")  # \"My name is Wiktoria\" in Polish\n",
-    "\n",
-    "for ent in doc.ents:\n",
-    "    print(\n",
-    "        f\"Text: {ent.text}, Start: {ent.start_char}, End: {ent.end_char}, Label: {ent.label_}\"\n",
-    "    )"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The name *Victoria* was classified as `persName`, which does not correspond to the default class names `PERSON`/`PER` implemented in Microsoft Presidio (look for `CHECK_LABEL_GROUPS` in [SpacyRecognizer implementation](https://github.com/microsoft/presidio/blob/main/presidio-analyzer/presidio_analyzer/predefined_recognizers/spacy_recognizer.py)). \n",
-    "\n",
-    "You can find out more about custom labels in spaCy models (including your own, trained ones) in [this thread](https://github.com/microsoft/presidio/issues/851).\n",
-    "\n",
-    "That's why our sentence will not be anonymized:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Nazywam się Wiktoria\n"
-     ]
-    }
-   ],
-   "source": [
-    "nlp_config = {\n",
-    "    \"nlp_engine_name\": \"spacy\",\n",
-    "    \"models\": [\n",
-    "        {\"lang_code\": \"en\", \"model_name\": \"en_core_web_md\"},\n",
-    "        {\"lang_code\": \"es\", \"model_name\": \"es_core_news_md\"},\n",
-    "        {\"lang_code\": \"pl\", \"model_name\": \"pl_core_news_md\"},\n",
-    "    ],\n",
-    "}\n",
-    "\n",
-    "anonymizer = PresidioReversibleAnonymizer(\n",
-    "    analyzed_fields=[\"PERSON\", \"LOCATION\", \"DATE_TIME\"],\n",
-    "    languages_config=nlp_config,\n",
-    ")\n",
-    "\n",
-    "print(\n",
-    "    anonymizer.anonymize(\"Nazywam się Wiktoria\", language=\"pl\")\n",
-    ")  # \"My name is Wiktoria\" in Polish"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "To address this, create your own `SpacyRecognizer` with your own class mapping and add it to the anonymizer:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from presidio_analyzer.predefined_recognizers import SpacyRecognizer\n",
-    "\n",
-    "polish_check_label_groups = [\n",
-    "    ({\"LOCATION\"}, {\"placeName\", \"geogName\"}),\n",
-    "    ({\"PERSON\"}, {\"persName\"}),\n",
-    "    ({\"DATE_TIME\"}, {\"date\", \"time\"}),\n",
-    "]\n",
-    "\n",
-    "spacy_recognizer = SpacyRecognizer(\n",
-    "    supported_language=\"pl\",\n",
-    "    check_label_groups=polish_check_label_groups,\n",
-    ")\n",
-    "\n",
-    "anonymizer.add_recognizer(spacy_recognizer)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Now everything works smoothly:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Nazywam się Morgan Walters\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(\n",
-    "    anonymizer.anonymize(\"Nazywam się Wiktoria\", language=\"pl\")\n",
-    ")  # \"My name is Wiktoria\" in Polish"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Let's try on more complex example:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Nazywam się Ernest Liu. New Taylorburgh to moje miasto rodzinne. Urodziłam się 1987-01-19\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(\n",
-    "    anonymizer.anonymize(\n",
-    "        \"Nazywam się Wiktoria. Płock to moje miasto rodzinne. Urodziłam się dnia 6 kwietnia 2001 roku\",\n",
-    "        language=\"pl\",\n",
-    "    )\n",
-    ")  # \"My name is Wiktoria. Płock is my home town. I was born on 6 April 2001\" in Polish"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "As you can see, thanks to class mapping, the anonymiser can cope with different types of entities. "
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Custom language-specific operators\n",
-    "\n",
-    "In the example above, the sentence has been anonymised correctly, but the fake data does not fit the Polish language at all. Custom operators can therefore be added, which will resolve the issue:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from faker import Faker\n",
-    "from presidio_anonymizer.entities import OperatorConfig\n",
-    "\n",
-    "fake = Faker(locale=\"pl_PL\")  # Setting faker to provide Polish data\n",
-    "\n",
-    "new_operators = {\n",
-    "    \"PERSON\": OperatorConfig(\"custom\", {\"lambda\": lambda _: fake.first_name_female()}),\n",
-    "    \"LOCATION\": OperatorConfig(\"custom\", {\"lambda\": lambda _: fake.city()}),\n",
-    "}\n",
-    "\n",
-    "anonymizer.add_operators(new_operators)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Nazywam się Marianna. Szczecin to moje miasto rodzinne. Urodziłam się 1976-11-16\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(\n",
-    "    anonymizer.anonymize(\n",
-    "        \"Nazywam się Wiktoria. Płock to moje miasto rodzinne. Urodziłam się dnia 6 kwietnia 2001 roku\",\n",
-    "        language=\"pl\",\n",
-    "    )\n",
-    ")  # \"My name is Wiktoria. Płock is my home town. I was born on 6 April 2001\" in Polish"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Limitations\n",
-    "\n",
-    "Remember - results are as good as your recognizers and as your NER models!\n",
-    "\n",
-    "Look at the example below - we downloaded the small model for Spanish (12MB) and it no longer performs as well as the medium version (40MB):"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Model: es_core_news_sm. Result: Me llamo Sofía\n",
-      "Model: es_core_news_md. Result: Me llamo Lawrence Davis\n"
-     ]
-    }
-   ],
-   "source": [
-    "# ! python -m spacy download es_core_news_sm\n",
-    "\n",
-    "for model in [\"es_core_news_sm\", \"es_core_news_md\"]:\n",
-    "    nlp_config = {\n",
-    "        \"nlp_engine_name\": \"spacy\",\n",
-    "        \"models\": [\n",
-    "            {\"lang_code\": \"es\", \"model_name\": model},\n",
-    "        ],\n",
-    "    }\n",
-    "\n",
-    "    anonymizer = PresidioReversibleAnonymizer(\n",
-    "        analyzed_fields=[\"PERSON\"],\n",
-    "        languages_config=nlp_config,\n",
-    "    )\n",
-    "\n",
-    "    print(\n",
-    "        f\"Model: {model}. Result: {anonymizer.anonymize('Me llamo Sofía', language='es')}\"\n",
-    "    )"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "In many cases, even the larger models from spaCy will not be sufficient - there are already other, more complex and better methods of detecting named entities, based on transformers. You can read more about this [here](https://microsoft.github.io/presidio/analyzer/nlp_engines/transformers/)."
-   ]
-  }
- ],
- "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": 4
-}