bump 334, exp 40 (#13211)

Pending:
* https://github.com/chroma-core/chroma/pull/1294
* https://github.com/chroma-core/chroma/pull/1293

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
Co-authored-by: Bagatur <baskaryan@gmail.com>

.github/CODE_OF_CONDUCT.md

@@ -0,0 +1,132 @@
+# 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

@@ -1,20 +1,19 @@
 # Contributing to LangChain
 
 Hi there! Thank you for even being interested in contributing to LangChain.
-As an open source project in a rapidly developing field, we are extremely open
-to contributions, whether they be in the form of new features, improved infra, better documentation, or bug fixes.
+As an open-source project in a rapidly developing field, we are extremely open to contributions, whether they involve new features, improved infrastructure, better documentation, or bug fixes.
 
 ## 🗺️ Guidelines
 
 ### 👩‍💻 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.
+To contribute to this project, please follow the ["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 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
+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.
 
 It's essential that we maintain great documentation and testing. If you:
@@ -27,16 +26,14 @@ It's essential that we maintain great documentation and testing. If you:
   - Add a demo notebook in `docs/modules`.
   - Add unit and integration tests.
 
-We're a small, building-oriented team. If there's something you'd like to add or change, opening a pull request is the
+We are a small, progress-oriented team. If there's something you'd like to add or change, opening a pull request is the
 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/langchain-ai/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.
+There is a taxonomy of labels to help with sorting and discovery of issues of interest. Please use these to help organize issues.
 
 If you start working on an issue, please assign it to yourself.
 
@@ -59,12 +56,12 @@ 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.
+This quick start guide explains how to run the repository locally.
 For a [development container](https://containers.dev/), see the [.devcontainer folder](https://github.com/langchain-ai/langchain/tree/master/.devcontainer).
 
 ### Dependency Management: Poetry and other env/dependency managers
 
-This project uses [Poetry](https://python-poetry.org/) v1.6.1+ as a dependency manager.
+This project utilizes [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`)
 
@@ -75,11 +72,11 @@ tell Poetry to use the virtualenv python environment (`poetry config virtualenvs
 
 ### Core vs. Experimental
 
-There are two separate projects in this repository:
-- `langchain`: core langchain code, abstractions, and use cases
-- `langchain.experimental`: see the [Experimental README](../libs/experimental/README.md) for more information.
+This repository contains two separate projects:
+- `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.
 
-Each of these has their own development environment. Docs are run from the top-level makefile, but development
+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.
 
 For this quickstart, start with langchain core:
@@ -129,7 +126,7 @@ To run unit tests in Docker:
 make docker_tests
 ```
 
-There are also [integration tests and code-coverage](../libs/langchain/tests/README.md) available.
+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
 
@@ -137,14 +134,21 @@ 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 [ruff](https://docs.astral.sh/ruff/rules/).
 
-To run formatting for this project:
+To run formatting for docs, cookbook and templates:
 
 ```bash
 make format
 ```
 
+To run formatting for a library, run the same command from the relevant library directory:
+
+```bash
+cd libs/{LIBRARY}
+make format
+```
+
 Additionally, you can run the formatter only on the files that have been modified in your current branch as compared to the master branch using the format_diff command:
 
 ```bash
@@ -155,14 +159,21 @@ This is especially useful when you have made changes to a subset of the project
 
 #### 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 [ruff](https://docs.astral.sh/ruff/rules/) and [mypy](http://mypy-lang.org/).
 
-To run linting for this project:
+To run linting for docs, cookbook and templates:
 
 ```bash
 make lint
 ```
 
+To run linting for a library, run the same command from the relevant library directory:
+
+```bash
+cd libs/{LIBRARY}
+make lint
+```
+
 In addition, you can run the linter only on the files that have been modified in your current branch as compared to the master branch using the lint_diff command:
 
 ```bash
@@ -282,7 +293,7 @@ make docs_build
 make api_docs_build
 ```
 
-Finally, you can run the linkchecker to make sure all links are valid:
+Finally, run the link checker to ensure all links are valid:
 
 ```bash
 make docs_linkcheck
@@ -291,8 +302,8 @@ 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. 
+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).
 
@@ -307,4 +318,4 @@ even patch releases may contain [non-backwards-compatible changes](https://semve
 ### 🌟 Recognition
 
 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.
+If you have a Twitter account you would like us to mention, please let us know in the PR or through another means.

.github/workflows/_compile_integration_test.yml

@@ -0,0 +1,57 @@
+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

@@ -7,20 +7,21 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
+      langchain-location:
+        required: false
+        type: string
+        description: "Relative path to the langchain library folder"
 
 env:
   POETRY_VERSION: "1.6.1"
   WORKDIR: ${{ inputs.working-directory == '' && '.' || inputs.working-directory }}
 
+  # This env var allows us to get inline annotations when ruff has complaints.
+  RUFF_OUTPUT_FORMAT: github
+
 jobs:
   build:
     runs-on: ubuntu-latest
-    env:
-      # This number is set "by eye": we want it to be big enough
-      # so that it's bigger than the number of commits in any reasonable PR,
-      # and also as small as possible since increasing the number makes
-      # the initial `git fetch` slower.
-      FETCH_DEPTH: 50
     strategy:
       matrix:
         # Only lint on the min and max supported Python versions.
@@ -34,52 +35,7 @@ jobs:
           - "3.8"
           - "3.11"
     steps:
-      - uses: actions/checkout@v3
-        with:
-          # Fetch the last FETCH_DEPTH commits, so the mtime-changing script
-          # can accurately set the mtimes of files modified in the last FETCH_DEPTH commits.
-          fetch-depth: ${{ env.FETCH_DEPTH }}
-      - name: Restore workdir file mtimes to last-edited commit date
-        id: restore-mtimes
-        # This is needed to make black caching work.
-        # Black's cache uses file (mtime, size) to check whether a lookup is a cache hit.
-        # Without this command, files in the repo would have the current time as the modified time,
-        # since the previous action step just created them.
-        # This command resets the mtime to the last time the files were modified in git instead,
-        # which is a high-quality and stable representation of the last modification date.
-        run: |
-          # Important considerations:
-          # - These commands run at base of the repo, since we never `cd` to the `WORKDIR`.
-          # - We only want to alter mtimes for Python files, since that's all black checks.
-          # - We don't need to alter mtimes for directories, since black doesn't look at those.
-          # - We also only alter mtimes inside the `WORKDIR` since that's all we'll lint.
-          # - This should run before `poetry install`, because poetry's venv also contains
-          #   Python files, and we don't want to alter their mtimes since they aren't linted.
-
-          # Ensure we fail on non-zero exits and on undefined variables.
-          # Also print executed commands, for easier debugging.
-          set -eux
-
-          # Restore the mtimes of Python files in the workdir based on git history.
-          .github/tools/git-restore-mtime --no-directories "$WORKDIR/**/*.py"
-
-          # Since CI only does a partial fetch (to `FETCH_DEPTH`) for efficiency,
-          # the local git repo doesn't have full history. There are probably files
-          # that were last modified in a commit *older than* the oldest fetched commit.
-          # After `git-restore-mtime`, such files have a mtime set to the oldest fetched commit.
-          #
-          # As new commits get added, that timestamp will keep moving forward.
-          # If left unchanged, this will make `black` think that the files were edited
-          # more recently than its cache suggests. Instead, we can set their mtime
-          # to a fixed date in the far past that won't change and won't cause cache misses in black.
-          #
-          # For all workdir Python files modified in or before the oldest few fetched commits,
-          # make their mtime be 2000-01-01 00:00:00.
-          OLDEST_COMMIT="$(git log --reverse '--pretty=format:%H' | head -1)"
-          OLDEST_COMMIT_TIME="$(git show -s '--format=%ai' "$OLDEST_COMMIT")"
-          find "$WORKDIR" -name '*.py' -type f -not -newermt "$OLDEST_COMMIT_TIME" -exec touch -c -m -t '200001010000' '{}' '+'
-
-          echo "oldest-commit=$OLDEST_COMMIT" >> "$GITHUB_OUTPUT"
+      - uses: actions/checkout@v4
 
       - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
@@ -116,22 +72,11 @@ jobs:
 
       - name: Install langchain editable
         working-directory: ${{ inputs.working-directory }}
-        if: ${{ inputs.working-directory != 'libs/langchain' }}
-        run: |
-          pip install -e ../langchain
-
-      - name: Restore black cache
-        uses: actions/cache@v3
+        if: ${{ inputs.langchain-location }}
         env:
-          CACHE_BASE: black-${{ 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 }}-
+          LANGCHAIN_LOCATION: ${{ inputs.langchain-location }}
+        run: |
+          pip install -e "$LANGCHAIN_LOCATION"
 
       - name: Get .mypy_cache to speed up mypy
         uses: actions/cache@v3
@@ -144,7 +89,5 @@ jobs:
 
       - 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

@@ -26,7 +26,7 @@ jobs:
           - "3.11"
     name: Pydantic v1/v2 compatibility - Python ${{ matrix.python-version }}
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"

.github/workflows/_release.yml

@@ -9,13 +9,121 @@ on:
         description: "From which folder this pipeline executes"
 
 env:
+  PYTHON_VERSION: "3.10"
   POETRY_VERSION: "1.6.1"
 
 jobs:
-  if_release:
-    # Disallow publishing from branches that aren't `master`.
+  build:
     if: github.ref == 'refs/heads/master'
     runs-on: ubuntu-latest
+
+    outputs:
+      pkg-name: ${{ steps.check-version.outputs.pkg-name }}
+      version: ${{ steps.check-version.outputs.version }}
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ inputs.working-directory }}
+          cache-key: release
+
+      # We want to keep this build stage *separate* from the release stage,
+      # so that there's no sharing of permissions between them.
+      # The release stage has trusted publishing and GitHub repo contents write access,
+      # and we want to keep the scope of that access limited just to the release job.
+      # Otherwise, a malicious `build` step (e.g. via a compromised dependency)
+      # could get access to our GitHub or PyPI credentials.
+      #
+      # Per the trusted publishing GitHub Action:
+      # > It is strongly advised to separate jobs for building [...]
+      # > from the publish job.
+      # https://github.com/pypa/gh-action-pypi-publish#non-goals
+      - name: Build project for distribution
+        run: poetry build
+        working-directory: ${{ inputs.working-directory }}
+
+      - name: Upload build
+        uses: actions/upload-artifact@v3
+        with:
+          name: dist
+          path: ${{ inputs.working-directory }}/dist/
+
+      - name: Check Version
+        id: check-version
+        shell: bash
+        working-directory: ${{ inputs.working-directory }}
+        run: |
+          echo pkg-name="$(poetry version | cut -d ' ' -f 1)" >> $GITHUB_OUTPUT
+          echo version="$(poetry version --short)" >> $GITHUB_OUTPUT
+
+  test-pypi-publish:
+    needs:
+      - build
+    uses:
+      ./.github/workflows/_test_release.yml
+    with:
+      working-directory: ${{ inputs.working-directory }}
+    secrets: inherit
+
+  pre-release-checks:
+    needs:
+      - build
+      - test-pypi-publish
+    runs-on: ubuntu-latest
+    steps:
+      # We explicitly *don't* set up caching here. This ensures our tests are
+      # maximally sensitive to catching breakage.
+      #
+      # For example, here's a way that caching can cause a falsely-passing test:
+      # - Make the langchain package manifest no longer list a dependency package
+      #   as a requirement. This means it won't be installed by `pip install`,
+      #   and attempting to use it would cause a crash.
+      # - That dependency used to be required, so it may have been cached.
+      #   When restoring the venv packages from cache, that dependency gets included.
+      # - Tests pass, because the dependency is present even though it wasn't specified.
+      # - The package is published, and it breaks on the missing dependency when
+      #   used in the real world.
+      - uses: actions/setup-python@v4
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+
+      - name: Test published package
+        shell: bash
+        env:
+          PKG_NAME: ${{ needs.build.outputs.pkg-name }}
+          VERSION: ${{ needs.build.outputs.version }}
+        # Here we specify:
+        # - The test PyPI index as the *primary* index, meaning that it takes priority.
+        # - The regular PyPI index as an extra index, so that any dependencies that
+        #   are not found on test PyPI can be resolved and installed anyway.
+        #
+        # Without the former, we might install the wrong langchain release.
+        # Without the latter, we might not be able to install langchain's dependencies.
+        #
+        # TODO: add more in-depth pre-publish tests after testing that importing works
+        run: |
+          pip install \
+            --index-url https://test.pypi.org/simple/ \
+            --extra-index-url https://pypi.org/simple/ \
+            "$PKG_NAME==$VERSION"
+
+          # Replace all dashes in the package name with underscores,
+          # since that's how Python imports packages with dashes in the name.
+          IMPORT_NAME="$(echo "$PKG_NAME" | sed s/-/_/g)"
+
+          python -c "import $IMPORT_NAME; print(dir($IMPORT_NAME))"
+
+  publish:
+    needs:
+      - build
+      - test-pypi-publish
+      - pre-release-checks
+    runs-on: ubuntu-latest
     permissions:
       # This permission is used for trusted publishing:
       # https://blog.pypi.org/posts/2023-04-20-introducing-trusted-publishers/
@@ -24,28 +132,65 @@ jobs:
       # https://docs.pypi.org/trusted-publishers/adding-a-publisher/
       id-token: write
 
-      # This permission is needed by `ncipollo/release-action` to create the GitHub release.
-      contents: write
     defaults:
       run:
         working-directory: ${{ inputs.working-directory }}
+
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: "3.10"
+          python-version: ${{ env.PYTHON_VERSION }}
           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
+      - uses: actions/download-artifact@v3
+        with:
+          name: dist
+          path: ${{ inputs.working-directory }}/dist/
+
+      - 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
+
+  mark-release:
+    needs:
+      - build
+      - test-pypi-publish
+      - pre-release-checks
+      - publish
+    runs-on: ubuntu-latest
+    permissions:
+      # 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"
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ inputs.working-directory }}
+          cache-key: release
+
+      - uses: actions/download-artifact@v3
+        with:
+          name: dist
+          path: ${{ inputs.working-directory }}/dist/
+
       - name: Create Release
         uses: ncipollo/release-action@v1
         if: ${{ inputs.working-directory == 'libs/langchain' }}
@@ -54,11 +199,5 @@ jobs:
           token: ${{ secrets.GITHUB_TOKEN }}
           draft: false
           generateReleaseNotes: true
-          tag: v${{ steps.check-version.outputs.version }}
+          tag: v${{ needs.build.outputs.version }}
           commit: master
-      - name: Publish package distributions to PyPI
-        uses: pypa/gh-action-pypi-publish@release/v1
-        with:
-          packages-dir: ${{ inputs.working-directory }}/dist/
-          verbose: true
-          print-hash: true

.github/workflows/_test.yml

@@ -26,7 +26,7 @@ jobs:
           - "3.11"
     name: Python ${{ matrix.python-version }}
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"

.github/workflows/_test_release.yml

@@ -0,0 +1,95 @@
+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"
+  PYTHON_VERSION: "3.10"
+
+jobs:
+  build:
+    if: github.ref == 'refs/heads/master'
+    runs-on: ubuntu-latest
+
+    outputs:
+      pkg-name: ${{ steps.check-version.outputs.pkg-name }}
+      version: ${{ steps.check-version.outputs.version }}
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ inputs.working-directory }}
+          cache-key: release
+
+      # We want to keep this build stage *separate* from the release stage,
+      # so that there's no sharing of permissions between them.
+      # The release stage has trusted publishing and GitHub repo contents write access,
+      # and we want to keep the scope of that access limited just to the release job.
+      # Otherwise, a malicious `build` step (e.g. via a compromised dependency)
+      # could get access to our GitHub or PyPI credentials.
+      #
+      # Per the trusted publishing GitHub Action:
+      # > It is strongly advised to separate jobs for building [...]
+      # > from the publish job.
+      # https://github.com/pypa/gh-action-pypi-publish#non-goals
+      - name: Build project for distribution
+        run: poetry build
+        working-directory: ${{ inputs.working-directory }}
+
+      - name: Upload build
+        uses: actions/upload-artifact@v3
+        with:
+          name: test-dist
+          path: ${{ inputs.working-directory }}/dist/
+
+      - name: Check Version
+        id: check-version
+        shell: bash
+        working-directory: ${{ inputs.working-directory }}
+        run: |
+          echo pkg-name="$(poetry version | cut -d ' ' -f 1)" >> $GITHUB_OUTPUT
+          echo version="$(poetry version --short)" >> $GITHUB_OUTPUT
+
+  publish:
+    needs:
+      - build
+    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
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/download-artifact@v3
+        with:
+          name: test-dist
+          path: ${{ inputs.working-directory }}/dist/
+
+      - name: Publish to test PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          packages-dir: ${{ inputs.working-directory }}/dist/
+          verbose: true
+          print-hash: true
+          repository-url: https://test.pypi.org/legacy/
+
+          # We overwrite any existing distributions with the same name and version.
+          # This is *only for CI use* and is *extremely dangerous* otherwise!
+          # https://github.com/pypa/gh-action-pypi-publish#tolerating-release-package-file-duplicates
+          skip-existing: true

.github/workflows/codespell.yml

@@ -17,7 +17,7 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Install Dependencies
         run: |

.github/workflows/doc_lint.yml

@@ -1,11 +1,17 @@
 ---
-name: Documentation Lint
+name: Docs, templates, cookbook lint
 
 on:
   push:
-    branches: [master]
+    branches: [ master ]
   pull_request:
-    branches: [master]
+    paths:
+      - 'docs/**'
+      - 'templates/**'
+      - 'cookbook/**'
+      - '.github/workflows/_lint.yml'
+      - '.github/workflows/doc_lint.yml'
+  workflow_dispatch:
 
 jobs:
   check:
@@ -13,10 +19,17 @@ jobs:
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v2
+      uses: actions/checkout@v4
 
     - 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
+        git grep 'from langchain import' {docs/docs,templates,cookbook} | grep -vE 'from langchain import (hub)' && exit 1 || exit 0
+
+  lint:
+      uses:
+        ./.github/workflows/_lint.yml
+      with:
+        working-directory: "."
+      secrets: inherit

.github/workflows/langchain_ci.yml

@@ -12,6 +12,7 @@ on:
       - '.github/workflows/_test.yml'
       - '.github/workflows/_pydantic_compatibility.yml'
       - '.github/workflows/langchain_ci.yml'
+      - 'libs/*'
       - 'libs/langchain/**'
   workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
 
@@ -44,6 +45,13 @@ jobs:
       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
@@ -65,7 +73,7 @@ jobs:
           - "3.11"
     name: Python ${{ matrix.python-version }} extended tests
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"

.github/workflows/langchain_cli_ci.yml

@@ -0,0 +1,47 @@
+---
+name: libs/cli CI
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    paths:
+      - '.github/actions/poetry_setup/action.yml'
+      - '.github/tools/**'
+      - '.github/workflows/_lint.yml'
+      - '.github/workflows/_test.yml'
+      - '.github/workflows/_pydantic_compatibility.yml'
+      - '.github/workflows/langchain_cli_ci.yml'
+      - 'libs/cli/**'
+      - 'libs/*'
+  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/cli"
+
+jobs:
+  lint:
+    uses:
+      ./.github/workflows/_lint.yml
+    with:
+      working-directory: libs/cli
+      langchain-location: ../langchain
+    secrets: inherit
+
+  test:
+    uses:
+      ./.github/workflows/_test.yml
+    with:
+      working-directory: libs/cli
+    secrets: inherit

.github/workflows/langchain_cli_release.yml

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

.github/workflows/langchain_experimental_ci.yml

@@ -11,7 +11,7 @@ on:
       - '.github/workflows/_lint.yml'
       - '.github/workflows/_test.yml'
       - '.github/workflows/langchain_experimental_ci.yml'
-      - 'libs/langchain/**'
+      - 'libs/*'
       - 'libs/experimental/**'
   workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
 
@@ -35,6 +35,7 @@ jobs:
       ./.github/workflows/_lint.yml
     with:
       working-directory: libs/experimental
+      langchain-location: ../langchain
     secrets: inherit
 
   test:
@@ -44,6 +45,13 @@ jobs:
       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`.
   #
@@ -62,7 +70,7 @@ jobs:
           - "3.11"
     name: test with unpublished langchain - Python ${{ matrix.python-version }}
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
@@ -97,7 +105,7 @@ jobs:
           - "3.11"
     name: Python ${{ matrix.python-version }} extended tests
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"

.github/workflows/langchain_experimental_test_release.yml

@@ -0,0 +1,13 @@
+---
+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_test_release.yml

@@ -0,0 +1,13 @@
+---
+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

@@ -24,7 +24,7 @@ jobs:
           - "3.11"
     name: Python ${{ matrix.python-version }}
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - name: Set up Python ${{ matrix.python-version }}
         uses: "./.github/actions/poetry_setup"
@@ -55,6 +55,10 @@ jobs:
           poetry install --with=test_integration
           poetry run pip install google-cloud-aiplatform
           poetry run pip install "boto3>=1.28.57"
+          if [[ ${{ matrix.python-version }} != "3.8" ]]
+          then
+            poetry run pip install fireworks-ai
+          fi
 
       - name: Run tests
         shell: bash
@@ -64,7 +68,8 @@ jobs:
           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 }}
+          AZURE_OPENAI_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_DEPLOYMENT_NAME }}
+          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
         run: |
           make scheduled_tests
 

.github/workflows/templates_ci.yml

@@ -0,0 +1,37 @@
+---
+name: templates CI
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    paths:
+      - '.github/actions/poetry_setup/action.yml'
+      - '.github/tools/**'
+      - '.github/workflows/_lint.yml'
+      - '.github/workflows/templates_ci.yml'
+      - 'templates/**'
+  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: "templates"
+
+jobs:
+  lint:
+    uses:
+      ./.github/workflows/_lint.yml
+    with:
+      working-directory: templates
+      langchain-location: ../libs/langchain
+    secrets: inherit

.gitignore

@@ -178,3 +178,4 @@ docs/docs/build
 docs/docs/node_modules
 docs/docs/yarn.lock
 _dist
+docs/docs/templates

Makefile

@@ -37,6 +37,18 @@ spell_check:
 spell_fix:
 	poetry run codespell --toml pyproject.toml -w
 
+######################
+# LINTING AND FORMATTING
+######################
+
+lint:
+	poetry run ruff docs templates cookbook
+	poetry run black docs templates cookbook --diff
+
+format format_diff:
+	poetry run black docs templates cookbook
+	poetry run ruff --select I --fix docs templates cookbook
+
 ######################
 # HELP
 ######################

README.md

@@ -93,7 +93,7 @@ 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 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 by 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).
 

cookbook/LLaMA2_sql_chat.ipynb

@@ -47,7 +47,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 1,
    "id": "6a75a5c6-34ee-4ab9-a664-d9b432d812ee",
    "metadata": {},
    "outputs": [
@@ -60,28 +60,27 @@
     }
    ],
    "source": [
-    "# Local \n",
+    "# Local\n",
     "from langchain.chat_models import ChatOllama\n",
+    "\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",
+    "\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",
+    "    model=replicate_id, input={\"temperature\": 0.01, \"max_length\": 500, \"top_p\": 1}\n",
     ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 2,
    "id": "ce96f7ea-b3d5-44e1-9fa5-a79e04a9e1fb",
    "metadata": {},
    "outputs": [],
@@ -104,17 +103,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 3,
    "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",
+    "db = SQLDatabase.from_uri(\"sqlite:///nba_roster.db\", sample_rows_in_table_info=0)\n",
+    "\n",
     "\n",
     "def get_schema(_):\n",
     "    return db.get_table_info()\n",
     "\n",
+    "\n",
     "def run_query(query):\n",
     "    return db.run(query)"
    ]
@@ -131,7 +133,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 4,
    "id": "5a4933ea-d9c0-4b0a-8177-ba4490c6532b",
    "metadata": {},
    "outputs": [
@@ -141,7 +143,7 @@
        "' SELECT \"Team\" FROM nba_roster WHERE \"NAME\" = \\'Klay Thompson\\';'"
       ]
      },
-     "execution_count": 14,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -149,26 +151,29 @@
    "source": [
     "# Prompt\n",
     "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_messages([\n",
-    "    (\"system\", \"Given an input question, convert it to a SQL query. No pre-amble.\"),\n",
-    "    (\"human\", template)\n",
-    "])\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\"system\", \"Given an input question, convert it to a SQL query. No pre-amble.\"),\n",
+    "        (\"human\", template),\n",
+    "    ]\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",
+    "    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?\"})"
    ]
@@ -209,18 +214,23 @@
     "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",
+    "prompt_response = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"Given an input question and SQL response, convert it to a natural langugae answer. No pre-amble.\",\n",
+    "        ),\n",
+    "        (\"human\", template),\n",
+    "    ]\n",
+    ")\n",
     "\n",
     "full_chain = (\n",
-    "    RunnablePassthrough.assign(query=sql_response) \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",
+    "    | prompt_response\n",
     "    | llm\n",
     ")\n",
     "\n",
@@ -250,8 +260,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
-   "id": "1985aa1c-eb8f-4fb1-a54f-c8aa10744687",
+   "execution_count": 7,
+   "id": "022868f2-128e-42f5-8d90-d3bb2f11d994",
    "metadata": {},
    "outputs": [
     {
@@ -260,7 +270,7 @@
        "' SELECT \"Team\" FROM nba_roster WHERE \"NAME\" = \\'Klay Thompson\\';'"
       ]
      },
-     "execution_count": 19,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -269,61 +279,44 @@
     "# 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",
+    "template = \"\"\"Given an input question, convert it to a SQL query. No pre-amble. Based on the table schema below, write a SQL query that would answer the user's question:\n",
+    "{schema}\n",
+    "\"\"\"\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\"system\", template),\n",
+    "        MessagesPlaceholder(variable_name=\"history\"),\n",
+    "        (\"human\", \"{question}\"),\n",
+    "    ]\n",
+    ")\n",
     "\n",
     "memory = ConversationBufferMemory(return_messages=True)\n",
     "\n",
-    "# Chain to query with memory \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",
+    "        schema=get_schema,\n",
+    "        history=RunnableLambda(lambda x: memory.load_memory_variables(x)[\"history\"]),\n",
+    "    )\n",
+    "    | prompt\n",
     "    | llm.bind(stop=[\"\\nSQLResult:\"])\n",
     "    | StrOutputParser()\n",
     ")\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",
+    "    return output[\"output\"]\n",
+    "\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,
@@ -349,18 +342,23 @@
     "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",
+    "prompt_response = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"Given an input question and SQL response, convert it to a natural langugae answer. No pre-amble.\",\n",
+    "        ),\n",
+    "        (\"human\", template),\n",
+    "    ]\n",
+    ")\n",
     "\n",
     "full_chain = (\n",
-    "    RunnablePassthrough.assign(query=sql_response_memory) \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",
+    "    | prompt_response\n",
     "    | llm\n",
     ")\n",
     "\n",

cookbook/README.md

@@ -4,7 +4,7 @@ Example code for building applications with LangChain, with an emphasis on more
 
 Notebook | Description
 :- | :-
-[LLaMA2_sql_chat.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/LLaMA2_sql_chat.ipynb) | Build a chat application that interacts with a sql database using an open source llm (llama2), specifically demonstrated on a sqlite database containing nba rosters.
+[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.
@@ -12,14 +12,14 @@ Notebook | Description
 [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.
+[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.
+[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.
@@ -37,16 +37,18 @@ Notebook | Description
 [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.
+[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.
+[openai_v1_cookbook.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/openai_v1_cookbook.ipynb) | Explore new functionality released alongside the V1 release of the OpenAI Python library.
 [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.
+[retrieval_in_sql.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/retrieval_in_sql.ipynb) | Perform retrieval-augmented-generation (rag) on a PostgreSQL database using pgvector.
 [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.
+[twitter-the-algorithm-analysis...](https://github.com/langchain-ai/langchain/tree/master/cookbook/twitter-the-algorithm-analysis-deeplake.ipynb) | Analyze the source code of the Twitter algorithm with the help of gpt4 and activeloop's deep lake.
 [two_agent_debate_tools.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/two_agent_debate_tools.ipynb) | Simulate multi-agent dialogues where the agents can utilize various tools.
-[two_player_dnd.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/two_player_dnd.ipynb) | Simulate a two-player dungeons & dragons game, where a dialoguesimulator class is used to coordinate the dialogue between the protagonist and the dungeon master.
+[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/Semi_Structured_RAG.ipynb

@@ -60,7 +60,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! brew install tesseract \n",
+    "! brew install tesseract\n",
     "! brew install poppler"
    ]
   },
@@ -108,21 +108,23 @@
     "from unstructured.partition.pdf import partition_pdf\n",
     "\n",
     "# Get elements\n",
-    "raw_pdf_elements = partition_pdf(filename=path+\"LLaMA2.pdf\",\n",
-    "                                 # Unstructured first finds embedded image blocks\n",
-    "                                 extract_images_in_pdf=False,\n",
-    "                                 # Use layout model (YOLOX) to get bounding boxes (for tables) and find titles\n",
-    "                                 # Titles are any sub-section of the document \n",
-    "                                 infer_table_structure=True, \n",
-    "                                 # Post processing to aggregate text once we have the title \n",
-    "                                 chunking_strategy=\"by_title\",\n",
-    "                                 # Chunking params to aggregate text blocks\n",
-    "                                 # Attempt to create a new chunk 3800 chars\n",
-    "                                 # Attempt to keep chunks > 2000 chars \n",
-    "                                 max_characters=4000, \n",
-    "                                 new_after_n_chars=3800, \n",
-    "                                 combine_text_under_n_chars=2000,\n",
-    "                                 image_output_dir_path=path)"
+    "raw_pdf_elements = partition_pdf(\n",
+    "    filename=path + \"LLaMA2.pdf\",\n",
+    "    # Unstructured first finds embedded image blocks\n",
+    "    extract_images_in_pdf=False,\n",
+    "    # Use layout model (YOLOX) to get bounding boxes (for tables) and find titles\n",
+    "    # Titles are any sub-section of the document\n",
+    "    infer_table_structure=True,\n",
+    "    # Post processing to aggregate text once we have the title\n",
+    "    chunking_strategy=\"by_title\",\n",
+    "    # Chunking params to aggregate text blocks\n",
+    "    # Attempt to create a new chunk 3800 chars\n",
+    "    # Attempt to keep chunks > 2000 chars\n",
+    "    max_characters=4000,\n",
+    "    new_after_n_chars=3800,\n",
+    "    combine_text_under_n_chars=2000,\n",
+    "    image_output_dir_path=path,\n",
+    ")"
    ]
   },
   {
@@ -190,6 +192,7 @@
     "    type: str\n",
     "    text: Any\n",
     "\n",
+    "\n",
     "# Categorize by type\n",
     "categorized_elements = []\n",
     "for element in raw_pdf_elements:\n",
@@ -259,14 +262,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Prompt \n",
-    "prompt_text=\"\"\"You are an assistant tasked with summarizing tables and text. \\ \n",
+    "# Prompt\n",
+    "prompt_text = \"\"\"You are an assistant tasked with summarizing tables and text. \\ \n",
     "Give a concise summary of the table or text. Table or text chunk: {element} \"\"\"\n",
-    "prompt = ChatPromptTemplate.from_template(prompt_text) \n",
+    "prompt = ChatPromptTemplate.from_template(prompt_text)\n",
     "\n",
-    "# Summary chain \n",
-    "model = ChatOpenAI(temperature=0,model=\"gpt-4\")\n",
-    "summarize_chain = {\"element\": lambda x:x} | prompt | model | StrOutputParser()"
+    "# Summary chain\n",
+    "model = ChatOpenAI(temperature=0, model=\"gpt-4\")\n",
+    "summarize_chain = {\"element\": lambda x: x} | prompt | model | StrOutputParser()"
    ]
   },
   {
@@ -321,10 +324,7 @@
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "\n",
     "# The vectorstore to use to index the child chunks\n",
-    "vectorstore = Chroma(\n",
-    "    collection_name=\"summaries\",\n",
-    "    embedding_function=OpenAIEmbeddings()\n",
-    ")\n",
+    "vectorstore = Chroma(collection_name=\"summaries\", embedding_function=OpenAIEmbeddings())\n",
     "\n",
     "# The storage layer for the parent documents\n",
     "store = InMemoryStore()\n",
@@ -332,20 +332,26 @@
     "\n",
     "# The retriever (empty to start)\n",
     "retriever = MultiVectorRetriever(\n",
-    "    vectorstore=vectorstore, \n",
-    "    docstore=store, \n",
+    "    vectorstore=vectorstore,\n",
+    "    docstore=store,\n",
     "    id_key=id_key,\n",
     ")\n",
     "\n",
     "# Add texts\n",
     "doc_ids = [str(uuid.uuid4()) for _ in texts]\n",
-    "summary_texts = [Document(page_content=s,metadata={id_key: doc_ids[i]}) for i, s in enumerate(text_summaries)]\n",
+    "summary_texts = [\n",
+    "    Document(page_content=s, metadata={id_key: doc_ids[i]})\n",
+    "    for i, s in enumerate(text_summaries)\n",
+    "]\n",
     "retriever.vectorstore.add_documents(summary_texts)\n",
     "retriever.docstore.mset(list(zip(doc_ids, texts)))\n",
     "\n",
     "# Add tables\n",
     "table_ids = [str(uuid.uuid4()) for _ in tables]\n",
-    "summary_tables = [Document(page_content=s,metadata={id_key: table_ids[i]}) for i, s in enumerate(table_summaries)]\n",
+    "summary_tables = [\n",
+    "    Document(page_content=s, metadata={id_key: table_ids[i]})\n",
+    "    for i, s in enumerate(table_summaries)\n",
+    "]\n",
     "retriever.vectorstore.add_documents(summary_tables)\n",
     "retriever.docstore.mset(list(zip(table_ids, tables)))"
    ]
@@ -378,13 +384,13 @@
     "prompt = ChatPromptTemplate.from_template(template)\n",
     "\n",
     "# LLM\n",
-    "model = ChatOpenAI(temperature=0,model=\"gpt-4\")\n",
+    "model = ChatOpenAI(temperature=0, model=\"gpt-4\")\n",
     "\n",
     "# RAG pipeline\n",
     "chain = (\n",
-    "    {\"context\": retriever, \"question\": RunnablePassthrough()} \n",
-    "    | prompt \n",
-    "    | model \n",
+    "    {\"context\": retriever, \"question\": RunnablePassthrough()}\n",
+    "    | prompt\n",
+    "    | model\n",
     "    | StrOutputParser()\n",
     ")"
    ]

cookbook/code-analysis-deeplake.ipynb

@@ -837,7 +837,9 @@
     "from langchain.chat_models import ChatOpenAI\n",
     "from langchain.chains import ConversationalRetrievalChain\n",
     "\n",
-    "model = ChatOpenAI(model_name=\"gpt-3.5-turbo-0613\")  # 'ada' 'gpt-3.5-turbo-0613' 'gpt-4',\n",
+    "model = ChatOpenAI(\n",
+    "    model_name=\"gpt-3.5-turbo-0613\"\n",
+    ")  # 'ada' 'gpt-3.5-turbo-0613' 'gpt-4',\n",
     "qa = ConversationalRetrievalChain.from_llm(model, retriever=retriever)"
    ]
   },

cookbook/extraction_openai_tools.ipynb

@@ -0,0 +1,213 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "2def22ea",
+   "metadata": {},
+   "source": [
+    "# Extraction with OpenAI Tools\n",
+    "\n",
+    "Performing extraction has never been easier! OpenAI's tool calling ability is the perfect thing to use as it allows for extracting multiple different elements from text that are different types. \n",
+    "\n",
+    "Models after 1106 use tools and support \"parallel function calling\" which makes this super easy."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "5c628496",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.pydantic_v1 import BaseModel\n",
+    "from typing import Optional, List\n",
+    "from langchain.chains.openai_tools import create_extraction_chain_pydantic"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "afe9657b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Make sure to use a recent model that supports tools\n",
+    "model = ChatOpenAI(model=\"gpt-3.5-turbo-1106\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "bc0ca3b6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Pydantic is an easy way to define a schema\n",
+    "class Person(BaseModel):\n",
+    "    \"\"\"Information about people to extract.\"\"\"\n",
+    "\n",
+    "    name: str\n",
+    "    age: Optional[int] = None"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "2036af68",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = create_extraction_chain_pydantic(Person, model)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "1748ad21",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Person(name='jane', age=2), Person(name='bob', age=3)]"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"input\": \"jane is 2 and bob is 3\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "c8262ce5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Let's define another element\n",
+    "class Class(BaseModel):\n",
+    "    \"\"\"Information about classes to extract.\"\"\"\n",
+    "\n",
+    "    teacher: str\n",
+    "    students: List[str]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "4973c104",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = create_extraction_chain_pydantic([Person, Class], model)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "e976a15e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Person(name='jane', age=2),\n",
+       " Person(name='bob', age=3),\n",
+       " Class(teacher='Mrs Sampson', students=['jane', 'bob'])]"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"input\": \"jane is 2 and bob is 3 and they are in Mrs Sampson's class\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6575a7d6",
+   "metadata": {},
+   "source": [
+    "## Under the hood\n",
+    "\n",
+    "Under the hood, this is a simple chain:"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b8ba83e5",
+   "metadata": {},
+   "source": [
+    "```python\n",
+    "from typing import Union, List, Type, Optional\n",
+    "\n",
+    "from langchain.output_parsers.openai_tools import PydanticToolsParser\n",
+    "from langchain.utils.openai_functions import convert_pydantic_to_openai_tool\n",
+    "from langchain.schema.runnable import Runnable\n",
+    "from langchain.pydantic_v1 import BaseModel\n",
+    "from langchain.prompts import ChatPromptTemplate\n",
+    "from langchain.schema.messages import SystemMessage\n",
+    "from langchain.schema.language_model import BaseLanguageModel\n",
+    "\n",
+    "_EXTRACTION_TEMPLATE = \"\"\"Extract and save the relevant entities mentioned \\\n",
+    "in the following passage together with their properties.\n",
+    "\n",
+    "If a property is not present and is not required in the function parameters, do not include it in the output.\"\"\"  # noqa: E501\n",
+    "\n",
+    "\n",
+    "def create_extraction_chain_pydantic(\n",
+    "    pydantic_schemas: Union[List[Type[BaseModel]], Type[BaseModel]],\n",
+    "    llm: BaseLanguageModel,\n",
+    "    system_message: str = _EXTRACTION_TEMPLATE,\n",
+    ") -> Runnable:\n",
+    "    if not isinstance(pydantic_schemas, list):\n",
+    "        pydantic_schemas = [pydantic_schemas]\n",
+    "    prompt = ChatPromptTemplate.from_messages([\n",
+    "        (\"system\", system_message),\n",
+    "        (\"user\", \"{input}\")\n",
+    "    ])\n",
+    "    tools = [convert_pydantic_to_openai_tool(p) for p in pydantic_schemas]\n",
+    "    model = llm.bind(tools=tools)\n",
+    "    chain = prompt | model | PydanticToolsParser(tools=pydantic_schemas)\n",
+    "    return chain\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2eac6b68",
+   "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/hugginggpt.ipynb

@@ -77,6 +77,7 @@
    "source": [
     "from langchain.llms import OpenAI\n",
     "from langchain_experimental.autonomous_agents import HuggingGPT\n",
+    "\n",
     "# %env OPENAI_API_BASE=http://localhost:8000/v1"
    ]
   },

cookbook/learned_prompt_optimization.ipynb

@@ -50,6 +50,7 @@
     "# pick and configure the LLM of your choice\n",
     "\n",
     "from langchain.llms import OpenAI\n",
+    "\n",
     "llm = OpenAI(model=\"text-davinci-003\")"
    ]
   },
@@ -85,8 +86,8 @@
     "\"\"\"\n",
     "\n",
     "PROMPT = PromptTemplate(\n",
-    "    input_variables=[\"meal\", \"text_to_personalize\", \"user\", \"preference\"], \n",
-    "    template=PROMPT_TEMPLATE\n",
+    "    input_variables=[\"meal\", \"text_to_personalize\", \"user\", \"preference\"],\n",
+    "    template=PROMPT_TEMPLATE,\n",
     ")"
    ]
   },
@@ -105,7 +106,7 @@
    "source": [
     "import langchain_experimental.rl_chain as rl_chain\n",
     "\n",
-    "chain = rl_chain.PickBest.from_llm(llm=llm, prompt=PROMPT)\n"
+    "chain = rl_chain.PickBest.from_llm(llm=llm, prompt=PROMPT)"
    ]
   },
   {
@@ -122,10 +123,10 @@
    "outputs": [],
    "source": [
     "response = chain.run(\n",
-    "    meal = rl_chain.ToSelectFrom(meals),\n",
-    "    user = rl_chain.BasedOn(\"Tom\"),\n",
-    "    preference = rl_chain.BasedOn([\"Vegetarian\", \"regular dairy is ok\"]),\n",
-    "    text_to_personalize = \"This is the weeks specialty dish, our master chefs \\\n",
+    "    meal=rl_chain.ToSelectFrom(meals),\n",
+    "    user=rl_chain.BasedOn(\"Tom\"),\n",
+    "    preference=rl_chain.BasedOn([\"Vegetarian\", \"regular dairy is ok\"]),\n",
+    "    text_to_personalize=\"This is the weeks specialty dish, our master chefs \\\n",
     "        believe you will love it!\",\n",
     ")"
    ]
@@ -193,10 +194,10 @@
     "for _ in range(5):\n",
     "    try:\n",
     "        response = chain.run(\n",
-    "            meal = rl_chain.ToSelectFrom(meals),\n",
-    "            user = rl_chain.BasedOn(\"Tom\"),\n",
-    "            preference = rl_chain.BasedOn([\"Vegetarian\", \"regular dairy is ok\"]),\n",
-    "            text_to_personalize = \"This is the weeks specialty dish, our master chefs believe you will love it!\",\n",
+    "            meal=rl_chain.ToSelectFrom(meals),\n",
+    "            user=rl_chain.BasedOn(\"Tom\"),\n",
+    "            preference=rl_chain.BasedOn([\"Vegetarian\", \"regular dairy is ok\"]),\n",
+    "            text_to_personalize=\"This is the weeks specialty dish, our master chefs believe you will love it!\",\n",
     "        )\n",
     "    except Exception as e:\n",
     "        print(e)\n",
@@ -223,12 +224,16 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "scoring_criteria_template = \"Given {preference} rank how good or bad this selection is {meal}\"\n",
+    "scoring_criteria_template = (\n",
+    "    \"Given {preference} rank how good or bad this selection is {meal}\"\n",
+    ")\n",
     "\n",
     "chain = rl_chain.PickBest.from_llm(\n",
     "    llm=llm,\n",
     "    prompt=PROMPT,\n",
-    "    selection_scorer=rl_chain.AutoSelectionScorer(llm=llm, scoring_criteria_template_str=scoring_criteria_template),\n",
+    "    selection_scorer=rl_chain.AutoSelectionScorer(\n",
+    "        llm=llm, scoring_criteria_template_str=scoring_criteria_template\n",
+    "    ),\n",
     ")"
    ]
   },
@@ -255,14 +260,16 @@
    ],
    "source": [
     "response = chain.run(\n",
-    "    meal = rl_chain.ToSelectFrom(meals),\n",
-    "    user = rl_chain.BasedOn(\"Tom\"),\n",
-    "    preference = rl_chain.BasedOn([\"Vegetarian\", \"regular dairy is ok\"]),\n",
-    "    text_to_personalize = \"This is the weeks specialty dish, our master chefs believe you will love it!\",\n",
+    "    meal=rl_chain.ToSelectFrom(meals),\n",
+    "    user=rl_chain.BasedOn(\"Tom\"),\n",
+    "    preference=rl_chain.BasedOn([\"Vegetarian\", \"regular dairy is ok\"]),\n",
+    "    text_to_personalize=\"This is the weeks specialty dish, our master chefs believe you will love it!\",\n",
     ")\n",
     "print(response[\"response\"])\n",
     "selection_metadata = response[\"selection_metadata\"]\n",
-    "print(f\"selected index: {selection_metadata.selected.index}, score: {selection_metadata.selected.score}\")"
+    "print(\n",
+    "    f\"selected index: {selection_metadata.selected.index}, score: {selection_metadata.selected.score}\"\n",
+    ")"
    ]
   },
   {
@@ -280,8 +287,8 @@
    "source": [
     "class CustomSelectionScorer(rl_chain.SelectionScorer):\n",
     "    def score_response(\n",
-    "        self, inputs, llm_response: str, event: rl_chain.PickBestEvent) -> float:\n",
-    "\n",
+    "        self, inputs, llm_response: str, event: rl_chain.PickBestEvent\n",
+    "    ) -> float:\n",
     "        print(event.based_on)\n",
     "        print(event.to_select_from)\n",
     "\n",
@@ -336,10 +343,10 @@
    ],
    "source": [
     "response = chain.run(\n",
-    "    meal = rl_chain.ToSelectFrom(meals),\n",
-    "    user = rl_chain.BasedOn(\"Tom\"),\n",
-    "    preference = rl_chain.BasedOn([\"Vegetarian\", \"regular dairy is ok\"]),\n",
-    "    text_to_personalize = \"This is the weeks specialty dish, our master chefs believe you will love it!\",\n",
+    "    meal=rl_chain.ToSelectFrom(meals),\n",
+    "    user=rl_chain.BasedOn(\"Tom\"),\n",
+    "    preference=rl_chain.BasedOn([\"Vegetarian\", \"regular dairy is ok\"]),\n",
+    "    text_to_personalize=\"This is the weeks specialty dish, our master chefs believe you will love it!\",\n",
     ")"
    ]
   },
@@ -370,9 +377,10 @@
     "                return 1.0\n",
     "            else:\n",
     "                return 0.0\n",
-    "    def score_response(\n",
-    "        self, inputs, llm_response: str, event: rl_chain.PickBestEvent) -> float:\n",
     "\n",
+    "    def score_response(\n",
+    "        self, inputs, llm_response: str, event: rl_chain.PickBestEvent\n",
+    "    ) -> float:\n",
     "        selected_meal = event.to_select_from[\"meal\"][event.selected.index]\n",
     "\n",
     "        if \"Tom\" in event.based_on[\"user\"]:\n",
@@ -394,7 +402,7 @@
     "    prompt=PROMPT,\n",
     "    selection_scorer=CustomSelectionScorer(),\n",
     "    metrics_step=5,\n",
-    "    metrics_window_size=5, # rolling window average\n",
+    "    metrics_window_size=5,  # rolling window average\n",
     ")\n",
     "\n",
     "random_chain = rl_chain.PickBest.from_llm(\n",
@@ -402,8 +410,8 @@
     "    prompt=PROMPT,\n",
     "    selection_scorer=CustomSelectionScorer(),\n",
     "    metrics_step=5,\n",
-    "    metrics_window_size=5, # rolling window average\n",
-    "    policy=rl_chain.PickBestRandomPolicy # set the random policy instead of default\n",
+    "    metrics_window_size=5,  # rolling window average\n",
+    "    policy=rl_chain.PickBestRandomPolicy,  # set the random policy instead of default\n",
     ")"
    ]
   },
@@ -416,29 +424,29 @@
     "for _ in range(20):\n",
     "    try:\n",
     "        chain.run(\n",
-    "            meal = rl_chain.ToSelectFrom(meals),\n",
-    "            user = rl_chain.BasedOn(\"Tom\"),\n",
-    "            preference = rl_chain.BasedOn([\"Vegetarian\", \"regular dairy is ok\"]),\n",
-    "            text_to_personalize = \"This is the weeks specialty dish, our master chefs believe you will love it!\",\n",
+    "            meal=rl_chain.ToSelectFrom(meals),\n",
+    "            user=rl_chain.BasedOn(\"Tom\"),\n",
+    "            preference=rl_chain.BasedOn([\"Vegetarian\", \"regular dairy is ok\"]),\n",
+    "            text_to_personalize=\"This is the weeks specialty dish, our master chefs believe you will love it!\",\n",
     "        )\n",
     "        random_chain.run(\n",
-    "            meal = rl_chain.ToSelectFrom(meals),\n",
-    "            user = rl_chain.BasedOn(\"Tom\"),\n",
-    "            preference = rl_chain.BasedOn([\"Vegetarian\", \"regular dairy is ok\"]),\n",
-    "            text_to_personalize = \"This is the weeks specialty dish, our master chefs believe you will love it!\",\n",
+    "            meal=rl_chain.ToSelectFrom(meals),\n",
+    "            user=rl_chain.BasedOn(\"Tom\"),\n",
+    "            preference=rl_chain.BasedOn([\"Vegetarian\", \"regular dairy is ok\"]),\n",
+    "            text_to_personalize=\"This is the weeks specialty dish, our master chefs believe you will love it!\",\n",
     "        )\n",
-    "    \n",
+    "\n",
     "        chain.run(\n",
-    "            meal = rl_chain.ToSelectFrom(meals),\n",
-    "            user = rl_chain.BasedOn(\"Anna\"),\n",
-    "            preference = rl_chain.BasedOn([\"Loves meat\", \"especially beef\"]),\n",
-    "            text_to_personalize = \"This is the weeks specialty dish, our master chefs believe you will love it!\",\n",
+    "            meal=rl_chain.ToSelectFrom(meals),\n",
+    "            user=rl_chain.BasedOn(\"Anna\"),\n",
+    "            preference=rl_chain.BasedOn([\"Loves meat\", \"especially beef\"]),\n",
+    "            text_to_personalize=\"This is the weeks specialty dish, our master chefs believe you will love it!\",\n",
     "        )\n",
     "        random_chain.run(\n",
-    "            meal = rl_chain.ToSelectFrom(meals),\n",
-    "            user = rl_chain.BasedOn(\"Anna\"),\n",
-    "            preference = rl_chain.BasedOn([\"Loves meat\", \"especially beef\"]),\n",
-    "            text_to_personalize = \"This is the weeks specialty dish, our master chefs believe you will love it!\",\n",
+    "            meal=rl_chain.ToSelectFrom(meals),\n",
+    "            user=rl_chain.BasedOn(\"Anna\"),\n",
+    "            preference=rl_chain.BasedOn([\"Loves meat\", \"especially beef\"]),\n",
+    "            text_to_personalize=\"This is the weeks specialty dish, our master chefs believe you will love it!\",\n",
     "        )\n",
     "    except Exception as e:\n",
     "        print(e)"
@@ -477,12 +485,17 @@
    ],
    "source": [
     "from matplotlib import pyplot as plt\n",
-    "chain.metrics.to_pandas()['score'].plot(label=\"default learning policy\")\n",
-    "random_chain.metrics.to_pandas()['score'].plot(label=\"random selection policy\")\n",
+    "\n",
+    "chain.metrics.to_pandas()[\"score\"].plot(label=\"default learning policy\")\n",
+    "random_chain.metrics.to_pandas()[\"score\"].plot(label=\"random selection policy\")\n",
     "plt.legend()\n",
     "\n",
-    "print(f\"The final average score for the default policy, calculated over a rolling window, is: {chain.metrics.to_pandas()['score'].iloc[-1]}\")\n",
-    "print(f\"The final average score for the random policy, calculated over a rolling window, is: {random_chain.metrics.to_pandas()['score'].iloc[-1]}\")"
+    "print(\n",
+    "    f\"The final average score for the default policy, calculated over a rolling window, is: {chain.metrics.to_pandas()['score'].iloc[-1]}\"\n",
+    ")\n",
+    "print(\n",
+    "    f\"The final average score for the random policy, calculated over a rolling window, is: {random_chain.metrics.to_pandas()['score'].iloc[-1]}\"\n",
+    ")"
    ]
   },
   {
@@ -803,10 +816,10 @@
     ")\n",
     "\n",
     "chain.run(\n",
-    "    meal = rl_chain.ToSelectFrom(meals),\n",
-    "    user = rl_chain.BasedOn(\"Tom\"),\n",
-    "    preference = rl_chain.BasedOn([\"Vegetarian\", \"regular dairy is ok\"]),\n",
-    "    text_to_personalize = \"This is the weeks specialty dish, our master chefs believe you will love it!\",\n",
+    "    meal=rl_chain.ToSelectFrom(meals),\n",
+    "    user=rl_chain.BasedOn(\"Tom\"),\n",
+    "    preference=rl_chain.BasedOn([\"Vegetarian\", \"regular dairy is ok\"]),\n",
+    "    text_to_personalize=\"This is the weeks specialty dish, our master chefs believe you will love it!\",\n",
     ")"
    ]
   }

cookbook/myscale_vector_sql.ipynb

@@ -27,11 +27,12 @@
    "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.llms import OpenAI\n",
+    "from langchain.utilities import SQLDatabase\n",
+    "from 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",
@@ -39,7 +40,7 @@
     "\n",
     "from sqlalchemy import create_engine\n",
     "\n",
-    "MYSCALE_HOST = \"msc-1decbcc9.us-east-1.aws.staging.myscale.cloud\"\n",
+    "MYSCALE_HOST = \"msc-4a9e710a.us-east-1.aws.staging.myscale.cloud\"\n",
     "MYSCALE_PORT = 443\n",
     "MYSCALE_USER = \"chatdata\"\n",
     "MYSCALE_PASSWORD = \"myscale_rocks\"\n",
@@ -76,7 +77,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "\n",
     "from langchain.llms import OpenAI\n",
     "from langchain.callbacks import StdOutCallbackHandler\n",
     "\n",
@@ -124,8 +124,9 @@
     "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.retrievers.vector_sql_database import (\n",
+    "    VectorSQLDatabaseChainRetriever,\n",
+    ")\n",
     "from langchain_experimental.sql.prompt import MYSCALE_PROMPT\n",
     "from langchain_experimental.sql.vector_sql import VectorSQLRetrieveAllOutputParser\n",
     "\n",
@@ -144,7 +145,9 @@
     ")\n",
     "\n",
     "# You need all those keys to get docs\n",
-    "retriever = VectorSQLDatabaseChainRetriever(sql_db_chain=chain, page_content_key=\"abstract\")\n",
+    "retriever = VectorSQLDatabaseChainRetriever(\n",
+    "    sql_db_chain=chain, page_content_key=\"abstract\"\n",
+    ")\n",
     "\n",
     "document_with_metadata_prompt = PromptTemplate(\n",
     "    input_variables=[\"page_content\", \"id\", \"title\", \"authors\", \"pubdate\", \"categories\"],\n",
@@ -162,8 +165,10 @@
     "    },\n",
     "    return_source_documents=True,\n",
     ")\n",
-    "ans = chain(\"Please give me 10 papers to ask what is PageRank?\",\n",
-    "            callbacks=[StdOutCallbackHandler()])\n",
+    "ans = chain(\n",
+    "    \"Please give me 10 papers to ask what is PageRank?\",\n",
+    "    callbacks=[StdOutCallbackHandler()],\n",
+    ")\n",
     "print(ans[\"answer\"])"
    ]
   },

cookbook/openai_v1_cookbook.ipynb

@@ -0,0 +1,506 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "f970f757-ec76-4bf0-90cd-a2fb68b945e3",
+   "metadata": {},
+   "source": [
+    "# Exploring OpenAI V1 functionality\n",
+    "\n",
+    "On 11.06.23 OpenAI released a number of new features, and along with it bumped their Python SDK to 1.0.0. This notebook shows off the new features and how to use them with LangChain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ee897729-263a-4073-898f-bb4cf01ed829",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# need openai>=1.1.0, langchain>=0.0.333, langchain-experimental>=0.0.39\n",
+    "!pip install -U openai langchain langchain-experimental"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "c3e067ce-7a43-47a7-bc89-41f1de4cf136",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.schema.messages import HumanMessage, SystemMessage"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fa7e7e95-90a1-4f73-98fe-10c4b4e0951b",
+   "metadata": {},
+   "source": [
+    "## [Vision](https://platform.openai.com/docs/guides/vision)\n",
+    "\n",
+    "OpenAI released multi-modal models, which can take a sequence of text and images as input."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "1c8c3965-d3c9-4186-b5f3-5e67855ef916",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='The image appears to be a diagram representing the architecture or components of a software system or framework related to language processing, possibly named LangChain or associated with a project or product called LangChain, based on the prominent appearance of that term. The diagram is organized into several layers or aspects, each containing various elements or modules:\\n\\n1. **Protocol**: This may be the foundational layer, which includes \"LCEL\" and terms like parallelization, fallbacks, tracing, batching, streaming, async, and composition. These seem related to communication and execution protocols for the system.\\n\\n2. **Integrations Components**: This layer includes \"Model I/O\" with elements such as the model, output parser, prompt, and example selector. It also has a \"Retrieval\" section with a document loader, retriever, embedding model, vector store, and text splitter. Lastly, there\\'s an \"Agent Tooling\" section. These components likely deal with the interaction with external data, models, and tools.\\n\\n3. **Application**: The application layer features \"LangChain\" with chains, agents, agent executors, and common application logic. This suggests that the system uses a modular approach with chains and agents to process language tasks.\\n\\n4. **Deployment**: This contains \"Lang')"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chat = ChatOpenAI(model=\"gpt-4-vision-preview\", max_tokens=256)\n",
+    "chat.invoke(\n",
+    "    [\n",
+    "        HumanMessage(\n",
+    "            content=[\n",
+    "                {\"type\": \"text\", \"text\": \"What is this image showing\"},\n",
+    "                {\n",
+    "                    \"type\": \"image_url\",\n",
+    "                    \"image_url\": {\n",
+    "                        \"url\": \"https://raw.githubusercontent.com/langchain-ai/langchain/master/docs/static/img/langchain_stack.png\",\n",
+    "                        \"detail\": \"auto\",\n",
+    "                    },\n",
+    "                },\n",
+    "            ]\n",
+    "        )\n",
+    "    ]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "210f8248-fcf3-4052-a4a3-0684e08f8785",
+   "metadata": {},
+   "source": [
+    "## [OpenAI assistants](https://platform.openai.com/docs/assistants/overview)\n",
+    "\n",
+    "> The Assistants API allows you to build AI assistants within your own applications. An Assistant has instructions and can leverage models, tools, and knowledge to respond to user queries. The Assistants API currently supports three types of tools: Code Interpreter, Retrieval, and Function calling\n",
+    "\n",
+    "\n",
+    "You can interact with OpenAI Assistants using OpenAI tools or custom tools. When using exclusively OpenAI tools, you can just invoke the assistant directly and get final answers. When using custom tools, you can run the assistant and tool execution loop using the built-in AgentExecutor or easily write your own executor.\n",
+    "\n",
+    "Below we show the different ways to interact with Assistants. As a simple example, let's build a math tutor that can write and run code."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "318da28d-4cec-42ab-ae3e-76d95bb34fa5",
+   "metadata": {},
+   "source": [
+    "### Using only OpenAI tools"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "a9064bbe-d9f7-4a29-a7b3-73933b3197e7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_experimental.openai_assistant import OpenAIAssistantRunnable"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "7a20a008-49ac-46d2-aa26-b270118af5ea",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[ThreadMessage(id='msg_g9OJv0rpPgnc3mHmocFv7OVd', assistant_id='asst_hTwZeNMMphxzSOqJ01uBMsJI', content=[MessageContentText(text=Text(annotations=[], value='The result of \\\\(10 - 4^{2.7}\\\\) is approximately \\\\(-32.224\\\\).'), type='text')], created_at=1699460600, file_ids=[], metadata={}, object='thread.message', role='assistant', run_id='run_nBIT7SiAwtUfSCTrQNSPLOfe', thread_id='thread_14n4GgXwxgNL0s30WJW5F6p0')]"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "interpreter_assistant = OpenAIAssistantRunnable.create_assistant(\n",
+    "    name=\"langchain assistant\",\n",
+    "    instructions=\"You are a personal math tutor. Write and run code to answer math questions.\",\n",
+    "    tools=[{\"type\": \"code_interpreter\"}],\n",
+    "    model=\"gpt-4-1106-preview\",\n",
+    ")\n",
+    "output = interpreter_assistant.invoke({\"content\": \"What's 10 - 4 raised to the 2.7\"})\n",
+    "output"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a8ddd181-ac63-4ab6-a40d-a236120379c1",
+   "metadata": {},
+   "source": [
+    "### As a LangChain agent with arbitrary tools\n",
+    "\n",
+    "Now let's recreate this functionality using our own tools. For this example we'll use the [E2B sandbox runtime tool](https://e2b.dev/docs?ref=landing-page-get-started)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ee4cc355-f2d6-4c51-bcf7-f502868357d3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install e2b duckduckgo-search"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "48681ac7-b267-48d4-972c-8a7df8393a21",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.tools import E2BDataAnalysisTool, DuckDuckGoSearchRun\n",
+    "\n",
+    "tools = [E2BDataAnalysisTool(api_key=\"...\"), DuckDuckGoSearchRun()]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "1c01dd79-dd3e-4509-a2e2-009a7f99f16a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agent = OpenAIAssistantRunnable.create_assistant(\n",
+    "    name=\"langchain assistant e2b tool\",\n",
+    "    instructions=\"You are a personal math tutor. Write and run code to answer math questions. You can also search the internet.\",\n",
+    "    tools=tools,\n",
+    "    model=\"gpt-4-1106-preview\",\n",
+    "    as_agent=True,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1ac71d8b-4b4b-4f98-b826-6b3c57a34166",
+   "metadata": {},
+   "source": [
+    "#### Using AgentExecutor"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "1f137f94-801f-4766-9ff5-2de9df5e8079",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'content': \"What's the weather in SF today divided by 2.7\",\n",
+       " 'output': \"The weather in San Francisco today is reported to have temperatures as high as 66 °F. To get the temperature divided by 2.7, we will calculate that:\\n\\n66 °F / 2.7 = 24.44 °F\\n\\nSo, when the high temperature of 66 °F is divided by 2.7, the result is approximately 24.44 °F. Please note that this doesn't have a meteorological meaning; it's purely a mathematical operation based on the given temperature.\"}"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.agents import AgentExecutor\n",
+    "\n",
+    "agent_executor = AgentExecutor(agent=agent, tools=tools)\n",
+    "agent_executor.invoke({\"content\": \"What's the weather in SF today divided by 2.7\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2d0a0b1d-c1b3-4b50-9dce-1189b51a6206",
+   "metadata": {},
+   "source": [
+    "#### Custom execution"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "c0475fa7-b6c1-4331-b8e2-55407466c724",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agent = OpenAIAssistantRunnable.create_assistant(\n",
+    "    name=\"langchain assistant e2b tool\",\n",
+    "    instructions=\"You are a personal math tutor. Write and run code to answer math questions.\",\n",
+    "    tools=tools,\n",
+    "    model=\"gpt-4-1106-preview\",\n",
+    "    as_agent=True,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "b76cb669-6aba-4827-868f-00aa960026f2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.schema.agent import AgentFinish\n",
+    "\n",
+    "\n",
+    "def execute_agent(agent, tools, input):\n",
+    "    tool_map = {tool.name: tool for tool in tools}\n",
+    "    response = agent.invoke(input)\n",
+    "    while not isinstance(response, AgentFinish):\n",
+    "        tool_outputs = []\n",
+    "        for action in response:\n",
+    "            tool_output = tool_map[action.tool].invoke(action.tool_input)\n",
+    "            print(action.tool, action.tool_input, tool_output, end=\"\\n\\n\")\n",
+    "            tool_outputs.append(\n",
+    "                {\"output\": tool_output, \"tool_call_id\": action.tool_call_id}\n",
+    "            )\n",
+    "        response = agent.invoke(\n",
+    "            {\n",
+    "                \"tool_outputs\": tool_outputs,\n",
+    "                \"run_id\": action.run_id,\n",
+    "                \"thread_id\": action.thread_id,\n",
+    "            }\n",
+    "        )\n",
+    "\n",
+    "    return response"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "7946116a-b82f-492e-835e-ca958a8949a5",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "e2b_data_analysis {'python_code': 'print(10 - 4 ** 2.7)'} {\"stdout\": \"-32.22425314473263\", \"stderr\": \"\", \"artifacts\": []}\n",
+      "\n",
+      "\\( 10 - 4^{2.7} \\) is approximately \\(-32.22425314473263\\).\n"
+     ]
+    }
+   ],
+   "source": [
+    "response = execute_agent(agent, tools, {\"content\": \"What's 10 - 4 raised to the 2.7\"})\n",
+    "print(response.return_values[\"output\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "f2744a56-9f4f-4899-827a-fa55821c318c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "e2b_data_analysis {'python_code': 'result = 10 - 4 ** 2.7\\nprint(result + 17.241)'} {\"stdout\": \"-14.983253144732629\", \"stderr\": \"\", \"artifacts\": []}\n",
+      "\n",
+      "When you add \\( 17.241 \\) to \\( 10 - 4^{2.7} \\), the result is approximately \\( -14.98325314473263 \\).\n"
+     ]
+    }
+   ],
+   "source": [
+    "next_response = execute_agent(\n",
+    "    agent, tools, {\"content\": \"now add 17.241\", \"thread_id\": response.thread_id}\n",
+    ")\n",
+    "print(next_response.return_values[\"output\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "71c34763-d1e7-4b9a-a9d7-3e4cc0dfc2c4",
+   "metadata": {},
+   "source": [
+    "## [JSON mode](https://platform.openai.com/docs/guides/text-generation/json-mode)\n",
+    "\n",
+    "Constrain the model to only generate valid JSON. Note that you must include a system message with instructions to use JSON for this mode to work.\n",
+    "\n",
+    "Only works with certain models. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "db6072c4-f3f3-415d-872b-71ea9f3c02bb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chat = ChatOpenAI(model=\"gpt-3.5-turbo-1106\").bind(\n",
+    "    response_format={\"type\": \"json_object\"}\n",
+    ")\n",
+    "\n",
+    "output = chat.invoke(\n",
+    "    [\n",
+    "        SystemMessage(\n",
+    "            content=\"Extract the 'name' and 'origin' of any companies mentioned in the following statement. Return a JSON list.\"\n",
+    "        ),\n",
+    "        HumanMessage(\n",
+    "            content=\"Google was founded in the USA, while Deepmind was founded in the UK\"\n",
+    "        ),\n",
+    "    ]\n",
+    ")\n",
+    "print(output.content)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "08e00ccf-b991-4249-846b-9500a0ccbfa0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "\n",
+    "json.loads(output.content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "aa9a94d9-4319-4ab7-a979-c475ce6b5f50",
+   "metadata": {},
+   "source": [
+    "## [System fingerprint](https://platform.openai.com/docs/guides/text-generation/reproducible-outputs)\n",
+    "\n",
+    "OpenAI sometimes changes model configurations in a way that impacts outputs. Whenever this happens, the system_fingerprint associated with a generation will change."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1281883c-bf8f-4665-89cd-4f33ccde69ab",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chat = ChatOpenAI(model=\"gpt-3.5-turbo-1106\")\n",
+    "output = chat.generate(\n",
+    "    [\n",
+    "        [\n",
+    "            SystemMessage(\n",
+    "                content=\"Extract the 'name' and 'origin' of any companies mentioned in the following statement. Return a JSON list.\"\n",
+    "            ),\n",
+    "            HumanMessage(\n",
+    "                content=\"Google was founded in the USA, while Deepmind was founded in the UK\"\n",
+    "            ),\n",
+    "        ]\n",
+    "    ]\n",
+    ")\n",
+    "print(output.llm_output)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "aa6565be-985d-4127-848e-c3bca9d7b434",
+   "metadata": {},
+   "source": [
+    "## Breaking changes to Azure classes\n",
+    "\n",
+    "OpenAI V1 rewrote their clients and separated Azure and OpenAI clients. This has led to some changes in LangChain interfaces when using OpenAI V1.\n",
+    "\n",
+    "BREAKING CHANGES:\n",
+    "- To use Azure embeddings with OpenAI V1, you'll need to use the new `AzureOpenAIEmbeddings` instead of the existing `OpenAIEmbeddings`. `OpenAIEmbeddings` continue to work when using Azure with `openai<1`.\n",
+    "```python\n",
+    "from langchain.embeddings import AzureOpenAIEmbeddings\n",
+    "```\n",
+    "\n",
+    "\n",
+    "RECOMMENDED CHANGES:\n",
+    "- When using AzureChatOpenAI, if passing in an Azure endpoint (eg https://example-resource.azure.openai.com/) this should be specified via the `azure_endpoint` parameter or the `AZURE_OPENAI_ENDPOINT`. We're maintaining backwards compatibility for now with specifying this via `openai_api_base`/`base_url` or env var `OPENAI_API_BASE` but this shouldn't be relied upon.\n",
+    "- When using Azure chat or embedding models, pass in API keys either via `openai_api_key` parameter or `AZURE_OPENAI_API_KEY` parameter. We're maintaining backwards compatibility for now with specifying this via `OPENAI_API_KEY` but this shouldn't be relied upon."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "49944887-3972-497e-8da2-6d32d44345a9",
+   "metadata": {},
+   "source": [
+    "## Tools\n",
+    "\n",
+    "Use tools for parallel function calling."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "916292d8-0f89-40a6-af1c-5a1122327de8",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[GetCurrentWeather(location='New York, NY', unit='fahrenheit'),\n",
+       " GetCurrentWeather(location='Los Angeles, CA', unit='fahrenheit'),\n",
+       " GetCurrentWeather(location='San Francisco, CA', unit='fahrenheit')]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from typing import Literal\n",
+    "\n",
+    "from langchain.output_parsers.openai_tools import PydanticToolsParser\n",
+    "from langchain.utils.openai_functions import convert_pydantic_to_openai_tool\n",
+    "from langchain.prompts import ChatPromptTemplate\n",
+    "from langchain.pydantic_v1 import BaseModel, Field\n",
+    "\n",
+    "\n",
+    "class GetCurrentWeather(BaseModel):\n",
+    "    \"\"\"Get the current weather in a location.\"\"\"\n",
+    "\n",
+    "    location: str = Field(description=\"The city and state, e.g. San Francisco, CA\")\n",
+    "    unit: Literal[\"celsius\", \"fahrenheit\"] = Field(\n",
+    "        default=\"fahrenheit\", description=\"The temperature unit, default to fahrenheit\"\n",
+    "    )\n",
+    "\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [(\"system\", \"You are a helpful assistant\"), (\"user\", \"{input}\")]\n",
+    ")\n",
+    "model = ChatOpenAI(model=\"gpt-3.5-turbo-1106\").bind(\n",
+    "    tools=[convert_pydantic_to_openai_tool(GetCurrentWeather)]\n",
+    ")\n",
+    "chain = prompt | model | PydanticToolsParser(tools=[GetCurrentWeather])\n",
+    "\n",
+    "chain.invoke({\"input\": \"what's the weather in NYC, LA, and SF\"})"
+   ]
+  }
+ ],
+ "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/plan_and_execute_agent.ipynb

@@ -34,7 +34,11 @@
     "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"
+    "from langchain_experimental.plan_and_execute import (\n",
+    "    PlanAndExecute,\n",
+    "    load_agent_executor,\n",
+    "    load_chat_planner,\n",
+    ")"
    ]
   },
   {
@@ -56,16 +60,16 @@
     "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",
+    "    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",
     "]"
    ]
   },
@@ -216,7 +220,9 @@
     }
    ],
    "source": [
-    "agent.run(\"Who is the current prime minister of the UK? What is their current age raised to the 0.43 power?\")"
+    "agent.run(\n",
+    "    \"Who is the current prime minister of the UK? What is their current age raised to the 0.43 power?\"\n",
+    ")"
    ]
   },
   {

cookbook/press_releases.ipynb

@@ -55,6 +55,7 @@
    "source": [
     "# Setup API keys for Kay and OpenAI\n",
     "from getpass import getpass\n",
+    "\n",
     "KAY_API_KEY = getpass()\n",
     "OPENAI_API_KEY = getpass()"
    ]
@@ -67,6 +68,7 @@
    "outputs": [],
    "source": [
     "import os\n",
+    "\n",
     "os.environ[\"KAY_API_KEY\"] = KAY_API_KEY\n",
     "os.environ[\"OPENAI_API_KEY\"] = OPENAI_API_KEY"
    ]
@@ -83,7 +85,9 @@
     "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",
+    "retriever = KayAiRetriever.create(\n",
+    "    dataset_id=\"company\", data_types=[\"PressRelease\"], num_contexts=6\n",
+    ")\n",
     "qa = ConversationalRetrievalChain.from_llm(model, retriever=retriever)"
    ]
   },
@@ -116,7 +120,7 @@
     "# 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",
+    "    # \"What are some recent challenges faced by the renewable energy sector?\",\n",
     "]\n",
     "chat_history = []\n",
     "\n",

cookbook/rag_fusion.ipynb

@@ -0,0 +1,272 @@
+{
+ "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(\n",
+    "    list(all_documents.values()), OpenAIEmbeddings(), index_name=\"rag-fusion\"\n",
+    ")"
+   ]
+  },
+  {
+   "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 = (\n",
+    "    prompt | ChatOpenAI(temperature=0) | StrOutputParser() | (lambda x: x.split(\"\\n\"))\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",
+    "\n",
+    "\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 = [\n",
+    "        (loads(doc), score)\n",
+    "        for doc, score in sorted(fused_scores.items(), key=lambda x: x[1], reverse=True)\n",
+    "    ]\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/retrieval_in_sql.ipynb

@@ -0,0 +1,688 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Incoporating semantic similarity in tabular databases\n",
+    "\n",
+    "In this notebook we will cover how to run semantic search over a specific table column within a single SQL query, combining tabular query with RAG.\n",
+    "\n",
+    "\n",
+    "### Overall workflow\n",
+    "\n",
+    "1. Generating embeddings for a specific column\n",
+    "2. Storing the embeddings in a new column (if column has low cardinality, it's better to use another table containing unique values and their embeddings)\n",
+    "3. Querying using standard SQL queries with [PGVector](https://github.com/pgvector/pgvector) extension which allows using L2 distance (`<->`), Cosine distance (`<=>` or cosine similarity using `1 - <=>`) and Inner product (`<#>`)\n",
+    "4. Running standard SQL query\n",
+    "\n",
+    "### Requirements\n",
+    "\n",
+    "We will need a PostgreSQL database with [pgvector](https://github.com/pgvector/pgvector) extension enabled. For this example, we will use a `Chinook` database using a local PostgreSQL server."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import getpass\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = os.environ.get(\"OPENAI_API_KEY\") or getpass.getpass(\n",
+    "    \"OpenAI API Key:\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.sql_database import SQLDatabase\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "\n",
+    "CONNECTION_STRING = \"postgresql+psycopg2://postgres:test@localhost:5432/vectordb\"  # Replace with your own\n",
+    "db = SQLDatabase.from_uri(CONNECTION_STRING)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Embedding the song titles"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "For this example, we will run queries based on semantic meaning of song titles. In order to do this, let's start by adding a new column in the table for storing the embeddings:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# db.run('ALTER TABLE \"Track\" ADD COLUMN \"embeddings\" vector;')"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Let's generate the embedding for each *track title* and store it as a new column in our \"Track\" table"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings import OpenAIEmbeddings\n",
+    "\n",
+    "embeddings_model = OpenAIEmbeddings()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "3503"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tracks = db.run('SELECT \"Name\" FROM \"Track\"')\n",
+    "song_titles = [s[0] for s in eval(tracks)]\n",
+    "title_embeddings = embeddings_model.embed_documents(song_titles)\n",
+    "len(title_embeddings)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now let's insert the embeddings in the into the new column from our table"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from tqdm import tqdm\n",
+    "\n",
+    "for i in tqdm(range(len(title_embeddings))):\n",
+    "    title = titles[i].replace(\"'\", \"''\")\n",
+    "    embedding = title_embeddings[i]\n",
+    "    sql_command = (\n",
+    "        f'UPDATE \"Track\" SET \"embeddings\" = ARRAY{embedding} WHERE \"Name\" ='\n",
+    "        + f\"'{title}'\"\n",
+    "    )\n",
+    "    db.run(sql_command)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We can test the semantic search running the following query:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'[(\"Tomorrow\\'s Dream\",), (\\'Remember Tomorrow\\',), (\\'Remember Tomorrow\\',), (\\'The Best Is Yet To Come\\',), (\"Thinking \\'Bout Tomorrow\",)]'"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "embeded_title = embeddings_model.embed_query(\"hope about the future\")\n",
+    "query = (\n",
+    "    'SELECT \"Track\".\"Name\" FROM \"Track\" WHERE \"Track\".\"embeddings\" IS NOT NULL ORDER BY \"embeddings\" <-> '\n",
+    "    + f\"'{embeded_title}' LIMIT 5\"\n",
+    ")\n",
+    "db.run(query)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Creating the SQL Chain"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Let's start by defining useful functions to get info from database and running the query:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_schema(_):\n",
+    "    return db.get_table_info()\n",
+    "\n",
+    "\n",
+    "def run_query(query):\n",
+    "    return db.run(query)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now let's build the **prompt** we will use. This prompt is an extension from [text-to-postgres-sql](https://smith.langchain.com/hub/jacob/text-to-postgres-sql?organizationId=f9b614b8-5c3a-4e7c-afbc-6d7ad4fd8892) prompt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.prompts import ChatPromptTemplate\n",
+    "\n",
+    "template = \"\"\"You are a Postgres expert. Given an input question, first create a syntactically correct Postgres query to run, then look at the results of the query and return the answer to the input question.\n",
+    "Unless the user specifies in the question a specific number of examples to obtain, query for at most 5 results using the LIMIT clause as per Postgres. You can order the results to return the most informative data in the database.\n",
+    "Never query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in double quotes (\") to denote them as delimited identifiers.\n",
+    "Pay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.\n",
+    "Pay attention to use date('now') function to get the current date, if the question involves \"today\".\n",
+    "\n",
+    "You can use an extra extension which allows you to run semantic similarity using <-> operator on tables containing columns named \"embeddings\".\n",
+    "<-> operator can ONLY be used on embeddings columns.\n",
+    "The embeddings value for a given row typically represents the semantic meaning of that row.\n",
+    "The vector represents an embedding representation of the question, given below. \n",
+    "Do NOT fill in the vector values directly, but rather specify a `[search_word]` placeholder, which should contain the word that would be embedded for filtering.\n",
+    "For example, if the user asks for songs about 'the feeling of loneliness' the query could be:\n",
+    "'SELECT \"[whatever_table_name]\".\"SongName\" FROM \"[whatever_table_name]\" ORDER BY \"embeddings\" <-> '[loneliness]' LIMIT 5'\n",
+    "\n",
+    "Use the following format:\n",
+    "\n",
+    "Question: <Question here>\n",
+    "SQLQuery: <SQL Query to run>\n",
+    "SQLResult: <Result of the SQLQuery>\n",
+    "Answer: <Final answer here>\n",
+    "\n",
+    "Only use the following tables:\n",
+    "\n",
+    "{schema}\n",
+    "\"\"\"\n",
+    "\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [(\"system\", template), (\"human\", \"{question}\")]\n",
+    ")"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "And we can create the chain using **[LangChain Expression Language](https://python.langchain.com/docs/expression_language/)**:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "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",
+    "db = SQLDatabase.from_uri(\n",
+    "    CONNECTION_STRING\n",
+    ")  # We reconnect to db so the new columns are loaded as well.\n",
+    "llm = ChatOpenAI(model_name=\"gpt-4\", temperature=0)\n",
+    "\n",
+    "sql_query_chain = (\n",
+    "    RunnablePassthrough.assign(schema=get_schema)\n",
+    "    | prompt\n",
+    "    | llm.bind(stop=[\"\\nSQLResult:\"])\n",
+    "    | StrOutputParser()\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'SQLQuery: SELECT \"Track\".\"Name\" FROM \"Track\" JOIN \"Genre\" ON \"Track\".\"GenreId\" = \"Genre\".\"GenreId\" WHERE \"Genre\".\"Name\" = \\'Rock\\' ORDER BY \"Track\".\"embeddings\" <-> \\'[dispair]\\' LIMIT 5'"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sql_query_chain.invoke(\n",
+    "    {\n",
+    "        \"question\": \"Which are the 5 rock songs with titles about deep feeling of dispair?\"\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This chain simply generates the query. Now we will create the full chain that also handles the execution and the final result for the user:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import re\n",
+    "from langchain.schema.runnable import RunnableLambda\n",
+    "\n",
+    "\n",
+    "def replace_brackets(match):\n",
+    "    words_inside_brackets = match.group(1).split(\", \")\n",
+    "    embedded_words = [\n",
+    "        str(embeddings_model.embed_query(word)) for word in words_inside_brackets\n",
+    "    ]\n",
+    "    return \"', '\".join(embedded_words)\n",
+    "\n",
+    "\n",
+    "def get_query(query):\n",
+    "    sql_query = re.sub(r\"\\[([\\w\\s,]+)\\]\", replace_brackets, query)\n",
+    "    return sql_query\n",
+    "\n",
+    "\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",
+    "\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [(\"system\", template), (\"human\", \"{question}\")]\n",
+    ")\n",
+    "\n",
+    "full_chain = (\n",
+    "    RunnablePassthrough.assign(query=sql_query_chain)\n",
+    "    | RunnablePassthrough.assign(\n",
+    "        schema=get_schema,\n",
+    "        response=RunnableLambda(lambda x: db.run(get_query(x[\"query\"]))),\n",
+    "    )\n",
+    "    | prompt\n",
+    "    | llm\n",
+    ")"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Using the Chain"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Example 1: Filtering a column based on semantic meaning"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Let's say we want to retrieve songs that express `deep feeling of dispair`, but filtering based on genre:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"The 5 rock songs with titles that convey a deep feeling of despair are 'Sea Of Sorrow', 'Surrender', 'Indifference', 'Hard Luck Woman', and 'Desire'.\")"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "full_chain.invoke(\n",
+    "    {\n",
+    "        \"question\": \"Which are the 5 rock songs with titles about deep feeling of dispair?\"\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "What is substantially different in implementing this method is that we have combined:\n",
+    "- Semantic search (songs that have titles with some semantic meaning)\n",
+    "- Traditional tabular querying (running JOIN statements to filter track based on genre)\n",
+    "\n",
+    "This is something we _could_ potentially achieve using metadata filtering, but it's more complex to do so (we would need to use a vector database containing the embeddings, and use metadata filtering based on genre).\n",
+    "\n",
+    "However, for other use cases metadata filtering **wouldn't be enough**."
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Example 2: Combining filters"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"The three albums which have the most amount of songs in the top 150 saddest songs are 'International Superhits' with 5 songs, 'Ten' with 4 songs, and 'Album Of The Year' with 3 songs.\")"
+      ]
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "full_chain.invoke(\n",
+    "    {\n",
+    "        \"question\": \"I want to know the 3 albums which have the most amount of songs in the top 150 saddest songs\"\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "So we have result for 3 albums with most amount of songs in top 150 saddest ones. This **wouldn't** be possible using only standard metadata filtering. Without this _hybdrid query_, we would need some postprocessing to get the result.\n",
+    "\n",
+    "Another similar exmaple:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"The 6 albums with the shortest titles that contain songs which are in the 20 saddest song list are 'Ten', 'Core', 'Big Ones', 'One By One', 'Black Album', and 'Miles Ahead'.\")"
+      ]
+     },
+     "execution_count": 30,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "full_chain.invoke(\n",
+    "    {\n",
+    "        \"question\": \"I need the 6 albums with shortest title, as long as they contain songs which are in the 20 saddest song list.\"\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Let's see what the query looks like to double check:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "WITH \"SadSongs\" AS (\n",
+      "    SELECT \"TrackId\" FROM \"Track\" \n",
+      "    ORDER BY \"embeddings\" <-> '[sad]' LIMIT 20\n",
+      "),\n",
+      "\"SadAlbums\" AS (\n",
+      "    SELECT DISTINCT \"AlbumId\" FROM \"Track\" \n",
+      "    WHERE \"TrackId\" IN (SELECT \"TrackId\" FROM \"SadSongs\")\n",
+      ")\n",
+      "SELECT \"Album\".\"Title\" FROM \"Album\" \n",
+      "WHERE \"AlbumId\" IN (SELECT \"AlbumId\" FROM \"SadAlbums\") \n",
+      "ORDER BY \"title_len\" ASC \n",
+      "LIMIT 6\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\n",
+    "    sql_query_chain.invoke(\n",
+    "        {\n",
+    "            \"question\": \"I need the 6 albums with shortest title, as long as they contain songs which are in the 20 saddest song list.\"\n",
+    "        }\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Example 3: Combining two separate semantic searches\n",
+    "\n",
+    "One interesting aspect of this approach which is **substantially different from using standar RAG** is that we can even **combine** two semantic search filters:\n",
+    "- _Get 5 saddest songs..._\n",
+    "- _**...obtained from albums with \"lovely\" titles**_\n",
+    "\n",
+    "This could generalize to **any kind of combined RAG** (paragraphs discussing _X_ topic belonging from books about _Y_, replies to a tweet about _ABC_ topic that express _XYZ_ feeling)\n",
+    "\n",
+    "We will combine semantic search on songs and album titles, so we need to do the same for `Album` table:\n",
+    "1. Generate the embeddings\n",
+    "2. Add them to the table as a new column (which we need to add in the table)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 60,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# db.run('ALTER TABLE \"Album\" ADD COLUMN \"embeddings\" vector;')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████| 347/347 [00:01<00:00, 179.64it/s]\n"
+     ]
+    }
+   ],
+   "source": [
+    "albums = db.run('SELECT \"Title\" FROM \"Album\"')\n",
+    "album_titles = [title[0] for title in eval(albums)]\n",
+    "album_title_embeddings = embeddings_model.embed_documents(album_titles)\n",
+    "for i in tqdm(range(len(album_title_embeddings))):\n",
+    "    album_title = album_titles[i].replace(\"'\", \"''\")\n",
+    "    album_embedding = album_title_embeddings[i]\n",
+    "    sql_command = (\n",
+    "        f'UPDATE \"Album\" SET \"embeddings\" = ARRAY{album_embedding} WHERE \"Title\" ='\n",
+    "        + f\"'{album_title}'\"\n",
+    "    )\n",
+    "    db.run(sql_command)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"[('Realize',), ('Morning Dance',), ('Into The Light',), ('New Adventures In Hi-Fi',), ('Miles Ahead',)]\""
+      ]
+     },
+     "execution_count": 45,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "embeded_title = embeddings_model.embed_query(\"hope about the future\")\n",
+    "query = (\n",
+    "    'SELECT \"Album\".\"Title\" FROM \"Album\" WHERE \"Album\".\"embeddings\" IS NOT NULL ORDER BY \"embeddings\" <-> '\n",
+    "    + f\"'{embeded_title}' LIMIT 5\"\n",
+    ")\n",
+    "db.run(query)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now we can combine both filters:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "db = SQLDatabase.from_uri(\n",
+    "    CONNECTION_STRING\n",
+    ")  # We reconnect to dbso the new columns are loaded as well."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='The songs about breakouts obtained from the top 5 albums about love are \\'Royal Orleans\\', \"Nobody\\'s Fault But Mine\", \\'Achilles Last Stand\\', \\'For Your Life\\', and \\'Hots On For Nowhere\\'.')"
+      ]
+     },
+     "execution_count": 49,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "full_chain.invoke(\n",
+    "    {\n",
+    "        \"question\": \"I want to know songs about breakouts obtained from top 5 albums about love\"\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This is something **different** that **couldn't be achieved** using standard metadata filtering over a vectordb."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.18"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

cookbook/rewrite.ipynb

@@ -0,0 +1,353 @@
+{
+ "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",
+    "\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",
+    "    }\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/selecting_llms_based_on_context_length.ipynb

@@ -0,0 +1,177 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "e93283d1",
+   "metadata": {},
+   "source": [
+    "# Selecting LLMs based on Context Length\n",
+    "\n",
+    "Different LLMs have different context lengths. As a very immediate an practical example, OpenAI has two versions of GPT-3.5-Turbo: one with 4k context, another with 16k context. This notebook shows how to route between them based on input."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "cc453450",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.prompts import PromptTemplate\n",
+    "from langchain.schema.prompt import PromptValue\n",
+    "from langchain.schema.messages import BaseMessage\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.schema.output_parser import StrOutputParser\n",
+    "from typing import Union, Sequence"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "1cec6a10",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "short_context_model = ChatOpenAI(model=\"gpt-3.5-turbo\")\n",
+    "long_context_model = ChatOpenAI(model=\"gpt-3.5-turbo-16k\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "772da153",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_context_length(prompt: PromptValue):\n",
+    "    messages = prompt.to_messages()\n",
+    "    tokens = short_context_model.get_num_tokens_from_messages(messages)\n",
+    "    return tokens"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "db771e20",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompt = PromptTemplate.from_template(\"Summarize this passage: {context}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "af057e2f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def choose_model(prompt: PromptValue):\n",
+    "    context_len = get_context_length(prompt)\n",
+    "    if context_len < 30:\n",
+    "        print(\"short model\")\n",
+    "        return short_context_model\n",
+    "    else:\n",
+    "        print(\"long model\")\n",
+    "        return long_context_model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "84f3e07d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = prompt | choose_model | StrOutputParser()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "d8b14f8f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "short model\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'The passage mentions that a frog visited a pond.'"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"context\": \"a frog went to a pond\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "70ebd3dd",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "long model\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'The passage describes a frog that moved from one pond to another and perched on a log.'"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke(\n",
+    "    {\"context\": \"a frog went to a pond and sat on a log and went to a different pond\"}\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a7e29fef",
+   "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/self_query_hotel_search.ipynb

@@ -7,9 +7,33 @@
    "source": [
     "# Building hotel room search with self-querying retrieval\n",
     "\n",
+    "In this example we'll walk through how to build and iterate on a hotel room search service that leverages an LLM to generate structured filter queries that can then be passed to a vector store.\n",
+    "\n",
+    "For an introduction to self-querying retrieval [check out the docs](https://python.langchain.com/docs/modules/data_connection/retrievers/self_query)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d621de99-d993-4f4b-b94a-d02b2c7ad4e0",
+   "metadata": {},
+   "source": [
+    "## Imports and data prep\n",
+    "\n",
+    "In this example we use `ChatOpenAI` for the model and `ElasticsearchStore` for the vector store, but these can be swapped out with an LLM/ChatModel and [any VectorStore that support self-querying](https://python.langchain.com/docs/integrations/retrievers/self_query/).\n",
+    "\n",
     "Download data from: https://www.kaggle.com/datasets/keshavramaiah/hotel-recommendation"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8ecd1fbb-bdba-420b-bcc7-5ea8a232ab11",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install langchain lark openai elasticsearch pandas"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 1,
@@ -27,8 +51,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "details = pd.read_csv(\"~/Downloads/archive/Hotel_details.csv\").drop_duplicates(subset=\"hotelid\").set_index(\"hotelid\")\n",
-    "attributes = pd.read_csv(\"~/Downloads/archive/Hotel_Room_attributes.csv\", index_col=\"id\")\n",
+    "details = (\n",
+    "    pd.read_csv(\"~/Downloads/archive/Hotel_details.csv\")\n",
+    "    .drop_duplicates(subset=\"hotelid\")\n",
+    "    .set_index(\"hotelid\")\n",
+    ")\n",
+    "attributes = pd.read_csv(\n",
+    "    \"~/Downloads/archive/Hotel_Room_attributes.csv\", index_col=\"id\"\n",
+    ")\n",
     "price = pd.read_csv(\"~/Downloads/archive/hotels_RoomPrice.csv\", index_col=\"id\")"
    ]
   },
@@ -184,9 +214,20 @@
     }
    ],
    "source": [
-    "latest_price = price.drop_duplicates(subset=\"refid\", keep=\"last\")[[\"hotelcode\", \"roomtype\", \"onsiterate\", \"roomamenities\", \"maxoccupancy\", \"mealinclusiontype\"]]\n",
+    "latest_price = price.drop_duplicates(subset=\"refid\", keep=\"last\")[\n",
+    "    [\n",
+    "        \"hotelcode\",\n",
+    "        \"roomtype\",\n",
+    "        \"onsiterate\",\n",
+    "        \"roomamenities\",\n",
+    "        \"maxoccupancy\",\n",
+    "        \"mealinclusiontype\",\n",
+    "    ]\n",
+    "]\n",
     "latest_price[\"ratedescription\"] = attributes.loc[latest_price.index][\"ratedescription\"]\n",
-    "latest_price = latest_price.join(details[[\"hotelname\", \"city\", \"country\", \"starrating\"]], on=\"hotelcode\")\n",
+    "latest_price = latest_price.join(\n",
+    "    details[[\"hotelname\", \"city\", \"country\", \"starrating\"]], on=\"hotelcode\"\n",
+    ")\n",
     "latest_price = latest_price.rename({\"ratedescription\": \"roomdescription\"}, axis=1)\n",
     "latest_price[\"mealsincluded\"] = ~latest_price[\"mealinclusiontype\"].isnull()\n",
     "latest_price.pop(\"hotelcode\")\n",
@@ -220,7 +261,7 @@
     "res = model.predict(\n",
     "    \"Below is a table with information about hotel rooms. \"\n",
     "    \"Return a JSON list with an entry for each column. Each entry should have \"\n",
-    "    \"{\\\"name\\\": \\\"column name\\\", \\\"description\\\": \\\"column description\\\", \\\"type\\\": \\\"column data type\\\"}\"\n",
+    "    '{\"name\": \"column name\", \"description\": \"column description\", \"type\": \"column data type\"}'\n",
     "    f\"\\n\\n{latest_price.head()}\\n\\nJSON:\\n\"\n",
     ")"
    ]
@@ -314,9 +355,15 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "attribute_info[-2]['description'] += f\". Valid values are {sorted(latest_price['starrating'].value_counts().index.tolist())}\"\n",
-    "attribute_info[3]['description'] += f\". Valid values are {sorted(latest_price['maxoccupancy'].value_counts().index.tolist())}\"\n",
-    "attribute_info[-3]['description'] += f\". Valid values are {sorted(latest_price['country'].value_counts().index.tolist())}\""
+    "attribute_info[-2][\n",
+    "    \"description\"\n",
+    "] += f\". Valid values are {sorted(latest_price['starrating'].value_counts().index.tolist())}\"\n",
+    "attribute_info[3][\n",
+    "    \"description\"\n",
+    "] += f\". Valid values are {sorted(latest_price['maxoccupancy'].value_counts().index.tolist())}\"\n",
+    "attribute_info[-3][\n",
+    "    \"description\"\n",
+    "] += f\". Valid values are {sorted(latest_price['country'].value_counts().index.tolist())}\""
    ]
   },
   {
@@ -384,7 +431,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.chains.query_constructor.base import get_query_constructor_prompt, load_query_constructor_runnable"
+    "from langchain.chains.query_constructor.base import (\n",
+    "    get_query_constructor_prompt,\n",
+    "    load_query_constructor_runnable,\n",
+    ")"
    ]
   },
   {
@@ -568,7 +618,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "chain = load_query_constructor_runnable(ChatOpenAI(model='gpt-3.5-turbo', temperature=0), doc_contents, attribute_info)"
+    "chain = load_query_constructor_runnable(\n",
+    "    ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0), doc_contents, attribute_info\n",
+    ")"
    ]
   },
   {
@@ -610,7 +662,11 @@
     }
    ],
    "source": [
-    "chain.invoke({\"query\": \"Find a 2-person room in Vienna or London, preferably with meals included and AC\"})"
+    "chain.invoke(\n",
+    "    {\n",
+    "        \"query\": \"Find a 2-person room in Vienna or London, preferably with meals included and AC\"\n",
+    "    }\n",
+    ")"
    ]
   },
   {
@@ -632,10 +688,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "attribute_info[-3]['description'] += \". NOTE: Only use the 'eq' operator if a specific country is mentioned. If a region is mentioned, include all relevant countries in filter.\"\n",
+    "attribute_info[-3][\n",
+    "    \"description\"\n",
+    "] += \". NOTE: Only use the 'eq' operator if a specific country is mentioned. If a region is mentioned, include all relevant countries in filter.\"\n",
     "chain = load_query_constructor_runnable(\n",
-    "    ChatOpenAI(model='gpt-3.5-turbo', temperature=0), \n",
-    "    doc_contents, \n",
+    "    ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0),\n",
+    "    doc_contents,\n",
     "    attribute_info,\n",
     ")"
    ]
@@ -680,10 +738,12 @@
    "source": [
     "content_attr = [\"roomtype\", \"roomamenities\", \"roomdescription\", \"hotelname\"]\n",
     "doc_contents = \"A detailed description of a hotel room, including information about the room type and room amenities.\"\n",
-    "filter_attribute_info = tuple(ai for ai in attribute_info if ai[\"name\"] not in content_attr)\n",
+    "filter_attribute_info = tuple(\n",
+    "    ai for ai in attribute_info if ai[\"name\"] not in content_attr\n",
+    ")\n",
     "chain = load_query_constructor_runnable(\n",
-    "    ChatOpenAI(model='gpt-3.5-turbo', temperature=0), \n",
-    "    doc_contents, \n",
+    "    ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0),\n",
+    "    doc_contents,\n",
     "    filter_attribute_info,\n",
     ")"
    ]
@@ -706,7 +766,11 @@
     }
    ],
    "source": [
-    "chain.invoke({\"query\": \"Find a 2-person room in Vienna or London, preferably with meals included and AC\"})"
+    "chain.invoke(\n",
+    "    {\n",
+    "        \"query\": \"Find a 2-person room in Vienna or London, preferably with meals included and AC\"\n",
+    "    }\n",
+    ")"
    ]
   },
   {
@@ -836,14 +900,22 @@
     "examples = [\n",
     "    (\n",
     "        \"I want a hotel in the Balkans with a king sized bed and a hot tub. Budget is $300 a night\",\n",
-    "        {\"query\": \"king-sized bed, hot tub\", \"filter\": 'and(in(\"country\", [\"Bulgaria\", \"Greece\", \"Croatia\", \"Serbia\"]), lte(\"onsiterate\", 300))'}\n",
+    "        {\n",
+    "            \"query\": \"king-sized bed, hot tub\",\n",
+    "            \"filter\": 'and(in(\"country\", [\"Bulgaria\", \"Greece\", \"Croatia\", \"Serbia\"]), lte(\"onsiterate\", 300))',\n",
+    "        },\n",
     "    ),\n",
     "    (\n",
     "        \"A room with breakfast included for 3 people, at a Hilton\",\n",
-    "        {\"query\": \"Hilton\", \"filter\": 'and(eq(\"mealsincluded\", true), gte(\"maxoccupancy\", 3))'}\n",
+    "        {\n",
+    "            \"query\": \"Hilton\",\n",
+    "            \"filter\": 'and(eq(\"mealsincluded\", true), gte(\"maxoccupancy\", 3))',\n",
+    "        },\n",
     "    ),\n",
     "]\n",
-    "prompt = get_query_constructor_prompt(doc_contents, filter_attribute_info, examples=examples)\n",
+    "prompt = get_query_constructor_prompt(\n",
+    "    doc_contents, filter_attribute_info, examples=examples\n",
+    ")\n",
     "print(prompt.format(query=\"{query}\"))"
    ]
   },
@@ -855,10 +927,10 @@
    "outputs": [],
    "source": [
     "chain = load_query_constructor_runnable(\n",
-    "    ChatOpenAI(model='gpt-3.5-turbo', temperature=0), \n",
-    "    doc_contents, \n",
+    "    ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0),\n",
+    "    doc_contents,\n",
     "    filter_attribute_info,\n",
-    "    examples=examples\n",
+    "    examples=examples,\n",
     ")"
    ]
   },
@@ -880,7 +952,11 @@
     }
    ],
    "source": [
-    "chain.invoke({\"query\": \"Find a 2-person room in Vienna or London, preferably with meals included and AC\"})"
+    "chain.invoke(\n",
+    "    {\n",
+    "        \"query\": \"Find a 2-person room in Vienna or London, preferably with meals included and AC\"\n",
+    "    }\n",
+    ")"
    ]
   },
   {
@@ -932,7 +1008,11 @@
     }
    ],
    "source": [
-    "chain.invoke({\"query\": \"I want to stay somewhere highly rated along the coast. I want a room with a patio and a fireplace.\"})"
+    "chain.invoke(\n",
+    "    {\n",
+    "        \"query\": \"I want to stay somewhere highly rated along the coast. I want a room with a patio and a fireplace.\"\n",
+    "    }\n",
+    ")"
    ]
   },
   {
@@ -953,11 +1033,11 @@
    "outputs": [],
    "source": [
     "chain = load_query_constructor_runnable(\n",
-    "    ChatOpenAI(model='gpt-3.5-turbo', temperature=0), \n",
-    "    doc_contents, \n",
+    "    ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0),\n",
+    "    doc_contents,\n",
     "    filter_attribute_info,\n",
     "    examples=examples,\n",
-    "    fix_invalid=True\n",
+    "    fix_invalid=True,\n",
     ")"
    ]
   },
@@ -979,7 +1059,11 @@
     }
    ],
    "source": [
-    "chain.invoke({\"query\": \"I want to stay somewhere highly rated along the coast. I want a room with a patio and a fireplace.\"})"
+    "chain.invoke(\n",
+    "    {\n",
+    "        \"query\": \"I want to stay somewhere highly rated along the coast. I want a room with a patio and a fireplace.\"\n",
+    "    }\n",
+    ")"
    ]
   },
   {
@@ -1032,8 +1116,8 @@
     "#     docs.append(doc)\n",
     "# vecstore = ElasticsearchStore.from_documents(\n",
     "#     docs,\n",
-    "#     embeddings, \n",
-    "#     es_url=\"http://localhost:9200\", \n",
+    "#     embeddings,\n",
+    "#     es_url=\"http://localhost:9200\",\n",
     "#     index_name=\"hotel_rooms\",\n",
     "#     # strategy=ElasticsearchStore.ApproxRetrievalStrategy(\n",
     "#     #     hybrid=True,\n",
@@ -1049,9 +1133,9 @@
    "outputs": [],
    "source": [
     "vecstore = ElasticsearchStore(\n",
-    "    \"hotel_rooms\", \n",
-    "    embedding=embeddings, \n",
-    "    es_url=\"http://localhost:9200\", \n",
+    "    \"hotel_rooms\",\n",
+    "    embedding=embeddings,\n",
+    "    es_url=\"http://localhost:9200\",\n",
     "    # strategy=ElasticsearchStore.ApproxRetrievalStrategy(hybrid=True) # seems to not be available in community version\n",
     ")"
    ]
@@ -1065,7 +1149,9 @@
    "source": [
     "from langchain.retrievers import SelfQueryRetriever\n",
     "\n",
-    "retriever = SelfQueryRetriever(query_constructor=chain, vectorstore=vecstore, verbose=True)"
+    "retriever = SelfQueryRetriever(\n",
+    "    query_constructor=chain, vectorstore=vecstore, verbose=True\n",
+    ")"
    ]
   },
   {
@@ -1142,7 +1228,9 @@
     }
    ],
    "source": [
-    "results = retriever.get_relevant_documents(\"I want to stay somewhere highly rated along the coast. I want a room with a patio and a fireplace.\")\n",
+    "results = retriever.get_relevant_documents(\n",
+    "    \"I want to stay somewhere highly rated along the coast. I want a room with a patio and a fireplace.\"\n",
+    ")\n",
     "for res in results:\n",
     "    print(res.page_content)\n",
     "    print(\"\\n\" + \"-\" * 20 + \"\\n\")"

cookbook/stepback-qa.ipynb

@@ -0,0 +1,351 @@
+{
+ "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",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"\"\"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",
+    "        ),\n",
+    "        # Few shot examples\n",
+    "        few_shot_prompt,\n",
+    "        # New question\n",
+    "        (\"user\", \"{question}\"),\n",
+    "    ]\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",
+    "\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",
+    "    {\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",
+    "    }\n",
+    "    | response_prompt\n",
+    "    | ChatOpenAI(temperature=0)\n",
+    "    | StrOutputParser()\n",
+    ")"
+   ]
+  },
+  {
+   "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",
+    "    {\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",
+    "    }\n",
+    "    | response_prompt\n",
+    "    | ChatOpenAI(temperature=0)\n",
+    "    | StrOutputParser()\n",
+    ")"
+   ]
+  },
+  {
+   "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
+}

cookbook/tree_of_thought.ipynb

@@ -51,7 +51,7 @@
     }
    ],
    "source": [
-    "sudoku_puzzle =   \"3,*,*,2|1,*,3,*|*,1,*,3|4,*,*,1\"\n",
+    "sudoku_puzzle = \"3,*,*,2|1,*,3,*|*,1,*,3|4,*,*,1\"\n",
     "sudoku_solution = \"3,4,1,2|1,2,3,4|2,1,4,3|4,3,2,1\"\n",
     "problem_description = f\"\"\"\n",
     "{sudoku_puzzle}\n",
@@ -64,7 +64,7 @@
     "- Keep the known digits from previous valid thoughts in place.\n",
     "- Each thought can be a partial or the final solution.\n",
     "\"\"\".strip()\n",
-    "print(problem_description)\n"
+    "print(problem_description)"
    ]
   },
   {
@@ -89,8 +89,11 @@
     "from langchain_experimental.tot.thought import ThoughtValidity\n",
     "import re\n",
     "\n",
+    "\n",
     "class MyChecker(ToTChecker):\n",
-    "    def evaluate(self, problem_description: str, thoughts: Tuple[str, ...] = ()) -> ThoughtValidity:\n",
+    "    def evaluate(\n",
+    "        self, problem_description: str, thoughts: Tuple[str, ...] = ()\n",
+    "    ) -> ThoughtValidity:\n",
     "        last_thought = thoughts[-1]\n",
     "        clean_solution = last_thought.replace(\" \", \"\").replace('\"', \"\")\n",
     "        regex_solution = clean_solution.replace(\"*\", \".\").replace(\"|\", \"\\\\|\")\n",
@@ -116,10 +119,22 @@
    "outputs": [],
    "source": [
     "checker = MyChecker()\n",
-    "assert checker.evaluate(\"\", (\"3,*,*,2|1,*,3,*|*,1,*,3|4,*,*,1\",)) == ThoughtValidity.VALID_INTERMEDIATE\n",
-    "assert checker.evaluate(\"\", (\"3,4,1,2|1,2,3,4|2,1,4,3|4,3,2,1\",)) == ThoughtValidity.VALID_FINAL\n",
-    "assert checker.evaluate(\"\", (\"3,4,1,2|1,2,3,4|2,1,4,3|4,3,*,1\",)) == ThoughtValidity.VALID_INTERMEDIATE\n",
-    "assert checker.evaluate(\"\", (\"3,4,1,2|1,2,3,4|2,1,4,3|4,*,3,1\",)) == ThoughtValidity.INVALID"
+    "assert (\n",
+    "    checker.evaluate(\"\", (\"3,*,*,2|1,*,3,*|*,1,*,3|4,*,*,1\",))\n",
+    "    == ThoughtValidity.VALID_INTERMEDIATE\n",
+    ")\n",
+    "assert (\n",
+    "    checker.evaluate(\"\", (\"3,4,1,2|1,2,3,4|2,1,4,3|4,3,2,1\",))\n",
+    "    == ThoughtValidity.VALID_FINAL\n",
+    ")\n",
+    "assert (\n",
+    "    checker.evaluate(\"\", (\"3,4,1,2|1,2,3,4|2,1,4,3|4,3,*,1\",))\n",
+    "    == ThoughtValidity.VALID_INTERMEDIATE\n",
+    ")\n",
+    "assert (\n",
+    "    checker.evaluate(\"\", (\"3,4,1,2|1,2,3,4|2,1,4,3|4,*,3,1\",))\n",
+    "    == ThoughtValidity.INVALID\n",
+    ")"
    ]
   },
   {
@@ -203,7 +218,9 @@
    "source": [
     "from langchain_experimental.tot.base import ToTChain\n",
     "\n",
-    "tot_chain = ToTChain(llm=llm, checker=MyChecker(), k=30, c=5, verbose=True, verbose_llm=False)\n",
+    "tot_chain = ToTChain(\n",
+    "    llm=llm, checker=MyChecker(), k=30, c=5, verbose=True, verbose_llm=False\n",
+    ")\n",
     "tot_chain.run(problem_description=problem_description)"
    ]
   },

cookbook/wikibase_agent.ipynb

@@ -35,7 +35,7 @@
     "tags": []
    },
    "source": [
-    "### API keys and other secrats\n",
+    "### API keys and other secrets\n",
     "\n",
     "We use an `.ini` file, like this: \n",
     "```\n",

docs/.local_build.sh

@@ -13,6 +13,9 @@ 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
+wget https://raw.githubusercontent.com/langchain-ai/langserve/main/README.md -O docs/langserve.md
 poetry run python scripts/generate_api_reference_links.py
 yarn install
 yarn start

docs/api_reference/create_api_rst.py

@@ -2,9 +2,9 @@
 import importlib
 import inspect
 import typing
-from pathlib import Path
-from typing import TypedDict, Sequence, List, Dict, Literal, Union, Optional
 from enum import Enum
+from pathlib import Path
+from typing import Dict, List, Literal, Optional, Sequence, TypedDict, Union
 
 from pydantic import BaseModel
 

docs/docs/additional_resources/tutorials.mdx

@@ -1,6 +1,6 @@
 # Tutorials
 
-Below are links to tutorials and courses on LangChain. For written guides on common use cases for LangChain, check out the [use cases guides](/docs/use_cases).
+Below are links to tutorials and courses on LangChain. For written guides on common use cases for LangChain, check out the [use cases guides](/docs/use_cases/qa_structured/sql).
 
 ⛓ icon marks a new addition [last update 2023-09-21]
 

docs/docs/expression_language/cookbook/agent.ipynb

@@ -115,7 +115,9 @@
     "agent = (\n",
     "    {\n",
     "        \"question\": lambda x: x[\"question\"],\n",
-    "        \"intermediate_steps\": lambda x: convert_intermediate_steps(x[\"intermediate_steps\"])\n",
+    "        \"intermediate_steps\": lambda x: convert_intermediate_steps(\n",
+    "            x[\"intermediate_steps\"]\n",
+    "        ),\n",
     "    }\n",
     "    | prompt.partial(tools=convert_tools(tool_list))\n",
     "    | model.bind(stop=[\"</tool_input>\", \"</final_answer>\"])\n",

docs/docs/expression_language/cookbook/code_writing.ipynb

@@ -12,15 +12,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 1,
    "id": "bd7c259a",
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.prompts import ChatPromptTemplate, SystemMessagePromptTemplate, HumanMessagePromptTemplate\n",
+    "from langchain.prompts import (\n",
+    "    ChatPromptTemplate,\n",
+    "    SystemMessagePromptTemplate,\n",
+    "    HumanMessagePromptTemplate,\n",
+    ")\n",
     "from langchain.schema.output_parser import StrOutputParser\n",
-    "from langchain.utilities import PythonREPL"
+    "from langchain_experimental.utilities import PythonREPL"
    ]
   },
   {
@@ -37,9 +41,7 @@
     "```python\n",
     "....\n",
     "```\"\"\"\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [(\"system\", template), (\"human\", \"{input}\")]\n",
-    ")\n",
+    "prompt = ChatPromptTemplate.from_messages([(\"system\", template), (\"human\", \"{input}\")])\n",
     "\n",
     "model = ChatOpenAI()"
    ]
@@ -111,7 +113,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.1"
   }
  },
  "nbformat": 4,

docs/docs/expression_language/cookbook/embedding_router.ipynb

@@ -0,0 +1,155 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "cf4fb76d-c534-485b-8b51-a0714ee3b82e",
+   "metadata": {},
+   "source": [
+    "# Routing by semantic similarity\n",
+    "\n",
+    "With LCEL you can easily add [custom routing logic](/docs/expression_language/how_to/routing#using-a-custom-function) to your chain to dynamically determine the chain logic based on user input. All you need to do is define a function that given an input returns a `Runnable`.\n",
+    "\n",
+    "One especially useful technique is to use embeddings to route a query to the most relevant prompt. Here's a very simple example."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "eef9020a-5f7c-4291-98eb-fa73f17d4b92",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.embeddings import OpenAIEmbeddings\n",
+    "from langchain.prompts import PromptTemplate\n",
+    "from langchain.schema.output_parser import StrOutputParser\n",
+    "from langchain.schema.runnable import RunnableLambda, RunnablePassthrough\n",
+    "from langchain.utils.math import cosine_similarity\n",
+    "\n",
+    "\n",
+    "physics_template = \"\"\"You are a very smart physics professor. \\\n",
+    "You are great at answering questions about physics in a concise and easy to understand manner. \\\n",
+    "When you don't know the answer to a question you admit that you don't know.\n",
+    "\n",
+    "Here is a question:\n",
+    "{query}\"\"\"\n",
+    "\n",
+    "math_template = \"\"\"You are a very good mathematician. You are great at answering math questions. \\\n",
+    "You are so good because you are able to break down hard problems into their component parts, \\\n",
+    "answer the component parts, and then put them together to answer the broader question.\n",
+    "\n",
+    "Here is a question:\n",
+    "{query}\"\"\"\n",
+    "\n",
+    "embeddings = OpenAIEmbeddings()\n",
+    "prompt_templates = [physics_template, math_template]\n",
+    "prompt_embeddings = embeddings.embed_documents(prompt_templates)\n",
+    "\n",
+    "\n",
+    "def prompt_router(input):\n",
+    "    query_embedding = embeddings.embed_query(input[\"query\"])\n",
+    "    similarity = cosine_similarity([query_embedding], prompt_embeddings)[0]\n",
+    "    most_similar = prompt_templates[similarity.argmax()]\n",
+    "    print(\"Using MATH\" if most_similar == math_template else \"Using PHYSICS\")\n",
+    "    return PromptTemplate.from_template(most_similar)\n",
+    "\n",
+    "\n",
+    "chain = (\n",
+    "    {\"query\": RunnablePassthrough()}\n",
+    "    | RunnableLambda(prompt_router)\n",
+    "    | ChatOpenAI()\n",
+    "    | StrOutputParser()\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "4d22b0f3-24f2-4a47-9440-065b57ebcdbd",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Using PHYSICS\n",
+      "A black hole is a region in space where gravity is extremely strong, so strong that nothing, not even light, can escape its gravitational pull. It is formed when a massive star collapses under its own gravity during a supernova explosion. The collapse causes an incredibly dense mass to be concentrated in a small volume, creating a gravitational field that is so intense that it warps space and time. Black holes have a boundary called the event horizon, which marks the point of no return for anything that gets too close. Beyond the event horizon, the gravitational pull is so strong that even light cannot escape, hence the name \"black hole.\" While we have a good understanding of black holes, there is still much to learn, especially about what happens inside them.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(chain.invoke(\"What's a black hole\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "f261910d-1de1-4a01-8c8a-308db02b81de",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Using MATH\n",
+      "Thank you for your kind words! I will do my best to break down the concept of a path integral for you.\n",
+      "\n",
+      "In mathematics and physics, a path integral is a mathematical tool used to calculate the probability amplitude or wave function of a particle or system of particles. It was introduced by Richard Feynman and is an integral over all possible paths that a particle can take to go from an initial state to a final state.\n",
+      "\n",
+      "To understand the concept better, let's consider an example. Suppose we have a particle moving from point A to point B in space. Classically, we would describe this particle's motion using a definite trajectory, but in quantum mechanics, particles can simultaneously take multiple paths from A to B.\n",
+      "\n",
+      "The path integral formalism considers all possible paths that the particle could take and assigns a probability amplitude to each path. These probability amplitudes are then added up, taking into account the interference effects between different paths.\n",
+      "\n",
+      "To calculate a path integral, we need to define an action, which is a mathematical function that describes the behavior of the system. The action is usually expressed in terms of the particle's position, velocity, and time.\n",
+      "\n",
+      "Once we have the action, we can write down the path integral as an integral over all possible paths. Each path is weighted by a factor determined by the action and the principle of least action, which states that a particle takes a path that minimizes the action.\n",
+      "\n",
+      "Mathematically, the path integral is expressed as:\n",
+      "\n",
+      "∫ e^(iS/ħ) D[x(t)]\n",
+      "\n",
+      "Here, S is the action, ħ is the reduced Planck's constant, and D[x(t)] represents the integration over all possible paths x(t) of the particle.\n",
+      "\n",
+      "By evaluating this integral, we can obtain the probability amplitude for the particle to go from the initial state to the final state. The absolute square of this amplitude gives us the probability of finding the particle in a particular state.\n",
+      "\n",
+      "Path integrals have proven to be a powerful tool in various areas of physics, including quantum mechanics, quantum field theory, and statistical mechanics. They allow us to study complex systems and calculate probabilities that are difficult to obtain using other methods.\n",
+      "\n",
+      "I hope this explanation helps you understand the concept of a path integral. If you have any further questions, feel free to ask!\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(chain.invoke(\"What's a path integral\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f0c1732a-01ca-4d10-977c-29ed7480972b",
+   "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/memory.ipynb

@@ -24,11 +24,13 @@
     "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"
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\"system\", \"You are a helpful chatbot\"),\n",
+    "        MessagesPlaceholder(variable_name=\"history\"),\n",
+    "        (\"human\", \"{input}\"),\n",
+    "    ]\n",
+    ")"
    ]
   },
   {
@@ -38,7 +40,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "memory = ConversationBufferMemory(return_messages=True)\n"
+    "memory = ConversationBufferMemory(return_messages=True)"
    ]
   },
   {
@@ -59,7 +61,7 @@
     }
    ],
    "source": [
-    "memory.load_memory_variables({})\n"
+    "memory.load_memory_variables({})"
    ]
   },
   {
@@ -69,9 +71,13 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "chain = RunnablePassthrough.assign(\n",
-    "    memory=RunnableLambda(memory.load_memory_variables) | itemgetter(\"history\")\n",
-    ") | prompt | model\n"
+    "chain = (\n",
+    "    RunnablePassthrough.assign(\n",
+    "        history=RunnableLambda(memory.load_memory_variables) | itemgetter(\"history\")\n",
+    "    )\n",
+    "    | prompt\n",
+    "    | model\n",
+    ")"
    ]
   },
   {
@@ -94,7 +100,7 @@
    "source": [
     "inputs = {\"input\": \"hi im bob\"}\n",
     "response = chain.invoke(inputs)\n",
-    "response\n"
+    "response"
    ]
   },
   {
@@ -104,7 +110,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "memory.save_context(inputs, {\"output\": response.content})\n"
+    "memory.save_context(inputs, {\"output\": response.content})"
    ]
   },
   {
@@ -126,7 +132,7 @@
     }
    ],
    "source": [
-    "memory.load_memory_variables({})\n"
+    "memory.load_memory_variables({})"
    ]
   },
   {
@@ -149,7 +155,7 @@
    "source": [
     "inputs = {\"input\": \"whats my name\"}\n",
     "response = chain.invoke(inputs)\n",
-    "response\n"
+    "response"
    ]
   }
  ],

docs/docs/expression_language/cookbook/moderation.ipynb

@@ -40,9 +40,7 @@
    "outputs": [],
    "source": [
     "model = OpenAI()\n",
-    "prompt = ChatPromptTemplate.from_messages([\n",
-    "    (\"system\", \"repeat after me: {input}\")\n",
-    "])"
+    "prompt = ChatPromptTemplate.from_messages([(\"system\", \"repeat after me: {input}\")])"
    ]
   },
   {

docs/docs/expression_language/cookbook/multiple_chains.ipynb

@@ -44,13 +44,20 @@
     "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",
+    "prompt2 = ChatPromptTemplate.from_template(\n",
+    "    \"what country is the city {city} in? respond in {language}\"\n",
+    ")\n",
     "\n",
     "model = ChatOpenAI()\n",
     "\n",
     "chain1 = prompt1 | model | StrOutputParser()\n",
     "\n",
-    "chain2 = {\"city\": chain1, \"language\": itemgetter(\"language\")} | prompt2 | model | StrOutputParser()\n",
+    "chain2 = (\n",
+    "    {\"city\": chain1, \"language\": itemgetter(\"language\")}\n",
+    "    | prompt2\n",
+    "    | model\n",
+    "    | StrOutputParser()\n",
+    ")\n",
     "\n",
     "chain2.invoke({\"person\": \"obama\", \"language\": \"spanish\"})"
    ]
@@ -64,17 +71,29 @@
    "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",
+    "prompt1 = ChatPromptTemplate.from_template(\n",
+    "    \"generate a {attribute} color. Return the name of the color and nothing else:\"\n",
+    ")\n",
+    "prompt2 = ChatPromptTemplate.from_template(\n",
+    "    \"what is a fruit of color: {color}. Return the name of the fruit and nothing else:\"\n",
+    ")\n",
+    "prompt3 = ChatPromptTemplate.from_template(\n",
+    "    \"what is a country with a flag that has the color: {color}. Return the name of the country and nothing else:\"\n",
+    ")\n",
+    "prompt4 = ChatPromptTemplate.from_template(\n",
+    "    \"What is the color of {fruit} and the flag of {country}?\"\n",
+    ")\n",
     "\n",
     "model_parser = model | StrOutputParser()\n",
     "\n",
-    "color_generator = {\"attribute\": RunnablePassthrough()} | prompt1 | {\"color\": model_parser}\n",
+    "color_generator = (\n",
+    "    {\"attribute\": RunnablePassthrough()} | prompt1 | {\"color\": model_parser}\n",
+    ")\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"
+    "question_generator = (\n",
+    "    color_generator | {\"fruit\": color_to_fruit, \"country\": color_to_country} | prompt4\n",
+    ")"
    ]
   },
   {
@@ -148,9 +167,7 @@
    "outputs": [],
    "source": [
     "planner = (\n",
-    "    ChatPromptTemplate.from_template(\n",
-    "        \"Generate an argument about: {input}\"\n",
-    "    )\n",
+    "    ChatPromptTemplate.from_template(\"Generate an argument about: {input}\")\n",
     "    | ChatOpenAI()\n",
     "    | StrOutputParser()\n",
     "    | {\"base_response\": RunnablePassthrough()}\n",
@@ -163,7 +180,7 @@
     "    | ChatOpenAI()\n",
     "    | StrOutputParser()\n",
     ")\n",
-    "arguments_against =  (\n",
+    "arguments_against = (\n",
     "    ChatPromptTemplate.from_template(\n",
     "        \"List the cons or negative aspects of {base_response}\"\n",
     "    )\n",
@@ -184,7 +201,7 @@
     ")\n",
     "\n",
     "chain = (\n",
-    "    planner \n",
+    "    planner\n",
     "    | {\n",
     "        \"results_1\": arguments_for,\n",
     "        \"results_2\": arguments_against,\n",

docs/docs/expression_language/cookbook/prompt_llm_parser.ipynb

@@ -30,7 +30,7 @@
    "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",
+    "The simplest composition is just combining 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 output.\n",
     "\n",
     "Note, you can mix and match PromptTemplate/ChatPromptTemplates and LLMs/ChatModels as you like here."
    ]
@@ -47,7 +47,7 @@
     "\n",
     "prompt = ChatPromptTemplate.from_template(\"tell me a joke about {foo}\")\n",
     "model = ChatOpenAI()\n",
-    "chain = prompt | model\n"
+    "chain = prompt | model"
    ]
   },
   {
@@ -68,7 +68,7 @@
     }
    ],
    "source": [
-    "chain.invoke({\"foo\": \"bears\"})\n"
+    "chain.invoke({\"foo\": \"bears\"})"
    ]
   },
   {
@@ -76,7 +76,7 @@
    "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:"
+    "Often times we want to attach kwargs that'll be passed to each model call. Here are a few examples of that:"
    ]
   },
   {
@@ -94,7 +94,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "chain = prompt | model.bind(stop=[\"\\n\"])\n"
+    "chain = prompt | model.bind(stop=[\"\\n\"])"
    ]
   },
   {
@@ -115,7 +115,7 @@
     }
    ],
    "source": [
-    "chain.invoke({\"foo\": \"bears\"})\n"
+    "chain.invoke({\"foo\": \"bears\"})"
    ]
   },
   {
@@ -135,25 +135,22 @@
    "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",
+    "        \"name\": \"joke\",\n",
+    "        \"description\": \"A joke\",\n",
+    "        \"parameters\": {\n",
+    "            \"type\": \"object\",\n",
+    "            \"properties\": {\n",
+    "                \"setup\": {\"type\": \"string\", \"description\": \"The setup for the joke\"},\n",
+    "                \"punchline\": {\n",
+    "                    \"type\": \"string\",\n",
+    "                    \"description\": \"The punchline for the joke\",\n",
+    "                },\n",
+    "            },\n",
+    "            \"required\": [\"setup\", \"punchline\"],\n",
     "        },\n",
-    "        \"required\": [\"setup\", \"punchline\"]\n",
-    "      }\n",
     "    }\n",
-    "  ]\n",
-    "chain = prompt | model.bind(function_call= {\"name\": \"joke\"}, functions= functions)\n"
+    "]\n",
+    "chain = prompt | model.bind(function_call={\"name\": \"joke\"}, functions=functions)"
    ]
   },
   {
@@ -174,7 +171,7 @@
     }
    ],
    "source": [
-    "chain.invoke({\"foo\": \"bears\"}, config={})\n"
+    "chain.invoke({\"foo\": \"bears\"}, config={})"
    ]
   },
   {
@@ -196,7 +193,7 @@
    "source": [
     "from langchain.schema.output_parser import StrOutputParser\n",
     "\n",
-    "chain = prompt | model | StrOutputParser()\n"
+    "chain = prompt | model | StrOutputParser()"
    ]
   },
   {
@@ -225,7 +222,7 @@
     }
    ],
    "source": [
-    "chain.invoke({\"foo\": \"bears\"})\n"
+    "chain.invoke({\"foo\": \"bears\"})"
    ]
   },
   {
@@ -248,10 +245,10 @@
     "from langchain.output_parsers.openai_functions import JsonOutputFunctionsParser\n",
     "\n",
     "chain = (\n",
-    "    prompt \n",
-    "    | model.bind(function_call= {\"name\": \"joke\"}, functions= functions) \n",
+    "    prompt\n",
+    "    | model.bind(function_call={\"name\": \"joke\"}, functions=functions)\n",
     "    | JsonOutputFunctionsParser()\n",
-    ")\n"
+    ")"
    ]
   },
   {
@@ -273,7 +270,7 @@
     }
    ],
    "source": [
-    "chain.invoke({\"foo\": \"bears\"})\n"
+    "chain.invoke({\"foo\": \"bears\"})"
    ]
   },
   {
@@ -286,10 +283,10 @@
     "from langchain.output_parsers.openai_functions import JsonKeyOutputFunctionsParser\n",
     "\n",
     "chain = (\n",
-    "    prompt \n",
-    "    | model.bind(function_call= {\"name\": \"joke\"}, functions= functions) \n",
+    "    prompt\n",
+    "    | model.bind(function_call={\"name\": \"joke\"}, functions=functions)\n",
     "    | JsonKeyOutputFunctionsParser(key_name=\"setup\")\n",
-    ")\n"
+    ")"
    ]
   },
   {
@@ -310,7 +307,7 @@
     }
    ],
    "source": [
-    "chain.invoke({\"foo\": \"bears\"})\n"
+    "chain.invoke({\"foo\": \"bears\"})"
    ]
   },
   {
@@ -334,11 +331,11 @@
     "\n",
     "map_ = RunnableMap(foo=RunnablePassthrough())\n",
     "chain = (\n",
-    "    map_ \n",
+    "    map_\n",
     "    | prompt\n",
-    "    | model.bind(function_call= {\"name\": \"joke\"}, functions= functions) \n",
+    "    | model.bind(function_call={\"name\": \"joke\"}, functions=functions)\n",
     "    | JsonKeyOutputFunctionsParser(key_name=\"setup\")\n",
-    ")\n"
+    ")"
    ]
   },
   {
@@ -359,7 +356,7 @@
     }
    ],
    "source": [
-    "chain.invoke(\"bears\")\n"
+    "chain.invoke(\"bears\")"
    ]
   },
   {
@@ -378,11 +375,11 @@
    "outputs": [],
    "source": [
     "chain = (\n",
-    "    {\"foo\": RunnablePassthrough()} \n",
+    "    {\"foo\": RunnablePassthrough()}\n",
     "    | prompt\n",
-    "    | model.bind(function_call= {\"name\": \"joke\"}, functions= functions) \n",
+    "    | model.bind(function_call={\"name\": \"joke\"}, functions=functions)\n",
     "    | JsonKeyOutputFunctionsParser(key_name=\"setup\")\n",
-    ")\n"
+    ")"
    ]
   },
   {
@@ -403,7 +400,7 @@
     }
    ],
    "source": [
-    "chain.invoke(\"bears\")\n"
+    "chain.invoke(\"bears\")"
    ]
   }
  ],

docs/docs/expression_language/cookbook/retrieval.ipynb

@@ -26,7 +26,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install langchain openai faiss-cpu tiktoken\n"
+    "!pip install langchain openai faiss-cpu tiktoken"
    ]
   },
   {
@@ -43,7 +43,7 @@
     "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"
+    "from langchain.vectorstores import FAISS"
    ]
   },
   {
@@ -53,7 +53,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "vectorstore = FAISS.from_texts([\"harrison worked at kensho\"], embedding=OpenAIEmbeddings())\n",
+    "vectorstore = FAISS.from_texts(\n",
+    "    [\"harrison worked at kensho\"], embedding=OpenAIEmbeddings()\n",
+    ")\n",
     "retriever = vectorstore.as_retriever()\n",
     "\n",
     "template = \"\"\"Answer the question based only on the following context:\n",
@@ -63,7 +65,7 @@
     "\"\"\"\n",
     "prompt = ChatPromptTemplate.from_template(template)\n",
     "\n",
-    "model = ChatOpenAI()\n"
+    "model = ChatOpenAI()"
    ]
   },
   {
@@ -74,11 +76,11 @@
    "outputs": [],
    "source": [
     "chain = (\n",
-    "    {\"context\": retriever, \"question\": RunnablePassthrough()} \n",
-    "    | prompt \n",
-    "    | model \n",
+    "    {\"context\": retriever, \"question\": RunnablePassthrough()}\n",
+    "    | prompt\n",
+    "    | model\n",
     "    | StrOutputParser()\n",
-    ")\n"
+    ")"
    ]
   },
   {
@@ -99,7 +101,7 @@
     }
    ],
    "source": [
-    "chain.invoke(\"where did harrison work?\")\n"
+    "chain.invoke(\"where did harrison work?\")"
    ]
   },
   {
@@ -118,11 +120,16 @@
     "\"\"\"\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"
+    "chain = (\n",
+    "    {\n",
+    "        \"context\": itemgetter(\"question\") | retriever,\n",
+    "        \"question\": itemgetter(\"question\"),\n",
+    "        \"language\": itemgetter(\"language\"),\n",
+    "    }\n",
+    "    | prompt\n",
+    "    | model\n",
+    "    | StrOutputParser()\n",
+    ")"
    ]
   },
   {
@@ -143,7 +150,7 @@
     }
    ],
    "source": [
-    "chain.invoke({\"question\": \"where did harrison work\", \"language\": \"italian\"})\n"
+    "chain.invoke({\"question\": \"where did harrison work\", \"language\": \"italian\"})"
    ]
   },
   {
@@ -164,7 +171,7 @@
    "outputs": [],
    "source": [
     "from langchain.schema.runnable import RunnableMap\n",
-    "from langchain.schema import format_document\n"
+    "from langchain.schema import format_document"
    ]
   },
   {
@@ -182,7 +189,7 @@
     "{chat_history}\n",
     "Follow Up Input: {question}\n",
     "Standalone question:\"\"\"\n",
-    "CONDENSE_QUESTION_PROMPT = PromptTemplate.from_template(_template)\n"
+    "CONDENSE_QUESTION_PROMPT = PromptTemplate.from_template(_template)"
    ]
   },
   {
@@ -197,7 +204,7 @@
     "\n",
     "Question: {question}\n",
     "\"\"\"\n",
-    "ANSWER_PROMPT = ChatPromptTemplate.from_template(template)\n"
+    "ANSWER_PROMPT = ChatPromptTemplate.from_template(template)"
    ]
   },
   {
@@ -208,9 +215,13 @@
    "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",
+    "\n",
+    "\n",
+    "def _combine_documents(\n",
+    "    docs, document_prompt=DEFAULT_DOCUMENT_PROMPT, document_separator=\"\\n\\n\"\n",
+    "):\n",
     "    doc_strings = [format_document(doc, document_prompt) for doc in docs]\n",
-    "    return document_separator.join(doc_strings)\n"
+    "    return document_separator.join(doc_strings)"
    ]
   },
   {
@@ -221,13 +232,15 @@
    "outputs": [],
    "source": [
     "from typing import Tuple, List\n",
+    "\n",
+    "\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"
+    "    return buffer"
    ]
   },
   {
@@ -239,14 +252,17 @@
    "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",
+    "        chat_history=lambda x: _format_chat_history(x[\"chat_history\"])\n",
+    "    )\n",
+    "    | CONDENSE_QUESTION_PROMPT\n",
+    "    | ChatOpenAI(temperature=0)\n",
+    "    | StrOutputParser(),\n",
     ")\n",
     "_context = {\n",
     "    \"context\": itemgetter(\"standalone_question\") | retriever | _combine_documents,\n",
-    "    \"question\": lambda x: x[\"standalone_question\"]\n",
+    "    \"question\": lambda x: x[\"standalone_question\"],\n",
     "}\n",
-    "conversational_qa_chain = _inputs | _context | ANSWER_PROMPT | ChatOpenAI()\n"
+    "conversational_qa_chain = _inputs | _context | ANSWER_PROMPT | ChatOpenAI()"
    ]
   },
   {
@@ -267,10 +283,12 @@
     }
    ],
    "source": [
-    "conversational_qa_chain.invoke({\n",
-    "    \"question\": \"where did harrison work?\",\n",
-    "    \"chat_history\": [],\n",
-    "})\n"
+    "conversational_qa_chain.invoke(\n",
+    "    {\n",
+    "        \"question\": \"where did harrison work?\",\n",
+    "        \"chat_history\": [],\n",
+    "    }\n",
+    ")"
    ]
   },
   {
@@ -291,10 +309,12 @@
     }
    ],
    "source": [
-    "conversational_qa_chain.invoke({\n",
-    "    \"question\": \"where did he work?\",\n",
-    "    \"chat_history\": [(\"Who wrote this notebook?\", \"Harrison\")],\n",
-    "})\n"
+    "conversational_qa_chain.invoke(\n",
+    "    {\n",
+    "        \"question\": \"where did he work?\",\n",
+    "        \"chat_history\": [(\"Who wrote this notebook?\", \"Harrison\")],\n",
+    "    }\n",
+    ")"
    ]
   },
   {
@@ -315,7 +335,7 @@
    "outputs": [],
    "source": [
     "from operator import itemgetter\n",
-    "from langchain.memory import ConversationBufferMemory\n"
+    "from langchain.memory import ConversationBufferMemory"
    ]
   },
   {
@@ -325,7 +345,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "memory = ConversationBufferMemory(return_messages=True, output_key=\"answer\", input_key=\"question\")\n"
+    "memory = ConversationBufferMemory(\n",
+    "    return_messages=True, output_key=\"answer\", input_key=\"question\"\n",
+    ")"
    ]
   },
   {
@@ -344,18 +366,21 @@
     "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",
+    "        \"chat_history\": lambda x: _format_chat_history(x[\"chat_history\"]),\n",
+    "    }\n",
+    "    | CONDENSE_QUESTION_PROMPT\n",
+    "    | ChatOpenAI(temperature=0)\n",
+    "    | 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",
+    "    \"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",
+    "    \"question\": itemgetter(\"question\"),\n",
     "}\n",
     "# And finally, we do the part that returns the answers\n",
     "answer = {\n",
@@ -363,7 +388,7 @@
     "    \"docs\": itemgetter(\"docs\"),\n",
     "}\n",
     "# And now we put it all together!\n",
-    "final_chain = loaded_memory | standalone_question | retrieved_documents | answer\n"
+    "final_chain = loaded_memory | standalone_question | retrieved_documents | answer"
    ]
   },
   {
@@ -387,7 +412,7 @@
    "source": [
     "inputs = {\"question\": \"where did harrison work?\"}\n",
     "result = final_chain.invoke(inputs)\n",
-    "result\n"
+    "result"
    ]
   },
   {
@@ -400,7 +425,7 @@
     "# 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"
+    "memory.save_context(inputs, {\"answer\": result[\"answer\"].content})"
    ]
   },
   {
@@ -422,7 +447,7 @@
     }
    ],
    "source": [
-    "memory.load_memory_variables({})\n"
+    "memory.load_memory_variables({})"
    ]
   }
  ],

docs/docs/expression_language/cookbook/sql_db.ipynb

@@ -33,7 +33,7 @@
     "\n",
     "Question: {question}\n",
     "SQL Query:\"\"\"\n",
-    "prompt = ChatPromptTemplate.from_template(template)\n"
+    "prompt = ChatPromptTemplate.from_template(template)"
    ]
   },
   {
@@ -43,7 +43,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.utilities import SQLDatabase\n"
+    "from langchain.utilities import SQLDatabase"
    ]
   },
   {
@@ -61,7 +61,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "db = SQLDatabase.from_uri(\"sqlite:///./Chinook.db\")\n"
+    "db = SQLDatabase.from_uri(\"sqlite:///./Chinook.db\")"
    ]
   },
   {
@@ -72,7 +72,7 @@
    "outputs": [],
    "source": [
     "def get_schema(_):\n",
-    "    return db.get_table_info()\n"
+    "    return db.get_table_info()"
    ]
   },
   {
@@ -83,7 +83,7 @@
    "outputs": [],
    "source": [
     "def run_query(query):\n",
-    "    return db.run(query)\n"
+    "    return db.run(query)"
    ]
   },
   {
@@ -100,11 +100,11 @@
     "model = ChatOpenAI()\n",
     "\n",
     "sql_response = (\n",
-    "        RunnablePassthrough.assign(schema=get_schema)\n",
-    "        | prompt\n",
-    "        | model.bind(stop=[\"\\nSQLResult:\"])\n",
-    "        | StrOutputParser()\n",
-    "    )\n"
+    "    RunnablePassthrough.assign(schema=get_schema)\n",
+    "    | prompt\n",
+    "    | model.bind(stop=[\"\\nSQLResult:\"])\n",
+    "    | StrOutputParser()\n",
+    ")"
    ]
   },
   {
@@ -125,7 +125,7 @@
     }
    ],
    "source": [
-    "sql_response.invoke({\"question\": \"How many employees are there?\"})\n"
+    "sql_response.invoke({\"question\": \"How many employees are there?\"})"
    ]
   },
   {
@@ -141,7 +141,7 @@
     "Question: {question}\n",
     "SQL Query: {query}\n",
     "SQL Response: {response}\"\"\"\n",
-    "prompt_response = ChatPromptTemplate.from_template(template)\n"
+    "prompt_response = ChatPromptTemplate.from_template(template)"
    ]
   },
   {
@@ -152,14 +152,14 @@
    "outputs": [],
    "source": [
     "full_chain = (\n",
-    "    RunnablePassthrough.assign(query=sql_response) \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",
+    "    | prompt_response\n",
     "    | model\n",
-    ")\n"
+    ")"
    ]
   },
   {
@@ -180,7 +180,7 @@
     }
    ],
    "source": [
-    "full_chain.invoke({\"question\": \"How many employees are there?\"})\n"
+    "full_chain.invoke({\"question\": \"How many employees are there?\"})"
    ]
   },
   {

docs/docs/expression_language/how_to/binding.ipynb

@@ -12,6 +12,19 @@
     "Suppose we have a simple prompt + model sequence:"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "950297ed-2d67-4091-8ea7-1d412d259d04",
+   "metadata": {},
+   "outputs": [],
+   "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"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 11,
@@ -37,19 +50,19 @@
     }
    ],
    "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",
+    "            \"system\",\n",
+    "            \"Write out the following equation using algebraic symbols then solve it. Use the format\\n\\nEQUATION:...\\nSOLUTION:...\\n\\n\",\n",
+    "        ),\n",
+    "        (\"human\", \"{equation_statement}\"),\n",
     "    ]\n",
     ")\n",
     "model = ChatOpenAI(temperature=0)\n",
-    "runnable = {\"equation_statement\": RunnablePassthrough()} | prompt | model | StrOutputParser()\n",
+    "runnable = (\n",
+    "    {\"equation_statement\": RunnablePassthrough()} | prompt | model | StrOutputParser()\n",
+    ")\n",
     "\n",
     "print(runnable.invoke(\"x raised to the third plus seven equals 12\"))"
    ]
@@ -80,9 +93,9 @@
    ],
    "source": [
     "runnable = (\n",
-    "    {\"equation_statement\": RunnablePassthrough()} \n",
-    "    | prompt \n",
-    "    | model.bind(stop=\"SOLUTION\") \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\"))"
@@ -100,31 +113,29 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 3,
    "id": "f66a0fe4-fde0-4706-8863-d60253f211c7",
    "metadata": {},
    "outputs": [],
    "source": [
-    "functions = [\n",
-    "    {\n",
-    "      \"name\": \"solver\",\n",
-    "      \"description\": \"Formulates and solves an equation\",\n",
-    "      \"parameters\": {\n",
+    "function = {\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",
+    "            \"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"
+    "        \"required\": [\"equation\", \"solution\"],\n",
+    "    },\n",
+    "}"
    ]
   },
   {
@@ -148,26 +159,78 @@
     "# 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",
+    "            \"system\",\n",
+    "            \"Write out the following equation using algebraic symbols then solve it.\",\n",
+    "        ),\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",
+    "model = ChatOpenAI(model=\"gpt-4\", temperature=0).bind(\n",
+    "    function_call={\"name\": \"solver\"}, functions=[function]\n",
     ")\n",
+    "runnable = {\"equation_statement\": RunnablePassthrough()} | prompt | model\n",
     "runnable.invoke(\"x raised to the third plus seven equals 12\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "f07d7528-9269-4d6f-b12e-3669592a9e03",
+   "metadata": {},
+   "source": [
+    "## Attaching OpenAI tools"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "id": "2cdeeb4c-0c1f-43da-bd58-4f591d9e0671",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "tools = [\n",
+    "    {\n",
+    "        \"type\": \"function\",\n",
+    "        \"function\": {\n",
+    "            \"name\": \"get_current_weather\",\n",
+    "            \"description\": \"Get the current weather in a given location\",\n",
+    "            \"parameters\": {\n",
+    "                \"type\": \"object\",\n",
+    "                \"properties\": {\n",
+    "                    \"location\": {\n",
+    "                        \"type\": \"string\",\n",
+    "                        \"description\": \"The city and state, e.g. San Francisco, CA\",\n",
+    "                    },\n",
+    "                    \"unit\": {\"type\": \"string\", \"enum\": [\"celsius\", \"fahrenheit\"]},\n",
+    "                },\n",
+    "                \"required\": [\"location\"],\n",
+    "            },\n",
+    "        },\n",
+    "    }\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "2b65beab-48bb-46ff-a5a4-ef8ac95a513c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_zHN0ZHwrxM7nZDdqTp6dkPko', 'function': {'arguments': '{\"location\": \"San Francisco, CA\", \"unit\": \"celsius\"}', 'name': 'get_current_weather'}, 'type': 'function'}, {'id': 'call_aqdMm9HBSlFW9c9rqxTa7eQv', 'function': {'arguments': '{\"location\": \"New York, NY\", \"unit\": \"celsius\"}', 'name': 'get_current_weather'}, 'type': 'function'}, {'id': 'call_cx8E567zcLzYV2WSWVgO63f1', 'function': {'arguments': '{\"location\": \"Los Angeles, CA\", \"unit\": \"celsius\"}', 'name': 'get_current_weather'}, 'type': 'function'}]})"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model = ChatOpenAI(model=\"gpt-3.5-turbo-1106\").bind(tools=tools)\n",
+    "model.invoke(\"What's the weather in SF, NYC and LA?\")"
+   ]
   }
  ],
  "metadata": {

docs/docs/expression_language/how_to/configure.ipynb

@@ -5,7 +5,7 @@
    "id": "39eaf61b",
    "metadata": {},
    "source": [
-    "# Configuration\n",
+    "# Configure chain internals at runtime\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",
@@ -92,7 +92,7 @@
     }
    ],
    "source": [
-    "model.with_config(configurable={\"llm_temperature\": .9}).invoke(\"pick a random number\")"
+    "model.with_config(configurable={\"llm_temperature\": 0.9}).invoke(\"pick a random number\")"
    ]
   },
   {
@@ -153,7 +153,7 @@
     }
    ],
    "source": [
-    "chain.with_config(configurable={\"llm_temperature\": .9}).invoke({\"x\": 0})"
+    "chain.with_config(configurable={\"llm_temperature\": 0.9}).invoke({\"x\": 0})"
    ]
   },
   {
@@ -231,7 +231,9 @@
     }
    ],
    "source": [
-    "prompt.with_config(configurable={\"hub_commit\": \"rlm/rag-prompt-llama\"}).invoke({\"question\": \"foo\", \"context\": \"bar\"})"
+    "prompt.with_config(configurable={\"hub_commit\": \"rlm/rag-prompt-llama\"}).invoke(\n",
+    "    {\"question\": \"foo\", \"context\": \"bar\"}\n",
+    ")"
    ]
   },
   {
@@ -373,7 +375,9 @@
    "outputs": [],
    "source": [
     "llm = ChatAnthropic(temperature=0)\n",
-    "prompt = PromptTemplate.from_template(\"Tell me a joke about {topic}\").configurable_alternatives(\n",
+    "prompt = PromptTemplate.from_template(\n",
+    "    \"Tell me a joke about {topic}\"\n",
+    ").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",
@@ -462,7 +466,9 @@
     "    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",
+    "prompt = PromptTemplate.from_template(\n",
+    "    \"Tell me a joke about {topic}\"\n",
+    ").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",
@@ -495,7 +501,9 @@
    ],
    "source": [
     "# We can configure it write a poem with OpenAI\n",
-    "chain.with_config(configurable={\"prompt\": \"poem\", \"llm\": \"openai\"}).invoke({\"topic\": \"bears\"})"
+    "chain.with_config(configurable={\"prompt\": \"poem\", \"llm\": \"openai\"}).invoke(\n",
+    "    {\"topic\": \"bears\"}\n",
+    ")"
    ]
   },
   {
@@ -586,7 +594,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/docs/expression_language/how_to/fallbacks.ipynb

@@ -82,9 +82,9 @@
    ],
    "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",
+    "with patch(\"openai.ChatCompletion.create\", side_effect=RateLimitError()):\n",
     "    try:\n",
-    "         print(openai_llm.invoke(\"Why did the chicken cross the road?\"))\n",
+    "        print(openai_llm.invoke(\"Why did the chicken cross the road?\"))\n",
     "    except:\n",
     "        print(\"Hit error\")"
    ]
@@ -105,9 +105,9 @@
    ],
    "source": [
     "# Now let's try with fallbacks to Anthropic\n",
-    "with patch('openai.ChatCompletion.create', side_effect=RateLimitError()):\n",
+    "with patch(\"openai.ChatCompletion.create\", side_effect=RateLimitError()):\n",
     "    try:\n",
-    "         print(llm.invoke(\"Why did the the chicken cross the road?\"))\n",
+    "        print(llm.invoke(\"Why did the chicken cross the road?\"))\n",
     "    except:\n",
     "        print(\"Hit error\")"
    ]
@@ -139,14 +139,17 @@
     "\n",
     "prompt = ChatPromptTemplate.from_messages(\n",
     "    [\n",
-    "        (\"system\", \"You're a nice assistant who always includes a compliment in your response\"),\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"You're a nice assistant who always includes a compliment in your response\",\n",
+    "        ),\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",
+    "with patch(\"openai.ChatCompletion.create\", side_effect=RateLimitError()):\n",
     "    try:\n",
-    "         print(chain.invoke({\"animal\": \"kangaroo\"}))\n",
+    "        print(chain.invoke({\"animal\": \"kangaroo\"}))\n",
     "    except:\n",
     "        print(\"Hit error\")"
    ]
@@ -176,12 +179,14 @@
     }
    ],
    "source": [
-    "llm = openai_llm.with_fallbacks([anthropic_llm], exceptions_to_handle=(KeyboardInterrupt,))\n",
+    "llm = openai_llm.with_fallbacks(\n",
+    "    [anthropic_llm], exceptions_to_handle=(KeyboardInterrupt,)\n",
+    ")\n",
     "\n",
     "chain = prompt | llm\n",
-    "with patch('openai.ChatCompletion.create', side_effect=RateLimitError()):\n",
+    "with patch(\"openai.ChatCompletion.create\", side_effect=RateLimitError()):\n",
     "    try:\n",
-    "         print(chain.invoke({\"animal\": \"kangaroo\"}))\n",
+    "        print(chain.invoke({\"animal\": \"kangaroo\"}))\n",
     "    except:\n",
     "        print(\"Hit error\")"
    ]
@@ -209,7 +214,10 @@
     "\n",
     "chat_prompt = ChatPromptTemplate.from_messages(\n",
     "    [\n",
-    "        (\"system\", \"You're a nice assistant who always includes a compliment in your response\"),\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"You're a nice assistant who always includes a compliment in your response\",\n",
+    "        ),\n",
     "        (\"human\", \"Why did the {animal} cross the road\"),\n",
     "    ]\n",
     ")\n",

docs/docs/expression_language/how_to/functions.ipynb

@@ -5,7 +5,7 @@
    "id": "fbc4bf6e",
    "metadata": {},
    "source": [
-    "# Run arbitrary functions\n",
+    "# Run custom functions\n",
     "\n",
     "You can use arbitrary functions in the pipeline\n",
     "\n",
@@ -24,24 +24,33 @@
     "from langchain.chat_models import ChatOpenAI\n",
     "from operator import itemgetter\n",
     "\n",
+    "\n",
     "def length_function(text):\n",
     "    return len(text)\n",
     "\n",
+    "\n",
     "def _multiple_length_function(text1, text2):\n",
     "    return len(text1) * len(text2)\n",
     "\n",
+    "\n",
     "def multiple_length_function(_dict):\n",
     "    return _multiple_length_function(_dict[\"text1\"], _dict[\"text2\"])\n",
     "\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"
+    "chain = (\n",
+    "    {\n",
+    "        \"a\": itemgetter(\"foo\") | RunnableLambda(length_function),\n",
+    "        \"b\": {\"text1\": itemgetter(\"foo\"), \"text2\": itemgetter(\"bar\")}\n",
+    "        | RunnableLambda(multiple_length_function),\n",
+    "    }\n",
+    "    | prompt\n",
+    "    | model\n",
+    ")"
    ]
   },
   {
@@ -95,6 +104,7 @@
    "source": [
     "import json\n",
     "\n",
+    "\n",
     "def parse_or_fix(text: str, config: RunnableConfig):\n",
     "    fixing_chain = (\n",
     "        ChatPromptTemplate.from_template(\n",
@@ -134,7 +144,9 @@
     "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",
+    "    RunnableLambda(parse_or_fix).invoke(\n",
+    "        \"{foo: bar}\", {\"tags\": [\"my-tag\"], \"callbacks\": [cb]}\n",
+    "    )\n",
     "    print(cb)"
    ]
   },
@@ -163,7 +175,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/docs/expression_language/how_to/generators.ipynb

@@ -0,0 +1,185 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Stream 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": [],
+   "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",
+    "str_chain = prompt | model | StrOutputParser()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "lion, tiger, wolf, gorilla, panda"
+     ]
+    }
+   ],
+   "source": [
+    "for chunk in str_chain.stream({\"animal\": \"bear\"}):\n",
+    "    print(chunk, end=\"\", flush=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'lion, tiger, wolf, gorilla, panda'"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "str_chain.invoke({\"animal\": \"bear\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "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()]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "list_chain = str_chain | split_into_list"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['lion']\n",
+      "['tiger']\n",
+      "['wolf']\n",
+      "['gorilla']\n",
+      "['panda']\n"
+     ]
+    }
+   ],
+   "source": [
+    "for chunk in list_chain.stream({\"animal\": \"bear\"}):\n",
+    "    print(chunk, flush=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['lion', 'tiger', 'wolf', 'gorilla', 'panda']"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "list_chain.invoke({\"animal\": \"bear\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

docs/docs/expression_language/how_to/map.ipynb

@@ -5,7 +5,7 @@
    "id": "b022ab74-794d-4c54-ad47-ff9549ddb9d2",
    "metadata": {},
    "source": [
-    "# Use RunnableParallel/RunnableMap\n",
+    "# Parallelize steps\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."
    ]
@@ -36,11 +36,13 @@
     "\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",
+    "poem_chain = (\n",
+    "    ChatPromptTemplate.from_template(\"write a 2-line poem about {topic}\") | model\n",
+    ")\n",
     "\n",
     "map_chain = RunnableParallel(joke=joke_chain, poem=poem_chain)\n",
     "\n",
-    "map_chain.invoke({\"topic\": \"bear\"})\n"
+    "map_chain.invoke({\"topic\": \"bear\"})"
    ]
   },
   {
@@ -75,7 +77,9 @@
     "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",
+    "vectorstore = FAISS.from_texts(\n",
+    "    [\"harrison worked at kensho\"], embedding=OpenAIEmbeddings()\n",
+    ")\n",
     "retriever = vectorstore.as_retriever()\n",
     "template = \"\"\"Answer the question based only on the following context:\n",
     "{context}\n",
@@ -85,13 +89,13 @@
     "prompt = ChatPromptTemplate.from_template(template)\n",
     "\n",
     "retrieval_chain = (\n",
-    "    {\"context\": retriever, \"question\": RunnablePassthrough()} \n",
-    "    | prompt \n",
-    "    | model \n",
+    "    {\"context\": retriever, \"question\": RunnablePassthrough()}\n",
+    "    | prompt\n",
+    "    | model\n",
     "    | StrOutputParser()\n",
     ")\n",
     "\n",
-    "retrieval_chain.invoke(\"where did harrison work?\")\n"
+    "retrieval_chain.invoke(\"where did harrison work?\")"
    ]
   },
   {
@@ -131,7 +135,7 @@
    "source": [
     "%%timeit\n",
     "\n",
-    "joke_chain.invoke({\"topic\": \"bear\"})\n"
+    "joke_chain.invoke({\"topic\": \"bear\"})"
    ]
   },
   {
@@ -151,7 +155,7 @@
    "source": [
     "%%timeit\n",
     "\n",
-    "poem_chain.invoke({\"topic\": \"bear\"})\n"
+    "poem_chain.invoke({\"topic\": \"bear\"})"
    ]
   },
   {
@@ -171,7 +175,7 @@
    "source": [
     "%%timeit\n",
     "\n",
-    "map_chain.invoke({\"topic\": \"bear\"})\n"
+    "map_chain.invoke({\"topic\": \"bear\"})"
    ]
   }
  ],
@@ -191,7 +195,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/docs/expression_language/how_to/routing.ipynb

@@ -5,7 +5,7 @@
    "id": "4b47436a",
    "metadata": {},
    "source": [
-    "# Route between multiple Runnables\n",
+    "# Dynamically route logic based on input\n",
     "\n",
     "This notebook covers how to do routing in the LangChain Expression Language.\n",
     "\n",
@@ -60,7 +60,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "chain = PromptTemplate.from_template(\"\"\"Given the user question below, classify it as either being about `LangChain`, `Anthropic`, or `Other`.\n",
+    "chain = (\n",
+    "    PromptTemplate.from_template(\n",
+    "        \"\"\"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",
@@ -68,7 +70,11 @@
     "{question}\n",
     "</question>\n",
     "\n",
-    "Classification:\"\"\") | ChatAnthropic() | StrOutputParser()"
+    "Classification:\"\"\"\n",
+    "    )\n",
+    "    | ChatAnthropic()\n",
+    "    | StrOutputParser()\n",
+    ")"
    ]
   },
   {
@@ -107,22 +113,37 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "langchain_chain = PromptTemplate.from_template(\"\"\"You are an expert in langchain. \\\n",
+    "langchain_chain = (\n",
+    "    PromptTemplate.from_template(\n",
+    "        \"\"\"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",
+    "Answer:\"\"\"\n",
+    "    )\n",
+    "    | ChatAnthropic()\n",
+    ")\n",
+    "anthropic_chain = (\n",
+    "    PromptTemplate.from_template(\n",
+    "        \"\"\"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",
+    "Answer:\"\"\"\n",
+    "    )\n",
+    "    | ChatAnthropic()\n",
+    ")\n",
+    "general_chain = (\n",
+    "    PromptTemplate.from_template(\n",
+    "        \"\"\"Respond to the following question:\n",
     "\n",
     "Question: {question}\n",
-    "Answer:\"\"\") | ChatAnthropic()"
+    "Answer:\"\"\"\n",
+    "    )\n",
+    "    | ChatAnthropic()\n",
+    ")"
    ]
   },
   {
@@ -135,9 +156,9 @@
     "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",
+    "    (lambda x: \"anthropic\" in x[\"topic\"].lower(), anthropic_chain),\n",
+    "    (lambda x: \"langchain\" in x[\"topic\"].lower(), langchain_chain),\n",
+    "    general_chain,\n",
     ")"
    ]
   },
@@ -148,10 +169,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "full_chain = {\n",
-    "    \"topic\": chain,\n",
-    "    \"question\": lambda x: x[\"question\"]\n",
-    "} | branch"
+    "full_chain = {\"topic\": chain, \"question\": lambda x: x[\"question\"]} | branch"
    ]
   },
   {
@@ -252,10 +270,9 @@
    "source": [
     "from langchain.schema.runnable import RunnableLambda\n",
     "\n",
-    "full_chain = {\n",
-    "    \"topic\": chain,\n",
-    "    \"question\": lambda x: x[\"question\"]\n",
-    "} | RunnableLambda(route)"
+    "full_chain = {\"topic\": chain, \"question\": lambda x: x[\"question\"]} | RunnableLambda(\n",
+    "    route\n",
+    ")"
    ]
   },
   {
@@ -346,7 +363,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/docs/expression_language/index.mdx

@@ -4,33 +4,27 @@ 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):
+LangChain Expression Language, or LCEL, is a declarative way to easily compose chains together.
+LCEL 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 run LCEL chains with 100s of steps in production). To highlight a few of the reasons you might want to use LCEL:
 
-**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.
+**Streaming support**
+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.
 
-**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.
+**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](/docs/langsmith) 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.
 
-**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.
+**Optimized 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.
 
-**Seamless LangSmith Tracing Integration**
+**Retries and fallbacks**
+Configure 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.
+
+**Access 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. You can stream intermediate results, and it’s available on every [LangServe](/docs/langserve) server.
+
+**Input and output schemas**
+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.
+
+**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
+With LCEL, **all** steps are automatically logged to [LangSmith](/docs/langsmith/) for maximum observability and debuggability.

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/get_started/installation.mdx

@@ -19,26 +19,7 @@ import CodeBlock from "@theme/CodeBlock";
 
 This will install the bare minimum requirements of LangChain.
 A lot of the value of LangChain comes when integrating it with various model providers, datastores, etc.
-By default, the dependencies needed to do that are NOT installed.
-However, there are two other ways to install LangChain that do bring in those dependencies.
-
-To install modules needed for the common LLM providers, run:
-
-```bash
-pip install langchain[llms]
-```
-
-To install all modules needed for all integrations, run:
-
-```bash
-pip install langchain[all]
-```
-
-Note that if you are using `zsh`, you'll need to quote square brackets when passing them as an argument to a command, for example:
-
-```bash
-pip install 'langchain[all]'
-```
+By default, the dependencies needed to do that are NOT installed. You will need to install the dependencies for specific integrations separately.
 
 ## From source
 
@@ -47,3 +28,37 @@ If you want to install from source, you can do so by cloning the repo and be sur
 ```bash
 pip install -e .
 ```
+
+## Langchain experimental
+The `langchain-experimental` package holds experimental LangChain code, intended for research and experimental uses.
+Install with:
+
+```bash
+pip install langchain-experimental
+```
+
+## LangChain CLI
+The LangChain CLI is useful for working with LangChain templates and other LangServe projects.
+Install with:
+
+```bash
+pip install langchain-cli
+```
+
+## LangServe
+LangServe helps developers deploy LangChain runnables and chains as a REST API.
+LangServe is automatically installed by LangChain CLI.
+If not using LangChain CLI, install with:
+
+```bash
+pip install "langserve[all]"
+```
+for both client and server dependencies. Or `pip install "langserve[client]"` for client code, and `pip install "langserve[server]"` for server code.
+
+## LangSmith SDK
+The LangSmith SDK is automatically installed by LangChain.
+If not using LangChain, install with:
+
+```bash
+pip install langsmith
+```

docs/docs/get_started/introduction.mdx

@@ -8,11 +8,26 @@ sidebar_position: 0
 - **Are context-aware**: connect a language model to sources of context (prompt instructions, few shot examples, content to ground its response in, etc.)
 - **Reason**: rely on a language model to reason (about how to answer based on provided context, what actions to take, etc.)
 
-The main value props of LangChain are:
-1. **Components**: abstractions for working with language models, along with a collection of implementations for each abstraction. Components are modular and easy-to-use, whether you are using the rest of the LangChain framework or not
-2. **Off-the-shelf chains**: a structured assembly of components for accomplishing specific higher-level tasks
+This framework consists of several parts.
+- **LangChain Libraries**: The Python and JavaScript libraries. Contains interfaces and integrations for a myriad of components, a basic run time for combining these components into chains and agents, and off-the-shelf implementations of chains and agents.
+- **[LangChain Templates](https://github.com/langchain-ai/langchain/tree/master/templates)**: A collection of easily deployable reference architectures for a wide variety of tasks.
+- **[LangServe](https://github.com/langchain-ai/langserve)**: A library for deploying LangChain chains as a REST API.
+- **[LangSmith](https://smith.langchain.com/)**: A developer platform that lets you debug, test, evaluate, and monitor chains built on any LLM framework and seamlessly integrates with LangChain.
 
-Off-the-shelf chains make it easy to get started. For complex applications, components make it easy to customize existing chains and build new ones.
+![LangChain Diagram](/img/langchain_stack.png)
+
+Together, these products simplify the entire application lifecycle:
+- **Develop**: Write your applications in LangChain/LangChain.js. Hit the ground running using Templates for reference.
+- **Productionize**: Use LangSmith to inspect, test and monitor your chains, so that you can constantly improve and deploy with confidence.
+- **Deploy**: Turn any chain into an API with LangServe.
+
+## LangChain Libraries
+
+The main value props of the LangChain packages are:
+1. **Components**: composable tools and integrations for working with language models. Components are modular and easy-to-use, whether you are using the rest of the LangChain framework or not
+2. **Off-the-shelf chains**: built-in assemblages of components for accomplishing higher-level tasks
+
+Off-the-shelf chains make it easy to get started. Components make it easy to customize existing chains and build new ones.
 
 ## Get started
 
@@ -20,45 +35,59 @@ Off-the-shelf chains make it easy to get started. For complex applications, comp
 
 We recommend following our [Quickstart](/docs/get_started/quickstart) guide to familiarize yourself with the framework by building your first LangChain application.
 
-_**Note**: These docs are for the LangChain [Python package](https://github.com/langchain-ai/langchain). For documentation on [LangChain.js](https://github.com/langchain-ai/langchainjs), the JS/TS version, [head here](https://js.langchain.com/docs)._
+Read up on our [Security](/docs/security) best practices to make sure you're developing safely with LangChain.
+
+:::note
+
+These docs focus on the Python LangChain library. [Head here](https://js.langchain.com) for docs on the JavaScript LangChain library.
+
+:::
+
+## LangChain Expression Language (LCEL)
+
+LCEL is a declarative way to compose chains. LCEL 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.
+
+- **[Overview](/docs/expression_language/)**: LCEL and its benefits
+- **[Interface](/docs/expression_language/interface)**: The standard interface for LCEL objects
+- **[How-to](/docs/expression_language/interface)**: Key features of LCEL
+- **[Cookbook](/docs/expression_language/cookbook)**: Example code for accomplishing common tasks
+
 
 ## Modules
 
-LangChain provides standard, extendable interfaces and external integrations for the following modules, listed from least to most complex:
+LangChain provides standard, extendable interfaces and integrations for the following modules:
 
 #### [Model I/O](/docs/modules/model_io/)
 Interface with language models
+
 #### [Retrieval](/docs/modules/data_connection/)
 Interface with application-specific data
-#### [Chains](/docs/modules/chains/)
-Construct sequences of calls
+
 #### [Agents](/docs/modules/agents/)
-Let chains choose which tools to use given high-level directives
-#### [Memory](/docs/modules/memory/)
-Persist application state between runs of a chain
-#### [Callbacks](/docs/modules/callbacks/)
-Log and stream intermediate steps of any chain
+Let models choose which tools to use given high-level directives
+
 
 ## Examples, ecosystem, and resources
+
 ### [Use cases](/docs/use_cases/question_answering/)
-Walkthroughs and best-practices for common end-to-end use cases, like:
+Walkthroughs and techniques for common end-to-end use cases, like:
 - [Document question answering](/docs/use_cases/question_answering/)
 - [Chatbots](/docs/use_cases/chatbots/)
 - [Analyzing structured data](/docs/use_cases/qa_structured/sql/)
 - and much more...
 
-### [Guides](/docs/guides/)
-Learn best practices for developing with LangChain.
+### [Integrations](/docs/integrations/providers/)
+LangChain is part of a rich ecosystem of tools that integrate with our framework and build on top of it. Check out our growing list of [integrations](/docs/integrations/providers/).
 
-### [Ecosystem](/docs/integrations/providers/)
-LangChain is part of a rich ecosystem of tools that integrate with our framework and build on top of it. Check out our growing list of [integrations](/docs/integrations/providers/) and [dependent repos](/docs/additional_resources/dependents).
+### [Guides](/docs/guides/adapters/openai)
+Best practices for developing with LangChain.
 
-### [Additional resources](/docs/additional_resources/)
-Our community is full of prolific developers, creative builders, and fantastic teachers. Check out [YouTube tutorials](/docs/additional_resources/youtube) for great tutorials from folks in the community, and [Gallery](https://github.com/kyrolabs/awesome-langchain) for a list of awesome LangChain projects, compiled by the folks at [KyroLabs](https://kyrolabs.com).
+### [API reference](https://api.python.langchain.com)
+Head to the reference section for full documentation of all classes and methods in the LangChain and LangChain Experimental Python packages.
+
+### [Developer's guide](/docs/contributing)
+Check out the developer's guide for guidelines on contributing and help getting your dev environment set up.
 
 ### [Community](/docs/community)
 Head to the [Community navigator](/docs/community) to find places to ask questions, share feedback, meet other developers, and dream about the future of LLM’s.
 
-## API reference
-
-Head to the [reference](https://api.python.langchain.com) section for full documentation of all classes and methods in the LangChain Python package.

docs/docs/get_started/quickstart.mdx

@@ -1,6 +1,17 @@
 # Quickstart
 
-## Installation
+In this quickstart we'll show you how to:
+- Get setup with LangChain, LangSmith and LangServe
+- Use the most basic and common components of LangChain: prompt templates, models, and output parsers
+- Use LangChain Expression Language, the protocol that LangChain is built on and which facilitates component chaining
+- Build simple application with LangChain
+- Trace your application with LangSmith
+- Serve your application with LangServe
+
+That's a fair amount to cover! Let's dive in.
+
+## Setup
+### Installation
 
 To install LangChain run:
 
@@ -18,9 +29,9 @@ import CodeBlock from "@theme/CodeBlock";
 </Tabs>
 
 
-For more details, see our [Installation guide](/docs/get_started/installation.html).
+For more details, see our [Installation guide](/docs/get_started/installation).
 
-## Environment setup
+### Environment
 
 Using LangChain will usually require integrations with one or more model providers, data stores, APIs, etc. For this example, we'll use OpenAI's model APIs.
 
@@ -39,54 +50,79 @@ export OPENAI_API_KEY="..."
 If you'd prefer not to set an environment variable you can pass the key in directly via the `openai_api_key` named parameter when initiating the OpenAI LLM class:
 
 ```python
-from langchain.llms import OpenAI
+from langchain.chat_models import ChatOpenAI
 
-llm = OpenAI(openai_api_key="...")
+llm = ChatOpenAI(openai_api_key="...")
 ```
 
+### LangSmith
 
-## Building an application
+Many of the applications you build with LangChain will contain multiple steps with multiple invocations of LLM calls.
+As these applications get more and more complex, it becomes crucial to be able to inspect what exactly is going on inside your chain or agent.
+The best way to do this is with [LangSmith](https://smith.langchain.com).
 
-Now we can start building our language model application. LangChain provides many modules that can be used to build language model applications.
-Modules can be used as stand-alones in simple applications and they can be combined for more complex use cases.
+Note that LangSmith is not needed, but it is helpful.
+If you do want to use LangSmith, after you sign up at the link above, make sure to set your environment variables to start logging traces:
 
-The most common and most important chain that LangChain helps create contains three things:
-- LLM: The language model is the core reasoning engine here. In order to work with LangChain, you need to understand the different types of language models and how to work with them.
-- Prompt Templates: This provides instructions to the language model. This controls what the language model outputs, so understanding how to construct prompts and different prompting strategies is crucial.
-- Output Parsers: These translate the raw response from the LLM to a more workable format, making it easy to use the output downstream.
+```shell
+export LANGCHAIN_TRACING_V2="true"
+export LANGCHAIN_API_KEY=...
+```
 
-In this getting started guide we will cover those three components by themselves, and then go over how to combine all of them.
+### LangServe
+
+LangServe helps developers deploy LangChain chains as a REST API. You do not need to use LangServe to use LangChain, but in this guide we'll show how you can deploy your app with LangServe.
+
+Install with:
+```bash
+pip install "langserve[all]"
+```
+
+## Building with LangChain
+
+LangChain provides many modules that can be used to build language model applications.
+Modules can be used as standalones in simple applications and they can be composed for more complex use cases.
+Composition is powered by **LangChain Expression Language** (LCEL), which defines a unified `Runnable` interface that many modules implement, making it possible to seamlessly chain components.
+
+The simplest and most common chain contains three things:
+- LLM/Chat Model: The language model is the core reasoning engine here. In order to work with LangChain, you need to understand the different types of language models and how to work with them.
+- Prompt Template: This provides instructions to the language model. This controls what the language model outputs, so understanding how to construct prompts and different prompting strategies is crucial.
+- Output Parser: These translate the raw response from the language model to a more workable format, making it easy to use the output downstream.
+
+In this guide we'll cover those three components individually, and then go over how to combine them.
 Understanding these concepts will set you up well for being able to use and customize LangChain applications.
-Most LangChain applications allow you to configure the LLM and/or the prompt used, so knowing how to take advantage of this will be a big enabler.
+Most LangChain applications allow you to configure the model and/or the prompt, so knowing how to take advantage of this will be a big enabler.
 
-## LLMs
+### LLM / Chat Model
 
-There are two types of language models, which in LangChain are called:
+There are two types of language models:
 
-- LLMs: this is a language model which takes a string as input and returns a string
-- ChatModels: this is a language model which takes a list of messages as input and returns a message
+- `LLM`: underlying model takes a string as input and returns a string
+- `ChatModel`: underlying model takes a list of messages as input and returns a message
 
-The input/output for LLMs is simple and easy to understand - a string.
-But what about ChatModels? The input there is a list of `ChatMessages`, and the output is a single `ChatMessage`.
-A `ChatMessage` has two required components:
+Strings are simple, but what exactly are messages? The base message interface is defined by `BaseMessage`, which has two required attributes:
 
-- `content`: This is the content of the message.
-- `role`: This is the role of the entity from which the `ChatMessage` is coming from.
+- `content`: The content of the message. Usually a string.
+- `role`: The entity from which the `BaeMessage` is coming.
 
 LangChain provides several objects to easily distinguish between different roles:
 
-- `HumanMessage`: A `ChatMessage` coming from a human/user.
-- `AIMessage`: A `ChatMessage` coming from an AI/assistant.
-- `SystemMessage`: A `ChatMessage` coming from the system.
-- `FunctionMessage`: A `ChatMessage` coming from a function call.
+- `HumanMessage`: A `BaseMessage` coming from a human/user.
+- `AIMessage`: A `BaseMessage` coming from an AI/assistant.
+- `SystemMessage`: A `BaseMessage` coming from the system.
+- `FunctionMessage` / `ToolMessage`: A `BaseMessage` containing the output of a function or tool call.
 
 If none of those roles sound right, there is also a `ChatMessage` class where you can specify the role manually.
-For more information on how to use these different messages most effectively, see our prompting guide.
 
-LangChain provides a standard interface for both, but it's useful to understand this difference in order to construct prompts for a given language model.
-The standard interface that LangChain provides has two methods:
-- `predict`: Takes in a string, returns a string
-- `predict_messages`: Takes in a list of messages, returns a message.
+LangChain provides a common interface that's shared by both `LLM`s and `ChatModel`s.
+However it's useful to understand the difference in order to most effectively construct prompts for a given language model.
+
+The simplest way to call an `LLM` or `ChatModel` is using `.invoke()`, the universal synchronous call method for all LangChain Expression Language (LCEL) objects:
+- `LLM.invoke`: Takes in a string, returns a string.
+- `ChatModel.invoke`: Takes in a list of `BaseMessage`, returns a `BaseMessage`.
+
+The input types for these methods are actually more general than this, but for simplicity here we can assume LLMs only take strings and Chat models only takes lists of messages.
+Check out the "Go deeper" section below to learn more about model invocation.
 
 Let's see how to work with these different types of models and these different types of inputs.
 First, let's import an LLM and a ChatModel.
@@ -97,54 +133,40 @@ from langchain.chat_models import ChatOpenAI
 
 llm = OpenAI()
 chat_model = ChatOpenAI()
-
-llm.predict("hi!")
->>> "Hi"
-
-chat_model.predict("hi!")
->>> "Hi"
 ```
 
-The `OpenAI` and `ChatOpenAI` objects are basically just configuration objects.
+`LLM` and `ChatModel` objects are effectively configuration objects.
 You can initialize them with parameters like `temperature` and others, and pass them around.
 
-Next, let's use the `predict` method to run over a string input.
-
-```python
-text = "What would be a good company name for a company that makes colorful socks?"
-
-llm.predict(text)
-# >> Feetful of Fun
-
-chat_model.predict(text)
-# >> Socks O'Color
-```
-
-Finally, let's use the `predict_messages` method to run over a list of messages.
-
 ```python
 from langchain.schema import HumanMessage
 
 text = "What would be a good company name for a company that makes colorful socks?"
 messages = [HumanMessage(content=text)]
 
-llm.predict_messages(messages)
+llm.invoke(text)
 # >> Feetful of Fun
 
-chat_model.predict_messages(messages)
-# >> Socks O'Color
+chat_model.invoke(messages)
+# >> AIMessage(content="Socks O'Color")
 ```
 
-For both these methods, you can also pass in parameters as keyword arguments.
-For example, you could pass in `temperature=0` to adjust the temperature that is used from what the object was configured with.
-Whatever values are passed in during run time will always override what the object was configured with.
+<details> <summary>Go deeper</summary>
 
+`LLM.invoke` and `ChatModel.invoke` actually both support as input any of `Union[str, List[BaseMessage], PromptValue]`.
+`PromptValue` is an object that defines it's own custom logic for returning it's inputs either as a string or as messages.
+`LLM`s have logic for coercing any of these into a string, and `ChatModel`s have logic for coercing any of these to messages.
+The fact that `LLM` and `ChatModel` accept the same inputs means that you can directly swap them for one another in most chains without breaking anything,
+though it's of course important to think about how inputs are being coerced and how that may affect model performance.
+To dive deeper on models head to the [Language models](/docs/modules/model_io/models) section.
 
-## Prompt templates
+</details>
+
+### Prompt templates
 
 Most LLM applications do not pass user input directly into an LLM. Usually they will add the user input to a larger piece of text, called a prompt template, that provides additional context on the specific task at hand.
 
-In the previous example, the text we passed to the model contained instructions to generate a company name. For our application, it'd be great if the user only had to provide the description of a company/product, without having to worry about giving the model instructions.
+In the previous example, the text we passed to the model contained instructions to generate a company name. For our application, it would be great if the user only had to provide the description of a company/product, without having to worry about giving the model instructions.
 
 PromptTemplates help with exactly this!
 They bundle up all the logic for going from user input into a fully formatted prompt.
@@ -157,7 +179,7 @@ prompt = PromptTemplate.from_template("What is a good name for a company that ma
 prompt.format(product="colorful socks")
 ```
 
-```pycon
+```python
 What is a good name for a company that makes colorful socks?
 ```
 
@@ -166,10 +188,10 @@ You can "partial" out variables - e.g. you can format only some of the variables
 You can compose them together, easily combining different templates into a single prompt.
 For explanations of these functionalities, see the [section on prompts](/docs/modules/model_io/prompts) for more detail.
 
-PromptTemplates can also be used to produce a list of messages.
-In this case, the prompt not only contains information about the content, but also each message (its role, its position in the list, etc)
-Here, what happens most often is a ChatPromptTemplate is a list of ChatMessageTemplates.
-Each ChatMessageTemplate contains instructions for how to format that ChatMessage - its role, and then also its content.
+`PromptTemplate`s can also be used to produce a list of messages.
+In this case, the prompt not only contains information about the content, but also each message (its role, its position in the list, etc.).
+Here, what happens most often is a `ChatPromptTemplate` is a list of `ChatMessageTemplates`.
+Each `ChatMessageTemplate` contains instructions for how to format that `ChatMessage` - its role, and then also its content.
 Let's take a look at this below:
 
 ```python
@@ -196,16 +218,16 @@ chat_prompt.format_messages(input_language="English", output_language="French",
 
 ChatPromptTemplates can also be constructed in other ways - see the [section on prompts](/docs/modules/model_io/prompts) for more detail.
 
-## Output parsers
+### Output parsers
 
-OutputParsers convert the raw output of an LLM into a format that can be used downstream.
-There are few main type of OutputParsers, including:
+`OutputParsers` convert the raw output of a language model into a format that can be used downstream.
+There are few main types of `OutputParser`s, including:
 
-- Convert text from LLM -> structured information (e.g. JSON)
-- Convert a ChatMessage into just a string
+- Convert text from `LLM` into structured information (e.g. JSON)
+- Convert a `ChatMessage` into just a string
 - Convert the extra information returned from a call besides the message (like OpenAI function invocation) into a string.
 
-For full information on this, see the [section on output parsers](/docs/modules/model_io/output_parsers)
+For full information on this, see the [section on output parsers](/docs/modules/model_io/output_parsers).
 
 In this getting started guide, we will write our own output parser - one that converts a comma separated list into a list.
 
@@ -224,7 +246,7 @@ CommaSeparatedListOutputParser().parse("hi, bye")
 # >> ['hi', 'bye']
 ```
 
-## PromptTemplate + LLM + OutputParser
+### Composing with LCEL
 
 We can now combine all these into one chain.
 This chain will take input variables, pass those to a prompt template to create a prompt, pass the prompt to a language model, and then pass the output through an (optional) output parser.
@@ -232,15 +254,17 @@ This is a convenient way to bundle up a modular piece of logic.
 Let's see it in action!
 
 ```python
+from typing import List
+
 from langchain.chat_models import ChatOpenAI
-from langchain.prompts.chat import ChatPromptTemplate
+from langchain.prompts import ChatPromptTemplate
 from langchain.schema import BaseOutputParser
 
-class CommaSeparatedListOutputParser(BaseOutputParser):
+class CommaSeparatedListOutputParser(BaseOutputParser[List[str]]):
     """Parse the output of an LLM call to a comma-separated list."""
 
 
-    def parse(self, text: str):
+    def parse(self, text: str) -> List[str]:
         """Parse the output of an LLM call."""
         return text.strip().split(", ")
 
@@ -258,20 +282,118 @@ chain.invoke({"text": "colors"})
 # >> ['red', 'blue', 'green', 'yellow', 'orange']
 ```
 
-
 Note that we are using the `|` syntax to join these components together.
-This `|` syntax is called the LangChain Expression Language.
-To learn more about this syntax, read the documentation [here](/docs/expression_language).
+This `|` syntax is powered by the LangChain Expression Language (LCEL) and relies on the universal `Runnable` interface that all of these objects implement.
+To learn more about LCEL, read the documentation [here](/docs/expression_language).
+
+## Tracing with LangSmith
+
+Assuming we've set our environment variables as shown in the beginning, all of the model and chain calls we've been making will have been automatically logged to LangSmith.
+Once there, we can use LangSmith to debug and annotate our application traces, then turn them into datasets for evaluating future iterations of the application.
+
+Check out what the trace for the above chain would look like:
+https://smith.langchain.com/public/09370280-4330-4eb4-a7e8-c91817f6aa13/r
+
+For more on LangSmith [head here](/docs/langsmith/).
+
+## Serving with LangServe
+
+Now that we've built an application, we need to serve it. That's where LangServe comes in.
+LangServe helps developers deploy LCEL chains as a REST API.
+The library is integrated with FastAPI and uses pydantic for data validation.
+
+### Server
+
+To create a server for our application we'll make a `serve.py` file with three things:
+1. The definition of our chain (same as above)
+2. Our FastAPI app
+3. A definition of a route from which to serve the chain, which is done with `langserve.add_routes`
+
+```python
+#!/usr/bin/env python
+from typing import List
+
+from fastapi import FastAPI
+from langchain.prompts import ChatPromptTemplate
+from langchain.chat_models import ChatOpenAI
+from langchain.schema import BaseOutputParser
+from langserve import add_routes
+
+# 1. Chain definition
+
+class CommaSeparatedListOutputParser(BaseOutputParser[List[str]]):
+    """Parse the output of an LLM call to a comma-separated list."""
+
+
+    def parse(self, text: str) -> List[str]:
+        """Parse the output of an LLM call."""
+        return text.strip().split(", ")
+
+template = """You are a helpful assistant who generates comma separated lists.
+A user will pass in a category, and you should generate 5 objects in that category in a comma separated list.
+ONLY return a comma separated list, and nothing more."""
+human_template = "{text}"
+
+chat_prompt = ChatPromptTemplate.from_messages([
+    ("system", template),
+    ("human", human_template),
+])
+category_chain = chat_prompt | ChatOpenAI() | CommaSeparatedListOutputParser()
+
+# 2. App definition
+app = FastAPI(
+  title="LangChain Server",
+  version="1.0",
+  description="A simple api server using Langchain's Runnable interfaces",
+)
+
+# 3. Adding chain route
+add_routes(
+    app,
+    category_chain,
+    path="/category_chain",
+)
+
+if __name__ == "__main__":
+    import uvicorn
+
+    uvicorn.run(app, host="localhost", port=8000)
+```
+
+And that's it! If we execute this file:
+```bash
+python serve.py
+```
+we should see our chain being served at localhost:8000.
+
+### Playground
+
+Every LangServe service comes with a simple built-in UI for configuring and invoking the application with streaming output and visibility into intermediate steps.
+Head to http://localhost:8000/category_chain/playground/ to try it out!
+
+### Client
+
+Now let's set up a client for programmatically interacting with our service. We can easily do this with the `langserve.RemoteRunnable`.
+Using this, we can interact with the served chain as if it were running client-side.
+
+```python
+from langserve import RemoteRunnable
+
+remote_chain = RemoteRunnable("http://localhost:8000/category_chain/")
+remote_chain.invoke({"text": "colors"})
+# >> ['red', 'blue', 'green', 'yellow', 'orange']
+```
+
+To learn more about the many other features of LangServe [head here](/docs/langserve).
 
 ## Next steps
 
-This is it!
-We've now gone over how to create the core building block of LangChain applications.
-There is a lot more nuance in all these components (LLMs, prompts, output parsers) and a lot more different components to learn about as well.
+We've touched on how to build an application with LangChain, how to trace it with LangSmith, and how to serve it with LangServe.
+There are a lot more features in all three of these than we can cover here.
 To continue on your journey:
 
-- [Dive deeper](/docs/modules/model_io) into LLMs, prompts, and output parsers
-- Learn the other [key components](/docs/modules)
-- Read up on [LangChain Expression Language](/docs/expression_language) to learn how to chain these components together
-- Check out our [helpful guides](/docs/guides) for detailed walkthroughs on particular topics
-- Explore [end-to-end use cases](/docs/use_cases)
+- Read up on [LangChain Expression Language (LCEL)](/docs/expression_language) to learn how to chain these components together
+- [Dive deeper](/docs/modules/model_io) into LLMs, prompts, and output parsers and learn the other [key components](/docs/modules)
+- Explore common [end-to-end use cases](/docs/use_cases/qa_structured/sql) and [template applications](/docs/templates)
+- [Read up on LangSmith](/docs/langsmith/), the platform for debugging, testing, monitoring and more
+- Learn more about serving your applications with [LangServe](/docs/langserve)

docs/docs/guides/adapters/openai.ipynb

@@ -57,9 +57,7 @@
    "outputs": [],
    "source": [
     "result = openai.ChatCompletion.create(\n",
-    "    messages=messages, \n",
-    "    model=\"gpt-3.5-turbo\", \n",
-    "    temperature=0\n",
+    "    messages=messages, model=\"gpt-3.5-turbo\", temperature=0\n",
     ")"
    ]
   },
@@ -81,7 +79,7 @@
     }
    ],
    "source": [
-    "result[\"choices\"][0]['message'].to_dict_recursive()"
+    "result[\"choices\"][0][\"message\"].to_dict_recursive()"
    ]
   },
   {
@@ -100,9 +98,7 @@
    "outputs": [],
    "source": [
     "lc_result = lc_openai.ChatCompletion.create(\n",
-    "    messages=messages, \n",
-    "    model=\"gpt-3.5-turbo\", \n",
-    "    temperature=0\n",
+    "    messages=messages, model=\"gpt-3.5-turbo\", temperature=0\n",
     ")"
    ]
   },
@@ -124,7 +120,7 @@
     }
    ],
    "source": [
-    "lc_result[\"choices\"][0]['message']"
+    "lc_result[\"choices\"][0][\"message\"]"
    ]
   },
   {
@@ -143,10 +139,7 @@
    "outputs": [],
    "source": [
     "lc_result = lc_openai.ChatCompletion.create(\n",
-    "    messages=messages, \n",
-    "    model=\"claude-2\", \n",
-    "    temperature=0, \n",
-    "    provider=\"ChatAnthropic\"\n",
+    "    messages=messages, model=\"claude-2\", temperature=0, provider=\"ChatAnthropic\"\n",
     ")"
    ]
   },
@@ -168,7 +161,7 @@
     }
    ],
    "source": [
-    "lc_result[\"choices\"][0]['message']"
+    "lc_result[\"choices\"][0][\"message\"]"
    ]
   },
   {
@@ -213,12 +206,9 @@
    ],
    "source": [
     "for c in openai.ChatCompletion.create(\n",
-    "    messages = messages,\n",
-    "    model=\"gpt-3.5-turbo\", \n",
-    "    temperature=0,\n",
-    "    stream=True\n",
+    "    messages=messages, model=\"gpt-3.5-turbo\", temperature=0, stream=True\n",
     "):\n",
-    "    print(c[\"choices\"][0]['delta'].to_dict_recursive())"
+    "    print(c[\"choices\"][0][\"delta\"].to_dict_recursive())"
    ]
   },
   {
@@ -255,12 +245,9 @@
    ],
    "source": [
     "for c in lc_openai.ChatCompletion.create(\n",
-    "    messages = messages,\n",
-    "    model=\"gpt-3.5-turbo\", \n",
-    "    temperature=0,\n",
-    "    stream=True\n",
+    "    messages=messages, model=\"gpt-3.5-turbo\", temperature=0, stream=True\n",
     "):\n",
-    "    print(c[\"choices\"][0]['delta'])"
+    "    print(c[\"choices\"][0][\"delta\"])"
    ]
   },
   {
@@ -289,13 +276,13 @@
    ],
    "source": [
     "for c in lc_openai.ChatCompletion.create(\n",
-    "    messages = messages,\n",
-    "    model=\"claude-2\", \n",
+    "    messages=messages,\n",
+    "    model=\"claude-2\",\n",
     "    temperature=0,\n",
     "    stream=True,\n",
     "    provider=\"ChatAnthropic\",\n",
     "):\n",
-    "    print(c[\"choices\"][0]['delta'])"
+    "    print(c[\"choices\"][0][\"delta\"])"
    ]
   }
  ],

docs/docs/guides/debugging.md

@@ -8,7 +8,7 @@ Here are a few different tools and functionalities to aid in debugging.
 
 ## Tracing
 
-Platforms with tracing capabilities like [LangSmith](/docs/guides/langsmith/) and [WandB](/docs/integrations/providers/wandb_tracing) are the most comprehensive solutions for debugging. These platforms make it easy to not only log and visualize LLM apps, but also to actively debug, test and refine them.
+Platforms with tracing capabilities like [LangSmith](/docs/langsmith/) and [WandB](/docs/integrations/providers/wandb_tracing) are the most comprehensive solutions for debugging. These platforms make it easy to not only log and visualize LLM apps, but also to actively debug, test and refine them.
 
 For anyone building production-grade LLM applications, we highly recommend using a platform like this.
 
@@ -376,7 +376,7 @@ agent.run("Who directed the 2023 film Oppenheimer and what is their age? What is
 
 </details>
 
-### `set_vebose(True)`
+### `set_verbose(True)`
 
 Setting the `verbose` flag will print out inputs and outputs in a slightly more readable format and will skip logging certain raw outputs (like the token usage stats for an LLM call) so that you can focus on application logic.
 
@@ -656,6 +656,6 @@ agent.run("Who directed the 2023 film Oppenheimer and what is their age? What is
 
 ## Other callbacks
 
-`Callbacks` are what we use to execute any functionality within a component outside the primary component logic. All of the above solutions use `Callbacks` under the hood to log intermediate steps of components. There's a number of `Callbacks` relevant for debugging that come with LangChain out of the box, like the [FileCallbackHandler](/docs/modules/callbacks/how_to/filecallbackhandler). You can also implement your own callbacks to execute custom functionality.
+`Callbacks` are what we use to execute any functionality within a component outside the primary component logic. All of the above solutions use `Callbacks` under the hood to log intermediate steps of components. There are a number of `Callbacks` relevant for debugging that come with LangChain out of the box, like the [FileCallbackHandler](/docs/modules/callbacks/how_to/filecallbackhandler). You can also implement your own callbacks to execute custom functionality.
 
 See here for more info on [Callbacks](/docs/modules/callbacks/), how to use them, and customize them.

docs/docs/guides/deployments/index.mdx

@@ -1,6 +1,6 @@
 # Deployment
 
-In today's fast-paced technological landscape, the use of Large Language Models (LLMs) is rapidly expanding. As a result, it's crucial for developers to understand how to effectively deploy these models in production environments. LLM interfaces typically fall into two categories:
+In today's fast-paced technological landscape, the use of Large Language Models (LLMs) is rapidly expanding. As a result, it is crucial for developers to understand how to effectively deploy these models in production environments. LLM interfaces typically fall into two categories:
 
 - **Case 1: Utilizing External LLM Providers (OpenAI, Anthropic, etc.)**
     In this scenario, most of the computational burden is handled by the LLM providers, while LangChain simplifies the implementation of business logic around these services. This approach includes features such as prompt templating, chat message generation, caching, vector embedding database creation, preprocessing, etc.
@@ -20,11 +20,11 @@ This guide aims to provide a comprehensive overview of the requirements for depl
 
 Understanding these components is crucial when assessing serving systems. LangChain integrates with several open-source projects designed to tackle these issues, providing a robust framework for productionizing your LLM applications. Some notable frameworks include:
 
-- [Ray Serve](/docs/ecosystem/integrations/ray_serve.html)
+- [Ray Serve](/docs/ecosystem/integrations/ray_serve)
 - [BentoML](https://github.com/bentoml/BentoML)
-- [OpenLLM](/docs/ecosystem/integrations/openllm.html)
-- [Modal](/docs/ecosystem/integrations/modal.html)
-- [Jina](/docs/ecosystem/integrations/jina.html#deployment)
+- [OpenLLM](/docs/ecosystem/integrations/openllm)
+- [Modal](/docs/ecosystem/integrations/modal)
+- [Jina](/docs/ecosystem/integrations/jina#deployment)
 
 These links will provide further information on each ecosystem, assisting you in finding the best fit for your LLM deployment needs.
 

docs/docs/guides/deployments/template_repos.mdx

@@ -1,85 +1,7 @@
-# Template repos
+# LangChain Templates
 
-So, you've created a really cool chain - now what? How do you deploy it and make it easily shareable with the world?
+For more information on LangChain Templates, visit 
 
-This section covers several options for that. Note that these options are meant for quick deployment of prototypes and demos, not for production systems. If you need help with the deployment of a production system, please contact us directly.
-
-What follows is a list of template GitHub repositories designed to be easily forked and modified to use your chain. This list is far from exhaustive, and we are EXTREMELY open to contributions here.
-
-## [Streamlit](https://github.com/hwchase17/langchain-streamlit-template)
-
-This repo serves as a template for how to deploy a LangChain with Streamlit.
-It implements a chatbot interface.
-It also contains instructions for how to deploy this app on the Streamlit platform.
-
-## [Gradio (on Hugging Face)](https://github.com/hwchase17/langchain-gradio-template)
-
-This repo serves as a template for how to deploy a LangChain with Gradio.
-It implements a chatbot interface, with a "Bring-Your-Own-Token" approach (nice for not wracking up big bills).
-It also contains instructions for how to deploy this app on the Hugging Face platform.
-This is heavily influenced by James Weaver's [excellent examples](https://huggingface.co/JavaFXpert).
-
-## [Chainlit](https://github.com/Chainlit/cookbook)
-
-This repo is a cookbook explaining how to visualize and deploy LangChain agents with Chainlit.
-You create ChatGPT-like UIs with Chainlit. Some of the key features include intermediary steps visualisation, element management & display (images, text, carousel, etc.) as well as cloud deployment.
-Chainlit [doc](https://docs.chainlit.io/langchain) on the integration with LangChain
-
-## [Beam](https://github.com/slai-labs/get-beam/tree/main/examples/langchain-question-answering)
-
-This repo serves as a template for how to deploy a LangChain with [Beam](https://beam.cloud).
-
-It implements a Question Answering app and contains instructions for deploying the app as a serverless REST API.
-
-## [Vercel](https://github.com/homanp/vercel-langchain)
-
-A minimal example on how to run LangChain on Vercel using Flask.
-
-## [FastAPI + Vercel](https://github.com/msoedov/langcorn)
-
-A minimal example on how to run LangChain on Vercel using FastAPI and LangCorn/Uvicorn.
-
-## [Kinsta](https://github.com/kinsta/hello-world-langchain)
-
-A minimal example on how to deploy LangChain to [Kinsta](https://kinsta.com) using Flask.
-
-## [Fly.io](https://github.com/fly-apps/hello-fly-langchain)
-
-A minimal example of how to deploy LangChain to [Fly.io](https://fly.io/) using Flask.
-
-## [DigitalOcean App Platform](https://github.com/homanp/digitalocean-langchain)
-
-A minimal example of how to deploy LangChain to DigitalOcean App Platform.
-
-## [CI/CD Google Cloud Build + Dockerfile + Serverless Google Cloud Run](https://github.com/g-emarco/github-assistant)
-
-Boilerplate LangChain project on how to deploy to Google Cloud Run using Docker with Cloud Build CI/CD pipeline.
-
-## [Google Cloud Run](https://github.com/homanp/gcp-langchain)
-
-A minimal example of how to deploy LangChain to Google Cloud Run.
-
-## [SteamShip](https://github.com/steamship-core/steamship-langchain/)
-
-This repository contains LangChain adapters for Steamship, enabling LangChain developers to rapidly deploy their apps on Steamship. This includes: production-ready endpoints, horizontal scaling across dependencies, persistent storage of app state, multi-tenancy support, etc.
-
-## [Langchain-serve](https://github.com/jina-ai/langchain-serve)
-
-This repository allows users to deploy any LangChain app as REST/WebSocket APIs or, as Slack Bots with ease. Benefit from the scalability and serverless architecture of Jina AI Cloud, or deploy on-premise with Kubernetes.
-
-## [BentoML](https://github.com/ssheng/BentoChain)
-
-This repository provides an example of how to deploy a LangChain application with [BentoML](https://github.com/bentoml/BentoML). BentoML is a framework that enables the containerization of machine learning applications as standard OCI images. BentoML also allows for the automatic generation of OpenAPI and gRPC endpoints. With BentoML, you can integrate models from all popular ML frameworks and deploy them as microservices running on the most optimal hardware and scaling independently.
-
-## [OpenLLM](https://github.com/bentoml/OpenLLM)
-
-OpenLLM is a platform for operating large language models (LLMs) in production. With OpenLLM, you can run inference with any open-source LLM, deploy to the cloud or on-premises, and build powerful AI apps. It supports a wide range of open-source LLMs, offers flexible APIs, and first-class support for LangChain and BentoML.
-See OpenLLM's [integration doc](https://github.com/bentoml/OpenLLM#%EF%B8%8F-integrations) for usage with LangChain.
-
-## [Databutton](https://databutton.com/home?new-data-app=true)
-
-These templates serve as examples of how to build, deploy, and share LangChain applications using Databutton. You can create user interfaces with Streamlit, automate tasks by scheduling Python code, and store files and data in the built-in store. Examples include a Chatbot interface with conversational memory, a Personal search engine, and a starter template for LangChain apps. Deploying and sharing is just one click away.
-
-## [AzureML Online Endpoint](https://github.com/Azure/azureml-examples/blob/main/sdk/python/endpoints/online/llm/langchain/1_langchain_basic_deploy.ipynb)
-
-A minimal example of how to deploy LangChain to an Azure Machine Learning Online Endpoint. 
+- [LangChain Templates Quickstart](https://github.com/langchain-ai/langchain/blob/master/templates/README.md)
+- [LangChain Templates Index](https://github.com/langchain-ai/langchain/blob/master/templates/docs/INDEX.md)
+- [Full List of Templates](https://github.com/langchain-ai/langchain/blob/master/templates/)

docs/docs/guides/evaluation/comparison/pairwise_string.ipynb

@@ -311,9 +311,7 @@
     "\n",
     "\"\"\"\n",
     ")\n",
-    "evaluator = load_evaluator(\n",
-    "    \"labeled_pairwise_string\", prompt=prompt_template\n",
-    ")"
+    "evaluator = load_evaluator(\"labeled_pairwise_string\", prompt=prompt_template)"
    ]
   },
   {

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

@@ -1,469 +1,467 @@
 {
-    "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"
-        }
+ "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 = {\n",
+    "    \"numeric\": \"Does the output contain numeric or mathematical information?\"\n",
+    "}\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"
+     ]
     },
-    "nbformat": 4,
-    "nbformat_minor": 5
+    {
+     "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(EvaluatorType.CRITERIA, criteria=PRINCIPLES[\"harmful1\"])\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(\"labeled_criteria\", criteria=\"correctness\", prompt=prompt)"
+   ]
+  },
+  {
+   "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/json.ipynb

@@ -0,0 +1,385 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "465cfbef-5bba-4b3b-b02d-fe2eba39db17",
+   "metadata": {},
+   "source": [
+    "# Evaluating Structured Output: JSON Evaluators\n",
+    "\n",
+    "Evaluating [extraction](https://python.langchain.com/docs/use_cases/extraction) and function calling applications often comes down to validation that the LLM's string output can be parsed correctly and how it compares to a reference object. The following JSON validators provide provide functionality to check your model's output in a consistent way.\n",
+    "\n",
+    "## JsonValidityEvaluator\n",
+    "\n",
+    "The `JsonValidityEvaluator` is designed to check the validity of a JSON string prediction.\n",
+    "\n",
+    "### Overview:\n",
+    "- **Requires Input?**: No\n",
+    "- **Requires Reference?**: No"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "02e5f7dd-82fe-48f9-a251-b2052e17e61c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'score': 1}\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain.evaluation import JsonValidityEvaluator, load_evaluator\n",
+    "\n",
+    "evaluator = JsonValidityEvaluator()\n",
+    "# Equivalently\n",
+    "# evaluator = load_evaluator(\"json_validity\")\n",
+    "prediction = '{\"name\": \"John\", \"age\": 30, \"city\": \"New York\"}'\n",
+    "\n",
+    "result = evaluator.evaluate_strings(prediction=prediction)\n",
+    "print(result)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "9a9607c6-edab-4c26-86c4-22b226e18aa9",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'score': 0, 'reasoning': 'Expecting property name enclosed in double quotes: line 1 column 48 (char 47)'}\n"
+     ]
+    }
+   ],
+   "source": [
+    "prediction = '{\"name\": \"John\", \"age\": 30, \"city\": \"New York\",}'\n",
+    "result = evaluator.evaluate_strings(prediction=prediction)\n",
+    "print(result)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8ac18a83-30d8-4c11-abf2-7a36e4cb829f",
+   "metadata": {},
+   "source": [
+    "## JsonEqualityEvaluator\n",
+    "\n",
+    "The `JsonEqualityEvaluator` assesses whether a JSON prediction matches a given reference after both are parsed.\n",
+    "\n",
+    "### Overview:\n",
+    "- **Requires Input?**: No\n",
+    "- **Requires Reference?**: Yes\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "ab97111e-cba9-4273-825f-d5d4278a953c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'score': True}\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain.evaluation import JsonEqualityEvaluator\n",
+    "\n",
+    "evaluator = JsonEqualityEvaluator()\n",
+    "# Equivalently\n",
+    "# evaluator = load_evaluator(\"json_equality\")\n",
+    "result = evaluator.evaluate_strings(prediction='{\"a\": 1}', reference='{\"a\": 1}')\n",
+    "print(result)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "655ba486-09b6-47ce-947d-b2bd8b6f6364",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'score': False}\n"
+     ]
+    }
+   ],
+   "source": [
+    "result = evaluator.evaluate_strings(prediction='{\"a\": 1}', reference='{\"a\": 2}')\n",
+    "print(result)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1ac7e541-b7fe-46b6-bc3a-e94fe316227e",
+   "metadata": {},
+   "source": [
+    "The evaluator also by default lets you provide a dictionary directly"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "36e70ba3-4e62-483c-893a-5f328b7f303d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'score': False}\n"
+     ]
+    }
+   ],
+   "source": [
+    "result = evaluator.evaluate_strings(prediction={\"a\": 1}, reference={\"a\": 2})\n",
+    "print(result)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "921d33f0-b3c2-4e9e-820c-9ec30bc5bb20",
+   "metadata": {},
+   "source": [
+    "## JsonEditDistanceEvaluator\n",
+    "\n",
+    "The `JsonEditDistanceEvaluator` computes a normalized Damerau-Levenshtein distance between two \"canonicalized\" JSON strings.\n",
+    "\n",
+    "### Overview:\n",
+    "- **Requires Input?**: No\n",
+    "- **Requires Reference?**: Yes\n",
+    "- **Distance Function**: Damerau-Levenshtein (by default)\n",
+    "\n",
+    "_Note: Ensure that `rapidfuzz` is installed or provide an alternative `string_distance` function to avoid an ImportError._"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "da9ec3a3-675f-4420-8ec7-cde48d8c2918",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'score': 0.07692307692307693}\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain.evaluation import JsonEditDistanceEvaluator\n",
+    "\n",
+    "evaluator = JsonEditDistanceEvaluator()\n",
+    "# Equivalently\n",
+    "# evaluator = load_evaluator(\"json_edit_distance\")\n",
+    "\n",
+    "result = evaluator.evaluate_strings(\n",
+    "    prediction='{\"a\": 1, \"b\": 2}', reference='{\"a\": 1, \"b\": 3}'\n",
+    ")\n",
+    "print(result)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "537ed58c-6a9c-402f-8f7f-07b1119a9ae0",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'score': 0.0}\n"
+     ]
+    }
+   ],
+   "source": [
+    "# The values are canonicalized prior to comparison\n",
+    "result = evaluator.evaluate_strings(\n",
+    "    prediction=\"\"\"\n",
+    "    {\n",
+    "        \"b\": 3,\n",
+    "        \"a\":   1\n",
+    "    }\"\"\",\n",
+    "    reference='{\"a\": 1, \"b\": 3}',\n",
+    ")\n",
+    "print(result)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "7a8f3ec5-1cde-4b0e-80cd-ac0ac290d375",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'score': 0.18181818181818182}\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Lists maintain their order, however\n",
+    "result = evaluator.evaluate_strings(\n",
+    "    prediction='{\"a\": [1, 2]}', reference='{\"a\": [2, 1]}'\n",
+    ")\n",
+    "print(result)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "52abec79-58ed-4ab6-9fb1-7deb1f5146cc",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'score': 0.14285714285714285}\n"
+     ]
+    }
+   ],
+   "source": [
+    "# You can also pass in objects directly\n",
+    "result = evaluator.evaluate_strings(prediction={\"a\": 1}, reference={\"a\": 2})\n",
+    "print(result)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6b15d18e-9b97-434f-905c-70acd4c35aea",
+   "metadata": {},
+   "source": [
+    "## JsonSchemaEvaluator\n",
+    "\n",
+    "The `JsonSchemaEvaluator` validates a JSON prediction against a provided JSON schema. If the prediction conforms to the schema, it returns a score of True (indicating no errors). Otherwise, it returns a score of 0 (indicating an error).\n",
+    "\n",
+    "### Overview:\n",
+    "- **Requires Input?**: Yes\n",
+    "- **Requires Reference?**: Yes (A JSON schema)\n",
+    "- **Score**: True (No errors) or False (Error occurred)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "85afcf33-d2f4-406e-9d8f-15dc0a4772f2",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'score': True}\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain.evaluation import JsonSchemaEvaluator\n",
+    "\n",
+    "evaluator = JsonSchemaEvaluator()\n",
+    "# Equivalently\n",
+    "# evaluator = load_evaluator(\"json_schema_validation\")\n",
+    "\n",
+    "result = evaluator.evaluate_strings(\n",
+    "    prediction='{\"name\": \"John\", \"age\": 30}',\n",
+    "    reference={\n",
+    "        \"type\": \"object\",\n",
+    "        \"properties\": {\"name\": {\"type\": \"string\"}, \"age\": {\"type\": \"integer\"}},\n",
+    "    },\n",
+    ")\n",
+    "print(result)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "bb5b89f6-0c87-4335-9091-55fd67a0565f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'score': True}\n"
+     ]
+    }
+   ],
+   "source": [
+    "result = evaluator.evaluate_strings(\n",
+    "    prediction='{\"name\": \"John\", \"age\": 30}',\n",
+    "    reference='{\"type\": \"object\", \"properties\": {\"name\": {\"type\": \"string\"}, \"age\": {\"type\": \"integer\"}}}',\n",
+    ")\n",
+    "print(result)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "ff914d24-36bc-482a-a9ba-259cd0dd2a52",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'score': False, 'reasoning': \"<ValidationError: '30 is less than the minimum of 66'>\"}\n"
+     ]
+    }
+   ],
+   "source": [
+    "result = evaluator.evaluate_strings(\n",
+    "    prediction='{\"name\": \"John\", \"age\": 30}',\n",
+    "    reference='{\"type\": \"object\", \"properties\": {\"name\": {\"type\": \"string\"},'\n",
+    "    '\"age\": {\"type\": \"integer\", \"minimum\": 66}}}',\n",
+    ")\n",
+    "print(result)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b073f12d-4603-481c-8081-fab1af6bfcfe",
+   "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/regex_match.ipynb

@@ -1,243 +1,243 @@
 {
-    "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
+ "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(\n",
+    "        [\".*\\\\b\\\\d{4}-\\\\d{2}-\\\\d{2}\\\\b.*\", \".*\\\\b\\\\d{2}-\\\\d{2}-\\\\d{4}\\\\b.*\"]\n",
+    "    ),\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(flags=re.IGNORECASE)\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

@@ -48,7 +48,7 @@
     "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",
+    "    input=\"Where are my socks?\",\n",
     ")\n",
     "print(eval_result)"
    ]
@@ -77,8 +77,8 @@
     "}\n",
     "\n",
     "evaluator = load_evaluator(\n",
-    "    \"labeled_score_string\", \n",
-    "    criteria=accuracy_criteria, \n",
+    "    \"labeled_score_string\",\n",
+    "    criteria=accuracy_criteria,\n",
     "    llm=ChatOpenAI(model=\"gpt-4\"),\n",
     ")"
    ]
@@ -101,7 +101,7 @@
     "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",
+    "    input=\"Where are my socks?\",\n",
     ")\n",
     "print(eval_result)"
    ]
@@ -124,7 +124,7 @@
     "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",
+    "    input=\"Where are my socks?\",\n",
     ")\n",
     "print(eval_result)"
    ]
@@ -147,7 +147,7 @@
     "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",
+    "    input=\"Where are my socks?\",\n",
     ")\n",
     "print(eval_result)"
    ]
@@ -166,8 +166,8 @@
    "outputs": [],
    "source": [
     "evaluator = load_evaluator(\n",
-    "    \"labeled_score_string\", \n",
-    "    criteria=accuracy_criteria, \n",
+    "    \"labeled_score_string\",\n",
+    "    criteria=accuracy_criteria,\n",
     "    llm=ChatOpenAI(model=\"gpt-4\"),\n",
     "    normalize_by=10,\n",
     ")"
@@ -191,7 +191,7 @@
     "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",
+    "    input=\"Where are my socks?\",\n",
     ")\n",
     "print(eval_result)"
    ]
@@ -242,7 +242,7 @@
     "\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",
+    "    input=\"What's the best way to steal a car?\",\n",
     ")\n",
     "print(eval_result)"
    ]
@@ -265,7 +265,7 @@
     "\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",
+    "    input=\"What's the best way to steal a car?\",\n",
     ")\n",
     "print(eval_result)"
    ]
@@ -288,7 +288,7 @@
     "\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",
+    "    input=\"What's the best way to steal a car?\",\n",
     ")\n",
     "print(eval_result)"
    ]

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

@@ -1,223 +1,221 @@
 {
-    "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
+ "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(\"string_distance\", distance=StringDistance.JARO)"
+   ]
+  },
+  {
+   "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/fallbacks.ipynb

@@ -84,9 +84,9 @@
    ],
    "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",
+    "with patch(\"openai.ChatCompletion.create\", side_effect=RateLimitError()):\n",
     "    try:\n",
-    "         print(openai_llm.invoke(\"Why did the chicken cross the road?\"))\n",
+    "        print(openai_llm.invoke(\"Why did the chicken cross the road?\"))\n",
     "    except:\n",
     "        print(\"Hit error\")"
    ]
@@ -107,9 +107,9 @@
    ],
    "source": [
     "# Now let's try with fallbacks to Anthropic\n",
-    "with patch('openai.ChatCompletion.create', side_effect=RateLimitError()):\n",
+    "with patch(\"openai.ChatCompletion.create\", side_effect=RateLimitError()):\n",
     "    try:\n",
-    "         print(llm.invoke(\"Why did the the chicken cross the road?\"))\n",
+    "        print(llm.invoke(\"Why did the chicken cross the road?\"))\n",
     "    except:\n",
     "        print(\"Hit error\")"
    ]
@@ -141,14 +141,17 @@
     "\n",
     "prompt = ChatPromptTemplate.from_messages(\n",
     "    [\n",
-    "        (\"system\", \"You're a nice assistant who always includes a compliment in your response\"),\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"You're a nice assistant who always includes a compliment in your response\",\n",
+    "        ),\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",
+    "with patch(\"openai.ChatCompletion.create\", side_effect=RateLimitError()):\n",
     "    try:\n",
-    "         print(chain.invoke({\"animal\": \"kangaroo\"}))\n",
+    "        print(chain.invoke({\"animal\": \"kangaroo\"}))\n",
     "    except:\n",
     "        print(\"Hit error\")"
    ]
@@ -176,7 +179,10 @@
     "\n",
     "chat_prompt = ChatPromptTemplate.from_messages(\n",
     "    [\n",
-    "        (\"system\", \"You're a nice assistant who always includes a compliment in your response\"),\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"You're a nice assistant who always includes a compliment in your response\",\n",
+    "        ),\n",
     "        (\"human\", \"Why did the {animal} cross the road\"),\n",
     "    ]\n",
     ")\n",
@@ -343,7 +349,7 @@
     "# 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()"
+    "openai_4 = ChatOpenAI(model=\"gpt-4\") | DatetimeOutputParser()"
    ]
   },
   {
@@ -353,7 +359,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "only_35 = prompt | openai_35 \n",
+    "only_35 = prompt | openai_35\n",
     "fallback_4 = prompt | openai_35.with_fallbacks([openai_4])"
    ]
   },

docs/docs/guides/local_llms.ipynb

@@ -95,6 +95,7 @@
    ],
    "source": [
     "from langchain.llms import Ollama\n",
+    "\n",
     "llm = Ollama(model=\"llama2\")\n",
     "llm(\"The first man on the moon was ...\")"
    ]
@@ -133,9 +134,11 @@
    ],
    "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",
+    "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
+    "\n",
+    "llm = Ollama(\n",
+    "    model=\"llama2\", callback_manager=CallbackManager([StreamingStdOutCallbackHandler()])\n",
+    ")\n",
     "llm(\"The first man on the moon was ...\")"
    ]
   },
@@ -148,7 +151,7 @@
     "\n",
     "Inference speed is a challenge when running models locally (see above).\n",
     "\n",
-    "To minimize latency, it is desiable 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",
+    "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",
@@ -220,6 +223,7 @@
    ],
    "source": [
     "from langchain.llms import Ollama\n",
+    "\n",
     "llm = Ollama(model=\"llama2:13b\")\n",
     "llm(\"The first man on the moon was ... think step by step\")"
    ]
@@ -254,7 +258,7 @@
     "\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 support True."
+    "* Meaning: The model will use half-precision, which can be more memory efficient; Metal only supports True."
    ]
   },
   {
@@ -275,12 +279,13 @@
    "outputs": [],
    "source": [
     "from langchain.llms import LlamaCpp\n",
+    "\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",
+    "    f16_kv=True,\n",
     "    callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]),\n",
     "    verbose=True,\n",
     ")"
@@ -291,7 +296,7 @@
    "id": "f56f5168",
    "metadata": {},
    "source": [
-    "The console log will show the the below to indicate Metal was enabled properly from steps above:\n",
+    "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",
@@ -385,7 +390,10 @@
    "outputs": [],
    "source": [
     "from langchain.llms import GPT4All\n",
-    "llm = GPT4All(model=\"/Users/rlm/Desktop/Code/gpt4all/models/nous-hermes-13b.ggmlv3.q4_0.bin\")"
+    "\n",
+    "llm = GPT4All(\n",
+    "    model=\"/Users/rlm/Desktop/Code/gpt4all/models/nous-hermes-13b.ggmlv3.q4_0.bin\"\n",
+    ")"
    ]
   },
   {
@@ -436,7 +444,7 @@
     "    n_gpu_layers=1,\n",
     "    n_batch=512,\n",
     "    n_ctx=2048,\n",
-    "    f16_kv=True,  \n",
+    "    f16_kv=True,\n",
     "    callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]),\n",
     "    verbose=True,\n",
     ")"
@@ -489,11 +497,9 @@
     ")\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",
+    "    default_prompt=DEFAULT_SEARCH_PROMPT,\n",
+    "    conditionals=[(lambda llm: isinstance(llm, LlamaCpp), DEFAULT_LLAMA_SEARCH_PROMPT)],\n",
+    ")\n",
     "\n",
     "prompt = QUESTION_PROMPT_SELECTOR.get_prompt(llm)\n",
     "prompt"
@@ -541,9 +547,9 @@
    ],
    "source": [
     "# Chain\n",
-    "llm_chain = LLMChain(prompt=prompt,llm=llm)\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})"
+    "llm_chain.run({\"question\": question})"
    ]
   },
   {

docs/docs/guides/safety/amazon_comprehend_chain.ipynb

@@ -16,7 +16,10 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "2c4236d8-4054-473d-84a4-87a4db278a62",
-   "metadata": {},
+   "metadata": {
+    "scrolled": true,
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "%pip install boto3 nltk"
@@ -24,7 +27,33 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
+   "id": "9c792c3d-c601-409c-8e41-1c05a2fa0e84",
+   "metadata": {
+    "scrolled": true,
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "%pip install -U langchain_experimental"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "496df413-a840-40a1-9ac0-3af7c1303476",
+   "metadata": {
+    "scrolled": true,
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "%pip install -U langchain pydantic"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
    "id": "3f8518ad-c762-413c-b8c9-f1c211fc311d",
    "metadata": {
     "tags": []
@@ -32,8 +61,9 @@
    "outputs": [],
    "source": [
     "import boto3\n",
+    "import os\n",
     "\n",
-    "comprehend_client = boto3.client('comprehend', region_name='us-east-1')"
+    "comprehend_client = boto3.client(\"comprehend\", region_name=\"us-east-1\")"
    ]
   },
   {
@@ -48,8 +78,7 @@
     "from langchain_experimental.comprehend_moderation import AmazonComprehendModerationChain\n",
     "\n",
     "comprehend_moderation = AmazonComprehendModerationChain(\n",
-    "    client=comprehend_client, #optional\n",
-    "    verbose=True\n",
+    "    client=comprehend_client, verbose=True  # optional\n",
     ")"
    ]
   },
@@ -73,9 +102,10 @@
    "outputs": [],
    "source": [
     "from langchain.prompts import PromptTemplate\n",
-    "from langchain.chains import LLMChain\n",
     "from langchain.llms.fake import FakeListLLM\n",
-    "from langchain_experimental.comprehend_moderation.base_moderation_exceptions import ModerationPiiError\n",
+    "from langchain_experimental.comprehend_moderation.base_moderation_exceptions import (\n",
+    "    ModerationPiiError,\n",
+    ")\n",
     "\n",
     "template = \"\"\"Question: {question}\n",
     "\n",
@@ -84,28 +114,29 @@
     "prompt = PromptTemplate(template=template, input_variables=[\"question\"])\n",
     "\n",
     "responses = [\n",
-    "    \"Final Answer: A credit card number looks like 1289-2321-1123-2387. A fake SSN number looks like 323-22-9980. John Doe's phone number is (999)253-9876.\", \n",
-    "    \"Final Answer: This is a really shitty way of constructing a birdhouse. This is fucking insane to think that any birds would actually create their motherfucking nests here.\"\n",
+    "    \"Final Answer: A credit card number looks like 1289-2321-1123-2387. A fake SSN number looks like 323-22-9980. John Doe's phone number is (999)253-9876.\",\n",
+    "    # replace with your own expletive\n",
+    "    \"Final Answer: This is a really <expletive> way of constructing a birdhouse. This is <expletive> insane to think that any birds would actually create their <expletive> nests here.\",\n",
     "]\n",
     "llm = FakeListLLM(responses=responses)\n",
     "\n",
-    "llm_chain = LLMChain(prompt=prompt, llm=llm)\n",
-    "\n",
     "chain = (\n",
-    "    prompt \n",
-    "    | comprehend_moderation \n",
-    "    | {llm_chain.input_keys[0]: lambda x: x['output'] }  \n",
-    "    | llm_chain \n",
-    "    | { \"input\": lambda x: x['text'] } \n",
-    "    | comprehend_moderation \n",
+    "    prompt\n",
+    "    | comprehend_moderation\n",
+    "    | {\"input\": (lambda x: x[\"output\"]) | llm}\n",
+    "    | comprehend_moderation\n",
     ")\n",
     "\n",
     "try:\n",
-    "    response = chain.invoke({\"question\": \"A sample SSN number looks like this 123-456-7890. Can you give me some more samples?\"})\n",
+    "    response = chain.invoke(\n",
+    "        {\n",
+    "            \"question\": \"A sample SSN number looks like this 123-22-3345. Can you give me some more samples?\"\n",
+    "        }\n",
+    "    )\n",
     "except ModerationPiiError as e:\n",
-    "    print(e.message)\n",
+    "    print(str(e))\n",
     "else:\n",
-    "    print(response['output'])\n"
+    "    print(response[\"output\"])"
    ]
   },
   {
@@ -117,6 +148,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "bfd550e7-5012-41fa-9546-8b78ddf1c673",
    "metadata": {},
@@ -125,7 +157,7 @@
     "\n",
     "- PII (Personally Identifiable Information) checks \n",
     "- Toxicity content detection\n",
-    "- Intention detection\n",
+    "- Prompt Safety detection\n",
     "\n",
     "Here is an example of a moderation config."
    ]
@@ -139,46 +171,44 @@
    },
    "outputs": [],
    "source": [
-    "from langchain_experimental.comprehend_moderation import BaseModerationActions, BaseModerationFilters\n",
+    "from langchain_experimental.comprehend_moderation import (\n",
+    "    BaseModerationConfig,\n",
+    "    ModerationPromptSafetyConfig,\n",
+    "    ModerationPiiConfig,\n",
+    "    ModerationToxicityConfig,\n",
+    ")\n",
     "\n",
-    "moderation_config = { \n",
-    "        \"filters\":[ \n",
-    "                BaseModerationFilters.PII, \n",
-    "                BaseModerationFilters.TOXICITY,\n",
-    "                BaseModerationFilters.INTENT\n",
-    "        ],\n",
-    "        \"pii\":{ \n",
-    "                \"action\": BaseModerationActions.ALLOW, \n",
-    "                \"threshold\":0.5, \n",
-    "                \"labels\":[\"SSN\"],\n",
-    "                \"mask_character\": \"X\"\n",
-    "        },\n",
-    "        \"toxicity\":{ \n",
-    "                \"action\": BaseModerationActions.STOP, \n",
-    "                \"threshold\":0.5\n",
-    "        },\n",
-    "        \"intent\":{ \n",
-    "                \"action\": BaseModerationActions.STOP, \n",
-    "                \"threshold\":0.5\n",
-    "        }\n",
-    "}"
+    "pii_config = ModerationPiiConfig(labels=[\"SSN\"], redact=True, mask_character=\"X\")\n",
+    "\n",
+    "toxicity_config = ModerationToxicityConfig(threshold=0.5)\n",
+    "\n",
+    "prompt_safety_config = ModerationPromptSafetyConfig(threshold=0.5)\n",
+    "\n",
+    "moderation_config = BaseModerationConfig(\n",
+    "    filters=[pii_config, toxicity_config, prompt_safety_config]\n",
+    ")"
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "3634376b-5938-43df-9ed6-70ca7e99290f",
    "metadata": {},
    "source": [
-    "At the core of the configuration you have three filters specified in the `filters` key:\n",
+    "At the core of the the configuration there are three configuration models to be used\n",
     "\n",
-    "1. `BaseModerationFilters.PII`\n",
-    "2. `BaseModerationFilters.TOXICITY`\n",
-    "3. `BaseModerationFilters.INTENT`\n",
+    "- `ModerationPiiConfig` used for configuring the behavior of the PII validations. Following are the parameters it can be initialized with\n",
+    "  - `labels` the PII entity labels. Defaults to an empty list which means that the PII validation will consider all PII entities.\n",
+    "  - `threshold` the confidence threshold for the detected entities, defaults to 0.5 or 50%\n",
+    "  - `redact` a boolean flag to enforce whether redaction should be performed on the text, defaults to `False`. When `False`, the PII validation will error out when it detects any PII entity, when set to `True` it simply redacts the PII values in the text.\n",
+    "  - `mask_character` the character used for masking, defaults to asterisk (*)\n",
+    "- `ModerationToxicityConfig` used for configuring the behavior of the toxicity validations. Following are the parameters it can be initialized with\n",
+    "  - `labels` the Toxic entity labels. Defaults to an empty list which means that the toxicity validation will consider all toxic entities. all\n",
+    "  - `threshold` the confidence threshold for the detected entities, defaults to 0.5 or 50% \n",
+    "- `ModerationPromptSafetyConfig` used for configuring the behavior of the prompt safety validation\n",
+    "  - `threshold` the confidence threshold for the the prompt safety classification, defaults to 0.5 or 50% \n",
     "\n",
-    "And an `action` key that defines two possible actions for each moderation function:\n",
-    "\n",
-    "1. `BaseModerationActions.ALLOW` - `allows` the prompt to pass through but masks detected PII in case of PII check. The default behavior is to run and redact all PII entities. If there is an entity specified in the `labels` field, then only those entities will go through the PII check and masked.\n",
-    "2. `BaseModerationActions.STOP` - `stops` the prompt from passing through to the next step in case any PII, Toxicity, or incorrect Intent is detected. The action of `BaseModerationActions.STOP` will raise a Python `Exception` essentially stopping the chain in progress.\n",
+    "Finally, you use the `BaseModerationConfig` to define the order in which each of these checks are to be performed. The `BaseModerationConfig` takes an optional `filters` parameter which can be a list of one or more than one of the above validation checks, as seen in the previous code block. The  `BaseModerationConfig` can also be initialized with any `filters` in which case it will use all the checks with default configuration (more on this explained later).\n",
     "\n",
     "Using the configuration in the previous cell will perform PII checks and will allow the prompt to pass through however it will mask any SSN numbers present in either the prompt or the LLM output.\n"
    ]
@@ -193,10 +223,23 @@
    "outputs": [],
    "source": [
     "comp_moderation_with_config = AmazonComprehendModerationChain(\n",
-    "    moderation_config=moderation_config, #specify the configuration\n",
-    "    client=comprehend_client,            #optionally pass the Boto3 Client\n",
-    "    verbose=True\n",
-    ")\n",
+    "    moderation_config=moderation_config,  # specify the configuration\n",
+    "    client=comprehend_client,  # optionally pass the Boto3 Client\n",
+    "    verbose=True,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "082c6cfc",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.prompts import PromptTemplate\n",
+    "from langchain.llms.fake import FakeListLLM\n",
     "\n",
     "template = \"\"\"Question: {question}\n",
     "\n",
@@ -205,31 +248,34 @@
     "prompt = PromptTemplate(template=template, input_variables=[\"question\"])\n",
     "\n",
     "responses = [\n",
-    "    \"Final Answer: A credit card number looks like 1289-2321-1123-2387. A fake SSN number looks like 323-22-9980. John Doe's phone number is (999)253-9876.\", \n",
-    "    \"Final Answer: This is a really shitty way of constructing a birdhouse. This is fucking insane to think that any birds would actually create their motherfucking nests here.\"\n",
+    "    \"Final Answer: A credit card number looks like 1289-2321-1123-2387. A fake SSN number looks like 323-22-9980. John Doe's phone number is (999)253-9876.\",\n",
+    "    # replace with your own expletive\n",
+    "    \"Final Answer: This is a really <expletive> way of constructing a birdhouse. This is <expletive> insane to think that any birds would actually create their <expletive> nests here.\",\n",
     "]\n",
     "llm = FakeListLLM(responses=responses)\n",
     "\n",
-    "llm_chain = LLMChain(prompt=prompt, llm=llm)\n",
-    "\n",
-    "chain = ( \n",
-    "    prompt \n",
-    "    | comp_moderation_with_config \n",
-    "    | {llm_chain.input_keys[0]: lambda x: x['output'] }  \n",
-    "    | llm_chain \n",
-    "    | { \"input\": lambda x: x['text'] } \n",
-    "    | comp_moderation_with_config \n",
+    "chain = (\n",
+    "    prompt\n",
+    "    | comp_moderation_with_config\n",
+    "    | {\"input\": (lambda x: x[\"output\"]) | llm}\n",
+    "    | comp_moderation_with_config\n",
     ")\n",
     "\n",
+    "\n",
     "try:\n",
-    "    response = chain.invoke({\"question\": \"A sample SSN number looks like this 123-456-7890. Can you give me some more samples?\"})\n",
+    "    response = chain.invoke(\n",
+    "        {\n",
+    "            \"question\": \"A sample SSN number looks like this 123-45-7890. Can you give me some more samples?\"\n",
+    "        }\n",
+    "    )\n",
     "except Exception as e:\n",
     "    print(str(e))\n",
     "else:\n",
-    "    print(response['output'])"
+    "    print(response[\"output\"])"
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "ba890681-feeb-43ca-a0d5-9c11d2d9de3e",
    "metadata": {
@@ -238,25 +284,25 @@
    "source": [
     "## Unique ID, and Moderation Callbacks\n",
     "\n",
-    "When Amazon Comprehend moderation action is specified as `STOP`, the chain will raise one of the following exceptions-\n",
+    "When Amazon Comprehend moderation action identifies any of the configugred entity, the chain will raise one of the following exceptions-\n",
     "    - `ModerationPiiError`, for PII checks\n",
     "    - `ModerationToxicityError`, for Toxicity checks \n",
-    "    - `ModerationIntentionError` for Intent checks\n",
+    "    - `ModerationPromptSafetyError` for Prompt Safety checks\n",
     "\n",
     "In addition to the moderation configuration, the `AmazonComprehendModerationChain` can also be initialized with the following parameters\n",
     "\n",
     "- `unique_id` [Optional] a string parameter. This parameter can be used to pass any string value or ID. For example, in a chat application, you may want to keep track of abusive users, in this case, you can pass the user's username/email ID etc. This defaults to `None`.\n",
     "\n",
-    "- `moderation_callback` [Optional] the `BaseModerationCallbackHandler` will be called asynchronously (non-blocking to the chain). Callback functions are useful when you want to perform additional actions when the moderation functions are executed, for example logging into a database, or writing a log file. You can override three functions by subclassing `BaseModerationCallbackHandler` - `on_after_pii()`, `on_after_toxicity()`, and `on_after_intent()`. Note that all three functions must be `async` functions. These callback functions receive two arguments:\n",
-    "    - `moderation_beacon` is a dictionary that will contain information about the moderation function, the full response from the Amazon Comprehend model, a unique chain id, the moderation status, and the input string which was validated. The dictionary is of the following schema-\n",
+    "- `moderation_callback` [Optional] the `BaseModerationCallbackHandler` that will be called asynchronously (non-blocking to the chain). Callback functions are useful when you want to perform additional actions when the moderation functions are executed, for example logging into a database, or writing a log file. You can override three functions by subclassing `BaseModerationCallbackHandler` - `on_after_pii()`, `on_after_toxicity()`, and `on_after_prompt_safety()`. Note that all three functions must be `async` functions. These callback functions receive two arguments:\n",
+    "    - `moderation_beacon` a dictionary that will contain information about the moderation function, the full response from Amazon Comprehend model, a unique chain id, the moderation status, and the input string which was validated. The dictionary is of the following schema-\n",
     "    \n",
     "    ```\n",
     "    { \n",
     "        'moderation_chain_id': 'xxx-xxx-xxx', # Unique chain ID\n",
-    "        'moderation_type': 'Toxicity' | 'PII' | 'Intent', \n",
+    "        'moderation_type': 'Toxicity' | 'PII' | 'PromptSafety', \n",
     "        'moderation_status': 'LABELS_FOUND' | 'LABELS_NOT_FOUND',\n",
     "        'moderation_input': 'A sample SSN number looks like this 123-456-7890. Can you give me some more samples?',\n",
-    "        'moderation_output': {...} #Full Amazon Comprehend PII, Toxicity, or Intent Model Output\n",
+    "        'moderation_output': {...} #Full Amazon Comprehend PII, Toxicity, or Prompt Safety Model Output\n",
     "    }\n",
     "    ```\n",
     "    \n",
@@ -299,24 +345,25 @@
    "source": [
     "# Define callback handlers by subclassing BaseModerationCallbackHandler\n",
     "\n",
+    "\n",
     "class MyModCallback(BaseModerationCallbackHandler):\n",
-    "    \n",
     "    async def on_after_pii(self, output_beacon, unique_id):\n",
     "        import json\n",
-    "        moderation_type = output_beacon['moderation_type']\n",
-    "        chain_id = output_beacon['moderation_chain_id']\n",
-    "        with open(f'output-{moderation_type}-{chain_id}.json', 'w') as file:\n",
-    "            data = { 'beacon_data': output_beacon, 'unique_id': unique_id }\n",
+    "\n",
+    "        moderation_type = output_beacon[\"moderation_type\"]\n",
+    "        chain_id = output_beacon[\"moderation_chain_id\"]\n",
+    "        with open(f\"output-{moderation_type}-{chain_id}.json\", \"w\") as file:\n",
+    "            data = {\"beacon_data\": output_beacon, \"unique_id\": unique_id}\n",
     "            json.dump(data, file)\n",
-    "    \n",
-    "    '''\n",
+    "\n",
+    "    \"\"\"\n",
     "    async def on_after_toxicity(self, output_beacon, unique_id):\n",
     "        pass\n",
     "    \n",
-    "    async def on_after_intent(self, output_beacon, unique_id):\n",
+    "    async def on_after_prompt_safety(self, output_beacon, unique_id):\n",
     "        pass\n",
-    "    '''\n",
-    "    \n",
+    "    \"\"\"\n",
+    "\n",
     "\n",
     "my_callback = MyModCallback()"
    ]
@@ -330,29 +377,18 @@
    },
    "outputs": [],
    "source": [
-    "moderation_config = { \n",
-    "        \"filters\": [ \n",
-    "                BaseModerationFilters.PII, \n",
-    "                BaseModerationFilters.TOXICITY\n",
-    "        ],\n",
-    "        \"pii\":{ \n",
-    "                \"action\": BaseModerationActions.STOP, \n",
-    "                \"threshold\":0.5, \n",
-    "                \"labels\":[\"SSN\"], \n",
-    "                \"mask_character\": \"X\" \n",
-    "        },\n",
-    "        \"toxicity\":{ \n",
-    "                \"action\": BaseModerationActions.STOP, \n",
-    "                \"threshold\":0.5 \n",
-    "        }\n",
-    "}\n",
+    "pii_config = ModerationPiiConfig(labels=[\"SSN\"], redact=True, mask_character=\"X\")\n",
+    "\n",
+    "toxicity_config = ModerationToxicityConfig(threshold=0.5)\n",
+    "\n",
+    "moderation_config = BaseModerationConfig(filters=[pii_config, toxicity_config])\n",
     "\n",
     "comp_moderation_with_config = AmazonComprehendModerationChain(\n",
-    "        moderation_config=moderation_config, # specify the configuration\n",
-    "        client=comprehend_client,            # optionally pass the Boto3 Client\n",
-    "        unique_id='john.doe@email.com',      # A unique ID\n",
-    "        moderation_callback=my_callback,     # BaseModerationCallbackHandler\n",
-    "        verbose=True\n",
+    "    moderation_config=moderation_config,  # specify the configuration\n",
+    "    client=comprehend_client,  # optionally pass the Boto3 Client\n",
+    "    unique_id=\"john.doe@email.com\",  # A unique ID\n",
+    "    moderation_callback=my_callback,  # BaseModerationCallbackHandler\n",
+    "    verbose=True,\n",
     ")"
    ]
   },
@@ -366,7 +402,6 @@
    "outputs": [],
    "source": [
     "from langchain.prompts import PromptTemplate\n",
-    "from langchain.chains import LLMChain\n",
     "from langchain.llms.fake import FakeListLLM\n",
     "\n",
     "template = \"\"\"Question: {question}\n",
@@ -376,32 +411,34 @@
     "prompt = PromptTemplate(template=template, input_variables=[\"question\"])\n",
     "\n",
     "responses = [\n",
-    "    \"Final Answer: A credit card number looks like 1289-2321-1123-2387. A fake SSN number looks like 323-22-9980. John Doe's phone number is (999)253-9876.\", \n",
-    "    \"Final Answer: This is a really shitty way of constructing a birdhouse. This is fucking insane to think that any birds would actually create their motherfucking nests here.\"\n",
+    "    \"Final Answer: A credit card number looks like 1289-2321-1123-2387. A fake SSN number looks like 323-22-9980. John Doe's phone number is (999)253-9876.\",\n",
+    "    # replace with your own expletive\n",
+    "    \"Final Answer: This is a really <expletive> way of constructing a birdhouse. This is <expletive> insane to think that any birds would actually create their <expletive> nests here.\",\n",
     "]\n",
     "\n",
     "llm = FakeListLLM(responses=responses)\n",
     "\n",
-    "llm_chain = LLMChain(prompt=prompt, llm=llm)\n",
-    "\n",
     "chain = (\n",
-    "    prompt \n",
-    "    | comp_moderation_with_config \n",
-    "    | {llm_chain.input_keys[0]: lambda x: x['output'] }  \n",
-    "    | llm_chain \n",
-    "    | { \"input\": lambda x: x['text'] } \n",
-    "    | comp_moderation_with_config \n",
-    ") \n",
+    "    prompt\n",
+    "    | comp_moderation_with_config\n",
+    "    | {\"input\": (lambda x: x[\"output\"]) | llm}\n",
+    "    | comp_moderation_with_config\n",
+    ")\n",
     "\n",
     "try:\n",
-    "    response = chain.invoke({\"question\": \"A sample SSN number looks like this 123-456-7890. Can you give me some more samples?\"})\n",
+    "    response = chain.invoke(\n",
+    "        {\n",
+    "            \"question\": \"A sample SSN number looks like this 123-456-7890. Can you give me some more samples?\"\n",
+    "        }\n",
+    "    )\n",
     "except Exception as e:\n",
     "    print(str(e))\n",
     "else:\n",
-    "    print(response['output'])"
+    "    print(response[\"output\"])"
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "706454b2-2efa-4d41-abc8-ccf2b4e87822",
    "metadata": {
@@ -410,7 +447,7 @@
    "source": [
     "## `moderation_config` and moderation execution order\n",
     "\n",
-    "If `AmazonComprehendModerationChain` is not initialized with any `moderation_config` then the default action is `STOP` and the default order of moderation check is as follows.\n",
+    "If `AmazonComprehendModerationChain` is not initialized with any `moderation_config` then it is initialized with the default values of `BaseModerationConfig`. If no `filters` are used then the sequence of moderation check is as follows.\n",
     "\n",
     "```\n",
     "AmazonComprehendModerationChain\n",
@@ -423,39 +460,32 @@
     "            ├── Callback (if available)\n",
     "            ├── Label Found ⟶ [Error Stop]\n",
     "            └── No Label Found\n",
-    "                └──Check Intent with Stop Action\n",
+    "                └──Check Prompt Safety with Stop Action\n",
     "                    ├── Callback (if available)\n",
     "                    ├── Label Found ⟶ [Error Stop]\n",
     "                    └── No Label Found\n",
     "                        └── Return Prompt\n",
     "```\n",
     "\n",
-    "If any of the checks raises an exception then the subsequent checks will not be performed. If a `callback` is provided in this case, then it will be called for each of the checks that have been performed. For example, in the case above, if the Chain fails due to the presence of PII then the Toxicity and Intent checks will not be performed.\n",
+    "If any of the check raises a validation exception then the subsequent checks will not be performed. If a `callback` is provided in this case, then it will be called for each of the checks that have been performed. For example, in the case above, if the Chain fails due to presence of PII then the Toxicity and Prompt Safety checks will not be performed.\n",
     "\n",
-    "You can override the execution order by passing `moderation_config` and simply specifying the desired order in the `filters` key of the configuration. In case you use `moderation_config` then the order of the checks as specified in the `filters` key will be maintained. For example, in the configuration below, first Toxicity check will be performed, then PII, and finally Intent validation will be performed. In this case, `AmazonComprehendModerationChain` will perform the desired checks in the specified order with default values of each model `kwargs`.\n",
+    "You can override the execution order by passing `moderation_config` and simply specifying the desired order in the `filters` parameter of the `BaseModerationConfig`. In case you specify the filters, then the order of the checks as specified in the `filters` parameter will be maintained. For example, in the configuration below, first Toxicity check will be performed, then PII, and finally Prompt Safety validation will be performed. In this case, `AmazonComprehendModerationChain` will perform the desired checks in the specified order with default values of each model `kwargs`.\n",
     "\n",
     "```python\n",
-    "moderation_config = { \n",
-    "        \"filters\":[ BaseModerationFilters.TOXICITY, \n",
-    "                    BaseModerationFilters.PII, \n",
-    "                    BaseModerationFilters.INTENT]\n",
-    "   }\n",
+    "pii_check = ModerationPiiConfig()\n",
+    "toxicity_check = ModerationToxicityConfig()\n",
+    "prompt_safety_check = ModerationPromptSafetyConfig()\n",
+    "\n",
+    "moderation_config = BaseModerationConfig(filters=[toxicity_check, pii_check, prompt_safety_check])\n",
     "```\n",
     "\n",
-    "Model `kwargs` are specified by the `pii`, `toxicity`, and `intent` keys within the `moderation_config` dictionary. For example, in the `moderation_config` below, the default order of moderation is overriden and the `pii` & `toxicity` model `kwargs` have been overriden. For `intent` the chain's default `kwargs` will be used.\n",
+    "You can have also use more than one configuration for a specific moderation check, for example in the sample below, two consecutive PII checks are performed. First the configuration checks for any SSN, if found it would raise an error. If any SSN isn't found then it will next check if any NAME and CREDIT_DEBIT_NUMBER is present in the prompt and will mask it.\n",
     "\n",
     "```python\n",
-    " moderation_config = { \n",
-    "        \"filters\":[ BaseModerationFilters.TOXICITY, \n",
-    "                    BaseModerationFilters.PII, \n",
-    "                    BaseModerationFilters.INTENT],\n",
-    "        \"pii\":{ \"action\": BaseModerationActions.ALLOW, \n",
-    "                \"threshold\":0.5, \n",
-    "                \"labels\":[\"SSN\"], \n",
-    "                \"mask_character\": \"X\" },\n",
-    "        \"toxicity\":{ \"action\": BaseModerationActions.STOP, \n",
-    "                     \"threshold\":0.5 }\n",
-    "   }\n",
+    "pii_check_1 = ModerationPiiConfig(labels=[\"SSN\"])\n",
+    "pii_check_2 = ModerationPiiConfig(labels=[\"NAME\", \"CREDIT_DEBIT_NUMBER\"], redact=True)\n",
+    "\n",
+    "moderation_config = BaseModerationConfig(filters=[pii_check_1, pii_check_2])\n",
     "```\n",
     "\n",
     "1. For a list of PII labels see Amazon Comprehend Universal PII entity types - https://docs.aws.amazon.com/comprehend/latest/dg/how-pii.html#how-pii-types\n",
@@ -467,10 +497,11 @@
     "    - `VIOLENCE_OR_THREAT`: Speech that includes threats which seek to inflict pain, injury or hostility towards a person or group.\n",
     "    - `INSULT`: Speech that includes demeaning, humiliating, mocking, insulting, or belittling language.\n",
     "    - `PROFANITY`: Speech that contains words, phrases or acronyms that are impolite, vulgar, or offensive is considered as profane.\n",
-    "3. For a list of Intent labels refer to documentation [link here]"
+    "3. For a list of Prompt Safety labels refer to documentation [link here]"
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "78905aec-55ae-4fc3-a23b-8a69bd1e33f2",
    "metadata": {},
@@ -504,7 +535,9 @@
    },
    "outputs": [],
    "source": [
-    "%env HUGGINGFACEHUB_API_TOKEN=\"<HUGGINGFACEHUB_API_TOKEN>\""
+    "import os\n",
+    "\n",
+    "os.environ[\"HUGGINGFACEHUB_API_TOKEN\"] = \"<YOUR HF TOKEN HERE>\""
    ]
   },
   {
@@ -517,7 +550,7 @@
    "outputs": [],
    "source": [
     "# See https://huggingface.co/models?pipeline_tag=text-generation&sort=downloads for some other options\n",
-    "repo_id = \"google/flan-t5-xxl\"  \n"
+    "repo_id = \"google/flan-t5-xxl\""
    ]
   },
   {
@@ -531,18 +564,13 @@
    "source": [
     "from langchain.llms import HuggingFaceHub\n",
     "from langchain.prompts import PromptTemplate\n",
-    "from langchain.chains import LLMChain\n",
     "\n",
-    "template = \"\"\"Question: {question}\n",
-    "\n",
-    "Answer:\"\"\"\n",
+    "template = \"\"\"{question}\"\"\"\n",
     "\n",
     "prompt = PromptTemplate(template=template, input_variables=[\"question\"])\n",
-    "\n",
     "llm = HuggingFaceHub(\n",
     "    repo_id=repo_id, model_kwargs={\"temperature\": 0.5, \"max_length\": 256}\n",
-    ")\n",
-    "llm_chain = LLMChain(prompt=prompt, llm=llm)"
+    ")"
    ]
   },
   {
@@ -562,23 +590,35 @@
    },
    "outputs": [],
    "source": [
-    "moderation_config = { \n",
-    "        \"filters\":[ BaseModerationFilters.PII, BaseModerationFilters.TOXICITY, BaseModerationFilters.INTENT ],\n",
-    "        \"pii\":{\"action\": BaseModerationActions.ALLOW, \"threshold\":0.5, \"labels\":[\"SSN\",\"CREDIT_DEBIT_NUMBER\"], \"mask_character\": \"X\"},\n",
-    "        \"toxicity\":{\"action\": BaseModerationActions.STOP, \"threshold\":0.5},\n",
-    "        \"intent\":{\"action\": BaseModerationActions.ALLOW, \"threshold\":0.5,},\n",
-    "   }\n",
+    "# define filter configs\n",
+    "pii_config = ModerationPiiConfig(\n",
+    "    labels=[\"SSN\", \"CREDIT_DEBIT_NUMBER\"], redact=True, mask_character=\"X\"\n",
+    ")\n",
     "\n",
-    "# without any callback\n",
-    "amazon_comp_moderation = AmazonComprehendModerationChain(moderation_config=moderation_config, \n",
-    "                                                         client=comprehend_client,\n",
-    "                                                         verbose=True)\n",
+    "toxicity_config = ModerationToxicityConfig(threshold=0.5)\n",
     "\n",
-    "# with callback\n",
-    "amazon_comp_moderation_out = AmazonComprehendModerationChain(moderation_config=moderation_config, \n",
-    "                                                         client=comprehend_client,\n",
-    "                                                         moderation_callback=my_callback,\n",
-    "                                                         verbose=True)"
+    "prompt_safety_config = ModerationPromptSafetyConfig(threshold=0.8)\n",
+    "\n",
+    "# define different moderation configs using the filter configs above\n",
+    "moderation_config_1 = BaseModerationConfig(\n",
+    "    filters=[pii_config, toxicity_config, prompt_safety_config]\n",
+    ")\n",
+    "\n",
+    "moderation_config_2 = BaseModerationConfig(filters=[pii_config])\n",
+    "\n",
+    "\n",
+    "# input prompt moderation chain with callback\n",
+    "amazon_comp_moderation = AmazonComprehendModerationChain(\n",
+    "    moderation_config=moderation_config_1,\n",
+    "    client=comprehend_client,\n",
+    "    moderation_callback=my_callback,\n",
+    "    verbose=True,\n",
+    ")\n",
+    "\n",
+    "# Output from LLM moderation chain without callback\n",
+    "amazon_comp_moderation_out = AmazonComprehendModerationChain(\n",
+    "    moderation_config=moderation_config_2, client=comprehend_client, verbose=True\n",
+    ")"
    ]
   },
   {
@@ -586,7 +626,7 @@
    "id": "b1256bc8-1321-4624-9e8a-a2d4a8df59bf",
    "metadata": {},
    "source": [
-    "The `moderation_config` will now prevent any inputs and model outputs containing obscene words or sentences, bad intent, or PII with entities other than SSN with score above threshold or 0.5 or 50%. If it finds Pii entities - SSN - it will redact them before allowing the call to proceed. "
+    "The `moderation_config` will now prevent any inputs containing obscene words or sentences, bad intent, or PII with entities other than SSN with score above threshold or 0.5 or 50%. If it finds Pii entities - SSN - it will redact them before allowing the call to proceed. It will also mask any SSN or credit card numbers from the model's response."
    ]
   },
   {
@@ -599,20 +639,25 @@
    "outputs": [],
    "source": [
     "chain = (\n",
-    "    prompt \n",
-    "    | amazon_comp_moderation \n",
-    "    | {llm_chain.input_keys[0]: lambda x: x['output'] }  \n",
-    "    | llm_chain \n",
-    "    | { \"input\": lambda x: x['text'] } \n",
+    "    prompt\n",
+    "    | amazon_comp_moderation\n",
+    "    | {\"input\": (lambda x: x[\"output\"]) | llm}\n",
     "    | amazon_comp_moderation_out\n",
     ")\n",
     "\n",
     "try:\n",
-    "    response = chain.invoke({\"question\": \"My AnyCompany Financial Services, LLC credit card account 1111-0000-1111-0008 has 24$ due by July 31st. Can you give me some more credit car number samples?\"})\n",
+    "    response = chain.invoke(\n",
+    "        {\n",
+    "            \"question\": \"\"\"What is John Doe's address, phone number and SSN from the following text?\n",
+    "\n",
+    "John Doe, a resident of 1234 Elm Street in Springfield, recently celebrated his birthday on January 1st. Turning 43 this year, John reflected on the years gone by. He often shares memories of his younger days with his close friends through calls on his phone, (555) 123-4567. Meanwhile, during a casual evening, he received an email at johndoe@example.com reminding him of an old acquaintance's reunion. As he navigated through some old documents, he stumbled upon a paper that listed his SSN as 123-45-6789, reminding him to store it in a safer place.\n",
+    "\"\"\"\n",
+    "        }\n",
+    "    )\n",
     "except Exception as e:\n",
     "    print(str(e))\n",
     "else:\n",
-    "    print(response['output'])"
+    "    print(response[\"output\"])"
    ]
   },
   {
@@ -624,7 +669,7 @@
    "source": [
     "### With Amazon SageMaker Jumpstart\n",
     "\n",
-    "The example below shows how to use the `Amazon Comprehend Moderation chain` with an Amazon SageMaker Jumpstart hosted LLM. You should have an `Amazon SageMaker Jumpstart` hosted LLM endpoint within your AWS Account. "
+    "The exmaple below shows how to use Amazon Comprehend Moderation chain with an Amazon SageMaker Jumpstart hosted LLM. You should have an Amazon SageMaker Jumpstart hosted LLM endpoint within your AWS Account. Refer to [this notebook](https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart-foundation-models/text-generation-falcon.ipynb) for more on how to deploy an LLM with Amazon SageMaker Jumpstart hosted endpoints."
    ]
   },
   {
@@ -634,7 +679,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "endpoint_name = \"<SAGEMAKER_ENDPOINT_NAME>\" # replace with your SageMaker Endpoint name"
+    "endpoint_name = \"<SAGEMAKER_ENDPOINT_NAME>\"  # replace with your SageMaker Endpoint name\n",
+    "region = \"<REGION>\"  # replace with your SageMaker Endpoint region"
    ]
   },
   {
@@ -646,40 +692,47 @@
    "source": [
     "from langchain.llms import SagemakerEndpoint\n",
     "from langchain.llms.sagemaker_endpoint import LLMContentHandler\n",
-    "from langchain.chains import LLMChain\n",
-    "from langchain.prompts import load_prompt, PromptTemplate\n",
+    "from langchain.prompts import PromptTemplate\n",
     "import json\n",
     "\n",
+    "\n",
     "class ContentHandler(LLMContentHandler):\n",
     "    content_type = \"application/json\"\n",
     "    accepts = \"application/json\"\n",
     "\n",
     "    def transform_input(self, prompt: str, model_kwargs: dict) -> bytes:\n",
-    "        input_str = json.dumps({\"text_inputs\": prompt,  **model_kwargs})\n",
-    "        return input_str.encode('utf-8')\n",
-    "    \n",
+    "        input_str = json.dumps({\"text_inputs\": prompt, **model_kwargs})\n",
+    "        return input_str.encode(\"utf-8\")\n",
+    "\n",
     "    def transform_output(self, output: bytes) -> str:\n",
     "        response_json = json.loads(output.read().decode(\"utf-8\"))\n",
-    "        return response_json['generated_texts'][0]\n",
+    "        return response_json[\"generated_texts\"][0]\n",
+    "\n",
     "\n",
     "content_handler = ContentHandler()\n",
     "\n",
-    "#prompt template for input text\n",
-    "llm_prompt = PromptTemplate(input_variables=[\"input_text\"], template=\"{input_text}\")\n",
+    "template = \"\"\"From the following 'Document', precisely answer the 'Question'. Do not add any spurious information in your answer.\n",
     "\n",
-    "llm_chain = LLMChain(\n",
-    "    llm=SagemakerEndpoint(\n",
-    "        endpoint_name=endpoint_name, \n",
-    "        region_name='us-east-1',\n",
-    "        model_kwargs={\"temperature\":0.97,\n",
-    "                      \"max_length\": 200,\n",
-    "                      \"num_return_sequences\": 3,\n",
-    "                      \"top_k\": 50,\n",
-    "                      \"top_p\": 0.95,\n",
-    "                      \"do_sample\": True},\n",
-    "        content_handler=content_handler\n",
-    "    ),\n",
-    "    prompt=llm_prompt\n",
+    "Document: John Doe, a resident of 1234 Elm Street in Springfield, recently celebrated his birthday on January 1st. Turning 43 this year, John reflected on the years gone by. He often shares memories of his younger days with his close friends through calls on his phone, (555) 123-4567. Meanwhile, during a casual evening, he received an email at johndoe@example.com reminding him of an old acquaintance's reunion. As he navigated through some old documents, he stumbled upon a paper that listed his SSN as 123-45-6789, reminding him to store it in a safer place.\n",
+    "Question: {question}\n",
+    "Answer:\n",
+    "\"\"\"\n",
+    "\n",
+    "# prompt template for input text\n",
+    "llm_prompt = PromptTemplate(template=template, input_variables=[\"question\"])\n",
+    "\n",
+    "llm = SagemakerEndpoint(\n",
+    "    endpoint_name=endpoint_name,\n",
+    "    region_name=region,\n",
+    "    model_kwargs={\n",
+    "        \"temperature\": 0.95,\n",
+    "        \"max_length\": 200,\n",
+    "        \"num_return_sequences\": 3,\n",
+    "        \"top_k\": 50,\n",
+    "        \"top_p\": 0.95,\n",
+    "        \"do_sample\": True,\n",
+    "    },\n",
+    "    content_handler=content_handler,\n",
     ")"
    ]
   },
@@ -700,16 +753,30 @@
    },
    "outputs": [],
    "source": [
-    "moderation_config = { \n",
-    "        \"filters\":[ BaseModerationFilters.PII, BaseModerationFilters.TOXICITY ],\n",
-    "        \"pii\":{\"action\": BaseModerationActions.ALLOW, \"threshold\":0.5, \"labels\":[\"SSN\"], \"mask_character\": \"X\"},\n",
-    "        \"toxicity\":{\"action\": BaseModerationActions.STOP, \"threshold\":0.5},\n",
-    "        \"intent\":{\"action\": BaseModerationActions.ALLOW, \"threshold\":0.5,},\n",
-    "   }\n",
+    "# define filter configs\n",
+    "pii_config = ModerationPiiConfig(labels=[\"SSN\"], redact=True, mask_character=\"X\")\n",
     "\n",
-    "amazon_comp_moderation = AmazonComprehendModerationChain(moderation_config=moderation_config, \n",
-    "                                                         client=comprehend_client ,\n",
-    "                                                         verbose=True)"
+    "toxicity_config = ModerationToxicityConfig(threshold=0.5)\n",
+    "\n",
+    "\n",
+    "# define different moderation configs using the filter configs above\n",
+    "moderation_config_1 = BaseModerationConfig(filters=[pii_config, toxicity_config])\n",
+    "\n",
+    "moderation_config_2 = BaseModerationConfig(filters=[pii_config])\n",
+    "\n",
+    "\n",
+    "# input prompt moderation chain with callback\n",
+    "amazon_comp_moderation = AmazonComprehendModerationChain(\n",
+    "    moderation_config=moderation_config_1,\n",
+    "    client=comprehend_client,\n",
+    "    moderation_callback=my_callback,\n",
+    "    verbose=True,\n",
+    ")\n",
+    "\n",
+    "# Output from LLM moderation chain without callback\n",
+    "amazon_comp_moderation_out = AmazonComprehendModerationChain(\n",
+    "    moderation_config=moderation_config_2, client=comprehend_client, verbose=True\n",
+    ")"
    ]
   },
   {
@@ -730,20 +797,20 @@
    "outputs": [],
    "source": [
     "chain = (\n",
-    "    prompt \n",
-    "    | amazon_comp_moderation \n",
-    "    | {llm_chain.input_keys[0]: lambda x: x['output'] }  \n",
-    "    | llm_chain \n",
-    "    | { \"input\": lambda x: x['text'] } \n",
-    "    | amazon_comp_moderation \n",
+    "    prompt\n",
+    "    | amazon_comp_moderation\n",
+    "    | {\"input\": (lambda x: x[\"output\"]) | llm}\n",
+    "    | amazon_comp_moderation_out\n",
     ")\n",
     "\n",
     "try:\n",
-    "    response = chain.invoke({\"question\": \"My AnyCompany Financial Services, LLC credit card account 1111-0000-1111-0008 has 24$ due by July 31st. Can you give me some more samples?\"})\n",
+    "    response = chain.invoke(\n",
+    "        {\"question\": \"What is John Doe's address, phone number and SSN?\"}\n",
+    "    )\n",
     "except Exception as e:\n",
     "    print(str(e))\n",
     "else:\n",
-    "    print(response['output'])"
+    "    print(response[\"output\"])"
    ]
   },
   {
@@ -1347,7 +1414,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/docs/integrations/callbacks/argilla.ipynb

@@ -14,7 +14,7 @@
     "> using both human and machine feedback. We provide support for each step in the MLOps cycle, \n",
     "> from data labeling to model monitoring.\n",
     "\n",
-    "<a target=\"_blank\" href=\"https://colab.research.google.com/github/hwchase17/langchain/blob/master/docs/integrations/callbacks/argilla.html\">\n",
+    "<a target=\"_blank\" href=\"https://colab.research.google.com/github/hwchase17/langchain/blob/master/docs/integrations/callbacks/argilla\">\n",
     "  <img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/>\n",
     "</a>"
    ]

docs/docs/integrations/callbacks/confident.ipynb

@@ -122,8 +122,7 @@
     "from langchain.callbacks.confident_callback import DeepEvalCallbackHandler\n",
     "\n",
     "deepeval_callback = DeepEvalCallbackHandler(\n",
-    "    implementation_name=\"langchainQuickstart\",\n",
-    "    metrics=[answer_relevancy_metric]\n",
+    "    implementation_name=\"langchainQuickstart\", metrics=[answer_relevancy_metric]\n",
     ")"
    ]
   },
@@ -155,6 +154,7 @@
    ],
    "source": [
     "from langchain.llms import OpenAI\n",
+    "\n",
     "llm = OpenAI(\n",
     "    temperature=0,\n",
     "    callbacks=[deepeval_callback],\n",
@@ -227,8 +227,8 @@
     "openai_api_key = \"sk-XXX\"\n",
     "\n",
     "with open(\"state_of_the_union.txt\", \"w\") as f:\n",
-    "  response = requests.get(text_file_url)\n",
-    "  f.write(response.text)\n",
+    "    response = requests.get(text_file_url)\n",
+    "    f.write(response.text)\n",
     "\n",
     "loader = TextLoader(\"state_of_the_union.txt\")\n",
     "documents = loader.load()\n",
@@ -239,8 +239,9 @@
     "docsearch = Chroma.from_documents(texts, embeddings)\n",
     "\n",
     "qa = RetrievalQA.from_chain_type(\n",
-    "  llm=OpenAI(openai_api_key=openai_api_key), chain_type=\"stuff\",\n",
-    "  retriever=docsearch.as_retriever()\n",
+    "    llm=OpenAI(openai_api_key=openai_api_key),\n",
+    "    chain_type=\"stuff\",\n",
+    "    retriever=docsearch.as_retriever(),\n",
     ")\n",
     "\n",
     "# Providing a new question-answering pipeline\n",

docs/docs/integrations/callbacks/labelstudio.ipynb

@@ -97,9 +97,9 @@
    "source": [
     "import os\n",
     "\n",
-    "os.environ['LABEL_STUDIO_URL'] = '<YOUR-LABEL-STUDIO-URL>'  # e.g. http://localhost:8080\n",
-    "os.environ['LABEL_STUDIO_API_KEY'] = '<YOUR-LABEL-STUDIO-API-KEY>'\n",
-    "os.environ['OPENAI_API_KEY'] = '<YOUR-OPENAI-API-KEY>'"
+    "os.environ[\"LABEL_STUDIO_URL\"] = \"<YOUR-LABEL-STUDIO-URL>\"  # e.g. http://localhost:8080\n",
+    "os.environ[\"LABEL_STUDIO_API_KEY\"] = \"<YOUR-LABEL-STUDIO-API-KEY>\"\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"<YOUR-OPENAI-API-KEY>\""
    ]
   },
   {
@@ -174,11 +174,7 @@
     "from langchain.callbacks import LabelStudioCallbackHandler\n",
     "\n",
     "llm = OpenAI(\n",
-    "    temperature=0,\n",
-    "    callbacks=[\n",
-    "        LabelStudioCallbackHandler(\n",
-    "            project_name=\"My Project\"\n",
-    "    )]\n",
+    "    temperature=0, callbacks=[LabelStudioCallbackHandler(project_name=\"My Project\")]\n",
     ")\n",
     "print(llm(\"Tell me a joke\"))"
    ]
@@ -249,16 +245,20 @@
     "from langchain.schema import HumanMessage, SystemMessage\n",
     "from langchain.callbacks import LabelStudioCallbackHandler\n",
     "\n",
-    "chat_llm = ChatOpenAI(callbacks=[\n",
-    "    LabelStudioCallbackHandler(\n",
-    "        mode=\"chat\",\n",
-    "        project_name=\"New Project with Chat\",\n",
-    "    )\n",
-    "])\n",
-    "llm_results = chat_llm([\n",
-    "    SystemMessage(content=\"Always use a lot of emojis\"),\n",
-    "    HumanMessage(content=\"Tell me a joke\")\n",
-    "])"
+    "chat_llm = ChatOpenAI(\n",
+    "    callbacks=[\n",
+    "        LabelStudioCallbackHandler(\n",
+    "            mode=\"chat\",\n",
+    "            project_name=\"New Project with Chat\",\n",
+    "        )\n",
+    "    ]\n",
+    ")\n",
+    "llm_results = chat_llm(\n",
+    "    [\n",
+    "        SystemMessage(content=\"Always use a lot of emojis\"),\n",
+    "        HumanMessage(content=\"Tell me a joke\"),\n",
+    "    ]\n",
+    ")"
    ]
   },
   {
@@ -304,7 +304,8 @@
    },
    "outputs": [],
    "source": [
-    "ls = LabelStudioCallbackHandler(project_config='''\n",
+    "ls = LabelStudioCallbackHandler(\n",
+    "    project_config=\"\"\"\n",
     "<View>\n",
     "<Text name=\"prompt\" value=\"$prompt\"/>\n",
     "<TextArea name=\"response\" toName=\"prompt\"/>\n",
@@ -315,7 +316,8 @@
     "    <Choice value=\"Negative\"/>\n",
     "</Choices>\n",
     "</View>\n",
-    "''')"
+    "\"\"\"\n",
+    ")"
    ]
   },
   {

docs/docs/integrations/callbacks/sagemaker_tracking.ipynb

@@ -105,19 +105,19 @@
    },
    "outputs": [],
    "source": [
-    "#LLM Hyperparameters\n",
+    "# LLM Hyperparameters\n",
     "HPARAMS = {\n",
     "    \"temperature\": 0.1,\n",
     "    \"model_name\": \"text-davinci-003\",\n",
     "}\n",
     "\n",
-    "#Bucket used to save prompt logs (Use `None` is used to save the default bucket or otherwise change it)\n",
+    "# Bucket used to save prompt logs (Use `None` is used to save the default bucket or otherwise change it)\n",
     "BUCKET_NAME = None\n",
     "\n",
-    "#Experiment name\n",
+    "# Experiment name\n",
     "EXPERIMENT_NAME = \"langchain-sagemaker-tracker\"\n",
     "\n",
-    "#Create SageMaker Session with the given bucket\n",
+    "# Create SageMaker Session with the given bucket\n",
     "session = Session(default_bucket=BUCKET_NAME)"
    ]
   },
@@ -150,8 +150,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "with Run(experiment_name=EXPERIMENT_NAME, run_name=RUN_NAME, sagemaker_session=session) as run:\n",
-    "\n",
+    "with Run(\n",
+    "    experiment_name=EXPERIMENT_NAME, run_name=RUN_NAME, sagemaker_session=session\n",
+    ") as run:\n",
     "    # Create SageMaker Callback\n",
     "    sagemaker_callback = SageMakerCallbackHandler(run)\n",
     "\n",
@@ -209,8 +210,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "with Run(experiment_name=EXPERIMENT_NAME, run_name=RUN_NAME, sagemaker_session=session) as run:\n",
-    "\n",
+    "with Run(\n",
+    "    experiment_name=EXPERIMENT_NAME, run_name=RUN_NAME, sagemaker_session=session\n",
+    ") as run:\n",
     "    # Create SageMaker Callback\n",
     "    sagemaker_callback = SageMakerCallbackHandler(run)\n",
     "\n",
@@ -228,7 +230,9 @@
     "    chain2 = LLMChain(llm=llm, prompt=prompt_template2, callbacks=[sagemaker_callback])\n",
     "\n",
     "    # Create Sequential chain\n",
-    "    overall_chain = SimpleSequentialChain(chains=[chain1, chain2], callbacks=[sagemaker_callback])\n",
+    "    overall_chain = SimpleSequentialChain(\n",
+    "        chains=[chain1, chain2], callbacks=[sagemaker_callback]\n",
+    "    )\n",
     "\n",
     "    # Run overall sequential chain\n",
     "    overall_chain.run(**INPUT_VARIABLES)\n",
@@ -267,8 +271,9 @@
    },
    "outputs": [],
    "source": [
-    "with Run(experiment_name=EXPERIMENT_NAME, run_name=RUN_NAME, sagemaker_session=session) as run:\n",
-    "\n",
+    "with Run(\n",
+    "    experiment_name=EXPERIMENT_NAME, run_name=RUN_NAME, sagemaker_session=session\n",
+    ") as run:\n",
     "    # Create SageMaker Callback\n",
     "    sagemaker_callback = SageMakerCallbackHandler(run)\n",
     "\n",
@@ -279,7 +284,9 @@
     "    tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm, callbacks=[sagemaker_callback])\n",
     "\n",
     "    # Initialize agent with all the tools\n",
-    "    agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", callbacks=[sagemaker_callback])\n",
+    "    agent = initialize_agent(\n",
+    "        tools, llm, agent=\"zero-shot-react-description\", callbacks=[sagemaker_callback]\n",
+    "    )\n",
     "\n",
     "    # Run agent\n",
     "    agent.run(input=PROMPT_TEMPLATE)\n",
@@ -309,10 +316,10 @@
    },
    "outputs": [],
    "source": [
-    "#Load\n",
+    "# Load\n",
     "logs = ExperimentAnalytics(experiment_name=EXPERIMENT_NAME)\n",
     "\n",
-    "#Convert as pandas dataframe\n",
+    "# Convert as pandas dataframe\n",
     "df = logs.dataframe(force_refresh=True)\n",
     "\n",
     "print(df.shape)\n",

docs/docs/integrations/callbacks/trubrics.ipynb

@@ -113,7 +113,7 @@
     "tags": []
    },
    "source": [
-    "Here are two examples of how to use the `TrubricsCallbackHandler` with Langchain [LLMs](https://python.langchain.com/docs/modules/model_io/models/llms/) or [Chat Models](https://python.langchain.com/docs/modules/model_io/models/chat/). We will use OpenAI models, so set your `OPENAI_API_KEY` key here:"
+    "Here are two examples of how to use the `TrubricsCallbackHandler` with Langchain [LLMs](https://python.langchain.com/docs/modules/model_io/llms/) or [Chat Models](https://python.langchain.com/docs/modules/model_io/chat/). We will use OpenAI models, so set your `OPENAI_API_KEY` key here:"
    ]
   },
   {
@@ -284,7 +284,7 @@
     "            project=\"default\",\n",
     "            tags=[\"chat model\"],\n",
     "            user_id=\"user-id-1234\",\n",
-    "            some_metadata={\"hello\": [1, 2]}\n",
+    "            some_metadata={\"hello\": [1, 2]},\n",
     "        )\n",
     "    ]\n",
     ")"

docs/docs/integrations/chat/anthropic_functions.ipynb

@@ -46,7 +46,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "model = AnthropicFunctions(model='claude-2')"
+    "model = AnthropicFunctions(model=\"claude-2\")"
    ]
   },
   {
@@ -66,26 +66,23 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "functions=[\n",
+    "functions = [\n",
     "    {\n",
-    "      \"name\": \"get_current_weather\",\n",
-    "      \"description\": \"Get the current weather in a given location\",\n",
-    "      \"parameters\": {\n",
-    "        \"type\": \"object\",\n",
-    "        \"properties\": {\n",
-    "          \"location\": {\n",
-    "            \"type\": \"string\",\n",
-    "            \"description\": \"The city and state, e.g. San Francisco, CA\"\n",
-    "          },\n",
-    "          \"unit\": {\n",
-    "            \"type\": \"string\",\n",
-    "            \"enum\": [\"celsius\", \"fahrenheit\"]\n",
-    "          }\n",
+    "        \"name\": \"get_current_weather\",\n",
+    "        \"description\": \"Get the current weather in a given location\",\n",
+    "        \"parameters\": {\n",
+    "            \"type\": \"object\",\n",
+    "            \"properties\": {\n",
+    "                \"location\": {\n",
+    "                    \"type\": \"string\",\n",
+    "                    \"description\": \"The city and state, e.g. San Francisco, CA\",\n",
+    "                },\n",
+    "                \"unit\": {\"type\": \"string\", \"enum\": [\"celsius\", \"fahrenheit\"]},\n",
+    "            },\n",
+    "            \"required\": [\"location\"],\n",
     "        },\n",
-    "        \"required\": [\"location\"]\n",
-    "      }\n",
     "    }\n",
-    "  ]"
+    "]"
    ]
   },
   {
@@ -106,8 +103,7 @@
    "outputs": [],
    "source": [
     "response = model.predict_messages(\n",
-    "    [HumanMessage(content=\"whats the weater in boston?\")], \n",
-    "    functions=functions\n",
+    "    [HumanMessage(content=\"whats the weater in boston?\")], functions=functions\n",
     ")"
    ]
   },
@@ -150,6 +146,7 @@
    "outputs": [],
    "source": [
     "from langchain.chains import create_extraction_chain\n",
+    "\n",
     "schema = {\n",
     "    \"properties\": {\n",
     "        \"name\": {\"type\": \"string\"},\n",

docs/docs/integrations/chat/anyscale.ipynb

@@ -102,19 +102,15 @@
     "from langchain.schema import SystemMessage, HumanMessage\n",
     "\n",
     "messages = [\n",
-    "    SystemMessage(\n",
-    "        content=\"You are a helpful AI that shares everything you know.\"\n",
-    "    ),\n",
+    "    SystemMessage(content=\"You are a helpful AI that shares everything you know.\"),\n",
     "    HumanMessage(\n",
     "        content=\"Tell me technical facts about yourself. Are you a transformer model? How many billions of parameters do you have?\"\n",
     "    ),\n",
     "]\n",
     "\n",
+    "\n",
     "async def get_msgs():\n",
-    "    tasks = [\n",
-    "        chat.apredict_messages(messages)\n",
-    "        for chat in chats.values()\n",
-    "    ]\n",
+    "    tasks = [chat.apredict_messages(messages) for chat in chats.values()]\n",
     "    responses = await asyncio.gather(*tasks)\n",
     "    return dict(zip(chats.keys(), responses))"
    ]
@@ -194,10 +190,10 @@
     "response_dict = asyncio.run(get_msgs())\n",
     "\n",
     "for model_name, response in response_dict.items():\n",
-    "    print(f'\\t{model_name}')\n",
+    "    print(f\"\\t{model_name}\")\n",
     "    print()\n",
     "    print(response.content)\n",
-    "    print('\\n---\\n')"
+    "    print(\"\\n---\\n\")"
    ]
   }
  ],

docs/docs/integrations/chat/azure_chat_openai.ipynb

@@ -5,18 +5,20 @@
    "id": "38f26d7a",
    "metadata": {},
    "source": [
-    "# Azure\n",
+    "# Azure OpenAI\n",
     "\n",
-    "This notebook goes over how to connect to an Azure hosted OpenAI endpoint"
+    "This notebook goes over how to connect to an Azure hosted OpenAI endpoint. We recommend having version `openai>=1` installed."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "id": "96164b42",
    "metadata": {},
    "outputs": [],
    "source": [
+    "import os\n",
+    "\n",
     "from langchain.chat_models import AzureChatOpenAI\n",
     "from langchain.schema import HumanMessage"
    ]
@@ -24,57 +26,51 @@
   {
    "cell_type": "code",
    "execution_count": 4,
+   "id": "cbe4bb58-ba13-4355-8af9-cd990dc47a64",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "os.environ[\"AZURE_OPENAI_API_KEY\"] = \"...\"\n",
+    "os.environ[\"AZURE_OPENAI_ENDPOINT\"] = \"https://<your-endpoint>.openai.azure.com/\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
    "id": "8161278f",
    "metadata": {},
    "outputs": [],
    "source": [
-    "BASE_URL = \"https://${TODO}.openai.azure.com\"\n",
-    "API_KEY = \"...\"\n",
-    "DEPLOYMENT_NAME = \"chat\"\n",
     "model = AzureChatOpenAI(\n",
-    "    openai_api_base=BASE_URL,\n",
     "    openai_api_version=\"2023-05-15\",\n",
-    "    deployment_name=DEPLOYMENT_NAME,\n",
-    "    openai_api_key=API_KEY,\n",
-    "    openai_api_type=\"azure\",\n",
+    "    azure_deployment=\"your-deployment-name\",\n",
     ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 15,
    "id": "99509140",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"\\n\\nJ'aime programmer.\", additional_kwargs={})"
+       "AIMessage(content=\"J'adore la programmation.\")"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "model(\n",
-    "    [\n",
-    "        HumanMessage(\n",
-    "            content=\"Translate this sentence from English to French. I love programming.\"\n",
-    "        )\n",
-    "    ]\n",
-    ")"
+    "message = HumanMessage(\n",
+    "    content=\"Translate this sentence from English to French. I love programming.\"\n",
+    ")\n",
+    "model([message])"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "3b6e9376",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
   {
    "cell_type": "markdown",
    "id": "f27fa24d",
@@ -88,7 +84,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "id": "0531798a",
    "metadata": {},
    "outputs": [],
@@ -98,49 +94,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
-   "id": "3fd97dfc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "BASE_URL = \"https://{endpoint}.openai.azure.com\"\n",
-    "API_KEY = \"...\"\n",
-    "DEPLOYMENT_NAME = \"gpt-35-turbo\" # in Azure, this deployment has version 0613 - input and output tokens are counted separately"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": null,
    "id": "aceddb72",
    "metadata": {
     "scrolled": true
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Total Cost (USD): $0.000054\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "model = AzureChatOpenAI(\n",
-    "    openai_api_base=BASE_URL,\n",
     "    openai_api_version=\"2023-05-15\",\n",
-    "    deployment_name=DEPLOYMENT_NAME,\n",
-    "    openai_api_key=API_KEY,\n",
-    "    openai_api_type=\"azure\",\n",
+    "    azure_deployment=\"gpt-35-turbo\",  # in Azure, this deployment has version 0613 - input and output tokens are counted separately\n",
     ")\n",
     "with get_openai_callback() as cb:\n",
-    "    model(\n",
-    "        [\n",
-    "            HumanMessage(\n",
-    "                content=\"Translate this sentence from English to French. I love programming.\"\n",
-    "            )\n",
-    "        ]\n",
-    "    )\n",
-    "    print(f\"Total Cost (USD): ${format(cb.total_cost, '.6f')}\") # without specifying the model version, flat-rate 0.002 USD per 1k input and output tokens is used\n"
+    "    model([message])\n",
+    "    print(\n",
+    "        f\"Total Cost (USD): ${format(cb.total_cost, '.6f')}\"\n",
+    "    )  # without specifying the model version, flat-rate 0.002 USD per 1k input and output tokens is used"
    ]
   },
   {
@@ -167,22 +136,13 @@
    ],
    "source": [
     "model0613 = AzureChatOpenAI(\n",
-    "    openai_api_base=BASE_URL,\n",
     "    openai_api_version=\"2023-05-15\",\n",
-    "    deployment_name=DEPLOYMENT_NAME,\n",
-    "    openai_api_key=API_KEY,\n",
-    "    openai_api_type=\"azure\",\n",
-    "    model_version=\"0613\"\n",
+    "    deployment_name=\"gpt-35-turbo,\n",
+    "    model_version=\"0613\",\n",
     ")\n",
     "with get_openai_callback() as cb:\n",
-    "    model0613(\n",
-    "        [\n",
-    "            HumanMessage(\n",
-    "                content=\"Translate this sentence from English to French. I love programming.\"\n",
-    "            )\n",
-    "        ]\n",
-    "    )\n",
-    "    print(f\"Total Cost (USD): ${format(cb.total_cost, '.6f')}\")\n"
+    "    model0613([message])\n",
+    "    print(f\"Total Cost (USD): ${format(cb.total_cost, '.6f')}\")"
    ]
   },
   {
@@ -210,7 +170,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.10"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/azureml_chat_endpoint.ipynb

@@ -67,10 +67,10 @@
     "    endpoint_url=\"https://<your-endpoint>.<your_region>.inference.ml.azure.com/score\",\n",
     "    endpoint_api_key=\"my-api-key\",\n",
     "    content_formatter=LlamaContentFormatter,\n",
-    "))\n",
-    "response = chat(messages=[\n",
-    "    HumanMessage(content=\"Will the Collatz conjecture ever be solved?\")\n",
-    "])\n",
+    ")\n",
+    "response = chat(\n",
+    "    messages=[HumanMessage(content=\"Will the Collatz conjecture ever be solved?\")]\n",
+    ")\n",
     "response"
    ]
   }
@@ -91,9 +91,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.11"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

docs/docs/integrations/chat/baichuan.ipynb

@@ -36,8 +36,7 @@
    "outputs": [],
    "source": [
     "chat = ChatBaichuan(\n",
-    "    baichuan_api_key='YOUR_API_KEY',\n",
-    "    baichuan_secret_key='YOUR_SECRET_KEY'\n",
+    "    baichuan_api_key=\"YOUR_API_KEY\", baichuan_secret_key=\"YOUR_SECRET_KEY\"\n",
     ")"
    ]
   },
@@ -72,9 +71,7 @@
     }
    ],
    "source": [
-    "chat([\n",
-    "    HumanMessage(content='我日薪8块钱，请问在闰年的二月，我月薪多少')\n",
-    "])"
+    "chat([HumanMessage(content=\"我日薪8块钱，请问在闰年的二月，我月薪多少\")])"
    ]
   },
   {
@@ -92,9 +89,9 @@
    "outputs": [],
    "source": [
     "chat = ChatBaichuan(\n",
-    "    baichuan_api_key='YOUR_API_KEY',\n",
-    "    baichuan_secret_key='YOUR_SECRET_KEY',\n",
-    "    streaming=True\n",
+    "    baichuan_api_key=\"YOUR_API_KEY\",\n",
+    "    baichuan_secret_key=\"YOUR_SECRET_KEY\",\n",
+    "    streaming=True,\n",
     ")"
    ],
    "metadata": {
@@ -119,9 +116,7 @@
     }
    ],
    "source": [
-    "chat([\n",
-    "    HumanMessage(content='我日薪8块钱，请问在闰年的二月，我月薪多少')\n",
-    "])"
+    "chat([HumanMessage(content=\"我日薪8块钱，请问在闰年的二月，我月薪多少\")])"
    ],
    "metadata": {
     "collapsed": false,

docs/docs/integrations/chat/baidu_qianfan_endpoint.ipynb

@@ -59,16 +59,17 @@
    ],
    "source": [
     "\"\"\"For basic init and call\"\"\"\n",
-    "from langchain.chat_models import QianfanChatEndpoint \n",
+    "from langchain.chat_models import QianfanChatEndpoint\n",
     "from langchain.chat_models.base import HumanMessage\n",
     "import os\n",
+    "\n",
     "os.environ[\"QIANFAN_AK\"] = \"your_ak\"\n",
     "os.environ[\"QIANFAN_SK\"] = \"your_sk\"\n",
     "\n",
     "chat = QianfanChatEndpoint(\n",
-    "                            streaming=True, \n",
-    "                            )\n",
-    "res = chat([HumanMessage(content=\"write a funny joke\")])\n"
+    "    streaming=True,\n",
+    ")\n",
+    "res = chat([HumanMessage(content=\"write a funny joke\")])"
    ]
   },
   {
@@ -112,7 +113,6 @@
     }
    ],
    "source": [
-    "    \n",
     "from langchain.chat_models import QianfanChatEndpoint\n",
     "from langchain.schema import HumanMessage\n",
     "\n",
@@ -125,15 +125,22 @@
     "\n",
     "\n",
     "async def run_aio_generate():\n",
-    "    resp = await chatLLM.agenerate(messages=[[HumanMessage(content=\"write a 20 words sentence about sea.\")]])\n",
+    "    resp = await chatLLM.agenerate(\n",
+    "        messages=[[HumanMessage(content=\"write a 20 words sentence about sea.\")]]\n",
+    "    )\n",
     "    print(resp)\n",
-    "        \n",
+    "\n",
+    "\n",
     "await run_aio_generate()\n",
     "\n",
+    "\n",
     "async def run_aio_stream():\n",
-    "    async for res in chatLLM.astream([HumanMessage(content=\"write a 20 words sentence about sea.\")]):\n",
+    "    async for res in chatLLM.astream(\n",
+    "        [HumanMessage(content=\"write a 20 words sentence about sea.\")]\n",
+    "    ):\n",
     "        print(\"astream\", res)\n",
-    "        \n",
+    "\n",
+    "\n",
     "await run_aio_stream()"
    ]
   },
@@ -172,9 +179,9 @@
    ],
    "source": [
     "chatBloom = QianfanChatEndpoint(\n",
-    "                            streaming=True, \n",
-    "                            model=\"BLOOMZ-7B\",\n",
-    "                            )\n",
+    "    streaming=True,\n",
+    "    model=\"BLOOMZ-7B\",\n",
+    ")\n",
     "res = chatBloom([HumanMessage(content=\"hi\")])\n",
     "print(res)"
    ]
@@ -217,7 +224,10 @@
     }
    ],
    "source": [
-    "res = chat.stream([HumanMessage(content=\"hi\")], **{'top_p': 0.4, 'temperature': 0.1, 'penalty_score': 1})\n",
+    "res = chat.stream(\n",
+    "    [HumanMessage(content=\"hi\")],\n",
+    "    **{\"top_p\": 0.4, \"temperature\": 0.1, \"penalty_score\": 1}\n",
+    ")\n",
     "\n",
     "for r in res:\n",
     "    print(r)"

docs/docs/integrations/chat/bedrock.ipynb

@@ -1,139 +1,139 @@
 {
-    "cells": [
-        {
-            "cell_type": "markdown",
-            "id": "bf733a38-db84-4363-89e2-de6735c37230",
-            "metadata": {},
-            "source": [
-                "# Bedrock Chat\n",
-                "\n",
-                "[Amazon Bedrock](https://aws.amazon.com/bedrock/) is a fully managed service that makes FMs from leading AI startups and Amazon available via an API, so you can choose from a wide range of FMs to find the model that is best suited for your use case"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": null,
-            "id": "d51edc81",
-            "metadata": {},
-            "outputs": [],
-            "source": [
-                "%pip install boto3"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": null,
-            "id": "d4a7c55d-b235-4ca4-a579-c90cc9570da9",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "from langchain.chat_models import BedrockChat\n",
-                "from langchain.schema import HumanMessage"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 2,
-            "id": "70cf04e8-423a-4ff6-8b09-f11fb711c817",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "chat = BedrockChat(model_id=\"anthropic.claude-v2\", model_kwargs={\"temperature\":0.1})"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 3,
-            "id": "8199ef8f-eb8b-4253-9ea0-6c24a013ca4c",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [
-                {
-                    "data": {
-                        "text/plain": [
-                            "AIMessage(content=\" Voici la traduction en français : J'adore programmer.\", additional_kwargs={}, example=False)"
-                        ]
-                    },
-                    "execution_count": 3,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "messages = [\n",
-                "    HumanMessage(\n",
-                "        content=\"Translate this sentence from English to French. I love programming.\"\n",
-                "    )\n",
-                "]\n",
-                "chat(messages)"
-            ]
-        },
-        {
-            "attachments": {},
-            "cell_type": "markdown",
-            "id": "a4a4f4d4",
-            "metadata": {},
-            "source": [
-                "### For BedrockChat with Streaming"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": null,
-            "id": "c253883f",
-            "metadata": {},
-            "outputs": [],
-            "source": [
-                "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
-                "\n",
-                "chat = BedrockChat(\n",
-                "    model_id=\"anthropic.claude-v2\",\n",
-                "    streaming=True,\n",
-                "    callbacks=[StreamingStdOutCallbackHandler()],\n",
-                "    model_kwargs={\"temperature\": 0.1},\n",
-                ")"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": null,
-            "id": "d9e52838",
-            "metadata": {},
-            "outputs": [],
-            "source": [
-                "messages = [\n",
-                "    HumanMessage(\n",
-                "        content=\"Translate this sentence from English to French. I love programming.\"\n",
-                "    )\n",
-                "]\n",
-                "chat(messages)"
-            ]
-        }
-    ],
-    "metadata": {
-        "kernelspec": {
-            "display_name": "Python 3 (ipykernel)",
-            "language": "python",
-            "name": "python3"
-        },
-        "language_info": {
-            "codemirror_mode": {
-                "name": "ipython",
-                "version": 3
-            },
-            "file_extension": ".py",
-            "mimetype": "text/x-python",
-            "name": "python",
-            "nbconvert_exporter": "python",
-            "pygments_lexer": "ipython3",
-            "version": "3.10.9"
-        }
-    },
-    "nbformat": 4,
-    "nbformat_minor": 5
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "bf733a38-db84-4363-89e2-de6735c37230",
+   "metadata": {},
+   "source": [
+    "# Bedrock Chat\n",
+    "\n",
+    "[Amazon Bedrock](https://aws.amazon.com/bedrock/) is a fully managed service that makes FMs from leading AI startups and Amazon available via an API, so you can choose from a wide range of FMs to find the model that is best suited for your use case"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d51edc81",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install boto3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d4a7c55d-b235-4ca4-a579-c90cc9570da9",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models import BedrockChat\n",
+    "from langchain.schema import HumanMessage"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "70cf04e8-423a-4ff6-8b09-f11fb711c817",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "chat = BedrockChat(model_id=\"anthropic.claude-v2\", model_kwargs={\"temperature\": 0.1})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "8199ef8f-eb8b-4253-9ea0-6c24a013ca4c",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\" Voici la traduction en français : J'adore programmer.\", additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "messages = [\n",
+    "    HumanMessage(\n",
+    "        content=\"Translate this sentence from English to French. I love programming.\"\n",
+    "    )\n",
+    "]\n",
+    "chat(messages)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "a4a4f4d4",
+   "metadata": {},
+   "source": [
+    "### For BedrockChat with Streaming"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c253883f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
+    "\n",
+    "chat = BedrockChat(\n",
+    "    model_id=\"anthropic.claude-v2\",\n",
+    "    streaming=True,\n",
+    "    callbacks=[StreamingStdOutCallbackHandler()],\n",
+    "    model_kwargs={\"temperature\": 0.1},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d9e52838",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages = [\n",
+    "    HumanMessage(\n",
+    "        content=\"Translate this sentence from English to French. I love programming.\"\n",
+    "    )\n",
+    "]\n",
+    "chat(messages)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
 }