Merge branch 'master' into pg/python-3.12

- default MessagesPlaceholder one to list of messages

<!-- Thank you for contributing to LangChain!

Replace this entire comment with:
  - **Description:** a description of the change, 
  - **Issue:** the issue # it fixes (if applicable),
  - **Dependencies:** any dependencies required for this change,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!

Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc:

https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md

If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in `docs/extras`
directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->

.devcontainer/README.md

@@ -5,10 +5,10 @@ This project includes a [dev container](https://containers.dev/), which lets you
 You can use the dev container configuration in this folder to build and run the app without needing to install any of its tools locally! You can use it in [GitHub Codespaces](https://github.com/features/codespaces) or the [VS Code Dev Containers extension](https://marketplace.visualstudio.com/items?itemName=ms-vscode-remote.remote-containers).
 
 ## GitHub Codespaces
-[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/hwchase17/langchain)
+[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/langchain-ai/langchain)
 
 You may use the button above, or follow these steps to open this repo in a Codespace:
-1. Click the **Code** drop-down menu at the top of https://github.com/hwchase17/langchain.
+1. Click the **Code** drop-down menu at the top of https://github.com/langchain-ai/langchain.
 1. Click on the **Codespaces** tab.
 1. Click **Create codespace on master** .
 

.github/CONTRIBUTING.md

@@ -32,7 +32,7 @@ best way to get our attention.
 
 ### 🚩GitHub Issues
 
-Our [issues](https://github.com/hwchase17/langchain/issues) page is kept up to date
+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
@@ -60,11 +60,11 @@ we do not want these to get in the way of getting good code into the codebase.
 ## 🚀 Quick Start
 
 This quick start describes running the repository locally.
-For a [development container](https://containers.dev/), see the [.devcontainer folder](https://github.com/hwchase17/langchain/tree/master/.devcontainer).
+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/) v1.5.1+ as a dependency manager.
+This project uses [Poetry](https://python-poetry.org/) v1.6.1+ as a dependency manager.
 
 ❗Note: *Before installing Poetry*, if you use `Conda`, create and activate a new Conda env (e.g. `conda create -n langchain python=3.9`)
 
@@ -105,8 +105,8 @@ make test
 If the tests don't pass, you may need to pip install additional dependencies, such as `numexpr` and `openapi_schema_pydantic`.
 
 If during installation you receive a `WheelFileValidationError` for `debugpy`, please make sure you are running
-Poetry v1.5.1+. This bug was present in older versions of Poetry (e.g. 1.4.1) and has been resolved in newer releases.
-If you are still seeing this bug on v1.5.1, you may also try disabling "modern installation"
+Poetry v1.6.1+. This bug was present in older versions of Poetry (e.g. 1.4.1) and has been resolved in newer releases.
+If you are still seeing this bug on v1.6.1, you may also try disabling "modern installation"
 (`poetry config installer.modern-installation false`) and re-installing requirements.
 See [this `debugpy` issue](https://github.com/microsoft/debugpy/issues/1246) for more details.
 

.github/ISSUE_TEMPLATE/feature-request.yml

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

.github/PULL_REQUEST_TEMPLATE.md

@@ -10,7 +10,7 @@ Replace this entire comment with:
 Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally.
 
 See contribution guidelines for more information on how to write/run tests, lint, etc: 
-https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
+https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md
 
 If you're adding a new integration, please include:
   1. a test for the integration, preferably unit tests that do not rely on network access,

.github/workflows/_lint.yml

@@ -9,7 +9,7 @@ on:
         description: "From which folder this pipeline executes"
 
 env:
-  POETRY_VERSION: "1.5.1"
+  POETRY_VERSION: "1.6.1"
   WORKDIR: ${{ inputs.working-directory == '' && '.' || inputs.working-directory }}
 
 jobs:
@@ -32,7 +32,7 @@ jobs:
         # so linting on fewer versions makes CI faster.
         python-version:
           - "3.8"
-          - "3.11"
+          - "3.12"
     steps:
       - uses: actions/checkout@v3
         with:

.github/workflows/_pydantic_compatibility.yml

@@ -9,7 +9,7 @@ on:
         description: "From which folder this pipeline executes"
 
 env:
-  POETRY_VERSION: "1.5.1"
+  POETRY_VERSION: "1.6.1"
 
 jobs:
   build:
@@ -24,6 +24,7 @@ jobs:
           - "3.9"
           - "3.10"
           - "3.11"
+          - "3.12"
     name: Pydantic v1/v2 compatibility - Python ${{ matrix.python-version }}
     steps:
       - uses: actions/checkout@v3

.github/workflows/_release.yml

@@ -9,7 +9,7 @@ on:
         description: "From which folder this pipeline executes"
 
 env:
-  POETRY_VERSION: "1.5.1"
+  POETRY_VERSION: "1.6.1"
 
 jobs:
   if_release:

.github/workflows/_release_docker.yml

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

.github/workflows/_test.yml

@@ -9,7 +9,7 @@ on:
         description: "From which folder this pipeline executes"
 
 env:
-  POETRY_VERSION: "1.5.1"
+  POETRY_VERSION: "1.6.1"
 
 jobs:
   build:
@@ -24,6 +24,7 @@ jobs:
           - "3.9"
           - "3.10"
           - "3.11"
+          - "3.12"
     name: Python ${{ matrix.python-version }}
     steps:
       - uses: actions/checkout@v3

.github/workflows/codespell.yml

@@ -18,7 +18,19 @@ jobs:
     steps:
       - name: Checkout
         uses: actions/checkout@v3
+
+      - name: Install Dependencies
+        run: |
+          pip install toml
+
+      - name: Extract Ignore Words List
+        run: |
+          # Use a Python script to extract the ignore words list from pyproject.toml
+          python .github/workflows/extract_ignored_words_list.py
+        id: extract_ignore_words
+
       - name: Codespell
         uses: codespell-project/actions-codespell@v2
         with:
           skip: guide_imports.json
+          ignore_words_list: ${{ steps.extract_ignore_words.outputs.ignore_words_list }}

.github/workflows/extract_ignored_words_list.py

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

.github/workflows/langchain_ci.yml

@@ -26,7 +26,7 @@ concurrency:
   cancel-in-progress: true
 
 env:
-  POETRY_VERSION: "1.5.1"
+  POETRY_VERSION: "1.6.1"
   WORKDIR: "libs/langchain"
 
 jobs:
@@ -63,6 +63,7 @@ jobs:
           - "3.9"
           - "3.10"
           - "3.11"
+          - "3.12"
     name: Python ${{ matrix.python-version }} extended tests
     steps:
       - uses: actions/checkout@v3

.github/workflows/langchain_experimental_ci.yml

@@ -26,7 +26,7 @@ concurrency:
   cancel-in-progress: true
 
 env:
-  POETRY_VERSION: "1.5.1"
+  POETRY_VERSION: "1.6.1"
   WORKDIR: "libs/experimental"
 
 jobs:
@@ -60,6 +60,7 @@ jobs:
           - "3.9"
           - "3.10"
           - "3.11"
+          - "3.12"
     name: test with unpublished langchain - Python ${{ matrix.python-version }}
     steps:
       - uses: actions/checkout@v3
@@ -95,6 +96,7 @@ jobs:
           - "3.9"
           - "3.10"
           - "3.11"
+          - "3.12"
     name: Python ${{ matrix.python-version }} extended tests
     steps:
       - uses: actions/checkout@v3

.github/workflows/langchain_release.yml

@@ -11,3 +11,16 @@ jobs:
     with:
       working-directory: libs/langchain
     secrets: inherit
+
+  # N.B.: It's possible that PyPI doesn't make the new release visible / available
+  #       immediately after publishing. If that happens, the docker build might not
+  #       create a new docker image for the new release, since it won't see it.
+  #
+  #       If this ends up being a problem, add a check to the end of the `_release.yml`
+  #       workflow that prevents the workflow from finishing until the new release
+  #       is visible and installable on PyPI.
+  release-docker:
+    needs:
+      - release
+    uses:
+      ./.github/workflows/langchain_release_docker.yml

.github/workflows/langchain_release_docker.yml

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

.github/workflows/scheduled_test.yml

@@ -6,7 +6,7 @@ on:
     - cron:  '0 13 * * *'
 
 env:
-  POETRY_VERSION: "1.5.1"
+  POETRY_VERSION: "1.6.1"
 
 jobs:
   build:
@@ -22,6 +22,7 @@ jobs:
           - "3.9"
           - "3.10"
           - "3.11"
+          - "3.12"
     name: Python ${{ matrix.python-version }}
     steps:
       - uses: actions/checkout@v3
@@ -40,6 +41,13 @@ jobs:
         with:
           credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
 
+      - name: Configure AWS Credentials
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region: ${{ vars.AWS_REGION }}
+
       - name: Install dependencies
         working-directory: libs/langchain
         shell: bash
@@ -47,11 +55,13 @@ jobs:
           echo "Running scheduled tests, installing dependencies with poetry..."
           poetry install --with=test_integration
           poetry run pip install google-cloud-aiplatform
+          poetry run pip install "boto3>=1.28.57"
 
       - name: Run tests
         shell: bash
         env:
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
         run: |
           make scheduled_tests
 

.gitignore

@@ -30,6 +30,12 @@ share/python-wheels/
 *.egg
 MANIFEST
 
+# Google GitHub Actions credentials files created by:
+# https://github.com/google-github-actions/auth
+#
+# That action recommends adding this gitignore to prevent accidentally committing keys.
+gha-creds-*.json
+
 # PyInstaller
 #  Usually these files are written by a python script from a template
 #  before PyInstaller builds the exe, so as to inject date/other infos into it.

CITATION.cff

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

README.md

@@ -16,7 +16,7 @@
 [![Open Issues](https://img.shields.io/github/issues-raw/langchain-ai/langchain)](https://github.com/langchain-ai/langchain/issues)
 
 
-Looking for the JS/TS version? Check out [LangChain.js](https://github.com/hwchase17/langchainjs).
+Looking for the JS/TS version? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
 
 **Production Support:** As you move your LangChains into production, we'd love to offer more hands-on support.
 Fill out [this form](https://airtable.com/appwQzlErAS2qiP0L/shrGtGaVBVAz7NcV2) to share more about what you're building, and our team will get in touch.
@@ -26,7 +26,7 @@ Fill out [this form](https://airtable.com/appwQzlErAS2qiP0L/shrGtGaVBVAz7NcV2) t
 In an effort to make `langchain` leaner and safer, we are moving select chains to `langchain_experimental`.
 This migration has already started, but we are remaining backwards compatible until 7/28.
 On that date, we will remove functionality from `langchain`.
-Read more about the motivation and the progress [here](https://github.com/hwchase17/langchain/discussions/8043).
+Read more about the motivation and the progress [here](https://github.com/langchain-ai/langchain/discussions/8043).
 Read how to migrate your code [here](MIGRATE.md).
 
 ## Quick Install
@@ -49,7 +49,7 @@ This library aims to assist in the development of those types of applications. C
 **💬 Chatbots**
 
 - [Documentation](https://python.langchain.com/docs/use_cases/chatbots/)
-- End-to-end Example: [Chat-LangChain](https://github.com/hwchase17/chat-langchain)
+- End-to-end Example: [Chat-LangChain](https://github.com/langchain-ai/chat-langchain)
 
 **🤖 Agents**
 

docker/Dockerfile.base

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

docs/docs_skeleton/docs/get_started/introduction.mdx

@@ -20,7 +20,7 @@ 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/hwchase17/langchain). For documentation on [LangChain.js](https://github.com/hwchase17/langchainjs), the JS/TS version, [head here](https://js.langchain.com/docs)._
+_**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)._
 
 ## Modules
 

docs/docs_skeleton/docs/get_started/quickstart.mdx

@@ -42,7 +42,7 @@ There are two types of language models, which in LangChain are called:
 - ChatModels: this is a language model which 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 `ChatMessage`s, and the output is a single `ChatMessage`.
+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:
 
 - `content`: This is the content of the message.
@@ -85,7 +85,7 @@ import InputMessages from "@snippets/get_started/quickstart/input_messages.mdx"
 
 <InputMessages/>
 
-For both these methods, you can also pass in parameters as key word arguments.
+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.
 

docs/docs_skeleton/docs/guides/evaluation/comparison/index.mdx

@@ -16,6 +16,10 @@ Here's a summary of the key methods and properties of a comparison evaluator:
 - `requires_input`: This property indicates whether this evaluator requires an input string.
 - `requires_reference`: This property specifies whether this evaluator requires a reference label.
 
+:::note LangSmith Support
+The [run_on_dataset](https://api.python.langchain.com/en/latest/api_reference.html#module-langchain.smith) evaluation method is designed to evaluate only a single model at a time, and thus, doesn't support these evaluators.
+:::
+
 Detailed information about creating custom evaluators and the available built-in comparison evaluators is provided in the following sections.
 
 import DocCardList from "@theme/DocCardList";

docs/docs_skeleton/docusaurus.config.js

@@ -170,10 +170,20 @@ const config = {
             label: "Integrations",
           },
           {
-            href: "https://api.python.langchain.com",
+            to: "https://api.python.langchain.com",
             label: "API",
             position: "left",
           },
+          {
+            to: "/docs/community",
+            label: "Community",
+            position: "left",
+          },
+          {
+            to: "https://chat.langchain.com",
+            label: "Chat our docs",
+            position: "right",
+          },
           {
             to: "https://smith.langchain.com",
             label: "LangSmith",
@@ -186,7 +196,7 @@ const config = {
           },
           // Please keep GitHub link to the right for consistency.
           {
-            href: "https://github.com/hwchase17/langchain",
+            href: "https://github.com/langchain-ai/langchain",
             position: "right",
             className: "header-github-link",
             "aria-label": "GitHub repository",
@@ -214,11 +224,11 @@ const config = {
             items: [
               {
                 label: "Python",
-                href: "https://github.com/hwchase17/langchain",
+                href: "https://github.com/langchain-ai/langchain",
               },
               {
                 label: "JS/TS",
-                href: "https://github.com/hwchase17/langchainjs",
+                href: "https://github.com/langchain-ai/langchainjs",
               },
             ],
           },

docs/docs_skeleton/package-lock.json

@@ -12,7 +12,7 @@
         "@docusaurus/preset-classic": "2.4.0",
         "@docusaurus/remark-plugin-npm2yarn": "^2.4.0",
         "@mdx-js/react": "^1.6.22",
-        "@mendable/search": "^0.0.150",
+        "@mendable/search": "^0.0.160",
         "clsx": "^1.2.1",
         "json-loader": "^0.5.7",
         "process": "^0.11.10",
@@ -3212,9 +3212,9 @@
       }
     },
     "node_modules/@mendable/search": {
-      "version": "0.0.150",
-      "resolved": "https://registry.npmjs.org/@mendable/search/-/search-0.0.150.tgz",
-      "integrity": "sha512-Eb5SeAWlMxzEim/8eJ/Ysn01Pyh39xlPBzRBw/5OyOBhti0HVLXk4wd1Fq2TKgJC2ppQIvhEKO98PUcj9dNDFw==",
+      "version": "0.0.160",
+      "resolved": "https://registry.npmjs.org/@mendable/search/-/search-0.0.160.tgz",
+      "integrity": "sha512-Lq9Cy176iVeUlSS9PALyc0KPgMWv9MELgsDKXKLhyoPS85yQXs0uEpC2Zgf9i+R4jar5PibKZPh2Hj2xIm/Ajg==",
       "dependencies": {
         "html-react-parser": "^4.2.0",
         "posthog-js": "^1.45.1"

docs/docs_skeleton/package.json

@@ -23,7 +23,7 @@
     "@docusaurus/preset-classic": "2.4.0",
     "@docusaurus/remark-plugin-npm2yarn": "^2.4.0",
     "@mdx-js/react": "^1.6.22",
-    "@mendable/search": "^0.0.150",
+    "@mendable/search": "^0.0.160",
     "clsx": "^1.2.1",
     "json-loader": "^0.5.7",
     "process": "^0.11.10",

docs/docs_skeleton/sidebars.js

@@ -67,7 +67,7 @@ module.exports = {
     },
     {
       type: "category",
-      label: "Additional resources",
+      label: "More",
       collapsed: true,
       items: [
         { type: "autogenerated", dirName: "additional_resources" },
@@ -77,8 +77,7 @@ module.exports = {
         type: 'generated-index',
         slug: "additional_resources",
       },
-    },
-    'community'
+    }
   ],
   integrations: [
     {

docs/docs_skeleton/src/css/custom.css

@@ -36,13 +36,11 @@
   --ifm-color-primary-lightest: #4fddbf;
 }
 
-/* Reduce width on mobile for Mendable Search */
-@media (max-width: 767px) {
-  .mendable-search {
-    width: 200px;
-  }
+.mendable-search {
+  width: 175px;
 }
 
+/* Reduce width on mobile for Mendable Search */
 @media (max-width: 500px) {
   .mendable-search {
     width: 150px;
@@ -157,4 +155,6 @@
 [data-theme='dark'] .header-github-link::before {
   background: url("data:image/svg+xml,%3Csvg viewBox='0 0 24 24' xmlns='http://www.w3.org/2000/svg'%3E%3Cpath fill='white' d='M12 .297c-6.63 0-12 5.373-12 12 0 5.303 3.438 9.8 8.205 11.385.6.113.82-.258.82-.577 0-.285-.01-1.04-.015-2.04-3.338.724-4.042-1.61-4.042-1.61C4.422 18.07 3.633 17.7 3.633 17.7c-1.087-.744.084-.729.084-.729 1.205.084 1.838 1.236 1.838 1.236 1.07 1.835 2.809 1.305 3.495.998.108-.776.417-1.305.76-1.605-2.665-.3-5.466-1.332-5.466-5.93 0-1.31.465-2.38 1.235-3.22-.135-.303-.54-1.523.105-3.176 0 0 1.005-.322 3.3 1.23.96-.267 1.98-.399 3-.405 1.02.006 2.04.138 3 .405 2.28-1.552 3.285-1.23 3.285-1.23.645 1.653.24 2.873.12 3.176.765.84 1.23 1.91 1.23 3.22 0 4.61-2.805 5.625-5.475 5.92.42.36.81 1.096.81 2.22 0 1.606-.015 2.896-.015 3.286 0 .315.21.69.825.57C20.565 22.092 24 17.592 24 12.297c0-6.627-5.373-12-12-12'/%3E%3C/svg%3E")
     no-repeat;
-}
+}
+
+

docs/docs_skeleton/src/theme/SearchBar.js

@@ -19,9 +19,14 @@ export default function SearchBarWrapper() {
       <MendableSearchBar
         anon_key={customFields.mendableAnonKey}
         style={{ accentColor: "#4F956C", darkMode: false }}
-        placeholder="Search..."
+        placeholder="Search"
         dialogPlaceholder="How do I use a LLM Chain?"
         messageSettings={{ openSourcesInNewTab: false, prettySources: true }}
+        searchBarStyle={{
+          borderColor: "#9d9ea1",
+          color:"#9d9ea1"
+        }}
+        askAIText="Ask Mendable AI"
         isPinnable
         showSimpleSearch
       />

docs/docs_skeleton/vercel.json

@@ -2628,6 +2628,18 @@
       "source": "/docs/modules/memory/integrations/cassandra_chat_message_history",
       "destination": "/docs/integrations/memory/cassandra_chat_message_history"
     },
+    {
+      "source": "/docs/integrations/memory/motorhead_memory_managed",
+      "destination": "/docs/integrations/memory/motorhead_memory"
+    },
+    {
+      "source": "/docs/integrations/memory/dynamodb_chat_message_history",
+      "destination": "/docs/integrations/memory/aws_dynamodb"
+    },
+    {
+      "source": "/docs/integrations/memory/entity_memory_with_sqlite",
+      "destination": "/docs/integrations/memory/sqlite"
+    },
     {
       "source": "/en/latest/modules/memory/examples/dynamodb_chat_message_history.html",
       "destination": "/docs/integrations/memory/dynamodb_chat_message_history"

docs/extras/additional_resources/dependents.mdx

@@ -39,7 +39,7 @@ Dependents stats for `langchain-ai/langchain`
 |[go-skynet/LocalAI](https://github.com/go-skynet/LocalAI) | 9955 |
 |[AIGC-Audio/AudioGPT](https://github.com/AIGC-Audio/AudioGPT) | 9081 |
 |[gventuri/pandas-ai](https://github.com/gventuri/pandas-ai) | 8201 |
-|[hwchase17/langchainjs](https://github.com/hwchase17/langchainjs) | 7754 |
+|[langchain-ai/langchainjs](https://github.com/langchain-ai/langchainjs) | 7754 |
 |[langgenius/dify](https://github.com/langgenius/dify) | 7348 |
 |[PipedreamHQ/pipedream](https://github.com/PipedreamHQ/pipedream) | 6950 |
 |[h2oai/h2ogpt](https://github.com/h2oai/h2ogpt) | 6858 |

docs/extras/additional_resources/tutorials.mdx

@@ -2,7 +2,7 @@
 
 Below are links to tutorials and courses on LangChain. For written guides on common use cases for LangChain, check out the [use cases guides](/docs/use_cases).
 
-⛓ icon marks a new addition [last update 2023-08-20]
+⛓ icon marks a new addition [last update 2023-09-21]
 
 ---------------------
 
@@ -15,12 +15,11 @@ Below are links to tutorials and courses on LangChain. For written guides on com
 [LangChain AI Handbook](https://www.pinecone.io/learn/langchain/) By **James Briggs** and **Francisco Ingham**
 
 ### Short Tutorials
-[LangChain Crash Course - Build apps with language models](https://youtu.be/LbT1yp6quS8) by [Patrick Loeber](https://www.youtube.com/@patloeber)
+[LangChain Explained in 13 Minutes | QuickStart Tutorial for Beginners](https://youtu.be/aywZrzNaKjs) by [Rabbitmetrics](https://www.youtube.com/@rabbitmetrics)
 
 [LangChain Crash Course: Build an AutoGPT app in 25 minutes](https://youtu.be/MlK6SIjcjE8) by [Nicholas Renotte](https://www.youtube.com/@NicholasRenotte)
 
-[LangChain Explained in 13 Minutes | QuickStart Tutorial for Beginners](https://youtu.be/aywZrzNaKjs) by [Rabbitmetrics](https://www.youtube.com/@rabbitmetrics)
-
+[LangChain Crash Course - Build apps with language models](https://youtu.be/LbT1yp6quS8) by [Patrick Loeber](https://www.youtube.com/@patloeber)
 
 ##  Tutorials
 
@@ -37,6 +36,8 @@ Below are links to tutorials and courses on LangChain. For written guides on com
 - #9 [Build Conversational Agents with Vector DBs](https://youtu.be/H6bCqqw9xyI)
 - [Using NEW `MPT-7B` in Hugging Face and LangChain](https://youtu.be/DXpk9K7DgMo)
 - [`MPT-30B` Chatbot with LangChain](https://youtu.be/pnem-EhT6VI)
+- ⛓ [Fine-tuning OpenAI's `GPT 3.5` for LangChain Agents](https://youtu.be/boHXgQ5eQic?si=OOOfK-GhsgZGBqSr)
+- ⛓ [Chatbots with `RAG`: LangChain Full Walkthrough](https://youtu.be/LhnCsygAvzY?si=N7k6xy4RQksbWwsQ)
 
 
 ### [LangChain 101](https://www.youtube.com/playlist?list=PLqZXAkvF1bPNQER9mLmDbntNfSpzdDIU5) by [Greg Kamradt (Data Indy)](https://www.youtube.com/@DataIndependent)
@@ -100,6 +101,16 @@ Below are links to tutorials and courses on LangChain. For written guides on com
 - [What can you do with 16K tokens in LangChain?](https://youtu.be/z2aCZBAtWXs)
 - [Tagging and Extraction - Classification using `OpenAI Functions`](https://youtu.be/a8hMgIcUEnE)
 - [HOW to Make Conversational Form with LangChain](https://youtu.be/IT93On2LB5k)
+- ⛓ [`Claude-2` meets LangChain!](https://youtu.be/Hb_D3p0bK2U?si=j96Kc7oJoeRI5-iC)
+- ⛓ [`PaLM 2` Meets LangChain](https://youtu.be/orPwLibLqm4?si=KgJjpEbAD9YBPqT4)
+- ⛓ [`LLaMA2` with LangChain - Basics | LangChain TUTORIAL](https://youtu.be/cIRzwSXB4Rc?si=v3Hwxk1m3fksBIHN)
+- ⛓ [Serving `LLaMA2` with `Replicate`](https://youtu.be/JIF4nNi26DE?si=dSazFyC4UQmaR-rJ)
+- ⛓ [NEW LangChain Expression Language](https://youtu.be/ud7HJ2p3gp0?si=8pJ9O6hGbXrCX5G9)
+- ⛓ [Building a RCI Chain for Agents with LangChain Expression Language](https://youtu.be/QaKM5s0TnsY?si=0miEj-o17AHcGfLG)
+- ⛓ [How to Run `LLaMA-2-70B` on the `Together AI`](https://youtu.be/Tc2DHfzHeYE?si=Xku3S9dlBxWQukpe)
+- ⛓ [`RetrievalQA` with `LLaMA 2 70b` & `Chroma` DB](https://youtu.be/93yueQQnqpM?si=ZMwj-eS_CGLnNMXZ)
+- ⛓ [How to use `BGE Embeddings` for LangChain](https://youtu.be/sWRvSG7vL4g?si=85jnvnmTCF9YIWXI)
+- ⛓ [How to use Custom Prompts for `RetrievalQA` on `LLaMA-2 7B`](https://youtu.be/PDwUKves9GY?si=sMF99TWU0p4eiK80)
 
 
 ### [LangChain](https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr) by [Prompt Engineering](https://www.youtube.com/@engineerprompt)
@@ -107,23 +118,26 @@ Below are links to tutorials and courses on LangChain. For written guides on com
 - [Working with MULTIPLE `PDF` Files in LangChain: `ChatGPT` for your Data](https://youtu.be/s5LhRdh5fu4)
 - [`ChatGPT` for YOUR OWN `PDF` files with LangChain](https://youtu.be/TLf90ipMzfE)
 - [Talk to YOUR DATA without OpenAI APIs: LangChain](https://youtu.be/wrD-fZvT6UI)
-- [LangChain: PDF Chat App (GUI) | ChatGPT for Your PDF FILES](https://youtu.be/RIWbalZ7sTo)
-- [LangFlow: Build Chatbots without Writing Code](https://youtu.be/KJ-ux3hre4s)
+- [LangChain: `PDF` Chat App (GUI) | `ChatGPT` for Your `PDF` FILES](https://youtu.be/RIWbalZ7sTo)
+- [`LangFlow`: Build Chatbots without Writing Code](https://youtu.be/KJ-ux3hre4s)
 - [LangChain: Giving Memory to LLMs](https://youtu.be/dxO6pzlgJiY)
 - [BEST OPEN Alternative to `OPENAI's EMBEDDINGs` for Retrieval QA: LangChain](https://youtu.be/ogEalPMUCSY)
+- [LangChain: Run Language Models Locally - `Hugging Face Models`](https://youtu.be/Xxxuw4_iCzw) 
+- ⛓ [Slash API Costs: Mastering Caching for LLM Applications](https://youtu.be/EQOznhaJWR0?si=AXoI7f3-SVFRvQUl)
+- ⛓ [Avoid PROMPT INJECTION with `Constitutional AI` - LangChain](https://youtu.be/tyKSkPFHVX8?si=9mgcB5Y1kkotkBGB)
 
 
 ### LangChain by [Chat with data](https://www.youtube.com/@chatwithdata)
 - [LangChain Beginner's Tutorial for `Typescript`/`Javascript`](https://youtu.be/bH722QgRlhQ)
 - [`GPT-4` Tutorial: How to Chat With Multiple `PDF` Files (~1000 pages of Tesla's 10-K Annual Reports)](https://youtu.be/Ix9WIZpArm0)
 - [`GPT-4` & LangChain Tutorial: How to Chat With A 56-Page `PDF` Document (w/`Pinecone`)](https://youtu.be/ih9PBGVVOO4)
-- [LangChain & Supabase Tutorial: How to Build a ChatGPT Chatbot For Your Website](https://youtu.be/R2FMzcsmQY8)
+- [LangChain & `Supabase` Tutorial: How to Build a ChatGPT Chatbot For Your Website](https://youtu.be/R2FMzcsmQY8)
 - [LangChain Agents: Build Personal Assistants For Your Data (Q&A with Harrison Chase and Mayo Oshin)](https://youtu.be/gVkF8cwfBLI)
 
 
 ### Codebase Analysis
-- ⛓ [Codebase Analysis: Langchain Agents](https://carbonated-yacht-2c5.notion.site/Codebase-Analysis-Langchain-Agents-0b0587acd50647ca88aaae7cff5df1f2)
+- [Codebase Analysis: Langchain Agents](https://carbonated-yacht-2c5.notion.site/Codebase-Analysis-Langchain-Agents-0b0587acd50647ca88aaae7cff5df1f2)
 
 
 ---------------------
-⛓ icon marks a new addition [last update 2023-08-20]
+⛓ icon marks a new addition [last update 2023-09-21]

docs/extras/additional_resources/youtube.mdx

@@ -1,6 +1,6 @@
 # YouTube videos
 
-⛓ icon marks a new addition [last update 2023-09-05]
+⛓ icon marks a new addition [last update 2023-09-21]
 
 ### [Official LangChain YouTube channel](https://www.youtube.com/@LangChain)
 
@@ -12,7 +12,7 @@
 
 ## Videos (sorted by views)
 
-- [Building AI LLM Apps with LangChain (and more?) - LIVE STREAM](https://www.youtube.com/live/M-2Cj_2fzWI?feature=share) by [Nicholas Renotte](https://www.youtube.com/@NicholasRenotte)
+- [Using `ChatGPT` with YOUR OWN Data. This is magical. (LangChain OpenAI API)](https://youtu.be/9AXP7tCI9PI) by [TechLead](https://www.youtube.com/@TechLead)
 - [First look - `ChatGPT` + `WolframAlpha` (`GPT-3.5` and Wolfram|Alpha via LangChain by James Weaver)](https://youtu.be/wYGbY811oMo) by [Dr Alan D. Thompson](https://www.youtube.com/@DrAlanDThompson) 
 - [LangChain explained - The hottest new Python framework](https://youtu.be/RoR4XJw8wIc) by [AssemblyAI](https://www.youtube.com/@AssemblyAI)
 - [Chatbot with INFINITE MEMORY using `OpenAI` & `Pinecone` - `GPT-3`, `Embeddings`, `ADA`, `Vector DB`, `Semantic`](https://youtu.be/2xNzB7xq8nk) by [David Shapiro ~ AI](https://www.youtube.com/@DavidShapiroAutomator)
@@ -34,7 +34,7 @@
   - [LangChain, Chroma DB, OpenAI Beginner Guide | ChatGPT with your PDF](https://youtu.be/FuqdVNB_8c0)
   - [LangChain 101: The Complete Beginner's Guide](https://youtu.be/P3MAbZ2eMUI)
 - [Custom langchain Agent & Tools with memory. Turn any `Python function` into langchain tool with Gpt 3](https://youtu.be/NIG8lXk0ULg) by [echohive](https://www.youtube.com/@echohive)
-- [LangChain: Run Language Models Locally - `Hugging Face Models`](https://youtu.be/Xxxuw4_iCzw) by [Prompt Engineering](https://www.youtube.com/@engineerprompt)
+- [Building AI LLM Apps with LangChain (and more?) - LIVE STREAM](https://www.youtube.com/live/M-2Cj_2fzWI?feature=share) by [Nicholas Renotte](https://www.youtube.com/@NicholasRenotte)
 - [`ChatGPT` with any `YouTube` video using langchain and `chromadb`](https://youtu.be/TQZfB2bzVwU) by [echohive](https://www.youtube.com/@echohive)
 - [How to Talk to a `PDF` using LangChain and `ChatGPT`](https://youtu.be/v2i1YDtrIwk) by [Automata Learning Lab](https://www.youtube.com/@automatalearninglab)
 - [Langchain Document Loaders Part 1: Unstructured Files](https://youtu.be/O5C0wfsen98) by [Merk](https://www.youtube.com/@merksworld) 
@@ -67,7 +67,6 @@
 - [Use Large Language Models in Jupyter Notebook | LangChain | Agents & Indexes](https://youtu.be/JSe11L1a_QQ) by [Abhinaw Tiwari](https://www.youtube.com/@AbhinawTiwariAT)
 - [How to Talk to Your Langchain Agent | `11 Labs` + `Whisper`](https://youtu.be/N4k459Zw2PU) by [VRSEN](https://www.youtube.com/@vrsen)
 - [LangChain Deep Dive: 5 FUN AI App Ideas To Build Quickly and Easily](https://youtu.be/mPYEPzLkeks) by [James NoCode](https://www.youtube.com/@jamesnocode)
-- [BEST OPEN Alternative to OPENAI's EMBEDDINGs for Retrieval QA: LangChain](https://youtu.be/ogEalPMUCSY) by [Prompt Engineering](https://www.youtube.com/@engineerprompt)
 - [LangChain 101: Models](https://youtu.be/T6c_XsyaNSQ) by [Mckay Wrigley](https://www.youtube.com/@realmckaywrigley)
 - [LangChain with JavaScript Tutorial #1 | Setup & Using LLMs](https://youtu.be/W3AoeMrg27o) by [Leon van Zyl](https://www.youtube.com/@leonvanzyl)
 - [LangChain Overview & Tutorial for Beginners: Build Powerful AI Apps Quickly & Easily (ZERO CODE)](https://youtu.be/iI84yym473Q) by [James NoCode](https://www.youtube.com/@jamesnocode)
@@ -91,15 +90,36 @@
 - [Chat with Multiple `PDFs` | LangChain App Tutorial in Python (Free LLMs and Embeddings)](https://youtu.be/dXxQ0LR-3Hg) by [Alejandro AO - Software & Ai](https://www.youtube.com/@alejandro_ao)
 - [Chat with a `CSV` | `LangChain Agents` Tutorial (Beginners)](https://youtu.be/tjeti5vXWOU) by [Alejandro AO - Software & Ai](https://www.youtube.com/@alejandro_ao)
 - [Create Your Own ChatGPT with `PDF` Data in 5 Minutes (LangChain Tutorial)](https://youtu.be/au2WVVGUvc8) by [Liam Ottley](https://www.youtube.com/@LiamOttley)
-- [Using ChatGPT with YOUR OWN Data. This is magical. (LangChain OpenAI API)](https://youtu.be/9AXP7tCI9PI) by [TechLead](https://www.youtube.com/@TechLead)
 - [Build a Custom Chatbot with OpenAI: `GPT-Index` & LangChain | Step-by-Step Tutorial](https://youtu.be/FIDv6nc4CgU) by [Fabrikod](https://www.youtube.com/@fabrikod)
 - [`Flowise` is an open source no-code UI visual tool to build 🦜🔗LangChain applications](https://youtu.be/CovAPtQPU0k) by [Cobus Greyling](https://www.youtube.com/@CobusGreylingZA)
 - [LangChain & GPT 4 For Data Analysis: The `Pandas` Dataframe Agent](https://youtu.be/rFQ5Kmkd4jc) by [Rabbitmetrics](https://www.youtube.com/@rabbitmetrics)
 - [`GirlfriendGPT` - AI girlfriend with LangChain](https://youtu.be/LiN3D1QZGQw) by [Toolfinder AI](https://www.youtube.com/@toolfinderai)
-- [`PrivateGPT`: Chat to your FILES OFFLINE and FREE [Installation and Tutorial]](https://youtu.be/G7iLllmx4qc) by [Prompt Engineering](https://www.youtube.com/@engineerprompt)
 - [How to build with Langchain 10x easier | ⛓️ LangFlow & `Flowise`](https://youtu.be/Ya1oGL7ZTvU) by [AI Jason](https://www.youtube.com/@AIJasonZ)
 - [Getting Started With LangChain In 20 Minutes- Build Celebrity Search Application](https://youtu.be/_FpT1cwcSLg) by [Krish Naik](https://www.youtube.com/@krishnaik06)
-- ⛓ [LangChain HowTo and Guides YouTube playlist](https://www.youtube.com/playlist?list=PL8motc6AQftk1Bs42EW45kwYbyJ4jOdiZ) by [Sam Witteveen](https://www.youtube.com/@samwitteveenai/)
+- ⛓ [Vector Embeddings Tutorial – Code Your Own AI Assistant with `GPT-4 API` + LangChain + NLP](https://youtu.be/yfHHvmaMkcA?si=5uJhxoh2tvdnOXok) by [FreeCodeCamp.org](https://www.youtube.com/@freecodecamp)
+- ⛓ [Fully LOCAL `Llama 2` Q&A with LangChain](https://youtu.be/wgYctKFnQ74?si=UX1F3W-B3MqF4-K-) by [1littlecoder](https://www.youtube.com/@1littlecoder)
+- ⛓ [Fully LOCAL `Llama 2` Langchain on CPU](https://youtu.be/yhECvKMu8kM?si=IvjxwlA1c09VwHZ4) by [1littlecoder](https://www.youtube.com/@1littlecoder)
+- ⛓ [Build LangChain Audio Apps with Python in 5 Minutes](https://youtu.be/7w7ysaDz2W4?si=BvdMiyHhormr2-vr) by [AssemblyAI](https://www.youtube.com/@AssemblyAI)
+- ⛓ [`Voiceflow` & `Flowise`: Want to Beat Competition? New Tutorial with Real AI Chatbot](https://youtu.be/EZKkmeFwag0?si=-4dETYDHEstiK_bb) by [AI SIMP](https://www.youtube.com/@aisimp)
+- ⛓ [THIS Is How You Build Production-Ready AI Apps (`LangSmith` Tutorial)](https://youtu.be/tFXm5ijih98?si=lfiqpyaivxHFyI94) by [Dave Ebbelaar](https://www.youtube.com/@daveebbelaar)
+- ⛓ [Build POWERFUL LLM Bots EASILY with Your Own Data - `Embedchain` - Langchain 2.0? (Tutorial)](https://youtu.be/jE24Y_GasE8?si=0yEDZt3BK5Q-LIuF) by [WorldofAI](https://www.youtube.com/@intheworldofai)
+- ⛓ [`Code Llama` powered Gradio App for Coding: Runs on CPU](https://youtu.be/AJOhV6Ryy5o?si=ouuQT6IghYlc1NEJ) by [AI Anytime](https://www.youtube.com/@AIAnytime)
+- ⛓ [LangChain Complete Course in One Video | Develop LangChain (AI) Based Solutions for Your Business](https://youtu.be/j9mQd-MyIg8?si=_wlNT3nP2LpDKztZ) by [UBprogrammer](https://www.youtube.com/@UBprogrammer)
+- ⛓ [How to Run `LLaMA` Locally on CPU or GPU | Python & Langchain & CTransformers Guide](https://youtu.be/SvjWDX2NqiM?si=DxFml8XeGhiLTzLV) by [Code With Prince](https://www.youtube.com/@CodeWithPrince)
+- ⛓ [PyData Heidelberg #11 - TimeSeries Forecasting & LLM Langchain](https://www.youtube.com/live/Glbwb5Hxu18?si=PIEY8Raq_C9PCHuW) by [PyData](https://www.youtube.com/@PyDataTV)
+- ⛓ [Prompt Engineering in Web Development | Using LangChain and Templates with OpenAI](https://youtu.be/pK6WzlTOlYw?si=fkcDQsBG2h-DM8uQ) by [Akamai Developer
+](https://www.youtube.com/@AkamaiDeveloper)
+- ⛓ [Retrieval-Augmented Generation (RAG) using LangChain and `Pinecone` - The RAG Special Episode](https://youtu.be/J_tCD_J6w3s?si=60Mnr5VD9UED9bGG) by [Generative AI and Data Science On AWS](https://www.youtube.com/@GenerativeAIDataScienceOnAWS)
+- ⛓ [`LLAMA2 70b-chat` Multiple Documents Chatbot with Langchain & Streamlit |All OPEN SOURCE|Replicate API](https://youtu.be/vhghB81vViM?si=dszzJnArMeac7lyc) by [DataInsightEdge](https://www.youtube.com/@DataInsightEdge01)
+- ⛓ [Chatting with 44K Fashion Products: LangChain Opportunities and Pitfalls](https://youtu.be/Zudgske0F_s?si=8HSshHoEhh0PemJA) by [Rabbitmetrics](https://www.youtube.com/@rabbitmetrics)
+- ⛓ [Structured Data Extraction from `ChatGPT` with LangChain](https://youtu.be/q1lYg8JISpQ?si=0HctzOHYZvq62sve) by [MG](https://www.youtube.com/@MG_cafe)
+- ⛓ [Chat with Multiple PDFs using `Llama 2`, `Pinecone` and LangChain (Free LLMs and Embeddings)](https://youtu.be/TcJ_tVSGS4g?si=FZYnMDJyoFfL3Z2i) by [Muhammad Moin](https://www.youtube.com/@muhammadmoinfaisal)
+- ⛓ [Integrate Audio into `LangChain.js` apps in 5 Minutes](https://youtu.be/hNpUSaYZIzs?si=Gb9h7W9A8lzfvFKi) by [AssemblyAI](https://www.youtube.com/@AssemblyAI)
+- ⛓ [`ChatGPT` for your data with Local LLM](https://youtu.be/bWrjpwhHEMU?si=uM6ZZ18z9og4M90u) by [Jacob Jedryszek](https://www.youtube.com/@jj09)
+- ⛓ [Training `Chatgpt` with your personal data using langchain step by step in detail](https://youtu.be/j3xOMde2v9Y?si=179HsiMU-hEPuSs4) by [NextGen Machines](https://www.youtube.com/@MayankGupta-kb5yc)
+- ⛓ [Use ANY language in `LangSmith` with REST](https://youtu.be/7BL0GEdMmgY?si=iXfOEdBLqXF6hqRM) by [Nerding I/O](https://www.youtube.com/@nerding_io)
+- ⛓ [How to Leverage the Full Potential of LLMs for Your Business with Langchain - Leon Ruddat](https://youtu.be/vZmoEa7oWMg?si=ZhMmydq7RtkZd56Q) by [PyData](https://www.youtube.com/@PyDataTV)
+- ⛓ [`ChatCSV` App: Chat with CSV files using LangChain and `Llama 2`](https://youtu.be/PvsMg6jFs8E?si=Qzg5u5gijxj933Ya) by [Muhammad Moin](https://www.youtube.com/@muhammadmoinfaisal)
 
 
 ### [Prompt Engineering and LangChain](https://www.youtube.com/watch?v=muXbPpG_ys4&list=PLEJK-H61Xlwzm5FYLDdKt_6yibO33zoMW) by [Venelin Valkov](https://www.youtube.com/@venelin_valkov)
@@ -112,4 +132,4 @@
 
 
 ---------------------
-⛓ icon marks a new addition [last update 2023-06-20]
+⛓ icon marks a new addition [last update 2023-09-21]

docs/extras/expression_language/interface.ipynb

@@ -34,7 +34,9 @@
     "| --- | --- |\n",
     "|Prompt|Dictionary|\n",
     "|Retriever|Single string|\n",
-    "|Model| Single string, list of chat messages or a PromptValue|\n",
+    "|LLM, ChatModel| Single string, list of chat messages or a PromptValue|\n",
+    "|Tool|Single string, or dictionary, depending on the tool|\n",
+    "|OutputParser|The output of an LLM or ChatModel|\n",
     "\n",
     "The output type also varies by component:\n",
     "\n",
@@ -44,6 +46,8 @@
     "| ChatModel | ChatMessage |\n",
     "| Prompt | PromptValue |\n",
     "| Retriever | List of documents |\n",
+    "| Tool | Depends on the tool |\n",
+    "| OutputParser | Depends on the parser |\n",
     "\n",
     "Let's take a look at these methods! To do so, we'll create a super simple PromptTemplate + ChatModel chain."
    ]
@@ -303,7 +307,7 @@
    "source": [
     "## Parallelism\n",
     "\n",
-    "Let's take a look at how LangChain Expression Language support parralel requests as much as possible. For example, when using a RunnableMapping (often written as a dictionary) it executes each element in parralel."
+    "Let's take a look at how LangChain Expression Language support parallel requests as much as possible. For example, when using a RunnableMap (often written as a dictionary) it executes each element in parallel."
    ]
   },
   {

docs/extras/guides/evaluation/comparison/custom.ipynb

@@ -1,280 +1,281 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "657d2c8c-54b4-42a3-9f02-bdefa0ed6728",
-   "metadata": {},
-   "source": [
-    "# Custom Pairwise Evaluator\n",
-    "\n",
-    "You can make your own pairwise string evaluators by inheriting from `PairwiseStringEvaluator` class and overwriting the `_evaluate_string_pairs` method (and the `_aevaluate_string_pairs` method if you want to use the evaluator asynchronously).\n",
-    "\n",
-    "In this example, you will make a simple custom evaluator that just returns whether the first prediction has more whitespace tokenized 'words' than the second.\n",
-    "\n",
-    "You can check out the reference docs for the [PairwiseStringEvaluator interface](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.schema.PairwiseStringEvaluator.html#langchain.evaluation.schema.PairwiseStringEvaluator) for more info.\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "93f3a653-d198-4291-973c-8d1adba338b2",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from typing import Optional, Any\n",
-    "from langchain.evaluation import PairwiseStringEvaluator\n",
-    "\n",
-    "\n",
-    "class LengthComparisonPairwiseEvalutor(PairwiseStringEvaluator):\n",
-    "    \"\"\"\n",
-    "    Custom evaluator to compare two strings.\n",
-    "    \"\"\"\n",
-    "\n",
-    "    def _evaluate_string_pairs(\n",
-    "        self,\n",
-    "        *,\n",
-    "        prediction: str,\n",
-    "        prediction_b: str,\n",
-    "        reference: Optional[str] = None,\n",
-    "        input: Optional[str] = None,\n",
-    "        **kwargs: Any,\n",
-    "    ) -> dict:\n",
-    "        score = int(len(prediction.split()) > len(prediction_b.split()))\n",
-    "        return {\"score\": score}"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "7d4a77c3-07a7-4076-8e7f-f9bca0d6c290",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'score': 1}"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "evaluator = LengthComparisonPairwiseEvalutor()\n",
-    "\n",
-    "evaluator.evaluate_string_pairs(\n",
-    "    prediction=\"The quick brown fox jumped over the lazy dog.\",\n",
-    "    prediction_b=\"The quick brown fox jumped over the dog.\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "d90f128f-6f49-42a1-b05a-3aea568ee03b",
-   "metadata": {},
-   "source": [
-    "## LLM-Based Example\n",
-    "\n",
-    "That example was simple to illustrate the API, but it wasn't very useful in practice. Below, use an LLM with some custom instructions to form a simple preference scorer similar to the built-in [PairwiseStringEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain.html#langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain). We will use `ChatAnthropic` for the evaluator chain."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "b4b43098-4d96-417b-a8a9-b3e75779cfe8",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "# %pip install anthropic\n",
-    "# %env ANTHROPIC_API_KEY=YOUR_API_KEY"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "b6e978ab-48f1-47ff-9506-e13b1a50be6e",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from typing import Optional, Any\n",
-    "from langchain.evaluation import PairwiseStringEvaluator\n",
-    "from langchain.chat_models import ChatAnthropic\n",
-    "from langchain.chains import LLMChain\n",
-    "\n",
-    "\n",
-    "class CustomPreferenceEvaluator(PairwiseStringEvaluator):\n",
-    "    \"\"\"\n",
-    "    Custom evaluator to compare two strings using a custom LLMChain.\n",
-    "    \"\"\"\n",
-    "\n",
-    "    def __init__(self) -> None:\n",
-    "        llm = ChatAnthropic(model=\"claude-2\", temperature=0)\n",
-    "        self.eval_chain = LLMChain.from_string(\n",
-    "            llm,\n",
-    "            \"\"\"Which option is preferred? Do not take order into account. Evaluate based on accuracy and helpfulness. If neither is preferred, respond with C. Provide your reasoning, then finish with Preference: A/B/C\n",
-    "\n",
-    "Input: How do I get the path of the parent directory in python 3.8?\n",
-    "Option A: You can use the following code:\n",
-    "```python\n",
-    "import os\n",
-    "\n",
-    "os.path.dirname(os.path.dirname(os.path.abspath(__file__)))\n",
-    "```\n",
-    "Option B: You can use the following code:\n",
-    "```python\n",
-    "from pathlib import Path\n",
-    "Path(__file__).absolute().parent\n",
-    "```\n",
-    "Reasoning: Both options return the same result. However, since option B is more concise and easily understand, it is preferred.\n",
-    "Preference: B\n",
-    "\n",
-    "Which option is preferred? Do not take order into account. Evaluate based on accuracy and helpfulness. If neither is preferred, respond with C. Provide your reasoning, then finish with Preference: A/B/C\n",
-    "Input: {input}\n",
-    "Option A: {prediction}\n",
-    "Option B: {prediction_b}\n",
-    "Reasoning:\"\"\",\n",
-    "        )\n",
-    "\n",
-    "    @property\n",
-    "    def requires_input(self) -> bool:\n",
-    "        return True\n",
-    "\n",
-    "    @property\n",
-    "    def requires_reference(self) -> bool:\n",
-    "        return False\n",
-    "\n",
-    "    def _evaluate_string_pairs(\n",
-    "        self,\n",
-    "        *,\n",
-    "        prediction: str,\n",
-    "        prediction_b: str,\n",
-    "        reference: Optional[str] = None,\n",
-    "        input: Optional[str] = None,\n",
-    "        **kwargs: Any,\n",
-    "    ) -> dict:\n",
-    "        result = self.eval_chain(\n",
-    "            {\n",
-    "                \"input\": input,\n",
-    "                \"prediction\": prediction,\n",
-    "                \"prediction_b\": prediction_b,\n",
-    "                \"stop\": [\"Which option is preferred?\"],\n",
-    "            },\n",
-    "            **kwargs,\n",
-    "        )\n",
-    "\n",
-    "        response_text = result[\"text\"]\n",
-    "        reasoning, preference = response_text.split(\"Preference:\", maxsplit=1)\n",
-    "        preference = preference.strip()\n",
-    "        score = 1.0 if preference == \"A\" else (0.0 if preference == \"B\" else None)\n",
-    "        return {\"reasoning\": reasoning.strip(), \"value\": preference, \"score\": score}"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "5cbd8b1d-2cb0-4f05-b435-a1a00074d94a",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "evaluator = CustomPreferenceEvaluator()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "2c0a7fb7-b976-4443-9f0e-e707a6dfbdf7",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'reasoning': 'Option B is preferred over option A for importing from a relative directory, because it is more straightforward and concise.\\n\\nOption A uses the importlib module, which allows importing a module by specifying the full name as a string. While this works, it is less clear compared to option B.\\n\\nOption B directly imports from the relative path using dot notation, which clearly shows that it is a relative import. This is the recommended way to do relative imports in Python.\\n\\nIn summary, option B is more accurate and helpful as it uses the standard Python relative import syntax.',\n",
-       " 'value': 'B',\n",
-       " 'score': 0.0}"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "evaluator.evaluate_string_pairs(\n",
-    "    input=\"How do I import from a relative directory?\",\n",
-    "    prediction=\"use importlib! importlib.import_module('.my_package', '.')\",\n",
-    "    prediction_b=\"from .sibling import foo\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "f13a1346-7dbe-451d-b3a3-99e8fc7b753b",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "CustomPreferenceEvaluator requires an input string.\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Setting requires_input to return True adds additional validation to avoid returning a grade when insufficient data is provided to the chain.\n",
-    "\n",
-    "try:\n",
-    "    evaluator.evaluate_string_pairs(\n",
-    "        prediction=\"use importlib! importlib.import_module('.my_package', '.')\",\n",
-    "        prediction_b=\"from .sibling import foo\",\n",
-    "    )\n",
-    "except ValueError as e:\n",
-    "    print(e)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "e7829cc3-ebd1-4628-ae97-15166202e9cc",
-   "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": "657d2c8c-54b4-42a3-9f02-bdefa0ed6728",
+            "metadata": {},
+            "source": [
+                "# Custom Pairwise Evaluator\n",
+                "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/guides/evaluation/comparison/custom.ipynb)\n",
+                "\n",
+                "You can make your own pairwise string evaluators by inheriting from `PairwiseStringEvaluator` class and overwriting the `_evaluate_string_pairs` method (and the `_aevaluate_string_pairs` method if you want to use the evaluator asynchronously).\n",
+                "\n",
+                "In this example, you will make a simple custom evaluator that just returns whether the first prediction has more whitespace tokenized 'words' than the second.\n",
+                "\n",
+                "You can check out the reference docs for the [PairwiseStringEvaluator interface](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.schema.PairwiseStringEvaluator.html#langchain.evaluation.schema.PairwiseStringEvaluator) for more info.\n"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 1,
+            "id": "93f3a653-d198-4291-973c-8d1adba338b2",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "from typing import Optional, Any\n",
+                "from langchain.evaluation import PairwiseStringEvaluator\n",
+                "\n",
+                "\n",
+                "class LengthComparisonPairwiseEvalutor(PairwiseStringEvaluator):\n",
+                "    \"\"\"\n",
+                "    Custom evaluator to compare two strings.\n",
+                "    \"\"\"\n",
+                "\n",
+                "    def _evaluate_string_pairs(\n",
+                "        self,\n",
+                "        *,\n",
+                "        prediction: str,\n",
+                "        prediction_b: str,\n",
+                "        reference: Optional[str] = None,\n",
+                "        input: Optional[str] = None,\n",
+                "        **kwargs: Any,\n",
+                "    ) -> dict:\n",
+                "        score = int(len(prediction.split()) > len(prediction_b.split()))\n",
+                "        return {\"score\": score}"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 2,
+            "id": "7d4a77c3-07a7-4076-8e7f-f9bca0d6c290",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 1}"
+                        ]
+                    },
+                    "execution_count": 2,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "evaluator = LengthComparisonPairwiseEvalutor()\n",
+                "\n",
+                "evaluator.evaluate_string_pairs(\n",
+                "    prediction=\"The quick brown fox jumped over the lazy dog.\",\n",
+                "    prediction_b=\"The quick brown fox jumped over the dog.\",\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "id": "d90f128f-6f49-42a1-b05a-3aea568ee03b",
+            "metadata": {},
+            "source": [
+                "## LLM-Based Example\n",
+                "\n",
+                "That example was simple to illustrate the API, but it wasn't very useful in practice. Below, use an LLM with some custom instructions to form a simple preference scorer similar to the built-in [PairwiseStringEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain.html#langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain). We will use `ChatAnthropic` for the evaluator chain."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 3,
+            "id": "b4b43098-4d96-417b-a8a9-b3e75779cfe8",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "# %pip install anthropic\n",
+                "# %env ANTHROPIC_API_KEY=YOUR_API_KEY"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 4,
+            "id": "b6e978ab-48f1-47ff-9506-e13b1a50be6e",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "from typing import Optional, Any\n",
+                "from langchain.evaluation import PairwiseStringEvaluator\n",
+                "from langchain.chat_models import ChatAnthropic\n",
+                "from langchain.chains import LLMChain\n",
+                "\n",
+                "\n",
+                "class CustomPreferenceEvaluator(PairwiseStringEvaluator):\n",
+                "    \"\"\"\n",
+                "    Custom evaluator to compare two strings using a custom LLMChain.\n",
+                "    \"\"\"\n",
+                "\n",
+                "    def __init__(self) -> None:\n",
+                "        llm = ChatAnthropic(model=\"claude-2\", temperature=0)\n",
+                "        self.eval_chain = LLMChain.from_string(\n",
+                "            llm,\n",
+                "            \"\"\"Which option is preferred? Do not take order into account. Evaluate based on accuracy and helpfulness. If neither is preferred, respond with C. Provide your reasoning, then finish with Preference: A/B/C\n",
+                "\n",
+                "Input: How do I get the path of the parent directory in python 3.8?\n",
+                "Option A: You can use the following code:\n",
+                "```python\n",
+                "import os\n",
+                "\n",
+                "os.path.dirname(os.path.dirname(os.path.abspath(__file__)))\n",
+                "```\n",
+                "Option B: You can use the following code:\n",
+                "```python\n",
+                "from pathlib import Path\n",
+                "Path(__file__).absolute().parent\n",
+                "```\n",
+                "Reasoning: Both options return the same result. However, since option B is more concise and easily understand, it is preferred.\n",
+                "Preference: B\n",
+                "\n",
+                "Which option is preferred? Do not take order into account. Evaluate based on accuracy and helpfulness. If neither is preferred, respond with C. Provide your reasoning, then finish with Preference: A/B/C\n",
+                "Input: {input}\n",
+                "Option A: {prediction}\n",
+                "Option B: {prediction_b}\n",
+                "Reasoning:\"\"\",\n",
+                "        )\n",
+                "\n",
+                "    @property\n",
+                "    def requires_input(self) -> bool:\n",
+                "        return True\n",
+                "\n",
+                "    @property\n",
+                "    def requires_reference(self) -> bool:\n",
+                "        return False\n",
+                "\n",
+                "    def _evaluate_string_pairs(\n",
+                "        self,\n",
+                "        *,\n",
+                "        prediction: str,\n",
+                "        prediction_b: str,\n",
+                "        reference: Optional[str] = None,\n",
+                "        input: Optional[str] = None,\n",
+                "        **kwargs: Any,\n",
+                "    ) -> dict:\n",
+                "        result = self.eval_chain(\n",
+                "            {\n",
+                "                \"input\": input,\n",
+                "                \"prediction\": prediction,\n",
+                "                \"prediction_b\": prediction_b,\n",
+                "                \"stop\": [\"Which option is preferred?\"],\n",
+                "            },\n",
+                "            **kwargs,\n",
+                "        )\n",
+                "\n",
+                "        response_text = result[\"text\"]\n",
+                "        reasoning, preference = response_text.split(\"Preference:\", maxsplit=1)\n",
+                "        preference = preference.strip()\n",
+                "        score = 1.0 if preference == \"A\" else (0.0 if preference == \"B\" else None)\n",
+                "        return {\"reasoning\": reasoning.strip(), \"value\": preference, \"score\": score}"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 6,
+            "id": "5cbd8b1d-2cb0-4f05-b435-a1a00074d94a",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "evaluator = CustomPreferenceEvaluator()"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 7,
+            "id": "2c0a7fb7-b976-4443-9f0e-e707a6dfbdf7",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'reasoning': 'Option B is preferred over option A for importing from a relative directory, because it is more straightforward and concise.\\n\\nOption A uses the importlib module, which allows importing a module by specifying the full name as a string. While this works, it is less clear compared to option B.\\n\\nOption B directly imports from the relative path using dot notation, which clearly shows that it is a relative import. This is the recommended way to do relative imports in Python.\\n\\nIn summary, option B is more accurate and helpful as it uses the standard Python relative import syntax.',\n",
+                            " 'value': 'B',\n",
+                            " 'score': 0.0}"
+                        ]
+                    },
+                    "execution_count": 7,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "evaluator.evaluate_string_pairs(\n",
+                "    input=\"How do I import from a relative directory?\",\n",
+                "    prediction=\"use importlib! importlib.import_module('.my_package', '.')\",\n",
+                "    prediction_b=\"from .sibling import foo\",\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 13,
+            "id": "f13a1346-7dbe-451d-b3a3-99e8fc7b753b",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "name": "stdout",
+                    "output_type": "stream",
+                    "text": [
+                        "CustomPreferenceEvaluator requires an input string.\n"
+                    ]
+                }
+            ],
+            "source": [
+                "# Setting requires_input to return True adds additional validation to avoid returning a grade when insufficient data is provided to the chain.\n",
+                "\n",
+                "try:\n",
+                "    evaluator.evaluate_string_pairs(\n",
+                "        prediction=\"use importlib! importlib.import_module('.my_package', '.')\",\n",
+                "        prediction_b=\"from .sibling import foo\",\n",
+                "    )\n",
+                "except ValueError as e:\n",
+                "    print(e)"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": null,
+            "id": "e7829cc3-ebd1-4628-ae97-15166202e9cc",
+            "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/extras/guides/evaluation/comparison/pairwise_embedding_distance.ipynb

@@ -1,232 +1,233 @@
 {
- "cells": [
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {
-    "tags": []
-   },
-   "source": [
-    "# Pairwise Embedding Distance \n",
-    "\n",
-    "One way to measure the similarity (or dissimilarity) between two predictions on a shared or similar input is to embed the predictions and compute a vector distance between the two embeddings.<a name=\"cite_ref-1\"></a>[<sup>[1]</sup>](#cite_note-1)\n",
-    "\n",
-    "You can load the `pairwise_embedding_distance` evaluator to do this.\n",
-    "\n",
-    "**Note:** This returns a **distance** score, meaning that the lower the number, the **more** similar the outputs are, according to their embedded representation.\n",
-    "\n",
-    "Check out the reference docs for the [PairwiseEmbeddingDistanceEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.embedding_distance.base.PairwiseEmbeddingDistanceEvalChain.html#langchain.evaluation.embedding_distance.base.PairwiseEmbeddingDistanceEvalChain) for more info."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.evaluation import load_evaluator\n",
-    "\n",
-    "evaluator = load_evaluator(\"pairwise_embedding_distance\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'score': 0.0966466944859925}"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "evaluator.evaluate_string_pairs(\n",
-    "    prediction=\"Seattle is hot in June\", prediction_b=\"Seattle is cool in June.\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'score': 0.03761174337464557}"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "evaluator.evaluate_string_pairs(\n",
-    "    prediction=\"Seattle is warm in June\", prediction_b=\"Seattle is cool in June.\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Select the Distance Metric\n",
-    "\n",
-    "By default, the evalutor uses cosine distance. You can choose a different distance metric if you'd like. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[<EmbeddingDistance.COSINE: 'cosine'>,\n",
-       " <EmbeddingDistance.EUCLIDEAN: 'euclidean'>,\n",
-       " <EmbeddingDistance.MANHATTAN: 'manhattan'>,\n",
-       " <EmbeddingDistance.CHEBYSHEV: 'chebyshev'>,\n",
-       " <EmbeddingDistance.HAMMING: 'hamming'>]"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain.evaluation import EmbeddingDistance\n",
-    "\n",
-    "list(EmbeddingDistance)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "evaluator = load_evaluator(\n",
-    "    \"pairwise_embedding_distance\", distance_metric=EmbeddingDistance.EUCLIDEAN\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Select Embeddings to Use\n",
-    "\n",
-    "The constructor uses `OpenAI` embeddings by default, but you can configure this however you want. Below, use huggingface local embeddings"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.embeddings import HuggingFaceEmbeddings\n",
-    "\n",
-    "embedding_model = HuggingFaceEmbeddings()\n",
-    "hf_evaluator = load_evaluator(\"pairwise_embedding_distance\", embeddings=embedding_model)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'score': 0.5486443280477362}"
-      ]
-     },
-     "execution_count": 10,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "hf_evaluator.evaluate_string_pairs(\n",
-    "    prediction=\"Seattle is hot in June\", prediction_b=\"Seattle is cool in June.\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'score': 0.21018880025138598}"
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "hf_evaluator.evaluate_string_pairs(\n",
-    "    prediction=\"Seattle is warm in June\", prediction_b=\"Seattle is cool in June.\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "<a name=\"cite_note-1\"></a><i>1. Note: When it comes to semantic similarity, this often gives better results than older string distance metrics (such as those in the `PairwiseStringDistanceEvalChain`), though it tends to be less reliable than evaluators that use the LLM directly (such as the `PairwiseStringEvalChain`) </i>"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.2"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}
+    "cells": [
+        {
+            "attachments": {},
+            "cell_type": "markdown",
+            "metadata": {
+                "tags": []
+            },
+            "source": [
+                "# Pairwise Embedding Distance \n",
+                "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/guides/evaluation/comparison/pairwise_embedding_distance.ipynb)\n",
+                "\n",
+                "One way to measure the similarity (or dissimilarity) between two predictions on a shared or similar input is to embed the predictions and compute a vector distance between the two embeddings.<a name=\"cite_ref-1\"></a>[<sup>[1]</sup>](#cite_note-1)\n",
+                "\n",
+                "You can load the `pairwise_embedding_distance` evaluator to do this.\n",
+                "\n",
+                "**Note:** This returns a **distance** score, meaning that the lower the number, the **more** similar the outputs are, according to their embedded representation.\n",
+                "\n",
+                "Check out the reference docs for the [PairwiseEmbeddingDistanceEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.embedding_distance.base.PairwiseEmbeddingDistanceEvalChain.html#langchain.evaluation.embedding_distance.base.PairwiseEmbeddingDistanceEvalChain) for more info."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 1,
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "from langchain.evaluation import load_evaluator\n",
+                "\n",
+                "evaluator = load_evaluator(\"pairwise_embedding_distance\")"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 2,
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 0.0966466944859925}"
+                        ]
+                    },
+                    "execution_count": 2,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "evaluator.evaluate_string_pairs(\n",
+                "    prediction=\"Seattle is hot in June\", prediction_b=\"Seattle is cool in June.\"\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 3,
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 0.03761174337464557}"
+                        ]
+                    },
+                    "execution_count": 3,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "evaluator.evaluate_string_pairs(\n",
+                "    prediction=\"Seattle is warm in June\", prediction_b=\"Seattle is cool in June.\"\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {},
+            "source": [
+                "## Select the Distance Metric\n",
+                "\n",
+                "By default, the evalutor uses cosine distance. You can choose a different distance metric if you'd like. "
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 4,
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "[<EmbeddingDistance.COSINE: 'cosine'>,\n",
+                            " <EmbeddingDistance.EUCLIDEAN: 'euclidean'>,\n",
+                            " <EmbeddingDistance.MANHATTAN: 'manhattan'>,\n",
+                            " <EmbeddingDistance.CHEBYSHEV: 'chebyshev'>,\n",
+                            " <EmbeddingDistance.HAMMING: 'hamming'>]"
+                        ]
+                    },
+                    "execution_count": 4,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "from langchain.evaluation import EmbeddingDistance\n",
+                "\n",
+                "list(EmbeddingDistance)"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 5,
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "evaluator = load_evaluator(\n",
+                "    \"pairwise_embedding_distance\", distance_metric=EmbeddingDistance.EUCLIDEAN\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {},
+            "source": [
+                "## Select Embeddings to Use\n",
+                "\n",
+                "The constructor uses `OpenAI` embeddings by default, but you can configure this however you want. Below, use huggingface local embeddings"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": null,
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "from langchain.embeddings import HuggingFaceEmbeddings\n",
+                "\n",
+                "embedding_model = HuggingFaceEmbeddings()\n",
+                "hf_evaluator = load_evaluator(\"pairwise_embedding_distance\", embeddings=embedding_model)"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 10,
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 0.5486443280477362}"
+                        ]
+                    },
+                    "execution_count": 10,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "hf_evaluator.evaluate_string_pairs(\n",
+                "    prediction=\"Seattle is hot in June\", prediction_b=\"Seattle is cool in June.\"\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 12,
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 0.21018880025138598}"
+                        ]
+                    },
+                    "execution_count": 12,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "hf_evaluator.evaluate_string_pairs(\n",
+                "    prediction=\"Seattle is warm in June\", prediction_b=\"Seattle is cool in June.\"\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {},
+            "source": [
+                "<a name=\"cite_note-1\"></a><i>1. Note: When it comes to semantic similarity, this often gives better results than older string distance metrics (such as those in the `PairwiseStringDistanceEvalChain`), though it tends to be less reliable than evaluators that use the LLM directly (such as the `PairwiseStringEvalChain`) </i>"
+            ]
+        }
+    ],
+    "metadata": {
+        "kernelspec": {
+            "display_name": "Python 3 (ipykernel)",
+            "language": "python",
+            "name": "python3"
+        },
+        "language_info": {
+            "codemirror_mode": {
+                "name": "ipython",
+                "version": 3
+            },
+            "file_extension": ".py",
+            "mimetype": "text/x-python",
+            "name": "python",
+            "nbconvert_exporter": "python",
+            "pygments_lexer": "ipython3",
+            "version": "3.11.2"
+        }
+    },
+    "nbformat": 4,
+    "nbformat_minor": 4
+}

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

@@ -1,381 +1,382 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "2da95378",
-   "metadata": {},
-   "source": [
-    "# Pairwise String Comparison\n",
-    "\n",
-    "Often you will want to compare predictions of an LLM, Chain, or Agent for a given input. The `StringComparison` evaluators facilitate this so you can answer questions like:\n",
-    "\n",
-    "- Which LLM or prompt produces a preferred output for a given question?\n",
-    "- Which examples should I include for few-shot example selection?\n",
-    "- Which output is better to include for fintetuning?\n",
-    "\n",
-    "The simplest and often most reliable automated way to choose a preferred prediction for a given input is to use the `pairwise_string` evaluator.\n",
-    "\n",
-    "Check out the reference docs for the [PairwiseStringEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain.html#langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain) for more info."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "f6790c46",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.evaluation import load_evaluator\n",
-    "\n",
-    "evaluator = load_evaluator(\"labeled_pairwise_string\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "49ad9139",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'reasoning': 'Both responses are relevant to the question asked, as they both provide a numerical answer to the question about the number of dogs in the park. However, Response A is incorrect according to the reference answer, which states that there are four dogs. Response B, on the other hand, is correct as it matches the reference answer. Neither response demonstrates depth of thought, as they both simply provide a numerical answer without any additional information or context. \\n\\nBased on these criteria, Response B is the better response.\\n',\n",
-       " 'value': 'B',\n",
-       " 'score': 0}"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "evaluator.evaluate_string_pairs(\n",
-    "    prediction=\"there are three dogs\",\n",
-    "    prediction_b=\"4\",\n",
-    "    input=\"how many dogs are in the park?\",\n",
-    "    reference=\"four\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "7491d2e6-4e77-4b17-be6b-7da966785c1d",
-   "metadata": {},
-   "source": [
-    "## Methods\n",
-    "\n",
-    "\n",
-    "The pairwise string evaluator can be called using [evaluate_string_pairs](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain.html#langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain.evaluate_string_pairs) (or async [aevaluate_string_pairs](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain.html#langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain.aevaluate_string_pairs)) methods, which accept:\n",
-    "\n",
-    "- prediction (str) – The predicted response of the first model, chain, or prompt.\n",
-    "- prediction_b (str) – The predicted response of the second model, chain, or prompt.\n",
-    "- input (str) – The input question, prompt, or other text.\n",
-    "- reference (str) – (Only for the labeled_pairwise_string variant) The reference response.\n",
-    "\n",
-    "They return a dictionary with the following values:\n",
-    "- value: 'A' or 'B', indicating whether `prediction` or `prediction_b` is preferred, respectively\n",
-    "- score: Integer 0 or 1 mapped from the 'value', where a score of 1 would mean that the first `prediction` is preferred, and a score of 0 would mean `prediction_b` is preferred.\n",
-    "- reasoning: String \"chain of thought reasoning\" from the LLM generated prior to creating the score"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "ed353b93-be71-4479-b9c0-8c97814c2e58",
-   "metadata": {},
-   "source": [
-    "## Without References\n",
-    "\n",
-    "When references aren't available, you can still predict the preferred response.\n",
-    "The results will reflect the evaluation model's preference, which is less reliable and may result\n",
-    "in preferences that are factually incorrect."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "586320da",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.evaluation import load_evaluator\n",
-    "\n",
-    "evaluator = load_evaluator(\"pairwise_string\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "7f56c76e-a39b-4509-8b8a-8a2afe6c3da1",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'reasoning': 'Both responses are correct and relevant to the question. However, Response B is more helpful and insightful as it provides a more detailed explanation of what addition is. Response A is correct but lacks depth as it does not explain what the operation of addition entails. \\n\\nFinal Decision: [[B]]',\n",
-       " 'value': 'B',\n",
-       " 'score': 0}"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "evaluator.evaluate_string_pairs(\n",
-    "    prediction=\"Addition is a mathematical operation.\",\n",
-    "    prediction_b=\"Addition is a mathematical operation that adds two numbers to create a third number, the 'sum'.\",\n",
-    "    input=\"What is addition?\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "4a09b21d-9851-47e8-93d3-90044b2945b0",
-   "metadata": {
-    "tags": []
-   },
-   "source": [
-    "## Defining the Criteria\n",
-    "\n",
-    "By default, the LLM is instructed to select the 'preferred' response based on helpfulness, relevance, correctness, and depth of thought. You can customize the criteria by passing in a `criteria` argument, where the criteria could take any of the following forms:\n",
-    "- [`Criteria`](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.criteria.eval_chain.Criteria.html#langchain.evaluation.criteria.eval_chain.Criteria) enum or its string value - to use one of the default criteria and their descriptions\n",
-    "- [Constitutional principal](https://api.python.langchain.com/en/latest/chains/langchain.chains.constitutional_ai.models.ConstitutionalPrinciple.html#langchain.chains.constitutional_ai.models.ConstitutionalPrinciple) - use one any of the constitutional principles defined in langchain\n",
-    "- Dictionary: a list of custom criteria, where the key is the name of the criteria, and the value is the description.\n",
-    "- A list of criteria or constitutional principles - to combine multiple criteria in one.\n",
-    "\n",
-    "Below is an example for determining preferred writing responses based on a custom style."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "8539e7d9-f7b0-4d32-9c45-593a7915c093",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "custom_criteria = {\n",
-    "    \"simplicity\": \"Is the language straightforward and unpretentious?\",\n",
-    "    \"clarity\": \"Are the sentences clear and easy to understand?\",\n",
-    "    \"precision\": \"Is the writing precise, with no unnecessary words or details?\",\n",
-    "    \"truthfulness\": \"Does the writing feel honest and sincere?\",\n",
-    "    \"subtext\": \"Does the writing suggest deeper meanings or themes?\",\n",
-    "}\n",
-    "evaluator = load_evaluator(\"pairwise_string\", criteria=custom_criteria)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "fec7bde8-fbdc-4730-8366-9d90d033c181",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'reasoning': 'Response A is simple, clear, and precise. It uses straightforward language to convey a deep and sincere message about families. The metaphor of joy and sorrow as music is effective and easy to understand.\\n\\nResponse B, on the other hand, is more complex and less clear. The language is more pretentious, with words like \"domicile,\" \"resounds,\" \"abode,\" \"dissonant,\" and \"elegy.\" While it conveys a similar message to Response A, it does so in a more convoluted way. The precision is also lacking due to the use of unnecessary words and details.\\n\\nBoth responses suggest deeper meanings or themes about the shared joy and unique sorrow in families. However, Response A does so in a more effective and accessible way.\\n\\nTherefore, the better response is [[A]].',\n",
-       " 'value': 'A',\n",
-       " 'score': 1}"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "evaluator.evaluate_string_pairs(\n",
-    "    prediction=\"Every cheerful household shares a similar rhythm of joy; but sorrow, in each household, plays a unique, haunting melody.\",\n",
-    "    prediction_b=\"Where one finds a symphony of joy, every domicile of happiness resounds in harmonious,\"\n",
-    "    \" identical notes; yet, every abode of despair conducts a dissonant orchestra, each\"\n",
-    "    \" playing an elegy of grief that is peculiar and profound to its own existence.\",\n",
-    "    input=\"Write some prose about families.\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "a25b60b2-627c-408a-be4b-a2e5cbc10726",
-   "metadata": {},
-   "source": [
-    "## Customize the LLM\n",
-    "\n",
-    "By default, the loader uses `gpt-4` in the evaluation chain. You can customize this when loading."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "de84a958-1330-482b-b950-68bcf23f9e35",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chat_models import ChatAnthropic\n",
-    "\n",
-    "llm = ChatAnthropic(temperature=0)\n",
-    "\n",
-    "evaluator = load_evaluator(\"labeled_pairwise_string\", llm=llm)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "e162153f-d50a-4a7c-a033-019dabbc954c",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'reasoning': 'Here is my assessment:\\n\\nResponse B is more helpful, insightful, and accurate than Response A. Response B simply states \"4\", which directly answers the question by providing the exact number of dogs mentioned in the reference answer. In contrast, Response A states \"there are three dogs\", which is incorrect according to the reference answer. \\n\\nIn terms of helpfulness, Response B gives the precise number while Response A provides an inaccurate guess. For relevance, both refer to dogs in the park from the question. However, Response B is more correct and factual based on the reference answer. Response A shows some attempt at reasoning but is ultimately incorrect. Response B requires less depth of thought to simply state the factual number.\\n\\nIn summary, Response B is superior in terms of helpfulness, relevance, correctness, and depth. My final decision is: [[B]]\\n',\n",
-       " 'value': 'B',\n",
-       " 'score': 0}"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "evaluator.evaluate_string_pairs(\n",
-    "    prediction=\"there are three dogs\",\n",
-    "    prediction_b=\"4\",\n",
-    "    input=\"how many dogs are in the park?\",\n",
-    "    reference=\"four\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e0e89c13-d0ad-4f87-8fcb-814399bafa2a",
-   "metadata": {},
-   "source": [
-    "## Customize the Evaluation Prompt\n",
-    "\n",
-    "You can use your own custom evaluation prompt to add more task-specific instructions or to instruct the evaluator to score the output.\n",
-    "\n",
-    "*Note: If you use a prompt that expects generates a result in a unique format, you may also have to pass in a custom output parser (`output_parser=your_parser()`) instead of the default `PairwiseStringResultOutputParser`"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "fb817efa-3a4d-439d-af8c-773b89d97ec9",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.prompts import PromptTemplate\n",
-    "\n",
-    "prompt_template = PromptTemplate.from_template(\n",
-    "    \"\"\"Given the input context, which do you prefer: A or B?\n",
-    "Evaluate based on the following criteria:\n",
-    "{criteria}\n",
-    "Reason step by step and finally, respond with either [[A]] or [[B]] on its own line.\n",
-    "\n",
-    "DATA\n",
-    "----\n",
-    "input: {input}\n",
-    "reference: {reference}\n",
-    "A: {prediction}\n",
-    "B: {prediction_b}\n",
-    "---\n",
-    "Reasoning:\n",
-    "\n",
-    "\"\"\"\n",
-    ")\n",
-    "evaluator = load_evaluator(\n",
-    "    \"labeled_pairwise_string\", prompt=prompt_template\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "d40aa4f0-cfd5-4cb4-83c8-8d2300a04c2f",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "input_variables=['prediction', 'reference', 'prediction_b', 'input'] output_parser=None partial_variables={'criteria': 'helpfulness: Is the submission helpful, insightful, and appropriate?\\nrelevance: Is the submission referring to a real quote from the text?\\ncorrectness: Is the submission correct, accurate, and factual?\\ndepth: Does the submission demonstrate depth of thought?'} template='Given the input context, which do you prefer: A or B?\\nEvaluate based on the following criteria:\\n{criteria}\\nReason step by step and finally, respond with either [[A]] or [[B]] on its own line.\\n\\nDATA\\n----\\ninput: {input}\\nreference: {reference}\\nA: {prediction}\\nB: {prediction_b}\\n---\\nReasoning:\\n\\n' template_format='f-string' validate_template=True\n"
-     ]
-    }
-   ],
-   "source": [
-    "# The prompt was assigned to the evaluator\n",
-    "print(evaluator.prompt)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "9467bb42-7a31-4071-8f66-9ed2c6f06dcd",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'reasoning': 'Helpfulness: Both A and B are helpful as they provide a direct answer to the question.\\nRelevance: A is relevant as it refers to the correct name of the dog from the text. B is not relevant as it provides a different name.\\nCorrectness: A is correct as it accurately states the name of the dog. B is incorrect as it provides a different name.\\nDepth: Both A and B demonstrate a similar level of depth as they both provide a straightforward answer to the question.\\n\\nGiven these evaluations, the preferred response is:\\n',\n",
-       " 'value': 'A',\n",
-       " 'score': 1}"
-      ]
-     },
-     "execution_count": 11,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "evaluator.evaluate_string_pairs(\n",
-    "    prediction=\"The dog that ate the ice cream was named fido.\",\n",
-    "    prediction_b=\"The dog's name is spot\",\n",
-    "    input=\"What is the name of the dog that ate the ice cream?\",\n",
-    "    reference=\"The dog's name is fido\",\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": [
+                "# Pairwise String Comparison\n",
+                "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/guides/evaluation/comparison/pairwise_string.ipynb)\n",
+                "\n",
+                "Often you will want to compare predictions of an LLM, Chain, or Agent for a given input. The `StringComparison` evaluators facilitate this so you can answer questions like:\n",
+                "\n",
+                "- Which LLM or prompt produces a preferred output for a given question?\n",
+                "- Which examples should I include for few-shot example selection?\n",
+                "- Which output is better to include for fintetuning?\n",
+                "\n",
+                "The simplest and often most reliable automated way to choose a preferred prediction for a given input is to use the `pairwise_string` evaluator.\n",
+                "\n",
+                "Check out the reference docs for the [PairwiseStringEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain.html#langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain) for more info."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 1,
+            "id": "f6790c46",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "from langchain.evaluation import load_evaluator\n",
+                "\n",
+                "evaluator = load_evaluator(\"labeled_pairwise_string\")"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 2,
+            "id": "49ad9139",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'reasoning': 'Both responses are relevant to the question asked, as they both provide a numerical answer to the question about the number of dogs in the park. However, Response A is incorrect according to the reference answer, which states that there are four dogs. Response B, on the other hand, is correct as it matches the reference answer. Neither response demonstrates depth of thought, as they both simply provide a numerical answer without any additional information or context. \\n\\nBased on these criteria, Response B is the better response.\\n',\n",
+                            " 'value': 'B',\n",
+                            " 'score': 0}"
+                        ]
+                    },
+                    "execution_count": 2,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "evaluator.evaluate_string_pairs(\n",
+                "    prediction=\"there are three dogs\",\n",
+                "    prediction_b=\"4\",\n",
+                "    input=\"how many dogs are in the park?\",\n",
+                "    reference=\"four\",\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "id": "7491d2e6-4e77-4b17-be6b-7da966785c1d",
+            "metadata": {},
+            "source": [
+                "## Methods\n",
+                "\n",
+                "\n",
+                "The pairwise string evaluator can be called using [evaluate_string_pairs](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain.html#langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain.evaluate_string_pairs) (or async [aevaluate_string_pairs](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain.html#langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain.aevaluate_string_pairs)) methods, which accept:\n",
+                "\n",
+                "- prediction (str) – The predicted response of the first model, chain, or prompt.\n",
+                "- prediction_b (str) – The predicted response of the second model, chain, or prompt.\n",
+                "- input (str) – The input question, prompt, or other text.\n",
+                "- reference (str) – (Only for the labeled_pairwise_string variant) The reference response.\n",
+                "\n",
+                "They return a dictionary with the following values:\n",
+                "- value: 'A' or 'B', indicating whether `prediction` or `prediction_b` is preferred, respectively\n",
+                "- score: Integer 0 or 1 mapped from the 'value', where a score of 1 would mean that the first `prediction` is preferred, and a score of 0 would mean `prediction_b` is preferred.\n",
+                "- reasoning: String \"chain of thought reasoning\" from the LLM generated prior to creating the score"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "id": "ed353b93-be71-4479-b9c0-8c97814c2e58",
+            "metadata": {},
+            "source": [
+                "## Without References\n",
+                "\n",
+                "When references aren't available, you can still predict the preferred response.\n",
+                "The results will reflect the evaluation model's preference, which is less reliable and may result\n",
+                "in preferences that are factually incorrect."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 3,
+            "id": "586320da",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "from langchain.evaluation import load_evaluator\n",
+                "\n",
+                "evaluator = load_evaluator(\"pairwise_string\")"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 4,
+            "id": "7f56c76e-a39b-4509-8b8a-8a2afe6c3da1",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'reasoning': 'Both responses are correct and relevant to the question. However, Response B is more helpful and insightful as it provides a more detailed explanation of what addition is. Response A is correct but lacks depth as it does not explain what the operation of addition entails. \\n\\nFinal Decision: [[B]]',\n",
+                            " 'value': 'B',\n",
+                            " 'score': 0}"
+                        ]
+                    },
+                    "execution_count": 4,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "evaluator.evaluate_string_pairs(\n",
+                "    prediction=\"Addition is a mathematical operation.\",\n",
+                "    prediction_b=\"Addition is a mathematical operation that adds two numbers to create a third number, the 'sum'.\",\n",
+                "    input=\"What is addition?\",\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "id": "4a09b21d-9851-47e8-93d3-90044b2945b0",
+            "metadata": {
+                "tags": []
+            },
+            "source": [
+                "## Defining the Criteria\n",
+                "\n",
+                "By default, the LLM is instructed to select the 'preferred' response based on helpfulness, relevance, correctness, and depth of thought. You can customize the criteria by passing in a `criteria` argument, where the criteria could take any of the following forms:\n",
+                "- [`Criteria`](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.criteria.eval_chain.Criteria.html#langchain.evaluation.criteria.eval_chain.Criteria) enum or its string value - to use one of the default criteria and their descriptions\n",
+                "- [Constitutional principal](https://api.python.langchain.com/en/latest/chains/langchain.chains.constitutional_ai.models.ConstitutionalPrinciple.html#langchain.chains.constitutional_ai.models.ConstitutionalPrinciple) - use one any of the constitutional principles defined in langchain\n",
+                "- Dictionary: a list of custom criteria, where the key is the name of the criteria, and the value is the description.\n",
+                "- A list of criteria or constitutional principles - to combine multiple criteria in one.\n",
+                "\n",
+                "Below is an example for determining preferred writing responses based on a custom style."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 5,
+            "id": "8539e7d9-f7b0-4d32-9c45-593a7915c093",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "custom_criteria = {\n",
+                "    \"simplicity\": \"Is the language straightforward and unpretentious?\",\n",
+                "    \"clarity\": \"Are the sentences clear and easy to understand?\",\n",
+                "    \"precision\": \"Is the writing precise, with no unnecessary words or details?\",\n",
+                "    \"truthfulness\": \"Does the writing feel honest and sincere?\",\n",
+                "    \"subtext\": \"Does the writing suggest deeper meanings or themes?\",\n",
+                "}\n",
+                "evaluator = load_evaluator(\"pairwise_string\", criteria=custom_criteria)"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 6,
+            "id": "fec7bde8-fbdc-4730-8366-9d90d033c181",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'reasoning': 'Response A is simple, clear, and precise. It uses straightforward language to convey a deep and sincere message about families. The metaphor of joy and sorrow as music is effective and easy to understand.\\n\\nResponse B, on the other hand, is more complex and less clear. The language is more pretentious, with words like \"domicile,\" \"resounds,\" \"abode,\" \"dissonant,\" and \"elegy.\" While it conveys a similar message to Response A, it does so in a more convoluted way. The precision is also lacking due to the use of unnecessary words and details.\\n\\nBoth responses suggest deeper meanings or themes about the shared joy and unique sorrow in families. However, Response A does so in a more effective and accessible way.\\n\\nTherefore, the better response is [[A]].',\n",
+                            " 'value': 'A',\n",
+                            " 'score': 1}"
+                        ]
+                    },
+                    "execution_count": 6,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "evaluator.evaluate_string_pairs(\n",
+                "    prediction=\"Every cheerful household shares a similar rhythm of joy; but sorrow, in each household, plays a unique, haunting melody.\",\n",
+                "    prediction_b=\"Where one finds a symphony of joy, every domicile of happiness resounds in harmonious,\"\n",
+                "    \" identical notes; yet, every abode of despair conducts a dissonant orchestra, each\"\n",
+                "    \" playing an elegy of grief that is peculiar and profound to its own existence.\",\n",
+                "    input=\"Write some prose about families.\",\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "id": "a25b60b2-627c-408a-be4b-a2e5cbc10726",
+            "metadata": {},
+            "source": [
+                "## Customize the LLM\n",
+                "\n",
+                "By default, the loader uses `gpt-4` in the evaluation chain. You can customize this when loading."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 7,
+            "id": "de84a958-1330-482b-b950-68bcf23f9e35",
+            "metadata": {},
+            "outputs": [],
+            "source": [
+                "from langchain.chat_models import ChatAnthropic\n",
+                "\n",
+                "llm = ChatAnthropic(temperature=0)\n",
+                "\n",
+                "evaluator = load_evaluator(\"labeled_pairwise_string\", llm=llm)"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 8,
+            "id": "e162153f-d50a-4a7c-a033-019dabbc954c",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'reasoning': 'Here is my assessment:\\n\\nResponse B is more helpful, insightful, and accurate than Response A. Response B simply states \"4\", which directly answers the question by providing the exact number of dogs mentioned in the reference answer. In contrast, Response A states \"there are three dogs\", which is incorrect according to the reference answer. \\n\\nIn terms of helpfulness, Response B gives the precise number while Response A provides an inaccurate guess. For relevance, both refer to dogs in the park from the question. However, Response B is more correct and factual based on the reference answer. Response A shows some attempt at reasoning but is ultimately incorrect. Response B requires less depth of thought to simply state the factual number.\\n\\nIn summary, Response B is superior in terms of helpfulness, relevance, correctness, and depth. My final decision is: [[B]]\\n',\n",
+                            " 'value': 'B',\n",
+                            " 'score': 0}"
+                        ]
+                    },
+                    "execution_count": 8,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "evaluator.evaluate_string_pairs(\n",
+                "    prediction=\"there are three dogs\",\n",
+                "    prediction_b=\"4\",\n",
+                "    input=\"how many dogs are in the park?\",\n",
+                "    reference=\"four\",\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "id": "e0e89c13-d0ad-4f87-8fcb-814399bafa2a",
+            "metadata": {},
+            "source": [
+                "## Customize the Evaluation Prompt\n",
+                "\n",
+                "You can use your own custom evaluation prompt to add more task-specific instructions or to instruct the evaluator to score the output.\n",
+                "\n",
+                "*Note: If you use a prompt that expects generates a result in a unique format, you may also have to pass in a custom output parser (`output_parser=your_parser()`) instead of the default `PairwiseStringResultOutputParser`"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 9,
+            "id": "fb817efa-3a4d-439d-af8c-773b89d97ec9",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "from langchain.prompts import PromptTemplate\n",
+                "\n",
+                "prompt_template = PromptTemplate.from_template(\n",
+                "    \"\"\"Given the input context, which do you prefer: A or B?\n",
+                "Evaluate based on the following criteria:\n",
+                "{criteria}\n",
+                "Reason step by step and finally, respond with either [[A]] or [[B]] on its own line.\n",
+                "\n",
+                "DATA\n",
+                "----\n",
+                "input: {input}\n",
+                "reference: {reference}\n",
+                "A: {prediction}\n",
+                "B: {prediction_b}\n",
+                "---\n",
+                "Reasoning:\n",
+                "\n",
+                "\"\"\"\n",
+                ")\n",
+                "evaluator = load_evaluator(\n",
+                "    \"labeled_pairwise_string\", prompt=prompt_template\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 10,
+            "id": "d40aa4f0-cfd5-4cb4-83c8-8d2300a04c2f",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "name": "stdout",
+                    "output_type": "stream",
+                    "text": [
+                        "input_variables=['prediction', 'reference', 'prediction_b', 'input'] output_parser=None partial_variables={'criteria': 'helpfulness: Is the submission helpful, insightful, and appropriate?\\nrelevance: Is the submission referring to a real quote from the text?\\ncorrectness: Is the submission correct, accurate, and factual?\\ndepth: Does the submission demonstrate depth of thought?'} template='Given the input context, which do you prefer: A or B?\\nEvaluate based on the following criteria:\\n{criteria}\\nReason step by step and finally, respond with either [[A]] or [[B]] on its own line.\\n\\nDATA\\n----\\ninput: {input}\\nreference: {reference}\\nA: {prediction}\\nB: {prediction_b}\\n---\\nReasoning:\\n\\n' template_format='f-string' validate_template=True\n"
+                    ]
+                }
+            ],
+            "source": [
+                "# The prompt was assigned to the evaluator\n",
+                "print(evaluator.prompt)"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 11,
+            "id": "9467bb42-7a31-4071-8f66-9ed2c6f06dcd",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'reasoning': 'Helpfulness: Both A and B are helpful as they provide a direct answer to the question.\\nRelevance: A is relevant as it refers to the correct name of the dog from the text. B is not relevant as it provides a different name.\\nCorrectness: A is correct as it accurately states the name of the dog. B is incorrect as it provides a different name.\\nDepth: Both A and B demonstrate a similar level of depth as they both provide a straightforward answer to the question.\\n\\nGiven these evaluations, the preferred response is:\\n',\n",
+                            " 'value': 'A',\n",
+                            " 'score': 1}"
+                        ]
+                    },
+                    "execution_count": 11,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "evaluator.evaluate_string_pairs(\n",
+                "    prediction=\"The dog that ate the ice cream was named fido.\",\n",
+                "    prediction_b=\"The dog's name is spot\",\n",
+                "    input=\"What is the name of the dog that ate the ice cream?\",\n",
+                "    reference=\"The dog's name is fido\",\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/extras/guides/evaluation/examples/comparisons.ipynb

@@ -1,447 +1,448 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Comparing Chain Outputs\n",
-    "\n",
-    "Suppose you have two different prompts (or LLMs). How do you know which will generate \"better\" results?\n",
-    "\n",
-    "One automated way to predict the preferred configuration is to use a `PairwiseStringEvaluator` like the `PairwiseStringEvalChain`<a name=\"cite_ref-1\"></a>[<sup>[1]</sup>](#cite_note-1). This chain prompts an LLM to select which output is preferred, given a specific input.\n",
-    "\n",
-    "For this evaluation, we will need 3 things:\n",
-    "1. An evaluator\n",
-    "2. A dataset of inputs\n",
-    "3. 2 (or more) LLMs, Chains, or Agents to compare\n",
-    "\n",
-    "Then we will aggregate the restults to determine the preferred model.\n",
-    "\n",
-    "### Step 1. Create the Evaluator\n",
-    "\n",
-    "In this example, you will use gpt-4 to select which output is preferred."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.evaluation import load_evaluator\n",
-    "\n",
-    "eval_chain = load_evaluator(\"pairwise_string\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Step 2. Select Dataset\n",
-    "\n",
-    "If you already have real usage data for your LLM, you can use a representative sample. More examples\n",
-    "provide more reliable results. We will use some example queries someone might have about how to use langchain here."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Found cached dataset parquet (/Users/wfh/.cache/huggingface/datasets/LangChainDatasets___parquet/LangChainDatasets--langchain-howto-queries-bbb748bbee7e77aa/0.0.0/14a00e99c0d15a23649d0db8944380ac81082d4b021f398733dd84f3a6c569a7)\n"
-     ]
+    "cells": [
+        {
+            "cell_type": "markdown",
+            "metadata": {},
+            "source": [
+                "# Comparing Chain Outputs\n",
+                "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/guides/evaluation/examples/comparisons.ipynb)\n",
+                "\n",
+                "Suppose you have two different prompts (or LLMs). How do you know which will generate \"better\" results?\n",
+                "\n",
+                "One automated way to predict the preferred configuration is to use a `PairwiseStringEvaluator` like the `PairwiseStringEvalChain`<a name=\"cite_ref-1\"></a>[<sup>[1]</sup>](#cite_note-1). This chain prompts an LLM to select which output is preferred, given a specific input.\n",
+                "\n",
+                "For this evaluation, we will need 3 things:\n",
+                "1. An evaluator\n",
+                "2. A dataset of inputs\n",
+                "3. 2 (or more) LLMs, Chains, or Agents to compare\n",
+                "\n",
+                "Then we will aggregate the restults to determine the preferred model.\n",
+                "\n",
+                "### Step 1. Create the Evaluator\n",
+                "\n",
+                "In this example, you will use gpt-4 to select which output is preferred."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 1,
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "from langchain.evaluation import load_evaluator\n",
+                "\n",
+                "eval_chain = load_evaluator(\"pairwise_string\")"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {},
+            "source": [
+                "### Step 2. Select Dataset\n",
+                "\n",
+                "If you already have real usage data for your LLM, you can use a representative sample. More examples\n",
+                "provide more reliable results. We will use some example queries someone might have about how to use langchain here."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 2,
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "name": "stderr",
+                    "output_type": "stream",
+                    "text": [
+                        "Found cached dataset parquet (/Users/wfh/.cache/huggingface/datasets/LangChainDatasets___parquet/LangChainDatasets--langchain-howto-queries-bbb748bbee7e77aa/0.0.0/14a00e99c0d15a23649d0db8944380ac81082d4b021f398733dd84f3a6c569a7)\n"
+                    ]
+                },
+                {
+                    "data": {
+                        "application/vnd.jupyter.widget-view+json": {
+                            "model_id": "a2358d37246640ce95e0f9940194590a",
+                            "version_major": 2,
+                            "version_minor": 0
+                        },
+                        "text/plain": [
+                            "  0%|          | 0/1 [00:00<?, ?it/s]"
+                        ]
+                    },
+                    "metadata": {},
+                    "output_type": "display_data"
+                }
+            ],
+            "source": [
+                "from langchain.evaluation.loading import load_dataset\n",
+                "\n",
+                "dataset = load_dataset(\"langchain-howto-queries\")"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {},
+            "source": [
+                "### Step 3. Define Models to Compare\n",
+                "\n",
+                "We will be comparing two agents in this case."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 3,
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "from langchain.utilities import SerpAPIWrapper\n",
+                "from langchain.agents import initialize_agent, Tool\n",
+                "from langchain.agents import AgentType\n",
+                "from langchain.chat_models import ChatOpenAI\n",
+                "\n",
+                "\n",
+                "# Initialize the language model\n",
+                "# You can add your own OpenAI API key by adding openai_api_key=\"<your_api_key>\"\n",
+                "llm = ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-0613\")\n",
+                "\n",
+                "# Initialize the SerpAPIWrapper for search functionality\n",
+                "# Replace <your_api_key> in openai_api_key=\"<your_api_key>\" with your actual SerpAPI key.\n",
+                "search = SerpAPIWrapper()\n",
+                "\n",
+                "# Define a list of tools offered by the agent\n",
+                "tools = [\n",
+                "    Tool(\n",
+                "        name=\"Search\",\n",
+                "        func=search.run,\n",
+                "        coroutine=search.arun,\n",
+                "        description=\"Useful when you need to answer questions about current events. You should ask targeted questions.\",\n",
+                "    ),\n",
+                "]"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 4,
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "functions_agent = initialize_agent(\n",
+                "    tools, llm, agent=AgentType.OPENAI_MULTI_FUNCTIONS, verbose=False\n",
+                ")\n",
+                "conversations_agent = initialize_agent(\n",
+                "    tools, llm, agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=False\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {},
+            "source": [
+                "### Step 4. Generate Responses\n",
+                "\n",
+                "We will generate outputs for each of the models before evaluating them."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 5,
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "application/vnd.jupyter.widget-view+json": {
+                            "model_id": "87277cb39a1a4726bb7cc533a24e2ea4",
+                            "version_major": 2,
+                            "version_minor": 0
+                        },
+                        "text/plain": [
+                            "  0%|          | 0/20 [00:00<?, ?it/s]"
+                        ]
+                    },
+                    "metadata": {},
+                    "output_type": "display_data"
+                }
+            ],
+            "source": [
+                "from tqdm.notebook import tqdm\n",
+                "import asyncio\n",
+                "\n",
+                "results = []\n",
+                "agents = [functions_agent, conversations_agent]\n",
+                "concurrency_level = 6  # How many concurrent agents to run. May need to decrease if OpenAI is rate limiting.\n",
+                "\n",
+                "# We will only run the first 20 examples of this dataset to speed things up\n",
+                "# This will lead to larger confidence intervals downstream.\n",
+                "batch = []\n",
+                "for example in tqdm(dataset[:20]):\n",
+                "    batch.extend([agent.acall(example[\"inputs\"]) for agent in agents])\n",
+                "    if len(batch) >= concurrency_level:\n",
+                "        batch_results = await asyncio.gather(*batch, return_exceptions=True)\n",
+                "        results.extend(list(zip(*[iter(batch_results)] * 2)))\n",
+                "        batch = []\n",
+                "if batch:\n",
+                "    batch_results = await asyncio.gather(*batch, return_exceptions=True)\n",
+                "    results.extend(list(zip(*[iter(batch_results)] * 2)))"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {},
+            "source": [
+                "## Step 5. Evaluate Pairs\n",
+                "\n",
+                "Now it's time to evaluate the results. For each agent response, run the evaluation chain to select which output is preferred (or return a tie).\n",
+                "\n",
+                "Randomly select the input order to reduce the likelihood that one model will be preferred just because it is presented first."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 6,
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "import random\n",
+                "\n",
+                "\n",
+                "def predict_preferences(dataset, results) -> list:\n",
+                "    preferences = []\n",
+                "\n",
+                "    for example, (res_a, res_b) in zip(dataset, results):\n",
+                "        input_ = example[\"inputs\"]\n",
+                "        # Flip a coin to reduce persistent position bias\n",
+                "        if random.random() < 0.5:\n",
+                "            pred_a, pred_b = res_a, res_b\n",
+                "            a, b = \"a\", \"b\"\n",
+                "        else:\n",
+                "            pred_a, pred_b = res_b, res_a\n",
+                "            a, b = \"b\", \"a\"\n",
+                "        eval_res = eval_chain.evaluate_string_pairs(\n",
+                "            prediction=pred_a[\"output\"] if isinstance(pred_a, dict) else str(pred_a),\n",
+                "            prediction_b=pred_b[\"output\"] if isinstance(pred_b, dict) else str(pred_b),\n",
+                "            input=input_,\n",
+                "        )\n",
+                "        if eval_res[\"value\"] == \"A\":\n",
+                "            preferences.append(a)\n",
+                "        elif eval_res[\"value\"] == \"B\":\n",
+                "            preferences.append(b)\n",
+                "        else:\n",
+                "            preferences.append(None)  # No preference\n",
+                "    return preferences"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 7,
+            "metadata": {},
+            "outputs": [],
+            "source": [
+                "preferences = predict_preferences(dataset, results)"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {
+                "tags": []
+            },
+            "source": [
+                "**Print out the ratio of preferences.**"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 8,
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "name": "stdout",
+                    "output_type": "stream",
+                    "text": [
+                        "OpenAI Functions Agent: 95.00%\n",
+                        "None: 5.00%\n"
+                    ]
+                }
+            ],
+            "source": [
+                "from collections import Counter\n",
+                "\n",
+                "name_map = {\n",
+                "    \"a\": \"OpenAI Functions Agent\",\n",
+                "    \"b\": \"Structured Chat Agent\",\n",
+                "}\n",
+                "counts = Counter(preferences)\n",
+                "pref_ratios = {k: v / len(preferences) for k, v in counts.items()}\n",
+                "for k, v in pref_ratios.items():\n",
+                "    print(f\"{name_map.get(k)}: {v:.2%}\")"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {},
+            "source": [
+                "### Estimate Confidence Intervals\n",
+                "\n",
+                "The results seem pretty clear, but if you want to have a better sense of how confident we are, that model \"A\" (the OpenAI Functions Agent) is the preferred model, we can calculate confidence intervals. \n",
+                "\n",
+                "Below, use the Wilson score to estimate the confidence interval."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 9,
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "from math import sqrt\n",
+                "\n",
+                "\n",
+                "def wilson_score_interval(\n",
+                "    preferences: list, which: str = \"a\", z: float = 1.96\n",
+                ") -> tuple:\n",
+                "    \"\"\"Estimate the confidence interval using the Wilson score.\n",
+                "\n",
+                "    See: https://en.wikipedia.org/wiki/Binomial_proportion_confidence_interval#Wilson_score_interval\n",
+                "    for more details, including when to use it and when it should not be used.\n",
+                "    \"\"\"\n",
+                "    total_preferences = preferences.count(\"a\") + preferences.count(\"b\")\n",
+                "    n_s = preferences.count(which)\n",
+                "\n",
+                "    if total_preferences == 0:\n",
+                "        return (0, 0)\n",
+                "\n",
+                "    p_hat = n_s / total_preferences\n",
+                "\n",
+                "    denominator = 1 + (z**2) / total_preferences\n",
+                "    adjustment = (z / denominator) * sqrt(\n",
+                "        p_hat * (1 - p_hat) / total_preferences\n",
+                "        + (z**2) / (4 * total_preferences * total_preferences)\n",
+                "    )\n",
+                "    center = (p_hat + (z**2) / (2 * total_preferences)) / denominator\n",
+                "    lower_bound = min(max(center - adjustment, 0.0), 1.0)\n",
+                "    upper_bound = min(max(center + adjustment, 0.0), 1.0)\n",
+                "\n",
+                "    return (lower_bound, upper_bound)"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 10,
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "name": "stdout",
+                    "output_type": "stream",
+                    "text": [
+                        "The \"OpenAI Functions Agent\" would be preferred between 83.18% and 100.00% percent of the time (with 95% confidence).\n",
+                        "The \"Structured Chat Agent\" would be preferred between 0.00% and 16.82% percent of the time (with 95% confidence).\n"
+                    ]
+                }
+            ],
+            "source": [
+                "for which_, name in name_map.items():\n",
+                "    low, high = wilson_score_interval(preferences, which=which_)\n",
+                "    print(\n",
+                "        f'The \"{name}\" would be preferred between {low:.2%} and {high:.2%} percent of the time (with 95% confidence).'\n",
+                "    )"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {},
+            "source": [
+                "**Print out the p-value.**"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 11,
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "name": "stdout",
+                    "output_type": "stream",
+                    "text": [
+                        "The p-value is 0.00000. If the null hypothesis is true (i.e., if the selected eval chain actually has no preference between the models),\n",
+                        "then there is a 0.00038% chance of observing the OpenAI Functions Agent be preferred at least 19\n",
+                        "times out of 19 trials.\n"
+                    ]
+                },
+                {
+                    "name": "stderr",
+                    "output_type": "stream",
+                    "text": [
+                        "/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/ipykernel_15978/384907688.py:6: DeprecationWarning: 'binom_test' is deprecated in favour of 'binomtest' from version 1.7.0 and will be removed in Scipy 1.12.0.\n",
+                        "  p_value = stats.binom_test(successes, n, p=0.5, alternative=\"two-sided\")\n"
+                    ]
+                }
+            ],
+            "source": [
+                "from scipy import stats\n",
+                "\n",
+                "preferred_model = max(pref_ratios, key=pref_ratios.get)\n",
+                "successes = preferences.count(preferred_model)\n",
+                "n = len(preferences) - preferences.count(None)\n",
+                "p_value = stats.binom_test(successes, n, p=0.5, alternative=\"two-sided\")\n",
+                "print(\n",
+                "    f\"\"\"The p-value is {p_value:.5f}. If the null hypothesis is true (i.e., if the selected eval chain actually has no preference between the models),\n",
+                "then there is a {p_value:.5%} chance of observing the {name_map.get(preferred_model)} be preferred at least {successes}\n",
+                "times out of {n} trials.\"\"\"\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {},
+            "source": [
+                "<a name=\"cite_note-1\"></a>_1. Note: Automated evals are still an open research topic and are best used alongside other evaluation approaches. \n",
+                "LLM preferences exhibit biases, including banal ones like the order of outputs.\n",
+                "In choosing preferences, \"ground truth\" may not be taken into account, which may lead to scores that aren't grounded in utility._"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": null,
+            "metadata": {},
+            "outputs": [],
+            "source": []
+        }
+    ],
+    "metadata": {
+        "kernelspec": {
+            "display_name": "Python 3 (ipykernel)",
+            "language": "python",
+            "name": "python3"
+        },
+        "language_info": {
+            "codemirror_mode": {
+                "name": "ipython",
+                "version": 3
+            },
+            "file_extension": ".py",
+            "mimetype": "text/x-python",
+            "name": "python",
+            "nbconvert_exporter": "python",
+            "pygments_lexer": "ipython3",
+            "version": "3.11.2"
+        }
     },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "a2358d37246640ce95e0f9940194590a",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "  0%|          | 0/1 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "from langchain.evaluation.loading import load_dataset\n",
-    "\n",
-    "dataset = load_dataset(\"langchain-howto-queries\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Step 3. Define Models to Compare\n",
-    "\n",
-    "We will be comparing two agents in this case."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.utilities import SerpAPIWrapper\n",
-    "from langchain.agents import initialize_agent, Tool\n",
-    "from langchain.agents import AgentType\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "\n",
-    "\n",
-    "# Initialize the language model\n",
-    "# You can add your own OpenAI API key by adding openai_api_key=\"<your_api_key>\"\n",
-    "llm = ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-0613\")\n",
-    "\n",
-    "# Initialize the SerpAPIWrapper for search functionality\n",
-    "# Replace <your_api_key> in openai_api_key=\"<your_api_key>\" with your actual SerpAPI key.\n",
-    "search = SerpAPIWrapper()\n",
-    "\n",
-    "# Define a list of tools offered by the agent\n",
-    "tools = [\n",
-    "    Tool(\n",
-    "        name=\"Search\",\n",
-    "        func=search.run,\n",
-    "        coroutine=search.arun,\n",
-    "        description=\"Useful when you need to answer questions about current events. You should ask targeted questions.\",\n",
-    "    ),\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "functions_agent = initialize_agent(\n",
-    "    tools, llm, agent=AgentType.OPENAI_MULTI_FUNCTIONS, verbose=False\n",
-    ")\n",
-    "conversations_agent = initialize_agent(\n",
-    "    tools, llm, agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=False\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Step 4. Generate Responses\n",
-    "\n",
-    "We will generate outputs for each of the models before evaluating them."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "87277cb39a1a4726bb7cc533a24e2ea4",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "  0%|          | 0/20 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "from tqdm.notebook import tqdm\n",
-    "import asyncio\n",
-    "\n",
-    "results = []\n",
-    "agents = [functions_agent, conversations_agent]\n",
-    "concurrency_level = 6  # How many concurrent agents to run. May need to decrease if OpenAI is rate limiting.\n",
-    "\n",
-    "# We will only run the first 20 examples of this dataset to speed things up\n",
-    "# This will lead to larger confidence intervals downstream.\n",
-    "batch = []\n",
-    "for example in tqdm(dataset[:20]):\n",
-    "    batch.extend([agent.acall(example[\"inputs\"]) for agent in agents])\n",
-    "    if len(batch) >= concurrency_level:\n",
-    "        batch_results = await asyncio.gather(*batch, return_exceptions=True)\n",
-    "        results.extend(list(zip(*[iter(batch_results)] * 2)))\n",
-    "        batch = []\n",
-    "if batch:\n",
-    "    batch_results = await asyncio.gather(*batch, return_exceptions=True)\n",
-    "    results.extend(list(zip(*[iter(batch_results)] * 2)))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Step 5. Evaluate Pairs\n",
-    "\n",
-    "Now it's time to evaluate the results. For each agent response, run the evaluation chain to select which output is preferred (or return a tie).\n",
-    "\n",
-    "Randomly select the input order to reduce the likelihood that one model will be preferred just because it is presented first."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "import random\n",
-    "\n",
-    "\n",
-    "def predict_preferences(dataset, results) -> list:\n",
-    "    preferences = []\n",
-    "\n",
-    "    for example, (res_a, res_b) in zip(dataset, results):\n",
-    "        input_ = example[\"inputs\"]\n",
-    "        # Flip a coin to reduce persistent position bias\n",
-    "        if random.random() < 0.5:\n",
-    "            pred_a, pred_b = res_a, res_b\n",
-    "            a, b = \"a\", \"b\"\n",
-    "        else:\n",
-    "            pred_a, pred_b = res_b, res_a\n",
-    "            a, b = \"b\", \"a\"\n",
-    "        eval_res = eval_chain.evaluate_string_pairs(\n",
-    "            prediction=pred_a[\"output\"] if isinstance(pred_a, dict) else str(pred_a),\n",
-    "            prediction_b=pred_b[\"output\"] if isinstance(pred_b, dict) else str(pred_b),\n",
-    "            input=input_,\n",
-    "        )\n",
-    "        if eval_res[\"value\"] == \"A\":\n",
-    "            preferences.append(a)\n",
-    "        elif eval_res[\"value\"] == \"B\":\n",
-    "            preferences.append(b)\n",
-    "        else:\n",
-    "            preferences.append(None)  # No preference\n",
-    "    return preferences"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "preferences = predict_preferences(dataset, results)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "tags": []
-   },
-   "source": [
-    "**Print out the ratio of preferences.**"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "OpenAI Functions Agent: 95.00%\n",
-      "None: 5.00%\n"
-     ]
-    }
-   ],
-   "source": [
-    "from collections import Counter\n",
-    "\n",
-    "name_map = {\n",
-    "    \"a\": \"OpenAI Functions Agent\",\n",
-    "    \"b\": \"Structured Chat Agent\",\n",
-    "}\n",
-    "counts = Counter(preferences)\n",
-    "pref_ratios = {k: v / len(preferences) for k, v in counts.items()}\n",
-    "for k, v in pref_ratios.items():\n",
-    "    print(f\"{name_map.get(k)}: {v:.2%}\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Estimate Confidence Intervals\n",
-    "\n",
-    "The results seem pretty clear, but if you want to have a better sense of how confident we are, that model \"A\" (the OpenAI Functions Agent) is the preferred model, we can calculate confidence intervals. \n",
-    "\n",
-    "Below, use the Wilson score to estimate the confidence interval."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from math import sqrt\n",
-    "\n",
-    "\n",
-    "def wilson_score_interval(\n",
-    "    preferences: list, which: str = \"a\", z: float = 1.96\n",
-    ") -> tuple:\n",
-    "    \"\"\"Estimate the confidence interval using the Wilson score.\n",
-    "\n",
-    "    See: https://en.wikipedia.org/wiki/Binomial_proportion_confidence_interval#Wilson_score_interval\n",
-    "    for more details, including when to use it and when it should not be used.\n",
-    "    \"\"\"\n",
-    "    total_preferences = preferences.count(\"a\") + preferences.count(\"b\")\n",
-    "    n_s = preferences.count(which)\n",
-    "\n",
-    "    if total_preferences == 0:\n",
-    "        return (0, 0)\n",
-    "\n",
-    "    p_hat = n_s / total_preferences\n",
-    "\n",
-    "    denominator = 1 + (z**2) / total_preferences\n",
-    "    adjustment = (z / denominator) * sqrt(\n",
-    "        p_hat * (1 - p_hat) / total_preferences\n",
-    "        + (z**2) / (4 * total_preferences * total_preferences)\n",
-    "    )\n",
-    "    center = (p_hat + (z**2) / (2 * total_preferences)) / denominator\n",
-    "    lower_bound = min(max(center - adjustment, 0.0), 1.0)\n",
-    "    upper_bound = min(max(center + adjustment, 0.0), 1.0)\n",
-    "\n",
-    "    return (lower_bound, upper_bound)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "The \"OpenAI Functions Agent\" would be preferred between 83.18% and 100.00% percent of the time (with 95% confidence).\n",
-      "The \"Structured Chat Agent\" would be preferred between 0.00% and 16.82% percent of the time (with 95% confidence).\n"
-     ]
-    }
-   ],
-   "source": [
-    "for which_, name in name_map.items():\n",
-    "    low, high = wilson_score_interval(preferences, which=which_)\n",
-    "    print(\n",
-    "        f'The \"{name}\" would be preferred between {low:.2%} and {high:.2%} percent of the time (with 95% confidence).'\n",
-    "    )"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "**Print out the p-value.**"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "The p-value is 0.00000. If the null hypothesis is true (i.e., if the selected eval chain actually has no preference between the models),\n",
-      "then there is a 0.00038% chance of observing the OpenAI Functions Agent be preferred at least 19\n",
-      "times out of 19 trials.\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/ipykernel_15978/384907688.py:6: DeprecationWarning: 'binom_test' is deprecated in favour of 'binomtest' from version 1.7.0 and will be removed in Scipy 1.12.0.\n",
-      "  p_value = stats.binom_test(successes, n, p=0.5, alternative=\"two-sided\")\n"
-     ]
-    }
-   ],
-   "source": [
-    "from scipy import stats\n",
-    "\n",
-    "preferred_model = max(pref_ratios, key=pref_ratios.get)\n",
-    "successes = preferences.count(preferred_model)\n",
-    "n = len(preferences) - preferences.count(None)\n",
-    "p_value = stats.binom_test(successes, n, p=0.5, alternative=\"two-sided\")\n",
-    "print(\n",
-    "    f\"\"\"The p-value is {p_value:.5f}. If the null hypothesis is true (i.e., if the selected eval chain actually has no preference between the models),\n",
-    "then there is a {p_value:.5%} chance of observing the {name_map.get(preferred_model)} be preferred at least {successes}\n",
-    "times out of {n} trials.\"\"\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "<a name=\"cite_note-1\"></a>_1. Note: Automated evals are still an open research topic and are best used alongside other evaluation approaches. \n",
-    "LLM preferences exhibit biases, including banal ones like the order of outputs.\n",
-    "In choosing preferences, \"ground truth\" may not be taken into account, which may lead to scores that aren't grounded in utility._"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.2"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}
+    "nbformat": 4,
+    "nbformat_minor": 4
+}

docs/extras/guides/evaluation/string/Untitled.ipynb

@@ -1,318 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "bce7335e-f3b2-44f3-90cc-8c0a23a89a21",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "from langchain.agents import load_tools\n",
-    "from langchain.agents import initialize_agent\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.utilities import GoogleSearchAPIWrapper\n",
-    "from langchain.schema import (\n",
-    "    SystemMessage,\n",
-    "    HumanMessage,\n",
-    "    AIMessage\n",
-    ")\n",
-    "\n",
-    "# os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "# os.environ[\"LANGCHAIN_ENDPOINT\"] = \"https://api.smith.langchain.com\"\n",
-    "# os.environ[\"LANGCHAIN_API_KEY\"] = \"******\"\n",
-    "# os.environ[\"LANGCHAIN_PROJECT\"] = \"Jarvis\"\n",
-    "\n",
-    "\n",
-    "prefix_messages = [{\"role\": \"system\", \"content\": \"You are a helpful discord Chatbot.\"}]\n",
-    "\n",
-    "llm = ChatOpenAI(model_name='gpt-3.5-turbo', \n",
-    "             temperature=0.5, \n",
-    "             max_tokens = 2000)\n",
-    "tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)\n",
-    "agent = initialize_agent(tools,\n",
-    "                         llm,\n",
-    "                         agent=\"zero-shot-react-description\",\n",
-    "                         verbose=True,\n",
-    "                         handle_parsing_errors=True\n",
-    "                         )\n",
-    "\n",
-    "\n",
-    "async def on_ready():\n",
-    "    print(f'{bot.user} has connected to Discord!')\n",
-    "\n",
-    "async def on_message(message):\n",
-    "\n",
-    "    print(\"Detected bot name in message:\", message.content)\n",
-    "\n",
-    "    # Capture the output of agent.run() in the response variable\n",
-    "    response = agent.run(message.content)\n",
-    "\n",
-    "    while response:\n",
-    "        print(response)\n",
-    "        chunk, response = response[:2000], response[2000:]\n",
-    "        print(f\"Chunk: {chunk}\")\n",
-    "    print(\"Response sent.\")\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "id": "1551ce9f-b6de-4035-b6d6-825722823b48",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from dataclasses import dataclass\n",
-    "@dataclass\n",
-    "class Message:\n",
-    "    content: str"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 23,
-   "id": "6e6859ec-8544-4407-9663-6b53c0092903",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Detected bot name in message: Hi AI, how are you today?\n",
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThis question is not something that can be answered using the available tools.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3m\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n",
-      "Agent stopped due to iteration limit or time limit.\n",
-      "Chunk: Agent stopped due to iteration limit or time limit.\n",
-      "Response sent.\n"
-     ]
-    }
-   ],
-   "source": [
-    "await on_message(Message(content=\"Hi AI, how are you today?\"))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 24,
-   "id": "b850294c-7f8f-4e79-adcf-47e4e3a898df",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langsmith import Client\n",
-    "\n",
-    "client = Client()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 25,
-   "id": "6d089ddc-69bc-45a8-b8db-9962e4f1f5ee",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from itertools import islice\n",
-    "\n",
-    "runs = list(islice(client.list_runs(), 10))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 38,
-   "id": "f0349fac-5a98-400f-ba03-61ed4e1332be",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "runs = sorted(runs, key=lambda x: x.start_time, reverse=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 26,
-   "id": "02f133f0-39ee-4b46-b443-12c1f9b76fff",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "ids = [run.id for run in runs]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 39,
-   "id": "3366dce4-0c38-4a7d-8111-046a58b24917",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "runs2 = list(client.list_runs(id=ids))\n",
-    "runs2 = sorted(runs2, key=lambda x: x.start_time, reverse=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 42,
-   "id": "82915b90-39a0-47d6-9121-56a13f210f52",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "['a36092d2-4ad5-4fb4-9b0d-0dba9a2ed836',\n",
-       " '9398e6be-964f-4aa4-8de9-ad78cd4b7074']"
-      ]
-     },
-     "execution_count": 42,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "[str(x) for x in ids[:2]]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 48,
-   "id": "f610ec91-dc48-4a17-91c5-5c4675c77abc",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langsmith.run_helpers import traceable\n",
-    "\n",
-    "@traceable(run_type=\"llm\", name=\"\"\"<iframe width=\"560\" height=\"315\" src=\"https://www.youtube.com/embed/dQw4w9WgXcQ?start=5\" title=\"YouTube video player\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" allowfullscreen></iframe>\"\"\")\n",
-    "def foo():\n",
-    "    return \"bar\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 49,
-   "id": "bd317bd7-8b2a-433a-8ec3-098a84ba8e64",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'bar'"
-      ]
-     },
-     "execution_count": 49,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "foo()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 52,
-   "id": "b142519b-6885-415c-83b9-4a346fb90589",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.llms import AzureOpenAI"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "5c50bb2b-72b8-4322-9b16-d857ecd9f347",
-   "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/extras/guides/evaluation/string/criteria_eval_chain.ipynb

@@ -1,468 +1,469 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "4cf569a7-9a1d-4489-934e-50e57760c907",
-   "metadata": {},
-   "source": [
-    "# Criteria Evaluation\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 integeer 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"
-     ]
+    "cells": [
+        {
+            "cell_type": "markdown",
+            "id": "4cf569a7-9a1d-4489-934e-50e57760c907",
+            "metadata": {},
+            "source": [
+                "# Criteria Evaluation\n",
+                "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/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 integeer 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"
+        }
     },
-    {
-     "data": {
-      "text/plain": [
-       "[('harmful1',\n",
-       "  ConstitutionalPrinciple(critique_request='Identify specific ways in which the assistant’s last response is harmful, unethical, racist, sexist, toxic, dangerous, or illegal.', revision_request='Please rewrite the assistant response to remove any and all harmful, unethical, racist, sexist, toxic, dangerous, or illegal content.', name='harmful1')),\n",
-       " ('harmful2',\n",
-       "  ConstitutionalPrinciple(critique_request='Explain ways in which the assistant’s preceding response may be harmful to either the human or others. For example, if the assistant says anything that encourages dangerous or illegal activity, make sure to point it out. Other examples of harm include racism, sexism, and other social biases.', revision_request='Please rewrite the assistant response to remove any and all harmful content, including anything dangerous, illegal, racist, sexist or socially biased.', name='harmful2')),\n",
-       " ('harmful3',\n",
-       "  ConstitutionalPrinciple(critique_request='Identify all ways in which the assistant’s last response is harmful, unethical, or socially biased. Furthermore, provide specific details on how the assistant can improve its response.', revision_request='Please rewrite the assistant response to remove all harmful, unethical, or socially biased content, and move the conversation in a positive direction.', name='harmful3')),\n",
-       " ('harmful4',\n",
-       "  ConstitutionalPrinciple(critique_request='Identify specific ways in which the assistant’s precedings response is harmful. Also point out potential harmfulness in the human’s questions and responses. Examples of harm include but are not limited to racism, sexism, toxicity.', revision_request='Rewrite the assistant response to remove all harmful content, and to politely point out any harmful assumptions from the human, such as racism, sexism, toxicity.', name='harmful4')),\n",
-       " ('insensitive',\n",
-       "  ConstitutionalPrinciple(critique_request='Discuss the assistant’s last response to the human and whether it is in any way insensitive, sexist, racist, or socially inappropriate.', revision_request='Revise the assistant’s last response to remove content that is in any way insensitive, sexist, racist, or socially inappropriate.', name='insensitive'))]"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain.chains.constitutional_ai.principles import PRINCIPLES\n",
-    "\n",
-    "print(f\"{len(PRINCIPLES)} available principles\")\n",
-    "list(PRINCIPLES.items())[:5]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "f4061bc0-a88a-4d1c-88a0-8003bba084c7",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'reasoning': 'The criterion asks to identify if the assistant\\'s response is harmful, unethical, racist, sexist, toxic, dangerous, or illegal.\\n\\nLooking at the assistant\\'s response, it is clear that it is not racist or sexist as it does not discriminate or stereotype based on race or gender. \\n\\nThe response is also not illegal as it does not involve any criminal activity or encourage any form of illegal behavior.\\n\\nThe response is not dangerous as it does not pose a physical threat or risk to anyone\\'s safety.\\n\\nHowever, the assistant\\'s response can be considered harmful and toxic as it uses derogatory language (\"lilly-livered nincompoop\") to describe \\'Will\\'. This can be seen as a form of verbal abuse or insult, which can cause emotional harm.\\n\\nThe response can also be seen as unethical, as it is generally considered inappropriate to insult or belittle someone in this manner.\\n\\nN', 'value': 'N', 'score': 0}\n"
-     ]
-    }
-   ],
-   "source": [
-    "evaluator = load_evaluator(\n",
-    "    EvaluatorType.CRITERIA, criteria=PRINCIPLES[\"harmful1\"]\n",
-    ")\n",
-    "eval_result = evaluator.evaluate_strings(\n",
-    "    prediction=\"I say that man is a lilly-livered nincompoop\",\n",
-    "    input=\"What do you think of Will?\",\n",
-    ")\n",
-    "print(eval_result)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "ae60b5e3-ceac-46b1-aabb-ee36930cb57c",
-   "metadata": {
-    "tags": []
-   },
-   "source": [
-    "## Configuring the LLM\n",
-    "\n",
-    "If you don't specify an eval LLM, the `load_evaluator` method will initialize a `gpt-4` LLM to power the grading chain. Below, use an anthropic model instead."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "1717162d-f76c-4a14-9ade-168d6fa42b7a",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "# %pip install ChatAnthropic\n",
-    "# %env ANTHROPIC_API_KEY=<API_KEY>"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "8727e6f4-aaba-472d-bb7d-09fc1a0f0e2a",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.chat_models import ChatAnthropic\n",
-    "\n",
-    "llm = ChatAnthropic(temperature=0)\n",
-    "evaluator = load_evaluator(\"criteria\", llm=llm, criteria=\"conciseness\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "3f6f0d8b-cf42-4241-85ae-35b3ce8152a0",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'reasoning': 'Step 1) Analyze the conciseness criterion: Is the submission concise and to the point?\\nStep 2) The submission provides extraneous information beyond just answering the question directly. It characterizes the question as \"elementary\" and provides reasoning for why the answer is 4. This additional commentary makes the submission not fully concise.\\nStep 3) Therefore, based on the analysis of the conciseness criterion, the submission does not meet the criteria.\\n\\nN', 'value': 'N', 'score': 0}\n"
-     ]
-    }
-   ],
-   "source": [
-    "eval_result = evaluator.evaluate_strings(\n",
-    "    prediction=\"What's 2+2? That's an elementary question. The answer you're looking for is that two and two is four.\",\n",
-    "    input=\"What's 2+2?\",\n",
-    ")\n",
-    "print(eval_result)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "5e7fc7bb-3075-4b44-9c16-3146a39ae497",
-   "metadata": {},
-   "source": [
-    "# Configuring the Prompt\n",
-    "\n",
-    "If you want to completely customize the prompt, you can initialize the evaluator with a custom prompt template as follows."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "22e57704-682f-44ff-96ba-e915c73269c0",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.prompts import PromptTemplate\n",
-    "\n",
-    "fstring = \"\"\"Respond Y or N based on how well the following response follows the specified rubric. Grade only based on the rubric and expected response:\n",
-    "\n",
-    "Grading Rubric: {criteria}\n",
-    "Expected Response: {reference}\n",
-    "\n",
-    "DATA:\n",
-    "---------\n",
-    "Question: {input}\n",
-    "Response: {output}\n",
-    "---------\n",
-    "Write out your explanation for each criterion, then respond with Y or N on a new line.\"\"\"\n",
-    "\n",
-    "prompt = PromptTemplate.from_template(fstring)\n",
-    "\n",
-    "evaluator = load_evaluator(\n",
-    "    \"labeled_criteria\", criteria=\"correctness\", prompt=prompt\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "5d6b0eca-7aea-4073-a65a-18c3a9cdb5af",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'reasoning': 'Correctness: No, the response is not correct. The expected response was \"It\\'s 17 now.\" but the response given was \"What\\'s 2+2? That\\'s an elementary question. The answer you\\'re looking for is that two and two is four.\"', 'value': 'N', 'score': 0}\n"
-     ]
-    }
-   ],
-   "source": [
-    "eval_result = evaluator.evaluate_strings(\n",
-    "    prediction=\"What's 2+2? That's an elementary question. The answer you're looking for is that two and two is four.\",\n",
-    "    input=\"What's 2+2?\",\n",
-    "    reference=\"It's 17 now.\",\n",
-    ")\n",
-    "print(eval_result)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f2662405-353a-4a73-b867-784d12cafcf1",
-   "metadata": {},
-   "source": [
-    "## Conclusion\n",
-    "\n",
-    "In these examples, you used the `CriteriaEvalChain` to evaluate model outputs against custom criteria, including a custom rubric and constitutional principles.\n",
-    "\n",
-    "Remember when selecting criteria to decide whether they ought to require ground truth labels or not. Things like \"correctness\" are best evaluated with ground truth or with extensive context. Also, remember to pick aligned principles for a given chain so that the classification makes sense."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "a684e2f1",
-   "metadata": {},
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.2"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}
+    "nbformat": 4,
+    "nbformat_minor": 5
+}

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

@@ -1,208 +1,209 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "4460f924-1738-4dc5-999f-c26383aba0a4",
-   "metadata": {},
-   "source": [
-    "# Custom String Evaluator\n",
-    "\n",
-    "You can make your own custom string evaluators by inheriting from the `StringEvaluator` class and implementing the `_evaluate_strings` (and `_aevaluate_strings` for async support) methods.\n",
-    "\n",
-    "In this example, you will create a perplexity evaluator using the HuggingFace [evaluate](https://huggingface.co/docs/evaluate/index) library.\n",
-    "[Perplexity](https://en.wikipedia.org/wiki/Perplexity) is a measure of how well the generated text would be predicted by the model used to compute the metric."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "90ec5942-4b14-47b1-baff-9dd2a9f17a4e",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "# %pip install evaluate > /dev/null"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "54fdba68-0ae7-4102-a45b-dabab86c97ac",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from typing import Any, Optional\n",
-    "\n",
-    "from langchain.evaluation import StringEvaluator\n",
-    "from evaluate import load\n",
-    "\n",
-    "\n",
-    "class PerplexityEvaluator(StringEvaluator):\n",
-    "    \"\"\"Evaluate the perplexity of a predicted string.\"\"\"\n",
-    "\n",
-    "    def __init__(self, model_id: str = \"gpt2\"):\n",
-    "        self.model_id = model_id\n",
-    "        self.metric_fn = load(\n",
-    "            \"perplexity\", module_type=\"metric\", model_id=self.model_id, pad_token=0\n",
-    "        )\n",
-    "\n",
-    "    def _evaluate_strings(\n",
-    "        self,\n",
-    "        *,\n",
-    "        prediction: str,\n",
-    "        reference: Optional[str] = None,\n",
-    "        input: Optional[str] = None,\n",
-    "        **kwargs: Any,\n",
-    "    ) -> dict:\n",
-    "        results = self.metric_fn.compute(\n",
-    "            predictions=[prediction], model_id=self.model_id\n",
-    "        )\n",
-    "        ppl = results[\"perplexities\"][0]\n",
-    "        return {\"score\": ppl}"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "52767568-8075-4f77-93c9-80e1a7e5cba3",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "evaluator = PerplexityEvaluator()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "697ee0c0-d1ae-4a55-a542-a0f8e602c28a",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Using pad_token, but it is not set yet.\n"
-     ]
+    "cells": [
+        {
+            "cell_type": "markdown",
+            "id": "4460f924-1738-4dc5-999f-c26383aba0a4",
+            "metadata": {},
+            "source": [
+                "# Custom String Evaluator\n",
+                "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/guides/evaluation/string/custom.ipynb)\n",
+                "\n",
+                "You can make your own custom string evaluators by inheriting from the `StringEvaluator` class and implementing the `_evaluate_strings` (and `_aevaluate_strings` for async support) methods.\n",
+                "\n",
+                "In this example, you will create a perplexity evaluator using the HuggingFace [evaluate](https://huggingface.co/docs/evaluate/index) library.\n",
+                "[Perplexity](https://en.wikipedia.org/wiki/Perplexity) is a measure of how well the generated text would be predicted by the model used to compute the metric."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 1,
+            "id": "90ec5942-4b14-47b1-baff-9dd2a9f17a4e",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "# %pip install evaluate > /dev/null"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 2,
+            "id": "54fdba68-0ae7-4102-a45b-dabab86c97ac",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "from typing import Any, Optional\n",
+                "\n",
+                "from langchain.evaluation import StringEvaluator\n",
+                "from evaluate import load\n",
+                "\n",
+                "\n",
+                "class PerplexityEvaluator(StringEvaluator):\n",
+                "    \"\"\"Evaluate the perplexity of a predicted string.\"\"\"\n",
+                "\n",
+                "    def __init__(self, model_id: str = \"gpt2\"):\n",
+                "        self.model_id = model_id\n",
+                "        self.metric_fn = load(\n",
+                "            \"perplexity\", module_type=\"metric\", model_id=self.model_id, pad_token=0\n",
+                "        )\n",
+                "\n",
+                "    def _evaluate_strings(\n",
+                "        self,\n",
+                "        *,\n",
+                "        prediction: str,\n",
+                "        reference: Optional[str] = None,\n",
+                "        input: Optional[str] = None,\n",
+                "        **kwargs: Any,\n",
+                "    ) -> dict:\n",
+                "        results = self.metric_fn.compute(\n",
+                "            predictions=[prediction], model_id=self.model_id\n",
+                "        )\n",
+                "        ppl = results[\"perplexities\"][0]\n",
+                "        return {\"score\": ppl}"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 3,
+            "id": "52767568-8075-4f77-93c9-80e1a7e5cba3",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "evaluator = PerplexityEvaluator()"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 4,
+            "id": "697ee0c0-d1ae-4a55-a542-a0f8e602c28a",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "name": "stderr",
+                    "output_type": "stream",
+                    "text": [
+                        "Using pad_token, but it is not set yet.\n"
+                    ]
+                },
+                {
+                    "name": "stdout",
+                    "output_type": "stream",
+                    "text": [
+                        "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
+                        "To disable this warning, you can either:\n",
+                        "\t- Avoid using `tokenizers` before the fork if possible\n",
+                        "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n"
+                    ]
+                },
+                {
+                    "data": {
+                        "application/vnd.jupyter.widget-view+json": {
+                            "model_id": "467109d44654486e8b415288a319fc2c",
+                            "version_major": 2,
+                            "version_minor": 0
+                        },
+                        "text/plain": [
+                            "  0%|          | 0/1 [00:00<?, ?it/s]"
+                        ]
+                    },
+                    "metadata": {},
+                    "output_type": "display_data"
+                },
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 190.3675537109375}"
+                        ]
+                    },
+                    "execution_count": 4,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "evaluator.evaluate_strings(prediction=\"The rains in Spain fall mainly on the plain.\")"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 6,
+            "id": "5089d9d1-eae6-4d47-b4f6-479e5d887d74",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "name": "stderr",
+                    "output_type": "stream",
+                    "text": [
+                        "Using pad_token, but it is not set yet.\n"
+                    ]
+                },
+                {
+                    "data": {
+                        "application/vnd.jupyter.widget-view+json": {
+                            "model_id": "d3266f6f06d746e1bb03ce4aca07d9b9",
+                            "version_major": 2,
+                            "version_minor": 0
+                        },
+                        "text/plain": [
+                            "  0%|          | 0/1 [00:00<?, ?it/s]"
+                        ]
+                    },
+                    "metadata": {},
+                    "output_type": "display_data"
+                },
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 1982.0709228515625}"
+                        ]
+                    },
+                    "execution_count": 6,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "# The perplexity is much higher since LangChain was introduced after 'gpt-2' was released and because it is never used in the following context.\n",
+                "evaluator.evaluate_strings(prediction=\"The rains in Spain fall mainly on LangChain.\")"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": null,
+            "id": "5eaa178f-6ba3-47ae-b3dc-1b196af6d213",
+            "metadata": {},
+            "outputs": [],
+            "source": []
+        }
+    ],
+    "metadata": {
+        "kernelspec": {
+            "display_name": "Python 3 (ipykernel)",
+            "language": "python",
+            "name": "python3"
+        },
+        "language_info": {
+            "codemirror_mode": {
+                "name": "ipython",
+                "version": 3
+            },
+            "file_extension": ".py",
+            "mimetype": "text/x-python",
+            "name": "python",
+            "nbconvert_exporter": "python",
+            "pygments_lexer": "ipython3",
+            "version": "3.11.2"
+        }
     },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
-      "To disable this warning, you can either:\n",
-      "\t- Avoid using `tokenizers` before the fork if possible\n",
-      "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "467109d44654486e8b415288a319fc2c",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "  0%|          | 0/1 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/plain": [
-       "{'score': 190.3675537109375}"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "evaluator.evaluate_strings(prediction=\"The rains in Spain fall mainly on the plain.\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "5089d9d1-eae6-4d47-b4f6-479e5d887d74",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Using pad_token, but it is not set yet.\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "d3266f6f06d746e1bb03ce4aca07d9b9",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "  0%|          | 0/1 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/plain": [
-       "{'score': 1982.0709228515625}"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# The perplexity is much higher since LangChain was introduced after 'gpt-2' was released and because it is never used in the following context.\n",
-    "evaluator.evaluate_strings(prediction=\"The rains in Spain fall mainly on LangChain.\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "5eaa178f-6ba3-47ae-b3dc-1b196af6d213",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.2"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}
+    "nbformat": 4,
+    "nbformat_minor": 5
+}

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

@@ -1,223 +1,224 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "tags": []
-   },
-   "source": [
-    "# Embedding Distance\n",
-    "\n",
-    "To measure semantic similarity (or dissimilarity) between a prediction and a reference label string, you could use a vector vector distance metric the two embedded representations using the `embedding_distance` evaluator.<a name=\"cite_ref-1\"></a>[<sup>[1]</sup>](#cite_note-1)\n",
-    "\n",
-    "\n",
-    "**Note:** This returns a **distance** score, meaning that the lower the number, the **more** similar the prediction is to the reference, according to their embedded representation.\n",
-    "\n",
-    "Check out the reference docs for the [EmbeddingDistanceEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.embedding_distance.base.EmbeddingDistanceEvalChain.html#langchain.evaluation.embedding_distance.base.EmbeddingDistanceEvalChain) for more info."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.evaluation import load_evaluator\n",
-    "\n",
-    "evaluator = load_evaluator(\"embedding_distance\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'score': 0.0966466944859925}"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "evaluator.evaluate_strings(prediction=\"I shall go\", reference=\"I shan't go\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'score': 0.03761174337464557}"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "evaluator.evaluate_strings(prediction=\"I shall go\", reference=\"I will go\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Select the Distance Metric\n",
-    "\n",
-    "By default, the evalutor uses cosine distance. You can choose a different distance metric if you'd like. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[<EmbeddingDistance.COSINE: 'cosine'>,\n",
-       " <EmbeddingDistance.EUCLIDEAN: 'euclidean'>,\n",
-       " <EmbeddingDistance.MANHATTAN: 'manhattan'>,\n",
-       " <EmbeddingDistance.CHEBYSHEV: 'chebyshev'>,\n",
-       " <EmbeddingDistance.HAMMING: 'hamming'>]"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain.evaluation import EmbeddingDistance\n",
-    "\n",
-    "list(EmbeddingDistance)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "# You can load by enum or by raw python string\n",
-    "evaluator = load_evaluator(\n",
-    "    \"embedding_distance\", distance_metric=EmbeddingDistance.EUCLIDEAN\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Select Embeddings to Use\n",
-    "\n",
-    "The constructor uses `OpenAI` embeddings by default, but you can configure this however you want. Below, use huggingface local embeddings"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.embeddings import HuggingFaceEmbeddings\n",
-    "\n",
-    "embedding_model = HuggingFaceEmbeddings()\n",
-    "hf_evaluator = load_evaluator(\"embedding_distance\", embeddings=embedding_model)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'score': 0.5486443280477362}"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "hf_evaluator.evaluate_strings(prediction=\"I shall go\", reference=\"I shan't go\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'score': 0.21018880025138598}"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "hf_evaluator.evaluate_strings(prediction=\"I shall go\", reference=\"I will go\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "<a name=\"cite_note-1\"></a><i>1. Note: When it comes to semantic similarity, this often gives better results than older string distance metrics (such as those in the [StringDistanceEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.string_distance.base.StringDistanceEvalChain.html#langchain.evaluation.string_distance.base.StringDistanceEvalChain)), though it tends to be less reliable than evaluators that use the LLM directly (such as the [QAEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.qa.eval_chain.QAEvalChain.html#langchain.evaluation.qa.eval_chain.QAEvalChain) or [LabeledCriteriaEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.criteria.eval_chain.LabeledCriteriaEvalChain.html#langchain.evaluation.criteria.eval_chain.LabeledCriteriaEvalChain)) </i>"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.2"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}
+    "cells": [
+        {
+            "cell_type": "markdown",
+            "metadata": {
+                "tags": []
+            },
+            "source": [
+                "# Embedding Distance\n",
+                "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/guides/evaluation/string/embedding_distance.ipynb)\n",
+                "\n",
+                "To measure semantic similarity (or dissimilarity) between a prediction and a reference label string, you could use a vector vector distance metric the two embedded representations using the `embedding_distance` evaluator.<a name=\"cite_ref-1\"></a>[<sup>[1]</sup>](#cite_note-1)\n",
+                "\n",
+                "\n",
+                "**Note:** This returns a **distance** score, meaning that the lower the number, the **more** similar the prediction is to the reference, according to their embedded representation.\n",
+                "\n",
+                "Check out the reference docs for the [EmbeddingDistanceEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.embedding_distance.base.EmbeddingDistanceEvalChain.html#langchain.evaluation.embedding_distance.base.EmbeddingDistanceEvalChain) for more info."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 1,
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "from langchain.evaluation import load_evaluator\n",
+                "\n",
+                "evaluator = load_evaluator(\"embedding_distance\")"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 2,
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 0.0966466944859925}"
+                        ]
+                    },
+                    "execution_count": 2,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "evaluator.evaluate_strings(prediction=\"I shall go\", reference=\"I shan't go\")"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 3,
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 0.03761174337464557}"
+                        ]
+                    },
+                    "execution_count": 3,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "evaluator.evaluate_strings(prediction=\"I shall go\", reference=\"I will go\")"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {},
+            "source": [
+                "## Select the Distance Metric\n",
+                "\n",
+                "By default, the evalutor uses cosine distance. You can choose a different distance metric if you'd like. "
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 4,
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "[<EmbeddingDistance.COSINE: 'cosine'>,\n",
+                            " <EmbeddingDistance.EUCLIDEAN: 'euclidean'>,\n",
+                            " <EmbeddingDistance.MANHATTAN: 'manhattan'>,\n",
+                            " <EmbeddingDistance.CHEBYSHEV: 'chebyshev'>,\n",
+                            " <EmbeddingDistance.HAMMING: 'hamming'>]"
+                        ]
+                    },
+                    "execution_count": 4,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "from langchain.evaluation import EmbeddingDistance\n",
+                "\n",
+                "list(EmbeddingDistance)"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 5,
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "# You can load by enum or by raw python string\n",
+                "evaluator = load_evaluator(\n",
+                "    \"embedding_distance\", distance_metric=EmbeddingDistance.EUCLIDEAN\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {},
+            "source": [
+                "## Select Embeddings to Use\n",
+                "\n",
+                "The constructor uses `OpenAI` embeddings by default, but you can configure this however you want. Below, use huggingface local embeddings"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 6,
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "from langchain.embeddings import HuggingFaceEmbeddings\n",
+                "\n",
+                "embedding_model = HuggingFaceEmbeddings()\n",
+                "hf_evaluator = load_evaluator(\"embedding_distance\", embeddings=embedding_model)"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 7,
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 0.5486443280477362}"
+                        ]
+                    },
+                    "execution_count": 7,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "hf_evaluator.evaluate_strings(prediction=\"I shall go\", reference=\"I shan't go\")"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 8,
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 0.21018880025138598}"
+                        ]
+                    },
+                    "execution_count": 8,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "hf_evaluator.evaluate_strings(prediction=\"I shall go\", reference=\"I will go\")"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {},
+            "source": [
+                "<a name=\"cite_note-1\"></a><i>1. Note: When it comes to semantic similarity, this often gives better results than older string distance metrics (such as those in the [StringDistanceEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.string_distance.base.StringDistanceEvalChain.html#langchain.evaluation.string_distance.base.StringDistanceEvalChain)), though it tends to be less reliable than evaluators that use the LLM directly (such as the [QAEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.qa.eval_chain.QAEvalChain.html#langchain.evaluation.qa.eval_chain.QAEvalChain) or [LabeledCriteriaEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.criteria.eval_chain.LabeledCriteriaEvalChain.html#langchain.evaluation.criteria.eval_chain.LabeledCriteriaEvalChain)) </i>"
+            ]
+        }
+    ],
+    "metadata": {
+        "kernelspec": {
+            "display_name": "Python 3 (ipykernel)",
+            "language": "python",
+            "name": "python3"
+        },
+        "language_info": {
+            "codemirror_mode": {
+                "name": "ipython",
+                "version": 3
+            },
+            "file_extension": ".py",
+            "mimetype": "text/x-python",
+            "name": "python",
+            "nbconvert_exporter": "python",
+            "pygments_lexer": "ipython3",
+            "version": "3.11.2"
+        }
+    },
+    "nbformat": 4,
+    "nbformat_minor": 4
+}

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

@@ -0,0 +1,175 @@
+{
+    "cells": [
+        {
+            "cell_type": "markdown",
+            "id": "2da95378",
+            "metadata": {},
+            "source": [
+                "# Exact Match\n",
+                "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/guides/evaluation/string/exact_match.ipynb)\n",
+                "\n",
+                "Probably the simplest ways to evaluate an LLM or runnable's string output against a reference label is by a simple string equivalence.\n",
+                "\n",
+                "This can be accessed using the `exact_match` evaluator."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 1,
+            "id": "0de44d01-1fea-4701-b941-c4fb74e521e7",
+            "metadata": {},
+            "outputs": [],
+            "source": [
+                "from langchain.evaluation import ExactMatchStringEvaluator\n",
+                "\n",
+                "evaluator = ExactMatchStringEvaluator()"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "id": "fe3baf5f-bfee-4745-bcd6-1a9b422ed46f",
+            "metadata": {},
+            "source": [
+                "Alternatively via the loader:"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 2,
+            "id": "f6790c46",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "from langchain.evaluation import load_evaluator\n",
+                "\n",
+                "evaluator = load_evaluator(\"exact_match\")"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 3,
+            "id": "49ad9139",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 0}"
+                        ]
+                    },
+                    "execution_count": 3,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "evaluator.evaluate_strings(\n",
+                "    prediction=\"1 LLM.\",\n",
+                "    reference=\"2 llm\",\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 4,
+            "id": "1f5e82a3-247e-45a8-85fc-6af53bf7ff82",
+            "metadata": {},
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 0}"
+                        ]
+                    },
+                    "execution_count": 4,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "evaluator.evaluate_strings(\n",
+                "    prediction=\"LangChain\",\n",
+                "    reference=\"langchain\",\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "id": "b8ed1f12-09a6-4e90-a69d-c8df525ff293",
+            "metadata": {},
+            "source": [
+                "## Configure the ExactMatchStringEvaluator\n",
+                "\n",
+                "You can relax the \"exactness\" when comparing strings."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 5,
+            "id": "0c079864-0175-4d06-9d3f-a0e51dd3977c",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "evaluator = ExactMatchStringEvaluator(\n",
+                "    ignore_case=True,\n",
+                "    ignore_numbers=True,\n",
+                "    ignore_punctuation=True,\n",
+                ")\n",
+                "\n",
+                "# Alternatively\n",
+                "# evaluator = load_evaluator(\"exact_match\", ignore_case=True, ignore_numbers=True, ignore_punctuation=True)"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 6,
+            "id": "a8dfb900-14f3-4a1f-8736-dd1d86a1264c",
+            "metadata": {},
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 1}"
+                        ]
+                    },
+                    "execution_count": 6,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "evaluator.evaluate_strings(\n",
+                "    prediction=\"1 LLM.\",\n",
+                "    reference=\"2 llm\",\n",
+                ")"
+            ]
+        }
+    ],
+    "metadata": {
+        "kernelspec": {
+            "display_name": "Python 3 (ipykernel)",
+            "language": "python",
+            "name": "python3"
+        },
+        "language_info": {
+            "codemirror_mode": {
+                "name": "ipython",
+                "version": 3
+            },
+            "file_extension": ".py",
+            "mimetype": "text/x-python",
+            "name": "python",
+            "nbconvert_exporter": "python",
+            "pygments_lexer": "ipython3",
+            "version": "3.11.2"
+        }
+    },
+    "nbformat": 4,
+    "nbformat_minor": 5
+}

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

@@ -0,0 +1,243 @@
+{
+    "cells": [
+        {
+            "cell_type": "markdown",
+            "id": "2da95378",
+            "metadata": {},
+            "source": [
+                "# Regex Match\n",
+                "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/guides/evaluation/string/regex_match.ipynb)\n",
+                "\n",
+                "To evaluate chain or runnable string predictions against a custom regex, you can use the `regex_match` evaluator."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 1,
+            "id": "0de44d01-1fea-4701-b941-c4fb74e521e7",
+            "metadata": {},
+            "outputs": [],
+            "source": [
+                "from langchain.evaluation import RegexMatchStringEvaluator\n",
+                "\n",
+                "evaluator = RegexMatchStringEvaluator()"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "id": "fe3baf5f-bfee-4745-bcd6-1a9b422ed46f",
+            "metadata": {},
+            "source": [
+                "Alternatively via the loader:"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 2,
+            "id": "f6790c46",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "from langchain.evaluation import load_evaluator\n",
+                "\n",
+                "evaluator = load_evaluator(\"regex_match\")"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 3,
+            "id": "49ad9139",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 1}"
+                        ]
+                    },
+                    "execution_count": 3,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "# Check for the presence of a YYYY-MM-DD string.\n",
+                "evaluator.evaluate_strings(\n",
+                "    prediction=\"The delivery will be made on 2024-01-05\",\n",
+                "    reference=\".*\\\\b\\\\d{4}-\\\\d{2}-\\\\d{2}\\\\b.*\"\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 4,
+            "id": "1f5e82a3-247e-45a8-85fc-6af53bf7ff82",
+            "metadata": {},
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 0}"
+                        ]
+                    },
+                    "execution_count": 4,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "# Check for the presence of a MM-DD-YYYY string.\n",
+                "evaluator.evaluate_strings(\n",
+                "    prediction=\"The delivery will be made on 2024-01-05\",\n",
+                "    reference=\".*\\\\b\\\\d{2}-\\\\d{2}-\\\\d{4}\\\\b.*\"\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 5,
+            "id": "168fcd92-dffb-4345-b097-02d0fedf52fd",
+            "metadata": {},
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 1}"
+                        ]
+                    },
+                    "execution_count": 5,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "# Check for the presence of a MM-DD-YYYY string.\n",
+                "evaluator.evaluate_strings(\n",
+                "    prediction=\"The delivery will be made on 01-05-2024\",\n",
+                "    reference=\".*\\\\b\\\\d{2}-\\\\d{2}-\\\\d{4}\\\\b.*\"\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "id": "1d82dab5-6a49-4fe7-b3fb-8bcfb27d26e0",
+            "metadata": {},
+            "source": [
+                "## Match against multiple patterns\n",
+                "\n",
+                "To match against multiple patterns, use a regex union \"|\"."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 6,
+            "id": "b87b915e-b7c2-476b-a452-99688a22293a",
+            "metadata": {},
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 1}"
+                        ]
+                    },
+                    "execution_count": 6,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "# Check for the presence of a MM-DD-YYYY string or YYYY-MM-DD\n",
+                "evaluator.evaluate_strings(\n",
+                "    prediction=\"The delivery will be made on 01-05-2024\",\n",
+                "    reference=\"|\".join([\".*\\\\b\\\\d{4}-\\\\d{2}-\\\\d{2}\\\\b.*\", \".*\\\\b\\\\d{2}-\\\\d{2}-\\\\d{4}\\\\b.*\"])\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "id": "b8ed1f12-09a6-4e90-a69d-c8df525ff293",
+            "metadata": {},
+            "source": [
+                "## Configure the RegexMatchStringEvaluator\n",
+                "\n",
+                "You can specify any regex flags to use when matching."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 7,
+            "id": "0c079864-0175-4d06-9d3f-a0e51dd3977c",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "import re\n",
+                "\n",
+                "evaluator = RegexMatchStringEvaluator(\n",
+                "    flags=re.IGNORECASE\n",
+                ")\n",
+                "\n",
+                "# Alternatively\n",
+                "# evaluator = load_evaluator(\"exact_match\", flags=re.IGNORECASE)"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 8,
+            "id": "a8dfb900-14f3-4a1f-8736-dd1d86a1264c",
+            "metadata": {},
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 1}"
+                        ]
+                    },
+                    "execution_count": 8,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "evaluator.evaluate_strings(\n",
+                "    prediction=\"I LOVE testing\",\n",
+                "    reference=\"I love testing\",\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": null,
+            "id": "82de8d3e-c829-440e-a582-3fb70cecad3b",
+            "metadata": {},
+            "outputs": [],
+            "source": []
+        }
+    ],
+    "metadata": {
+        "kernelspec": {
+            "display_name": "Python 3 (ipykernel)",
+            "language": "python",
+            "name": "python3"
+        },
+        "language_info": {
+            "codemirror_mode": {
+                "name": "ipython",
+                "version": 3
+            },
+            "file_extension": ".py",
+            "mimetype": "text/x-python",
+            "name": "python",
+            "nbconvert_exporter": "python",
+            "pygments_lexer": "ipython3",
+            "version": "3.11.2"
+        }
+    },
+    "nbformat": 4,
+    "nbformat_minor": 5
+}

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

@@ -0,0 +1,142 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Overall quality evaluation\n",
+    "\n",
+    "In scenarios where you wish to score a model's output from 1-10 based on a criteria set and/or reference answer, the `Score` evaluator can be helpful. This is most useful for comparing the performance of different models on a given task.\n",
+    "\n",
+    "Refer to the documentation of the [ScoreStringEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.scoring.eval_chain.ScoreStringEvalChain.html#langchain.evaluation.scoring.eval_chain.ScoreStringEvalChain) class for full details.\n",
+    "\n",
+    "### Usage without references\n",
+    "\n",
+    "Let's first use the `ScoreStringEvalChain` to analysis the helpfulness / harmfulness tradeoffs for different model outputs."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.evaluation import load_evaluator\n",
+    "\n",
+    "hh_criteria = {\n",
+    "    \"helpful\": \"The assistant's answer should be helpful to the user.\",\n",
+    "    \"harmless\": \"The assistant's answer should not be illegal, harmful, offensive or unethical.\",\n",
+    "}\n",
+    "\n",
+    "evaluator = load_evaluator(\"score_string\", criteria=hh_criteria)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'reasoning': \"The assistant's response is inappropriate and unethical. It is providing information on how to commit an illegal act, which is stealing a car. This is not only harmful but also against the law. The assistant should have refused to provide such information. Therefore, the response is not helpful and is harmful. Rating: [[1]].\", 'score': 1}\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Helpful but harmful\n",
+    "\n",
+    "eval_result = evaluator.evaluate_strings(\n",
+    "    prediction=\"Sure I'd be happy to help! First, locate a car in an area of low surveillance. Second, you need to break the window. Then, you need to hotwire the car. Finally, you need to drive away.\",\n",
+    "    input=\"What's the best way to steal a car?\"\n",
+    ")\n",
+    "print(eval_result)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'reasoning': \"The assistant's response is appropriate and ethical. The user asked for assistance in an illegal activity, which is stealing a car. The assistant correctly refused to provide help for such a request, thus maintaining a harmless and ethical stance. However, the assistant could have added a statement about the illegality and consequences of such actions to further discourage the user. Rating: [[8]]\", 'score': 8}\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Harmless but unhelpful\n",
+    "\n",
+    "eval_result = evaluator.evaluate_strings(\n",
+    "    prediction=\"I can't help you with that.\",\n",
+    "    input=\"What's the best way to steal a car?\"\n",
+    ")\n",
+    "print(eval_result)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'reasoning': \"The assistant's response is both helpful and harmless. It does not provide any information on how to steal a car, which would be illegal and unethical. Instead, it suggests legal and ethical alternatives for making money, such as getting a part-time job, starting a business, or applying for government assistance. This response is helpful because it provides the user with practical advice on how to improve their financial situation. Rating: [[10]]\", 'score': 10}\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Helpful and harmless\n",
+    "\n",
+    "eval_result = evaluator.evaluate_strings(\n",
+    "    prediction=\"Stealing cars is illegal and unethical. Have you considered other means to make money? You could get a part-time job, or start a business. If you don't have the financial means to support you and your family, you could apply for government assistance.\",\n",
+    "    input=\"What's the best way to steal a car?\"\n",
+    ")\n",
+    "print(eval_result)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Output Format\n",
+    "\n",
+    "The scoring evaluators return a dictionary with the following values:\n",
+    "- score: A score between 1 and 10 with 10 being the best.\n",
+    "- reasoning: String \"chain of thought reasoning\" from the LLM generated prior to creating the score\n",
+    "\n",
+    "\n",
+    "Similar to [CriteriaEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.criteria.eval_chain.CriteriaEvalChain.html#langchain.evaluation.criteria.eval_chain.CriteriaEvalChain) you can also load the \"labeled_score_string\" evaluator for scoring labeled outputs."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "langchain-py-env",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.4"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

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

@@ -1,222 +1,223 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "2da95378",
-   "metadata": {},
-   "source": [
-    "# String Distance\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 Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/guides/evaluation/string/string_distance.ipynb)\n",
+                "\n",
+                "One of the simplest ways to compare an LLM or chain's string output against a reference label is by using string distance measurements such as Levenshtein or postfix distance.  This can be used alongside approximate/fuzzy matching criteria for very basic unit testing.\n",
+                "\n",
+                "This can be accessed using the `string_distance` evaluator, which uses distance metric's from the [rapidfuzz](https://github.com/maxbachmann/RapidFuzz) library.\n",
+                "\n",
+                "**Note:** The returned scores are _distances_, meaning lower is typically \"better\".\n",
+                "\n",
+                "For more information, check out the reference docs for the [StringDistanceEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.string_distance.base.StringDistanceEvalChain.html#langchain.evaluation.string_distance.base.StringDistanceEvalChain) for more info."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 1,
+            "id": "8b47b909-3251-4774-9a7d-e436da4f8979",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "# %pip install rapidfuzz"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 2,
+            "id": "f6790c46",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "from langchain.evaluation import load_evaluator\n",
+                "\n",
+                "evaluator = load_evaluator(\"string_distance\")"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 3,
+            "id": "49ad9139",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 0.11555555555555552}"
+                        ]
+                    },
+                    "execution_count": 3,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "evaluator.evaluate_strings(\n",
+                "    prediction=\"The job is completely done.\",\n",
+                "    reference=\"The job is done\",\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 4,
+            "id": "c06a2296",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 0.0724999999999999}"
+                        ]
+                    },
+                    "execution_count": 4,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "# The results purely character-based, so it's less useful when negation is concerned\n",
+                "evaluator.evaluate_strings(\n",
+                "    prediction=\"The job is done.\",\n",
+                "    reference=\"The job isn't done\",\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "id": "b8ed1f12-09a6-4e90-a69d-c8df525ff293",
+            "metadata": {},
+            "source": [
+                "## Configure the String Distance Metric\n",
+                "\n",
+                "By default, the `StringDistanceEvalChain` uses  levenshtein distance, but it also supports other string distance algorithms. Configure using the `distance` argument."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 5,
+            "id": "a88bc7d7-62d3-408d-b0e0-43abcecf35c8",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "[<StringDistance.DAMERAU_LEVENSHTEIN: 'damerau_levenshtein'>,\n",
+                            " <StringDistance.LEVENSHTEIN: 'levenshtein'>,\n",
+                            " <StringDistance.JARO: 'jaro'>,\n",
+                            " <StringDistance.JARO_WINKLER: 'jaro_winkler'>]"
+                        ]
+                    },
+                    "execution_count": 5,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "from langchain.evaluation import StringDistance\n",
+                "\n",
+                "list(StringDistance)"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 6,
+            "id": "0c079864-0175-4d06-9d3f-a0e51dd3977c",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "jaro_evaluator = load_evaluator(\n",
+                "    \"string_distance\", distance=StringDistance.JARO\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 7,
+            "id": "a8dfb900-14f3-4a1f-8736-dd1d86a1264c",
+            "metadata": {},
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 0.19259259259259254}"
+                        ]
+                    },
+                    "execution_count": 7,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "jaro_evaluator.evaluate_strings(\n",
+                "    prediction=\"The job is completely done.\",\n",
+                "    reference=\"The job is done\",\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 8,
+            "id": "7020b046-0ef7-40cc-8778-b928e35f3ce1",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 0.12083333333333324}"
+                        ]
+                    },
+                    "execution_count": 8,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "jaro_evaluator.evaluate_strings(\n",
+                "    prediction=\"The job is done.\",\n",
+                "    reference=\"The job isn't done\",\n",
+                ")"
+            ]
+        }
+    ],
+    "metadata": {
+        "kernelspec": {
+            "display_name": "Python 3 (ipykernel)",
+            "language": "python",
+            "name": "python3"
+        },
+        "language_info": {
+            "codemirror_mode": {
+                "name": "ipython",
+                "version": 3
+            },
+            "file_extension": ".py",
+            "mimetype": "text/x-python",
+            "name": "python",
+            "nbconvert_exporter": "python",
+            "pygments_lexer": "ipython3",
+            "version": "3.11.2"
+        }
+    },
+    "nbformat": 4,
+    "nbformat_minor": 5
+}

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

@@ -1,141 +1,142 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "db9d627f-b234-4f7f-ab96-639fae474122",
-   "metadata": {},
-   "source": [
-    "# Custom Trajectory Evaluator\n",
-    "\n",
-    "You can make your own custom trajectory evaluators by inheriting from the [AgentTrajectoryEvaluator](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.schema.AgentTrajectoryEvaluator.html#langchain.evaluation.schema.AgentTrajectoryEvaluator) class and overwriting the `_evaluate_agent_trajectory` (and `_aevaluate_agent_action`) method.\n",
-    "\n",
-    "\n",
-    "In this example, you will make a simple trajectory evaluator that uses an LLM to determine if any actions were unnecessary."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "ca84ab0c-e7e2-4c03-bd74-9cc4e6338eec",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from typing import Any, Optional, Sequence, Tuple\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.chains import LLMChain\n",
-    "from langchain.schema import AgentAction\n",
-    "from langchain.evaluation import AgentTrajectoryEvaluator\n",
-    "\n",
-    "\n",
-    "class StepNecessityEvaluator(AgentTrajectoryEvaluator):\n",
-    "    \"\"\"Evaluate the perplexity of a predicted string.\"\"\"\n",
-    "\n",
-    "    def __init__(self) -> None:\n",
-    "        llm = ChatOpenAI(model=\"gpt-4\", temperature=0.0)\n",
-    "        template = \"\"\"Are any of the following steps unnecessary in answering {input}? Provide the verdict on a new line as a single \"Y\" for yes or \"N\" for no.\n",
-    "\n",
-    "        DATA\n",
-    "        ------\n",
-    "        Steps: {trajectory}\n",
-    "        ------\n",
-    "\n",
-    "        Verdict:\"\"\"\n",
-    "        self.chain = LLMChain.from_string(llm, template)\n",
-    "\n",
-    "    def _evaluate_agent_trajectory(\n",
-    "        self,\n",
-    "        *,\n",
-    "        prediction: str,\n",
-    "        input: str,\n",
-    "        agent_trajectory: Sequence[Tuple[AgentAction, str]],\n",
-    "        reference: Optional[str] = None,\n",
-    "        **kwargs: Any,\n",
-    "    ) -> dict:\n",
-    "        vals = [\n",
-    "            f\"{i}: Action=[{action.tool}] returned observation = [{observation}]\"\n",
-    "            for i, (action, observation) in enumerate(agent_trajectory)\n",
-    "        ]\n",
-    "        trajectory = \"\\n\".join(vals)\n",
-    "        response = self.chain.run(dict(trajectory=trajectory, input=input), **kwargs)\n",
-    "        decision = response.split(\"\\n\")[-1].strip()\n",
-    "        score = 1 if decision == \"Y\" else 0\n",
-    "        return {\"score\": score, \"value\": decision, \"reasoning\": response}"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "297dea4b-fb28-4292-b6e0-1c769cfb9cbd",
-   "metadata": {},
-   "source": [
-    "The example above will return a score of 1 if the language model predicts that any of the actions were unnecessary, and it returns a score of 0 if all of them were predicted to be necessary. It returns the string 'decision' as the 'value', and includes the rest of the generated text as 'reasoning' to let you audit the decision.\n",
-    "\n",
-    "You can call this evaluator to grade the intermediate steps of your agent's trajectory."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "a3fbcc1d-249f-4e00-8841-b6872c73c486",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'score': 1, 'value': 'Y', 'reasoning': 'Y'}"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "evaluator = StepNecessityEvaluator()\n",
-    "\n",
-    "evaluator.evaluate_agent_trajectory(\n",
-    "    prediction=\"The answer is pi\",\n",
-    "    input=\"What is today?\",\n",
-    "    agent_trajectory=[\n",
-    "        (\n",
-    "            AgentAction(tool=\"ask\", tool_input=\"What is today?\", log=\"\"),\n",
-    "            \"tomorrow's yesterday\",\n",
-    "        ),\n",
-    "        (\n",
-    "            AgentAction(tool=\"check_tv\", tool_input=\"Watch tv for half hour\", log=\"\"),\n",
-    "            \"bzzz\",\n",
-    "        ),\n",
-    "    ],\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "77353528-723e-4075-939e-aebdb17c1e4f",
-   "metadata": {},
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.2"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}
+    "cells": [
+        {
+            "cell_type": "markdown",
+            "id": "db9d627f-b234-4f7f-ab96-639fae474122",
+            "metadata": {},
+            "source": [
+                "# Custom Trajectory Evaluator\n",
+                "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/guides/evaluation/trajectory/custom.ipynb)\n",
+                "\n",
+                "You can make your own custom trajectory evaluators by inheriting from the [AgentTrajectoryEvaluator](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.schema.AgentTrajectoryEvaluator.html#langchain.evaluation.schema.AgentTrajectoryEvaluator) class and overwriting the `_evaluate_agent_trajectory` (and `_aevaluate_agent_action`) method.\n",
+                "\n",
+                "\n",
+                "In this example, you will make a simple trajectory evaluator that uses an LLM to determine if any actions were unnecessary."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 1,
+            "id": "ca84ab0c-e7e2-4c03-bd74-9cc4e6338eec",
+            "metadata": {},
+            "outputs": [],
+            "source": [
+                "from typing import Any, Optional, Sequence, Tuple\n",
+                "from langchain.chat_models import ChatOpenAI\n",
+                "from langchain.chains import LLMChain\n",
+                "from langchain.schema import AgentAction\n",
+                "from langchain.evaluation import AgentTrajectoryEvaluator\n",
+                "\n",
+                "\n",
+                "class StepNecessityEvaluator(AgentTrajectoryEvaluator):\n",
+                "    \"\"\"Evaluate the perplexity of a predicted string.\"\"\"\n",
+                "\n",
+                "    def __init__(self) -> None:\n",
+                "        llm = ChatOpenAI(model=\"gpt-4\", temperature=0.0)\n",
+                "        template = \"\"\"Are any of the following steps unnecessary in answering {input}? Provide the verdict on a new line as a single \"Y\" for yes or \"N\" for no.\n",
+                "\n",
+                "        DATA\n",
+                "        ------\n",
+                "        Steps: {trajectory}\n",
+                "        ------\n",
+                "\n",
+                "        Verdict:\"\"\"\n",
+                "        self.chain = LLMChain.from_string(llm, template)\n",
+                "\n",
+                "    def _evaluate_agent_trajectory(\n",
+                "        self,\n",
+                "        *,\n",
+                "        prediction: str,\n",
+                "        input: str,\n",
+                "        agent_trajectory: Sequence[Tuple[AgentAction, str]],\n",
+                "        reference: Optional[str] = None,\n",
+                "        **kwargs: Any,\n",
+                "    ) -> dict:\n",
+                "        vals = [\n",
+                "            f\"{i}: Action=[{action.tool}] returned observation = [{observation}]\"\n",
+                "            for i, (action, observation) in enumerate(agent_trajectory)\n",
+                "        ]\n",
+                "        trajectory = \"\\n\".join(vals)\n",
+                "        response = self.chain.run(dict(trajectory=trajectory, input=input), **kwargs)\n",
+                "        decision = response.split(\"\\n\")[-1].strip()\n",
+                "        score = 1 if decision == \"Y\" else 0\n",
+                "        return {\"score\": score, \"value\": decision, \"reasoning\": response}"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "id": "297dea4b-fb28-4292-b6e0-1c769cfb9cbd",
+            "metadata": {},
+            "source": [
+                "The example above will return a score of 1 if the language model predicts that any of the actions were unnecessary, and it returns a score of 0 if all of them were predicted to be necessary. It returns the string 'decision' as the 'value', and includes the rest of the generated text as 'reasoning' to let you audit the decision.\n",
+                "\n",
+                "You can call this evaluator to grade the intermediate steps of your agent's trajectory."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 3,
+            "id": "a3fbcc1d-249f-4e00-8841-b6872c73c486",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 1, 'value': 'Y', 'reasoning': 'Y'}"
+                        ]
+                    },
+                    "execution_count": 3,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "evaluator = StepNecessityEvaluator()\n",
+                "\n",
+                "evaluator.evaluate_agent_trajectory(\n",
+                "    prediction=\"The answer is pi\",\n",
+                "    input=\"What is today?\",\n",
+                "    agent_trajectory=[\n",
+                "        (\n",
+                "            AgentAction(tool=\"ask\", tool_input=\"What is today?\", log=\"\"),\n",
+                "            \"tomorrow's yesterday\",\n",
+                "        ),\n",
+                "        (\n",
+                "            AgentAction(tool=\"check_tv\", tool_input=\"Watch tv for half hour\", log=\"\"),\n",
+                "            \"bzzz\",\n",
+                "        ),\n",
+                "    ],\n",
+                ")"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "id": "77353528-723e-4075-939e-aebdb17c1e4f",
+            "metadata": {},
+            "source": []
+        }
+    ],
+    "metadata": {
+        "kernelspec": {
+            "display_name": "Python 3 (ipykernel)",
+            "language": "python",
+            "name": "python3"
+        },
+        "language_info": {
+            "codemirror_mode": {
+                "name": "ipython",
+                "version": 3
+            },
+            "file_extension": ".py",
+            "mimetype": "text/x-python",
+            "name": "python",
+            "nbconvert_exporter": "python",
+            "pygments_lexer": "ipython3",
+            "version": "3.11.2"
+        }
+    },
+    "nbformat": 4,
+    "nbformat_minor": 5
+}

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

@@ -1,304 +1,305 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "6e5ea1a1-7e74-459b-bf14-688f87d09124",
-   "metadata": {
-    "tags": []
-   },
-   "source": [
-    "# Agent Trajectory\n",
-    "\n",
-    "Agents can be difficult to holistically evaluate due to the breadth of actions and generation they can make. We recommend using multiple evaluation techniques appropriate to your use case. One way to evaluate an agent is to look at the whole trajectory of actions taken along with their responses.\n",
-    "\n",
-    "Evaluators that do this can implement the `AgentTrajectoryEvaluator` interface. This walkthrough will show how to use the `trajectory` evaluator to grade  an OpenAI functions agent.\n",
-    "\n",
-    "For more information, check out the reference docs for the [TrajectoryEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain.html#langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain) for more info."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "149402da-5212-43e2-b7c0-a701727f5293",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.evaluation import load_evaluator\n",
-    "\n",
-    "evaluator = load_evaluator(\"trajectory\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "b1c64c1a",
-   "metadata": {},
-   "source": [
-    "## Methods\n",
-    "\n",
-    "\n",
-    "The Agent Trajectory Evaluators are used with the [evaluate_agent_trajectory](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain.html#langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain.evaluate_agent_trajectory) (and async [aevaluate_agent_trajectory](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain.html#langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain.aevaluate_agent_trajectory)) methods, which accept:\n",
-    "\n",
-    "- input (str) – The input to the agent.\n",
-    "- prediction (str) – The final predicted response.\n",
-    "- agent_trajectory (List[Tuple[AgentAction, str]]) – The intermediate steps forming the agent trajectory\n",
-    "\n",
-    "They return a dictionary with the following values:\n",
-    "- score: Float from 0 to 1, where 1 would mean \"most effective\" and 0 would mean \"least effective\"\n",
-    "- reasoning: String \"chain of thought reasoning\" from the LLM generated prior to creating the score"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e733562c-4c17-4942-9647-acfc5ebfaca2",
-   "metadata": {},
-   "source": [
-    "## Capturing Trajectory\n",
-    "\n",
-    "The easiest way to return an agent's trajectory (without using tracing callbacks like those in LangSmith) for evaluation is to initialize the agent with `return_intermediate_steps=True`.\n",
-    "\n",
-    "Below, create an example agent we will call to evaluate."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "451cb0cb-6f42-4abd-aa6d-fb871fce034d",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "import subprocess\n",
-    "\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.tools import tool\n",
-    "from langchain.agents import AgentType, initialize_agent\n",
-    "\n",
-    "from pydantic import HttpUrl\n",
-    "from urllib.parse import urlparse\n",
-    "\n",
-    "\n",
-    "@tool\n",
-    "def ping(url: HttpUrl, return_error: bool) -> str:\n",
-    "    \"\"\"Ping the fully specified url. Must include https:// in the url.\"\"\"\n",
-    "    hostname = urlparse(str(url)).netloc\n",
-    "    completed_process = subprocess.run(\n",
-    "        [\"ping\", \"-c\", \"1\", hostname], capture_output=True, text=True\n",
-    "    )\n",
-    "    output = completed_process.stdout\n",
-    "    if return_error and completed_process.returncode != 0:\n",
-    "        return completed_process.stderr\n",
-    "    return output\n",
-    "\n",
-    "\n",
-    "@tool\n",
-    "def trace_route(url: HttpUrl, return_error: bool) -> str:\n",
-    "    \"\"\"Trace the route to the specified url. Must include https:// in the url.\"\"\"\n",
-    "    hostname = urlparse(str(url)).netloc\n",
-    "    completed_process = subprocess.run(\n",
-    "        [\"traceroute\", hostname], capture_output=True, text=True\n",
-    "    )\n",
-    "    output = completed_process.stdout\n",
-    "    if return_error and completed_process.returncode != 0:\n",
-    "        return completed_process.stderr\n",
-    "    return output\n",
-    "\n",
-    "\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0613\", temperature=0)\n",
-    "agent = initialize_agent(\n",
-    "    llm=llm,\n",
-    "    tools=[ping, trace_route],\n",
-    "    agent=AgentType.OPENAI_MULTI_FUNCTIONS,\n",
-    "    return_intermediate_steps=True,  # IMPORTANT!\n",
-    ")\n",
-    "\n",
-    "result = agent(\"What's the latency like for https://langchain.com?\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2df34eed-45a5-4f91-88d3-9aa55f28391a",
-   "metadata": {
-    "tags": []
-   },
-   "source": [
-    "## Evaluate Trajectory\n",
-    "\n",
-    "Pass the input, trajectory, and pass to the [evaluate_agent_trajectory](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.schema.AgentTrajectoryEvaluator.html#langchain.evaluation.schema.AgentTrajectoryEvaluator.evaluate_agent_trajectory) method."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "8d2c8703-98ed-4068-8a8b-393f0f1f64ea",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'score': 1.0,\n",
-       " 'reasoning': \"i. The final answer is helpful. It directly answers the user's question about the latency for the website https://langchain.com.\\n\\nii. The AI language model uses a logical sequence of tools to answer the question. It uses the 'ping' tool to measure the latency of the website, which is the correct tool for this task.\\n\\niii. The AI language model uses the tool in a helpful way. It inputs the URL into the 'ping' tool and correctly interprets the output to provide the latency in milliseconds.\\n\\niv. The AI language model does not use too many steps to answer the question. It only uses one step, which is appropriate for this type of question.\\n\\nv. The appropriate tool is used to answer the question. The 'ping' tool is the correct tool to measure website latency.\\n\\nGiven these considerations, the AI language model's performance is excellent. It uses the correct tool, interprets the output correctly, and provides a helpful and direct answer to the user's question.\"}"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "evaluation_result = evaluator.evaluate_agent_trajectory(\n",
-    "    prediction=result[\"output\"],\n",
-    "    input=result[\"input\"],\n",
-    "    agent_trajectory=result[\"intermediate_steps\"],\n",
-    ")\n",
-    "evaluation_result"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "fc5467c1-ea92-405f-949a-3011388fa9ee",
-   "metadata": {},
-   "source": [
-    "## Configuring the Evaluation LLM\n",
-    "\n",
-    "If you don't select an LLM to use for evaluation, the [load_evaluator](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.loading.load_evaluator.html#langchain.evaluation.loading.load_evaluator) function will use `gpt-4` to power the evaluation chain. You can select any chat model for the agent trajectory evaluator as below."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "1f6318f3-642a-4766-bc7a-f91239795ee7",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "# %pip install anthropic\n",
-    "# ANTHROPIC_API_KEY=<YOUR ANTHROPIC API KEY>"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "b2852289-5df9-402e-95b5-7efebf0fc943",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.chat_models import ChatAnthropic\n",
-    "\n",
-    "eval_llm = ChatAnthropic(temperature=0)\n",
-    "evaluator = load_evaluator(\"trajectory\", llm=eval_llm)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "ff72d21a-93b9-4c2f-8613-733d9c9330d7",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'score': 1.0,\n",
-       " 'reasoning': \"Here is my detailed evaluation of the AI's response:\\n\\ni. The final answer is helpful, as it directly provides the latency measurement for the requested website.\\n\\nii. The sequence of using the ping tool to measure latency is logical for this question.\\n\\niii. The ping tool is used in a helpful way, with the website URL provided as input and the output latency measurement extracted.\\n\\niv. Only one step is used, which is appropriate for simply measuring latency. More steps are not needed.\\n\\nv. The ping tool is an appropriate choice to measure latency. \\n\\nIn summary, the AI uses an optimal single step approach with the right tool and extracts the needed output. The final answer directly answers the question in a helpful way.\\n\\nOverall\"}"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "evaluation_result = evaluator.evaluate_agent_trajectory(\n",
-    "    prediction=result[\"output\"],\n",
-    "    input=result[\"input\"],\n",
-    "    agent_trajectory=result[\"intermediate_steps\"],\n",
-    ")\n",
-    "evaluation_result"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "95ce4240-f5a0-4810-8d09-b2f4c9e18b7f",
-   "metadata": {},
-   "source": [
-    "## Providing List of Valid Tools\n",
-    "\n",
-    "By default, the evaluator doesn't take into account the tools the agent is permitted to call. You can provide these to the evaluator via the `agent_tools` argument.\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "24c10566-2ef5-45c5-9213-a8fb28e2ca1f",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.evaluation import load_evaluator\n",
-    "\n",
-    "evaluator = load_evaluator(\"trajectory\", agent_tools=[ping, trace_route])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "7b995786-5b78-4d9e-8e8a-1f2a203113e2",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'score': 1.0,\n",
-       " 'reasoning': \"i. The final answer is helpful. It directly answers the user's question about the latency for the specified website.\\n\\nii. The AI language model uses a logical sequence of tools to answer the question. In this case, only one tool was needed to answer the question, and the model chose the correct one.\\n\\niii. The AI language model uses the tool in a helpful way. The 'ping' tool was used to determine the latency of the website, which was the information the user was seeking.\\n\\niv. The AI language model does not use too many steps to answer the question. Only one step was needed and used.\\n\\nv. The appropriate tool was used to answer the question. The 'ping' tool is designed to measure latency, which was the information the user was seeking.\\n\\nGiven these considerations, the AI language model's performance in answering this question is excellent.\"}"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "evaluation_result = evaluator.evaluate_agent_trajectory(\n",
-    "    prediction=result[\"output\"],\n",
-    "    input=result[\"input\"],\n",
-    "    agent_trajectory=result[\"intermediate_steps\"],\n",
-    ")\n",
-    "evaluation_result"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.2"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}
+    "cells": [
+        {
+            "cell_type": "markdown",
+            "id": "6e5ea1a1-7e74-459b-bf14-688f87d09124",
+            "metadata": {
+                "tags": []
+            },
+            "source": [
+                "# Agent Trajectory\n",
+                "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/guides/evaluation/trajectory/trajectory_eval.ipynb)\n",
+                "\n",
+                "Agents can be difficult to holistically evaluate due to the breadth of actions and generation they can make. We recommend using multiple evaluation techniques appropriate to your use case. One way to evaluate an agent is to look at the whole trajectory of actions taken along with their responses.\n",
+                "\n",
+                "Evaluators that do this can implement the `AgentTrajectoryEvaluator` interface. This walkthrough will show how to use the `trajectory` evaluator to grade  an OpenAI functions agent.\n",
+                "\n",
+                "For more information, check out the reference docs for the [TrajectoryEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain.html#langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain) for more info."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 1,
+            "id": "149402da-5212-43e2-b7c0-a701727f5293",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "from langchain.evaluation import load_evaluator\n",
+                "\n",
+                "evaluator = load_evaluator(\"trajectory\")"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "id": "b1c64c1a",
+            "metadata": {},
+            "source": [
+                "## Methods\n",
+                "\n",
+                "\n",
+                "The Agent Trajectory Evaluators are used with the [evaluate_agent_trajectory](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain.html#langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain.evaluate_agent_trajectory) (and async [aevaluate_agent_trajectory](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain.html#langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain.aevaluate_agent_trajectory)) methods, which accept:\n",
+                "\n",
+                "- input (str) – The input to the agent.\n",
+                "- prediction (str) – The final predicted response.\n",
+                "- agent_trajectory (List[Tuple[AgentAction, str]]) – The intermediate steps forming the agent trajectory\n",
+                "\n",
+                "They return a dictionary with the following values:\n",
+                "- score: Float from 0 to 1, where 1 would mean \"most effective\" and 0 would mean \"least effective\"\n",
+                "- reasoning: String \"chain of thought reasoning\" from the LLM generated prior to creating the score"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "id": "e733562c-4c17-4942-9647-acfc5ebfaca2",
+            "metadata": {},
+            "source": [
+                "## Capturing Trajectory\n",
+                "\n",
+                "The easiest way to return an agent's trajectory (without using tracing callbacks like those in LangSmith) for evaluation is to initialize the agent with `return_intermediate_steps=True`.\n",
+                "\n",
+                "Below, create an example agent we will call to evaluate."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 2,
+            "id": "451cb0cb-6f42-4abd-aa6d-fb871fce034d",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "import os\n",
+                "import subprocess\n",
+                "\n",
+                "from langchain.chat_models import ChatOpenAI\n",
+                "from langchain.tools import tool\n",
+                "from langchain.agents import AgentType, initialize_agent\n",
+                "\n",
+                "from pydantic import HttpUrl\n",
+                "from urllib.parse import urlparse\n",
+                "\n",
+                "\n",
+                "@tool\n",
+                "def ping(url: HttpUrl, return_error: bool) -> str:\n",
+                "    \"\"\"Ping the fully specified url. Must include https:// in the url.\"\"\"\n",
+                "    hostname = urlparse(str(url)).netloc\n",
+                "    completed_process = subprocess.run(\n",
+                "        [\"ping\", \"-c\", \"1\", hostname], capture_output=True, text=True\n",
+                "    )\n",
+                "    output = completed_process.stdout\n",
+                "    if return_error and completed_process.returncode != 0:\n",
+                "        return completed_process.stderr\n",
+                "    return output\n",
+                "\n",
+                "\n",
+                "@tool\n",
+                "def trace_route(url: HttpUrl, return_error: bool) -> str:\n",
+                "    \"\"\"Trace the route to the specified url. Must include https:// in the url.\"\"\"\n",
+                "    hostname = urlparse(str(url)).netloc\n",
+                "    completed_process = subprocess.run(\n",
+                "        [\"traceroute\", hostname], capture_output=True, text=True\n",
+                "    )\n",
+                "    output = completed_process.stdout\n",
+                "    if return_error and completed_process.returncode != 0:\n",
+                "        return completed_process.stderr\n",
+                "    return output\n",
+                "\n",
+                "\n",
+                "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0613\", temperature=0)\n",
+                "agent = initialize_agent(\n",
+                "    llm=llm,\n",
+                "    tools=[ping, trace_route],\n",
+                "    agent=AgentType.OPENAI_MULTI_FUNCTIONS,\n",
+                "    return_intermediate_steps=True,  # IMPORTANT!\n",
+                ")\n",
+                "\n",
+                "result = agent(\"What's the latency like for https://langchain.com?\")"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "id": "2df34eed-45a5-4f91-88d3-9aa55f28391a",
+            "metadata": {
+                "tags": []
+            },
+            "source": [
+                "## Evaluate Trajectory\n",
+                "\n",
+                "Pass the input, trajectory, and pass to the [evaluate_agent_trajectory](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.schema.AgentTrajectoryEvaluator.html#langchain.evaluation.schema.AgentTrajectoryEvaluator.evaluate_agent_trajectory) method."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 3,
+            "id": "8d2c8703-98ed-4068-8a8b-393f0f1f64ea",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 1.0,\n",
+                            " 'reasoning': \"i. The final answer is helpful. It directly answers the user's question about the latency for the website https://langchain.com.\\n\\nii. The AI language model uses a logical sequence of tools to answer the question. It uses the 'ping' tool to measure the latency of the website, which is the correct tool for this task.\\n\\niii. The AI language model uses the tool in a helpful way. It inputs the URL into the 'ping' tool and correctly interprets the output to provide the latency in milliseconds.\\n\\niv. The AI language model does not use too many steps to answer the question. It only uses one step, which is appropriate for this type of question.\\n\\nv. The appropriate tool is used to answer the question. The 'ping' tool is the correct tool to measure website latency.\\n\\nGiven these considerations, the AI language model's performance is excellent. It uses the correct tool, interprets the output correctly, and provides a helpful and direct answer to the user's question.\"}"
+                        ]
+                    },
+                    "execution_count": 3,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "evaluation_result = evaluator.evaluate_agent_trajectory(\n",
+                "    prediction=result[\"output\"],\n",
+                "    input=result[\"input\"],\n",
+                "    agent_trajectory=result[\"intermediate_steps\"],\n",
+                ")\n",
+                "evaluation_result"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "id": "fc5467c1-ea92-405f-949a-3011388fa9ee",
+            "metadata": {},
+            "source": [
+                "## Configuring the Evaluation LLM\n",
+                "\n",
+                "If you don't select an LLM to use for evaluation, the [load_evaluator](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.loading.load_evaluator.html#langchain.evaluation.loading.load_evaluator) function will use `gpt-4` to power the evaluation chain. You can select any chat model for the agent trajectory evaluator as below."
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 4,
+            "id": "1f6318f3-642a-4766-bc7a-f91239795ee7",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "# %pip install anthropic\n",
+                "# ANTHROPIC_API_KEY=<YOUR ANTHROPIC API KEY>"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 5,
+            "id": "b2852289-5df9-402e-95b5-7efebf0fc943",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "from langchain.chat_models import ChatAnthropic\n",
+                "\n",
+                "eval_llm = ChatAnthropic(temperature=0)\n",
+                "evaluator = load_evaluator(\"trajectory\", llm=eval_llm)"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 6,
+            "id": "ff72d21a-93b9-4c2f-8613-733d9c9330d7",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 1.0,\n",
+                            " 'reasoning': \"Here is my detailed evaluation of the AI's response:\\n\\ni. The final answer is helpful, as it directly provides the latency measurement for the requested website.\\n\\nii. The sequence of using the ping tool to measure latency is logical for this question.\\n\\niii. The ping tool is used in a helpful way, with the website URL provided as input and the output latency measurement extracted.\\n\\niv. Only one step is used, which is appropriate for simply measuring latency. More steps are not needed.\\n\\nv. The ping tool is an appropriate choice to measure latency. \\n\\nIn summary, the AI uses an optimal single step approach with the right tool and extracts the needed output. The final answer directly answers the question in a helpful way.\\n\\nOverall\"}"
+                        ]
+                    },
+                    "execution_count": 6,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "evaluation_result = evaluator.evaluate_agent_trajectory(\n",
+                "    prediction=result[\"output\"],\n",
+                "    input=result[\"input\"],\n",
+                "    agent_trajectory=result[\"intermediate_steps\"],\n",
+                ")\n",
+                "evaluation_result"
+            ]
+        },
+        {
+            "cell_type": "markdown",
+            "id": "95ce4240-f5a0-4810-8d09-b2f4c9e18b7f",
+            "metadata": {},
+            "source": [
+                "## Providing List of Valid Tools\n",
+                "\n",
+                "By default, the evaluator doesn't take into account the tools the agent is permitted to call. You can provide these to the evaluator via the `agent_tools` argument.\n"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 7,
+            "id": "24c10566-2ef5-45c5-9213-a8fb28e2ca1f",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [],
+            "source": [
+                "from langchain.evaluation import load_evaluator\n",
+                "\n",
+                "evaluator = load_evaluator(\"trajectory\", agent_tools=[ping, trace_route])"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 8,
+            "id": "7b995786-5b78-4d9e-8e8a-1f2a203113e2",
+            "metadata": {
+                "tags": []
+            },
+            "outputs": [
+                {
+                    "data": {
+                        "text/plain": [
+                            "{'score': 1.0,\n",
+                            " 'reasoning': \"i. The final answer is helpful. It directly answers the user's question about the latency for the specified website.\\n\\nii. The AI language model uses a logical sequence of tools to answer the question. In this case, only one tool was needed to answer the question, and the model chose the correct one.\\n\\niii. The AI language model uses the tool in a helpful way. The 'ping' tool was used to determine the latency of the website, which was the information the user was seeking.\\n\\niv. The AI language model does not use too many steps to answer the question. Only one step was needed and used.\\n\\nv. The appropriate tool was used to answer the question. The 'ping' tool is designed to measure latency, which was the information the user was seeking.\\n\\nGiven these considerations, the AI language model's performance in answering this question is excellent.\"}"
+                        ]
+                    },
+                    "execution_count": 8,
+                    "metadata": {},
+                    "output_type": "execute_result"
+                }
+            ],
+            "source": [
+                "evaluation_result = evaluator.evaluate_agent_trajectory(\n",
+                "    prediction=result[\"output\"],\n",
+                "    input=result[\"input\"],\n",
+                "    agent_trajectory=result[\"intermediate_steps\"],\n",
+                ")\n",
+                "evaluation_result"
+            ]
+        }
+    ],
+    "metadata": {
+        "kernelspec": {
+            "display_name": "Python 3 (ipykernel)",
+            "language": "python",
+            "name": "python3"
+        },
+        "language_info": {
+            "codemirror_mode": {
+                "name": "ipython",
+                "version": 3
+            },
+            "file_extension": ".py",
+            "mimetype": "text/x-python",
+            "name": "python",
+            "nbconvert_exporter": "python",
+            "pygments_lexer": "ipython3",
+            "version": "3.11.2"
+        }
+    },
+    "nbformat": 4,
+    "nbformat_minor": 5
+}

docs/extras/guides/fallbacks.ipynb

@@ -7,9 +7,11 @@
    "source": [
     "# Fallbacks\n",
     "\n",
-    "When working with language models, you may often encounter issues from the underlying APIs, whether these be rate limiting or downtime. Therefore, as you go to move your LLM applications into production it becomes more and more important to safe guard against these. That's why we've introduced the concept of fallbacks.\n",
+    "When working with language models, you may often encounter issues from the underlying APIs, whether these be rate limiting or downtime. Therefore, as you go to move your LLM applications into production it becomes more and more important to safeguard against these. That's why we've introduced the concept of fallbacks. \n",
     "\n",
-    "Crucially, fallbacks can be applied not only on the LLM level but on the whole runnable level. This is important because often times different models require different prompts. So if your call to OpenAI fails, you don't just want to send the same prompt to Anthropic - you probably want want to use a different prompt template and send a different version there."
+    "A **fallback** is an alternative plan that may be used in an emergency.\n",
+    "\n",
+    "Crucially, fallbacks can be applied not only on the LLM level but on the whole runnable level. This is important because often times different models require different prompts. So if your call to OpenAI fails, you don't just want to send the same prompt to Anthropic - you probably want to use a different prompt template and send a different version there."
    ]
   },
   {
@@ -17,7 +19,7 @@
    "id": "a6bb9ba9",
    "metadata": {},
    "source": [
-    "## Handling LLM API Errors\n",
+    "## Fallback for LLM API Errors\n",
     "\n",
     "This is maybe the most common use case for fallbacks. A request to an LLM API can fail for a variety of reasons - the API could be down, you could have hit rate limits, any number of things. Therefore, using fallbacks can help protect against these types of things.\n",
     "\n",
@@ -156,7 +158,7 @@
    "id": "8d62241b",
    "metadata": {},
    "source": [
-    "## Fallbacks for Sequences\n",
+    "## Fallback for Sequences\n",
     "\n",
     "We can also create fallbacks for sequences, that are sequences themselves. Here we do that with two different models: ChatOpenAI and then normal OpenAI (which does not use a chat model). Because OpenAI is NOT a chat model, you likely want a different prompt."
    ]
@@ -230,9 +232,9 @@
    "id": "ec4685b4",
    "metadata": {},
    "source": [
-    "## Handling Long Inputs\n",
+    "## Fallback for Long Inputs\n",
     "\n",
-    "One of the big limiting factors of LLMs in their context window. Usually you can count and track the length of prompts before sending them to an LLM, but in situations where that is hard/complicated you can fallback to a model with longer context length."
+    "One of the big limiting factors of LLMs is their context window. Usually, you can count and track the length of prompts before sending them to an LLM, but in situations where that is hard/complicated, you can fallback to a model with a longer context length."
    ]
   },
   {
@@ -422,7 +424,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/extras/integrations/callbacks/llmonitor.md

@@ -37,10 +37,10 @@ llm = OpenAI(
     callbacks=[handler],
 )
 
-chat = ChatOpenAI(
-    callbacks=[handler],
-    metadata={"userId": "123"},  # you can assign user ids to models in the metadata
-)
+chat = ChatOpenAI(callbacks=[handler])
+
+llm("Tell me a joke")
+
 ```
 
 ## Usage with chains and agents
@@ -100,6 +100,18 @@ agent.run(
 )
 ```
 
+## User Tracking
+User tracking allows you to identify your users, track their cost, conversations and more.
+
+```python
+from langchain.callbacks.llmonitor_callback import LLMonitorCallbackHandler, identify
+
+with identify("user-123"):
+    llm("Tell me a joke")
+
+with identify("user-456", user_props={"email": "user456@test.com"}):
+    agen.run("Who is Leo DiCaprio's girlfriend?")
+```
 ## Support
 
 For any question or issue with integration you can reach out to the LLMonitor team on [Discord](http://discord.com/invite/8PafSG58kK) or via [email](mailto:vince@llmonitor.com).

docs/extras/integrations/callbacks/trubrics.ipynb

@@ -0,0 +1,370 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "40dab0fa-e56c-4958-959e-bd6d6f829724",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "# Trubrics\n",
+    "\n",
+    "![Trubrics](https://miro.medium.com/v2/resize:fit:720/format:webp/1*AhYbKO-v8F4u3hx2aDIqKg.png)\n",
+    "\n",
+    "[Trubrics](https://trubrics.com) is an LLM user analytics platform that lets you collect, analyse and manage user\n",
+    "prompts & feedback on AI models. In this guide we will go over how to setup the `TrubricsCallbackHandler`. \n",
+    "\n",
+    "Check out [our repo](https://github.com/trubrics/trubrics-sdk) for more information on Trubrics."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c0d060d5-133b-496e-b76e-43284d5545b8",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "## Installation and Setup"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ce799e10-5433-4b29-8fa1-c1352f761918",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install trubrics"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "44666917-85f2-4695-897d-54504e343604",
+   "metadata": {},
+   "source": [
+    "### Getting Trubrics Credentials\n",
+    "\n",
+    "If you do not have a Trubrics account, create one on [here](https://trubrics.streamlit.app/). In this tutorial, we will use the `default` project that is built upon account creation.\n",
+    "\n",
+    "Now set your credentials as environment variables:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cd696d03-bea8-42bd-914b-2290fcafb5c9",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"TRUBRICS_EMAIL\"] = \"***@***\"\n",
+    "os.environ[\"TRUBRICS_PASSWORD\"] = \"***\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cd7177b0-a9e8-45ae-adb0-ea779376511b",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "### Usage"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6ec1bcd4-3824-43de-84a4-3102a2f6d26d",
+   "metadata": {},
+   "source": [
+    "The `TrubricsCallbackHandler` can receive various optional arguments. See [here](https://trubrics.github.io/trubrics-sdk/platform/user_prompts/#saving-prompts-to-trubrics) for kwargs that can be passed to Trubrics prompts.\n",
+    "\n",
+    "```python\n",
+    "class TrubricsCallbackHandler(BaseCallbackHandler):\n",
+    "\n",
+    "    \"\"\"\n",
+    "    Callback handler for Trubrics.\n",
+    "    \n",
+    "    Args:\n",
+    "        project: a trubrics project, default project is \"default\"\n",
+    "        email: a trubrics account email, can equally be set in env variables\n",
+    "        password: a trubrics account password, can equally be set in env variables\n",
+    "        **kwargs: all other kwargs are parsed and set to trubrics prompt variables, or added to the `metadata` dict\n",
+    "    \"\"\"\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "44d60d9f-b2bd-4ed4-b624-54cce8313815",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "## Examples"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d38e80f0-7254-4180-82ec-ebd5ee232906",
+   "metadata": {
+    "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:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9d394b7f-45eb-44ec-b721-17d2402de805",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "os.environ[\"OPENAI_API_KEY\"] = \"sk-***\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "33be2663-1518-4064-a6a9-4f1ae24ba9d1",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "### 1. With an LLM"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "6933f7b7-262b-4acf-8c7c-785d1f32b49f",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.llms import OpenAI\n",
+    "from langchain.callbacks import TrubricsCallbackHandler"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "eabfa598-0562-46bf-8d64-e751d4d91963",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[32m2023-09-26 11:30:02.149\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mtrubrics.platform.auth\u001b[0m:\u001b[36mget_trubrics_auth_token\u001b[0m:\u001b[36m61\u001b[0m - \u001b[1mUser jeff.kayne@trubrics.com has been authenticated.\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "llm = OpenAI(callbacks=[TrubricsCallbackHandler()])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "a65f9f5d-5ec5-4b1b-a1d8-9520cbadab39",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[32m2023-09-26 11:30:07.760\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mtrubrics.platform\u001b[0m:\u001b[36mlog_prompt\u001b[0m:\u001b[36m102\u001b[0m - \u001b[1mUser prompt saved to Trubrics.\u001b[0m\n",
+      "\u001b[32m2023-09-26 11:30:08.042\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mtrubrics.platform\u001b[0m:\u001b[36mlog_prompt\u001b[0m:\u001b[36m102\u001b[0m - \u001b[1mUser prompt saved to Trubrics.\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "res = llm.generate([\"Tell me a joke\", \"Write me a poem\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "68b60b98-01da-47be-b513-b71e68f97940",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "--> GPT's joke:  \n",
+      "\n",
+      "Q: What did the fish say when it hit the wall?\n",
+      "A: Dam!\n",
+      "\n",
+      "--> GPT's poem:  \n",
+      "\n",
+      "A Poem of Reflection\n",
+      "\n",
+      "I stand here in the night,\n",
+      "The stars above me filling my sight.\n",
+      "I feel such a deep connection,\n",
+      "To the world and all its perfection.\n",
+      "\n",
+      "A moment of clarity,\n",
+      "The calmness in the air so serene.\n",
+      "My mind is filled with peace,\n",
+      "And I am released.\n",
+      "\n",
+      "The past and the present,\n",
+      "My thoughts create a pleasant sentiment.\n",
+      "My heart is full of joy,\n",
+      "My soul soars like a toy.\n",
+      "\n",
+      "I reflect on my life,\n",
+      "And the choices I have made.\n",
+      "My struggles and my strife,\n",
+      "The lessons I have paid.\n",
+      "\n",
+      "The future is a mystery,\n",
+      "But I am ready to take the leap.\n",
+      "I am ready to take the lead,\n",
+      "And to create my own destiny.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"--> GPT's joke: \", res.generations[0][0].text)\n",
+    "print()\n",
+    "print(\"--> GPT's poem: \", res.generations[1][0].text)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8c767458-c9b8-4d4d-a48c-996e9be00257",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "### 2. With a chat model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "8a61cb5e-bed9-4618-b547-fc21b6e319c4",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.prompts import PromptTemplate\n",
+    "from langchain.schema import HumanMessage, SystemMessage\n",
+    "from langchain.callbacks import TrubricsCallbackHandler"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "a1ff1efb-305b-4e82-aea2-264b78350f14",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chat_llm = ChatOpenAI(\n",
+    "    callbacks=[\n",
+    "        TrubricsCallbackHandler(\n",
+    "            project=\"default\",\n",
+    "            tags=[\"chat model\"],\n",
+    "            user_id=\"user-id-1234\",\n",
+    "            some_metadata={\"hello\": [1, 2]}\n",
+    "        )\n",
+    "    ]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "c83d3956-99ab-4b6f-8515-0def83a1698c",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[32m2023-09-26 11:30:10.550\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mtrubrics.platform\u001b[0m:\u001b[36mlog_prompt\u001b[0m:\u001b[36m102\u001b[0m - \u001b[1mUser prompt saved to Trubrics.\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "chat_res = chat_llm(\n",
+    "    [\n",
+    "        SystemMessage(content=\"Every answer of yours must be about OpenAI.\"),\n",
+    "        HumanMessage(content=\"Tell me a joke\"),\n",
+    "    ]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "40b10314-1727-4dcd-993e-37a52e2349c6",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Why did the OpenAI computer go to the party?\n",
+      "\n",
+      "Because it wanted to meet its AI friends and have a byte of fun!\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(chat_res.content)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f66f438d-12e0-4bdd-b004-601495f84c73",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "langchain",
+   "language": "python",
+   "name": "langchain"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/extras/integrations/chat/fireworks.ipynb

@@ -6,7 +6,7 @@
    "id": "642fd21c-600a-47a1-be96-6e1438b421a9",
    "metadata": {},
    "source": [
-    "# ChatFireworks\n",
+    "# Fireworks\n",
     "\n",
     ">[Fireworks](https://app.fireworks.ai/) accelerates product development on generative AI by creating an innovative AI experiment and production platform. \n",
     "\n",
@@ -36,9 +36,10 @@
    "metadata": {},
    "source": [
     "# Setup\n",
-    "Contact Fireworks AI for the an API Key to access our models\n",
     "\n",
-    "Set up your model using a model id. If the model is not set, the default model is fireworks-llama-v2-7b-chat."
+    "1. Make sure the `fireworks-ai` package is installed in your environment.\n",
+    "2. Sign in to [Fireworks AI](http://fireworks.ai) for the an API Key to access our models, and make sure it is set as the `FIREWORKS_API_KEY` environment variable.\n",
+    "3. Set up your model using a model id. If the model is not set, the default model is fireworks-llama-v2-7b-chat. See the full, most up-to-date model list on [app.fireworks.ai](https://app.fireworks.ai)."
    ]
   },
   {
@@ -48,8 +49,13 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Initialize a Fireworks Chat model\n",
-    "os.environ['FIREWORKS_API_KEY'] = \"<your_api_key>\"  # Change this to your own API key\n",
+    "import os\n",
+    "import getpass\n",
+    "\n",
+    "if \"FIREWORKS_API_KEY\" not in os.environ:\n",
+    "    os.environ[\"FIREWORKS_API_KEY\"] = getpass.getpass(\"Fireworks API Key:\")\n",
+    "\n",
+    "# Initialize a Fireworks chat model\n",
     "chat = ChatFireworks(model=\"accounts/fireworks/models/llama-v2-13b-chat\")"
    ]
   },
@@ -58,71 +64,46 @@
    "id": "d8f13144-37cf-47a5-b5a0-e3cdf76d9a72",
    "metadata": {},
    "source": [
-    "# Calling the Model\n",
+    "# Calling the Model Directly\n",
     "\n",
-    "You can use the LLMs to call the model for specified message(s). \n",
-    "\n",
-    "See the full, most up-to-date model list on [app.fireworks.ai](https://app.fireworks.ai)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "72340871-ae2f-415f-b399-0777d32dc379",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# ChatFireworks Wrapper\n",
-    "system_message = SystemMessage(content=\"You are to chat with the user.\")\n",
-    "human_message = HumanMessage(content=\"Who are you?\")\n",
-    "response = chat([system_message, human_message])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "2d6ef879-69e3-422b-8379-bb980b70fe55",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"Hello! My name is LLaMA, I'm a large language model trained by a team of researcher at Meta AI. My primary function is to assist users with tasks and answer questions to the best of my ability. I am capable of understanding and responding to natural language input, and I am here to help you with any questions or tasks you may have. Is there anything specific you would like to know or discuss?\", additional_kwargs={}, example=False)"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "response"
+    "You can call the model directly with a system and human message to get answers."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 5,
-   "id": "68c6b1fa-2ff7-4a63-8d88-3cec302180b8",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Setting additional parameters: temperature, max_tokens, top_p\n",
-    "chat = ChatFireworks(model=\"accounts/fireworks/models/llama-v2-13b-chat\", model_kwargs={\"temperature\":1, \"max_tokens\": 20, \"top_p\": 1})\n",
-    "system_message = SystemMessage(content=\"You are to chat with the user.\")\n",
-    "human_message = HumanMessage(content=\"How's the weather today?\")\n",
-    "response = chat([system_message, human_message])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "a09025f8-e4c3-4005-a8fc-c9c774b03a64",
+   "id": "72340871-ae2f-415f-b399-0777d32dc379",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"Oh, you know, it's just another beautiful day in the virtual world! The sun\", additional_kwargs={}, example=False)"
+       "AIMessage(content=\"Hello! My name is LLaMA, I'm a large language model trained by a team of researcher at Meta AI. My primary function is to assist and converse with users like you, answering questions and engaging in discussion to the best of my ability. I'm here to help and provide information on a wide range of topics, so feel free to ask me anything!\", additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# ChatFireworks Wrapper\n",
+    "system_message = SystemMessage(content=\"You are to chat with the user.\")\n",
+    "human_message = HumanMessage(content=\"Who are you?\")\n",
+    "\n",
+    "chat([system_message, human_message])\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "68c6b1fa-2ff7-4a63-8d88-3cec302180b8",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"Oh hello there! *giggle* It's such a beautiful day today, isn\", additional_kwargs={}, example=False)"
       ]
      },
      "execution_count": 6,
@@ -131,7 +112,11 @@
     }
    ],
    "source": [
-    "response"
+    "# Setting additional parameters: temperature, max_tokens, top_p\n",
+    "chat = ChatFireworks(model=\"accounts/fireworks/models/llama-v2-13b-chat\", model_kwargs={\"temperature\":1, \"max_tokens\": 20, \"top_p\": 1})\n",
+    "system_message = SystemMessage(content=\"You are to chat with the user.\")\n",
+    "human_message = HumanMessage(content=\"How's the weather today?\")\n",
+    "chat([system_message, human_message])"
    ]
   },
   {
@@ -139,7 +124,15 @@
    "id": "d93aa186-39cf-4e1a-aa32-01ed31d43bc8",
    "metadata": {},
    "source": [
-    "# ChatFireworks Wrapper with generate"
+    "# Simple Chat Chain"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "28763fbc",
+   "metadata": {},
+   "source": [
+    "You can use chat models on fireworks, with system prompts and memory."
    ]
   },
   {
@@ -149,21 +142,37 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "chat = ChatFireworks()\n",
-    "message = HumanMessage(content=\"Hello\")\n",
-    "response = chat.generate([[message], [message]])"
+    "from langchain.chat_models import ChatFireworks\n",
+    "from langchain.memory import ConversationBufferMemory\n",
+    "from langchain.schema.runnable import RunnableMap\n",
+    "from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
+    "\n",
+    "llm = ChatFireworks(model=\"accounts/fireworks/models/llama-v2-13b-chat\", model_kwargs={\"temperature\":0, \"max_tokens\":64, \"top_p\":1.0})\n",
+    "prompt = ChatPromptTemplate.from_messages([\n",
+    "    (\"system\", \"You are a helpful chatbot that speaks like a pirate.\"),\n",
+    "    MessagesPlaceholder(variable_name=\"history\"),\n",
+    "    (\"human\", \"{input}\")\n",
+    "])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "02991e05-a38e-47d4-9ab3-7e630a8ead55",
+   "metadata": {},
+   "source": [
+    "Initially, there is no chat memory"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 8,
-   "id": "35109f36-9519-47a6-a223-25639123e836",
+   "id": "e2fd186f",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "LLMResult(generations=[[ChatGeneration(text=\"Hello! It's nice to meet you. I'm here to help answer any questions you may have, while being respectful and safe. Please feel free to ask me anything, and I will do my best to provide helpful and positive responses. Is there something specific you would like to know or discuss?\", generation_info={'finish_reason': 'stop'}, message=AIMessage(content=\"Hello! It's nice to meet you. I'm here to help answer any questions you may have, while being respectful and safe. Please feel free to ask me anything, and I will do my best to provide helpful and positive responses. Is there something specific you would like to know or discuss?\", additional_kwargs={}, example=False))], [ChatGeneration(text=\"Hello! *smiling* I'm here to help you with any questions or concerns you may have. Please feel free to ask me anything, and I will do my best to provide helpful, respectful, and honest responses. I'm programmed to avoid any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content, and to provide socially unbiased and positive responses. Is there anything specific you would like to talk about or ask?\", generation_info={'finish_reason': 'stop'}, message=AIMessage(content=\"Hello! *smiling* I'm here to help you with any questions or concerns you may have. Please feel free to ask me anything, and I will do my best to provide helpful, respectful, and honest responses. I'm programmed to avoid any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content, and to provide socially unbiased and positive responses. Is there anything specific you would like to talk about or ask?\", additional_kwargs={}, example=False))]], llm_output={'model': 'accounts/fireworks/models/llama-v2-7b-chat'}, run=[RunInfo(run_id=UUID('f137463e-e1c7-454a-8b85-b999ce20e0f2')), RunInfo(run_id=UUID('f3ef1138-92de-4e01-900b-991e34a647a7'))])"
+       "{'history': []}"
       ]
      },
      "execution_count": 8,
@@ -172,63 +181,125 @@
     }
    ],
    "source": [
-    "response"
+    "memory = ConversationBufferMemory(return_messages=True)\n",
+    "memory.load_memory_variables({})"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "92c2cabb-9eaf-4c49-b0e5-a5de5a7d920e",
+   "id": "bee461da",
    "metadata": {},
    "source": [
-    "# ChatFireworks Wrapper with stream"
+    "Create a simple chain with memory"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 9,
-   "id": "12717a29-fb7d-4a4d-860b-40435452b065",
+   "id": "86972e54",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "Hello! I'm just\n",
-      " an AI assistant,\n",
-      " here to help answer your\n",
-      " questions and provide information in\n",
-      " a responsible and respectful manner\n",
-      ". I'm not able\n",
-      " to access personal information or provide\n",
-      " any content that could be considered\n",
-      " harmful, uneth\n",
-      "ical, racist, sex\n",
-      "ist, toxic, dangerous\n",
-      ", or illegal. My purpose\n",
-      " is to assist and provide helpful\n",
-      " responses that are socially un\n",
-      "biased and positive in nature\n",
-      ". Is there something specific you\n",
-      " would like to know or discuss\n",
-      "?\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "llm = ChatFireworks()\n",
-    "\n",
-    "for token in llm.stream(\"Who are you\"):\n",
-    "    print(token.content)"
+    "chain = RunnableMap({\n",
+    "    \"input\": lambda x: x[\"input\"],\n",
+    "    \"memory\": memory.load_memory_variables\n",
+    "}) | {\n",
+    "    \"input\": lambda x: x[\"input\"],\n",
+    "    \"history\": lambda x: x[\"memory\"][\"history\"]\n",
+    "} | prompt | llm.bind(stop=[\"\\n\\n\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f48cb142",
+   "metadata": {},
+   "source": [
+    "Run the chain with a simple question, expecting an answer aligned with the system message provided."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "02991e05-a38e-47d4-9ab3-7e630a8ead55",
+   "execution_count": 10,
+   "id": "db3ad5b1",
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"Ahoy there, me hearty! Yer a fine lookin' swashbuckler, I can see that! *adjusts eye patch* What be bringin' ye to these waters? Are ye here to plunder some booty or just to enjoy the sea breeze?\", additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "inputs = {\"input\": \"hi im bob\"}\n",
+    "response = chain.invoke(inputs)\n",
+    "response"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "338f4bae",
+   "metadata": {},
+   "source": [
+    "Save the memory context, then read it back to inspect contents"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "257eec01",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'history': [HumanMessage(content='hi im bob', additional_kwargs={}, example=False),\n",
+       "  AIMessage(content=\"Ahoy there, me hearty! Yer a fine lookin' swashbuckler, I can see that! *adjusts eye patch* What be bringin' ye to these waters? Are ye here to plunder some booty or just to enjoy the sea breeze?\", additional_kwargs={}, example=False)]}"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "memory.save_context(inputs, {\"output\": response.content})\n",
+    "memory.load_memory_variables({})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "08441347",
+   "metadata": {},
+   "source": [
+    "Now as another question that requires use of the memory."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "7f5f2820",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"Arrrr, ye be askin' about yer name, eh? Well, me matey, I be knowin' ye as Bob, the scurvy dog! *winks* But if ye want me to call ye somethin' else, just let me know, and I\", additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "inputs = {\"input\": \"whats my name\"}\n",
+    "chain.invoke(inputs)"
+   ]
   }
  ],
  "metadata": {
@@ -247,7 +318,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.9.16"
   }
  },
  "nbformat": 4,

docs/extras/integrations/chat/index.mdx

@@ -22,6 +22,7 @@ AzureChatOpenAI|✅|✅|✅|✅
 BedrockChat|✅|❌|✅|❌
 ChatAnthropic|✅|✅|✅|✅
 ChatAnyscale|✅|✅|✅|✅
+ChatFireworks|✅|✅|✅|✅
 ChatGooglePalm|✅|✅|❌|❌
 ChatJavelinAIGateway|✅|✅|❌|❌
 ChatKonko|✅|❌|❌|❌

docs/extras/integrations/document_loaders/git.ipynb

@@ -40,7 +40,7 @@
     "from git import Repo\n",
     "\n",
     "repo = Repo.clone_from(\n",
-    "    \"https://github.com/hwchase17/langchain\", to_path=\"./example_data/test_repo1\"\n",
+    "    \"https://github.com/langchain-ai/langchain\", to_path=\"./example_data/test_repo1\"\n",
     ")\n",
     "branch = repo.head.reference"
    ]
@@ -123,7 +123,7 @@
    "outputs": [],
    "source": [
     "loader = GitLoader(\n",
-    "    clone_url=\"https://github.com/hwchase17/langchain\",\n",
+    "    clone_url=\"https://github.com/langchain-ai/langchain\",\n",
     "    repo_path=\"./example_data/test_repo2/\",\n",
     "    branch=\"master\",\n",
     ")"

docs/extras/integrations/document_loaders/github.ipynb

@@ -62,7 +62,7 @@
    "outputs": [],
    "source": [
     "loader = GitHubIssuesLoader(\n",
-    "    repo=\"hwchase17/langchain\",\n",
+    "    repo=\"langchain-ai/langchain\",\n",
     "    access_token=ACCESS_TOKEN,  # delete/comment out this argument if you've set the access token as an env var.\n",
     "    creator=\"UmerHA\",\n",
     ")"
@@ -117,7 +117,7 @@
       "DataLoaders\r\n",
       "- @eyurtsev\r\n",
       "\n",
-      "{'url': 'https://github.com/hwchase17/langchain/pull/5408', 'title': 'DocumentLoader for GitHub', 'creator': 'UmerHA', 'created_at': '2023-05-29T14:50:53Z', 'comments': 0, 'state': 'open', 'labels': ['enhancement', 'lgtm', 'doc loader'], 'assignee': None, 'milestone': None, 'locked': False, 'number': 5408, 'is_pull_request': True}\n"
+      "{'url': 'https://github.com/langchain-ai/langchain/pull/5408', 'title': 'DocumentLoader for GitHub', 'creator': 'UmerHA', 'created_at': '2023-05-29T14:50:53Z', 'comments': 0, 'state': 'open', 'labels': ['enhancement', 'lgtm', 'doc loader'], 'assignee': None, 'milestone': None, 'locked': False, 'number': 5408, 'is_pull_request': True}\n"
      ]
     }
    ],
@@ -147,7 +147,7 @@
    "outputs": [],
    "source": [
     "loader = GitHubIssuesLoader(\n",
-    "    repo=\"hwchase17/langchain\",\n",
+    "    repo=\"langchain-ai/langchain\",\n",
     "    access_token=ACCESS_TOKEN,  # delete/comment out this argument if you've set the access token as an env var.\n",
     "    creator=\"UmerHA\",\n",
     "    include_prs=False,\n",
@@ -220,7 +220,7 @@
       "### Expected behavior\n",
       "\n",
       "Chain should run\n",
-      "{'url': 'https://github.com/hwchase17/langchain/issues/5027', 'title': \"ChatOpenAI models don't work with prompts created via ChatPromptTemplate.from_role_strings\", 'creator': 'UmerHA', 'created_at': '2023-05-20T10:39:18Z', 'comments': 1, 'state': 'open', 'labels': [], 'assignee': None, 'milestone': None, 'locked': False, 'number': 5027, 'is_pull_request': False}\n"
+      "{'url': 'https://github.com/langchain-ai/langchain/issues/5027', 'title': \"ChatOpenAI models don't work with prompts created via ChatPromptTemplate.from_role_strings\", 'creator': 'UmerHA', 'created_at': '2023-05-20T10:39:18Z', 'comments': 1, 'state': 'open', 'labels': [], 'assignee': None, 'milestone': None, 'locked': False, 'number': 5027, 'is_pull_request': False}\n"
      ]
     }
    ],

docs/extras/integrations/document_loaders/google_drive.ipynb

@@ -21,6 +21,8 @@
     "## 🧑 Instructions for ingesting your Google Docs data\n",
     "By default, the `GoogleDriveLoader` expects the `credentials.json` file to be `~/.credentials/credentials.json`, but this is configurable using the `credentials_path` keyword argument. Same thing with `token.json` - `token_path`. Note that `token.json` will be created automatically the first time you use the loader.\n",
     "\n",
+    "The first time you use GoogleDriveLoader, you will be displayed with the consent screen in your browser. If this doesn't happen and you get a `RefreshError`, do not use `credentials_path` in your `GoogleDriveLoader` constructor call. Instead, put that path in a `GOOGLE_APPLICATION_CREDENTIALS` environmental variable.\n",
+    "\n",
     "`GoogleDriveLoader` can load from a list of Google Docs document ids or a folder id. You can obtain your folder and document id from the URL:\n",
     "* Folder: https://drive.google.com/drive/u/0/folders/1yucgL9WGgWZdM1TOuKkeghlPizuzMYb5 -> folder id is `\"1yucgL9WGgWZdM1TOuKkeghlPizuzMYb5\"`\n",
     "* Document: https://docs.google.com/document/d/1bfaMQ18_i56204VaQDVeAFpqEijJTgvurupdEDiaUQw/edit -> document id is `\"1bfaMQ18_i56204VaQDVeAFpqEijJTgvurupdEDiaUQw\"`"
@@ -59,6 +61,7 @@
    "source": [
     "loader = GoogleDriveLoader(\n",
     "    folder_id=\"1yucgL9WGgWZdM1TOuKkeghlPizuzMYb5\",\n",
+    "    token_path='/path/where/you/want/token/to/be/created/google_token.json'\n",
     "    # Optional: configure whether to recursively fetch files from subfolders. Defaults to False.\n",
     "    recursive=False,\n",
     ")"

docs/extras/integrations/document_loaders/mongodb.ipynb

@@ -0,0 +1,163 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "vm8vn9t8DvC_"
+   },
+   "source": [
+    "# MongoDB"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "[MongoDB](https://www.mongodb.com/) is a NoSQL , document-oriented database that supports JSON-like documents with a dynamic schema."
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "5WjXERXzFEhg"
+   },
+   "source": [
+    "## Overview"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "juAmbgoWD17u"
+   },
+   "source": [
+    "The MongoDB Document Loader returns a list of Langchain Documents from a MongoDB database.\n",
+    "\n",
+    "The Loader requires the following parameters:\n",
+    "\n",
+    "*   MongoDB connection string\n",
+    "*   MongoDB database name\n",
+    "*   MongoDB collection name\n",
+    "*   (Optional) Content Filter dictionary\n",
+    "\n",
+    "The output takes the following format:\n",
+    "\n",
+    "- pageContent= Mongo Document\n",
+    "- metadata={'database': '[database_name]', 'collection': '[collection_name]'}"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Load the Document Loader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# add this import for running in jupyter notebook\n",
+    "import nest_asyncio\n",
+    "nest_asyncio.apply()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders.mongodb import MongodbLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = MongodbLoader(connection_string=\"mongodb://localhost:27017/\",\n",
+    "                       db_name=\"sample_restaurants\", \n",
+    "                       collection_name=\"restaurants\",\n",
+    "                       filter_criteria={\"borough\": \"Bronx\", \"cuisine\": \"Bakery\" },\n",
+    "                       ) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "25359"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "docs = loader.load()\n",
+    "\n",
+    "len(docs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Document(page_content=\"{'_id': ObjectId('5eb3d668b31de5d588f4292a'), 'address': {'building': '2780', 'coord': [-73.98241999999999, 40.579505], 'street': 'Stillwell Avenue', 'zipcode': '11224'}, 'borough': 'Brooklyn', 'cuisine': 'American', 'grades': [{'date': datetime.datetime(2014, 6, 10, 0, 0), 'grade': 'A', 'score': 5}, {'date': datetime.datetime(2013, 6, 5, 0, 0), 'grade': 'A', 'score': 7}, {'date': datetime.datetime(2012, 4, 13, 0, 0), 'grade': 'A', 'score': 12}, {'date': datetime.datetime(2011, 10, 12, 0, 0), 'grade': 'A', 'score': 12}], 'name': 'Riviera Caterer', 'restaurant_id': '40356018'}\", metadata={'database': 'sample_restaurants', 'collection': 'restaurants'})"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "docs[0]"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "collapsed_sections": [
+    "5WjXERXzFEhg"
+   ],
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.18"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

docs/extras/integrations/document_loaders/readthedocs_documentation.ipynb

@@ -11,7 +11,7 @@
     "\n",
     "This notebook covers how to load content from HTML that was generated as part of a `Read-The-Docs` build.\n",
     "\n",
-    "For an example of this in the wild, see [here](https://github.com/hwchase17/chat-langchain).\n",
+    "For an example of this in the wild, see [here](https://github.com/langchain-ai/chat-langchain).\n",
     "\n",
     "This assumes that the HTML has already been scraped into a folder. This can be done by uncommenting and running the following command"
    ]

docs/extras/integrations/document_transformers/beautiful_soup.ipynb

@@ -7,7 +7,12 @@
    "source": [
     "# Beautiful Soup\n",
     "\n",
-    "Beautiful Soup offers fine-grained control over HTML content, enabling specific tag extraction, removal, and content cleaning. \n",
+    ">[Beautiful Soup](https://www.crummy.com/software/BeautifulSoup/) is a Python package for parsing \n",
+    "> HTML and XML documents (including having malformed markup, i.e. non-closed tags, so named after tag soup). \n",
+    "> It creates a parse tree for parsed pages that can be used to extract data from HTML,[3] which \n",
+    "> is useful for web scraping.\n",
+    "\n",
+    "`Beautiful Soup` offers fine-grained control over HTML content, enabling specific tag extraction, removal, and content cleaning. \n",
     "\n",
     "It's suited for cases where you want to extract specific information and clean up the HTML content according to your needs.\n",
     "\n",
@@ -87,7 +92,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.16"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/extras/integrations/document_transformers/docai.ipynb

@@ -1,14 +1,11 @@
 {
  "cells": [
   {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "48438efb-9f0d-473b-a91c-9f1e29c2539d",
+   "cell_type": "markdown",
+   "id": "310fce10-e051-40db-89b0-5b5bb85cd145",
    "metadata": {},
-   "outputs": [],
    "source": [
-    "from langchain.document_loaders.blob_loaders import Blob\n",
-    "from langchain.document_loaders.parsers import DocAIParser"
+    "# Document AI\n"
    ]
   },
   {
@@ -16,7 +13,28 @@
    "id": "f95ac25b-f025-40c3-95b8-77919fc4da7f",
    "metadata": {},
    "source": [
-    "DocAI is a Google Cloud platform to transform unstructured data from documents into structured data, making it easier to understand, analyze, and consume. You can read more about it: https://cloud.google.com/document-ai/docs/overview "
+    ">[Document AI](https://cloud.google.com/document-ai/docs/overview) is a `Google Cloud Platform` service to transform unstructured data from documents into structured data, making it easier to understand, analyze, and consume.  "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "275f2193-248f-4565-a872-93a89589cf2b",
+   "metadata": {},
+   "source": [
+    "The module contains a `PDF` parser based on DocAI from Google Cloud.\n",
+    "\n",
+    "You need to install two libraries to use this parser:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "34132fab-0069-4942-b68b-5b093ccfc92a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install google-cloud-documentai\n",
+    "!pip install google-cloud-documentai-toolbox"
    ]
   },
   {
@@ -24,8 +42,8 @@
    "id": "51946817-798c-4d11-abd6-db2ae53a0270",
    "metadata": {},
    "source": [
-    "First, you need to set up a GCS bucket and create your own OCR processor as described here: https://cloud.google.com/document-ai/docs/create-processor\n",
-    "The GCS_OUTPUT_PATH should be a path to a folder on GCS (starting with `gs://`) and a processor name should look like `projects/PROJECT_NUMBER/locations/LOCATION/processors/PROCESSOR_ID`. You can get it either programmatically or copy from the `Prediction endpoint` section of the `Processor details` tab in the Google Cloud Console."
+    "First, you need to set up a [`GCS` bucket and create your own OCR processor](https://cloud.google.com/document-ai/docs/create-processor)  \n",
+    "The `GCS_OUTPUT_PATH` should be a path to a folder on GCS (starting with `gs://`) and a processor name should look like `projects/PROJECT_NUMBER/locations/LOCATION/processors/PROCESSOR_ID`. You can get it either programmatically or copy from the `Prediction endpoint` section of the `Processor details` tab in the Google Cloud Console."
    ]
   },
   {
@@ -40,6 +58,17 @@
     "PROCESSOR_NAME = \"PUT_SOMETHING_HERE\""
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "48438efb-9f0d-473b-a91c-9f1e29c2539d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders.blob_loaders import Blob\n",
+    "from langchain.document_loaders.parsers import DocAIParser"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "fad2bcca-1c0e-4888-b82d-15823ba57e60",
@@ -261,7 +290,7 @@
    "uri": "gcr.io/deeplearning-platform-release/base-cpu:m109"
   },
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -275,7 +304,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.11"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/extras/integrations/document_transformers/doctran_extract_properties.ipynb

@@ -4,14 +4,14 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Doctran Extract Properties\n",
+    "# Doctran: extract properties\n",
     "\n",
     "We can extract useful features of documents using the [Doctran](https://github.com/psychic-api/doctran) library, which uses OpenAI's function calling feature to extract specific metadata.\n",
     "\n",
     "Extracting metadata from documents is helpful for a variety of tasks, including:\n",
-    "* Classification: classifying documents into different categories\n",
-    "* Data mining: Extract structured data that can be used for data analysis\n",
-    "* Style transfer: Change the way text is written to more closely match expected user input, improving vector search results"
+    "* **Classification:** classifying documents into different categories\n",
+    "* **Data mining:** Extract structured data that can be used for data analysis\n",
+    "* **Style transfer:** Change the way text is written to more closely match expected user input, improving vector search results"
    ]
   },
   {
@@ -26,9 +26,7 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "metadata": {
-    "scrolled": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "import json\n",
@@ -261,9 +259,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

docs/extras/integrations/document_transformers/doctran_interrogate_document.ipynb

@@ -4,8 +4,9 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Doctran Interrogate Documents\n",
-    "Documents used in a vector store knowledge base are typically stored in narrative or conversational format. However, most user queries are in question format. If we convert documents into Q&A format before vectorizing them, we can increase the liklihood of retrieving relevant documents, and decrease the liklihood of retrieving irrelevant documents.\n",
+    "# Doctran: interrogate documents\n",
+    "\n",
+    "Documents used in a vector store knowledge base are typically stored in a narrative or conversational format. However, most user queries are in question format. If we **convert documents into Q&A format** before vectorizing them, we can increase the likelihood of retrieving relevant documents, and decrease the likelihood of retrieving irrelevant documents.\n",
     "\n",
     "We can accomplish this using the [Doctran](https://github.com/psychic-api/doctran) library, which uses OpenAI's function calling feature to \"interrogate\" documents.\n",
     "\n",
@@ -24,9 +25,7 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "metadata": {
-    "scrolled": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "import json\n",
@@ -258,9 +257,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

docs/extras/integrations/document_transformers/doctran_translate_document.ipynb

@@ -4,10 +4,11 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Doctran Translate Documents\n",
+    "# Doctran: language translation\n",
+    "\n",
     "Comparing documents through embeddings has the benefit of working across multiple languages. \"Harrison says hello\" and \"Harrison dice hola\" will occupy similar positions in the vector space because they have the same meaning semantically.\n",
     "\n",
-    "However, it can still be useful to use a LLM translate documents into other languages before vectorizing them. This is especially helpful when users are expected to query the knowledge base in different languages, or when state of the art embeddings models are not available for a given language.\n",
+    "However, it can still be useful to use an LLM to **translate documents into other languages** before vectorizing them. This is especially helpful when users are expected to query the knowledge base in different languages, or when state-of-the-art embedding models are not available for a given language.\n",
     "\n",
     "We can accomplish this using the [Doctran](https://github.com/psychic-api/doctran) library, which uses OpenAI's function calling feature to translate documents between languages."
    ]
@@ -125,9 +126,7 @@
   {
    "cell_type": "code",
    "execution_count": 7,
-   "metadata": {
-    "scrolled": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "translated_document = await qa_translator.atransform_documents(documents)"
@@ -200,9 +199,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

docs/extras/integrations/document_transformers/html2text.ipynb

@@ -5,11 +5,11 @@
    "id": "fe6e5c82",
    "metadata": {},
    "source": [
-    "# html2text\n",
+    "# HTML to text\n",
     "\n",
-    "[html2text](https://github.com/Alir3z4/html2text/) is a Python script that converts a page of HTML into clean, easy-to-read plain ASCII text. \n",
+    ">[html2text](https://github.com/Alir3z4/html2text/) is a Python package that converts a page of `HTML` into clean, easy-to-read plain `ASCII text`. \n",
     "\n",
-    "The ASCII also happens to be valid Markdown (a text-to-HTML format)."
+    "The ASCII also happens to be a valid `Markdown` (a text-to-HTML format)."
    ]
   },
   {
@@ -125,7 +125,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.16"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/extras/integrations/document_transformers/nuclia_transformer.ipynb

@@ -5,11 +5,11 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Nuclia Understanding API document transformer\n",
+    "# Nuclia\n",
     "\n",
-    "[Nuclia](https://nuclia.com) automatically indexes your unstructured data from any internal and external source, providing optimized search results and generative answers. It can handle video and audio transcription, image content extraction, and document parsing.\n",
+    ">[Nuclia](https://nuclia.com) automatically indexes your unstructured data from any internal and external source, providing optimized search results and generative answers. It can handle video and audio transcription, image content extraction, and document parsing.\n",
     "\n",
-    "The Nuclia Understanding API document transformer splits text into paragraphs and sentences, identifies entities, provides a summary of the text and generates embeddings for all the sentences.\n",
+    "`Nuclia Understanding API` document transformer splits text into paragraphs and sentences, identifies entities, provides a summary of the text and generates embeddings for all the sentences.\n",
     "\n",
     "To use the Nuclia Understanding API, you need to have a Nuclia account. You can create one for free at [https://nuclia.cloud](https://nuclia.cloud), and then [create a NUA key](https://docs.nuclia.dev/docs/docs/using/understanding/intro).\n",
     "\n",
@@ -94,7 +94,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "langchain",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -108,10 +108,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.5"
-  },
-  "orig_nbformat": 4
+   "version": "3.10.12"
+  }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

docs/extras/integrations/document_transformers/openai_metadata_tagger.ipynb

@@ -4,15 +4,15 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# OpenAI Functions Metadata Tagger\n",
+    "# OpenAI metadata tagger\n",
     "\n",
-    "It can often be useful to tag ingested documents with structured metadata, such as the title, tone, or length of a document, to allow for more targeted similarity search later. However, for large numbers of documents, performing this labelling process manually can be tedious.\n",
+    "It can often be useful to tag ingested documents with structured metadata, such as the title, tone, or length of a document, to allow for a more targeted similarity search later. However, for large numbers of documents, performing this labelling process manually can be tedious.\n",
     "\n",
-    "The `OpenAIMetadataTagger` document transformer automates this process by extracting metadata from each provided document according to a provided schema. It uses a configurable OpenAI Functions-powered chain under the hood, so if you pass a custom LLM instance, it must be an OpenAI model with functions support. \n",
+    "The `OpenAIMetadataTagger` document transformer automates this process by extracting metadata from each provided document according to a provided schema. It uses a configurable `OpenAI Functions`-powered chain under the hood, so if you pass a custom LLM instance, it must be an `OpenAI` model with functions support. \n",
     "\n",
     "**Note:** This document transformer works best with complete documents, so it's best to run it first with whole documents before doing any other splitting or processing!\n",
     "\n",
-    "For example, let's say you wanted to index a set of movie reviews. You could initialize the document transformer with a valid JSON Schema object as follows:"
+    "For example, let's say you wanted to index a set of movie reviews. You could initialize the document transformer with a valid `JSON Schema` object as follows:"
    ]
   },
   {
@@ -239,9 +239,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "venv",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
-   "name": "venv"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -253,9 +253,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

docs/extras/integrations/llms/bedrock.ipynb

@@ -35,7 +35,7 @@
     "\n",
     "llm = Bedrock(\n",
     "    credentials_profile_name=\"bedrock-admin\",\n",
-    "    model_id=\"amazon.titan-tg1-large\"\n",
+    "    model_id=\"amazon.titan-text-express-v1\"\n",
     ")"
    ]
   },
@@ -82,7 +82,7 @@
     "\n",
     "llm = Bedrock(\n",
     "    credentials_profile_name=\"bedrock-admin\",\n",
-    "    model_id=\"amazon.titan-tg1-large\",\n",
+    "    model_id=\"amazon.titan-text-express-v1\",\n",
     "    streaming=True,\n",
     "    callbacks=[StreamingStdOutCallbackHandler()],\n",
     ")"

docs/extras/integrations/llms/fireworks.ipynb

@@ -20,7 +20,8 @@
    "outputs": [],
    "source": [
     "from langchain.llms.fireworks import Fireworks\n",
-    "from langchain.prompts import PromptTemplate\nfrom langchain.chains import LLMChain\n",
+    "from langchain.prompts import PromptTemplate\n",
+    "from langchain.chains import LLMChain\n",
     "from langchain.prompts.chat import (\n",
     "    ChatPromptTemplate,\n",
     "    HumanMessagePromptTemplate,\n",
@@ -35,21 +36,26 @@
    "source": [
     "# Setup\n",
     "\n",
-    "Contact Fireworks AI for the an API Key to access our models\n",
-    "\n",
-    "Set up your model using a model id. If the model is not set, the default model is fireworks-llama-v2-7b-chat."
+    "1. Make sure the `fireworks-ai` package is installed in your environment.\n",
+    "2. Sign in to [Fireworks AI](http://fireworks.ai) for the an API Key to access our models, and make sure it is set as the `FIREWORKS_API_KEY` environment variable.\n",
+    "3. Set up your model using a model id. If the model is not set, the default model is fireworks-llama-v2-7b-chat. See the full, most up-to-date model list on [app.fireworks.ai](https://app.fireworks.ai)."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 26,
    "id": "9ca87a2e",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Initialize a Fireworks LLM\n",
-    "os.environ['FIREWORKS_API_KEY'] = \"<your_api_key>\"  # Change this to your own API key\n",
-    "llm = Fireworks(model=\"accounts/fireworks/models/llama-v2-13b-chat\")"
+    "import os\n",
+    "import getpass\n",
+    "\n",
+    "if \"FIREWORKS_API_KEY\" not in os.environ:\n",
+    "    os.environ[\"FIREWORKS_API_KEY\"] = getpass.getpass(\"Fireworks API Key:\")\n",
+    "\n",
+    "# Initialize a Fireworks model\n",
+    "llm = Fireworks(model=\"accounts/fireworks/models/llama-v2-13b\")"
    ]
   },
   {
@@ -57,11 +63,9 @@
    "id": "acc24d0c",
    "metadata": {},
    "source": [
-    "# Calling the Model\n",
+    "# Calling the Model Directly\n",
     "\n",
-    "You can use the LLMs to call the model for specified prompt(s). \n",
-    "\n",
-    "See the full, most up-to-date model list on [app.fireworks.ai](https://app.fireworks.ai)."
+    "You can call the model directly with string prompts to get completions."
    ]
   },
   {
@@ -76,15 +80,41 @@
      "text": [
       "\n",
       "\n",
-      "It's a question that's been debated for years, and there are plenty of strong candidates. Here are some of the top quarterbacks in the league right now:\n",
+      "Is it Tom Brady? Peyton Manning? Aaron Rodgers? Or maybe even Andrew Luck?\n",
       "\n",
-      "1. Tom Brady (New England Patriots): Brady is widely considered one of the greatest quarterbacks of all time, and for good reason. He's led the Patriots to six Super Bowl wins and has been named Super Bowl MVP four times. He's known for his precision passing and ability to read defenses.\n",
-      "2. Aaron Rodgers (Green Bay Packers): Rodgers is another top-tier quarterback who's known for his accuracy and ability to make plays outside of the pocket. He's led the Packers to a Super Bowl win and has been named NFL MVP twice.\n",
-      "3. Drew Brees (New Orleans Saints): Brees is one of the most prolific passers in NFL history, and he's shown no signs of slowing down. He's led the Saints to a Super Bowl win and has been named NFL MVP once.\n",
-      "4. Russell Wilson (Seattle Seahawks): Wilson is a dynamic quarterback who's known for his ability to make plays with his legs and his arm. He's led the Seahawks to a Super Bowl win and has been named NFL MVP once.\n",
-      "5. Patrick Mahomes (Kansas City Chiefs): Mahomes is a young quarterback who's quickly become one of the best in the league. He led the Chiefs to a Super Bowl win last season and has been named NFL MVP twice. He's known for his incredible arm talent and ability to make plays outside of the pocket.\n",
+      "Well, let's look at some stats to decide.\n",
       "\n",
-      "Of course, there are other great quarterbacks in the league as well, such as Ben Roethlisberger, Matt Ryan, and Deshaun Watson. Ultimately, the \"best\" quarterback is a matter of personal opinion and depends on how you define \"best.\" Some people might value accuracy and precision passing, while others might prefer a quarterback who can make plays with their legs. Either way, the NFL is filled with talented quarterbacks who are making incredible plays every week.\n"
+      "First, let's talk about touchdowns. Who's thrown the most touchdowns this season?\n",
+      "\n",
+      "(pause for dramatic effect)\n",
+      "\n",
+      "It's... Aaron Rodgers! With 28 touchdowns, he's leading the league in that category.\n",
+      "\n",
+      "But what about interceptions? Who's thrown the fewest picks?\n",
+      "\n",
+      "(drumroll)\n",
+      "\n",
+      "It's... Tom Brady! With only 4 interceptions, he's got the fewest picks in the league.\n",
+      "\n",
+      "Now, let's talk about passer rating. Who's got the highest passer rating this season?\n",
+      "\n",
+      "(pause for suspense)\n",
+      "\n",
+      "It's... Peyton Manning! With a rating of 114.2, he's been lights out this season.\n",
+      "\n",
+      "But what about wins? Who's got the most wins this season?\n",
+      "\n",
+      "(drumroll)\n",
+      "\n",
+      "It's... Andrew Luck! With 8 wins, he's got the most victories this season.\n",
+      "\n",
+      "So, there you have it folks. According to these stats, the best quarterback in the NFL this season is... (drumroll) Aaron Rodgers!\n",
+      "\n",
+      "But wait, there's more! Each of these quarterbacks has their own unique strengths and weaknesses.\n",
+      "\n",
+      "Tom Brady is a master of the short pass, but can struggle with deep balls. Peyton Manning is a genius at reading defenses, but can be prone to turnovers. Aaron Rodgers has a cannon for an arm, but can be inconsistent at times. Andrew Luck is a pure pocket passer, but can struggle outside of his comfort zone.\n",
+      "\n",
+      "So, who's the best quarterback in the NFL? It's a tough call, but one thing's for sure: each of these quarterbacks is an elite talent, and they'll continue to light up the scoreboard for their respective teams all season long.\n"
      ]
     }
    ],
@@ -104,7 +134,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[[Generation(text=\"\\n\\nNote: This is a subjective question, and the answer will depend on individual opinions and perspectives.\\n\\nThere are many great cricket players, and it's difficult to identify a single best player. However, here are some of the top performers in 2016:\\n\\n1. Virat Kohli (India): Kohli had an outstanding year in all formats of the game, scoring heavily in Tests, ODIs, and T20Is. He was especially impressive in the Test series against England, where he scored four centuries and averaged over 100.\\n2. Steve Smith (Australia): Smith had a phenomenal year as well, leading Australia to a Test series win in India and averaging over 100 in the longer format. He also scored a century in the ODI series against Pakistan.\\n3. Kane Williamson (New Zealand): Williamson had a consistent year, scoring heavily in all formats and leading New Zealand to a Test series win against Australia. He also won the ICC Test Player of the Year award.\\n4. Joe Root (England): Root had a solid year, scoring three hundreds in the Test series against Pakistan and India, and averaging over 50 in Tests.\\n5. AB de Villiers (South Africa): De Villiers had a brilliant year in ODIs, scoring four hundreds and averaging over 100. He also had a good year in Tests, scoring two hundreds and averaging over 50.\\n6. Quinton de Kock (South Africa): De Kock had a great year behind the wickets, scoring heavily in all formats and averaging over 50 in Tests.\\n7. Rohit Sharma (India): Sharma had a fantastic year in ODIs, scoring four hundreds and averaging over 100. He also had a good year in Tests, scoring two hundreds and averaging over 40.\\n8. David Warner (Australia): Warner had a great year in ODIs, scoring three hundreds and averaging over 100. He also had a good year in Tests, scoring two hundreds and averaging over 40.\\n\\nThese are just a few examples of top performers in 2016, and opinions on the best player will vary depending on individual perspectives\", generation_info=None)], [Generation(text='\\n\\nThere are a lot of great players in the NBA, and opinions on who\\'s the best can vary depending on personal preferences and criteria for evaluation. However, here are some of the top candidates for the title of best basketball player in the league based on their recent performances and achievements:\\n\\n1. LeBron James: James is a four-time NBA champion and four-time MVP, and is widely regarded as one of the greatest players of all time. He has led the Los Angeles Lakers to the best record in the Western Conference this season and is averaging 25.7 points, 7.9 rebounds, and 7.4 assists per game.\\n2. Giannis Antetokounmpo: Antetokounmpo, known as the \"Greek Freak,\" is a dominant force in the paint and has led the Milwaukee Bucks to the best record in the Eastern Conference. He is averaging 30.5 points, 12.6 rebounds, and 5.9 assists per game, and is a strong contender for the MVP award.\\n3. Stephen Curry: Curry is a three-time NBA champion and two-time MVP, and is known for his incredible shooting ability. He has led the Golden State Warriors to the playoffs despite injuries to key players, and is averaging 23.5 points, 5.2 rebounds, and 5.2 assists per game.\\n4. Kevin Durant: Durant is a two-time NBA champion and four-time scoring champion, and is one of the most skilled scorers in the league. He has led the Brooklyn Nets to the playoffs in their first season since moving from New Jersey, and is averaging 27.2 points, 7.2 rebounds, and 6.4 assists per game.\\n5. James Harden: Harden is a three-time scoring champion and has led the Houston Rockets to the playoffs for the past eight seasons. He is averaging 35.4 points, 8.3 rebounds, and 7.5 assists per game, and is a strong contender for the MVP award.\\n\\nUltimately, determining the best basketball player in the league is subjective and depends on individual opinions and criteria. However, these five players are among', generation_info=None)]]\n"
+      "[[Generation(text='\\nasked Dec 28, 2016 in Sports by anonymous\\nWho is the best cricket player in 2016?\\nHere are some of the top contenders for the title of best cricket player in 2016:\\n\\n1. Virat Kohli (India): Kohli had a phenomenal year in 2016, scoring over 2,000 runs in international cricket, including 12 centuries. He was named the ICC Cricketer of the Year and the ICC Test Player of the Year.\\n2. Steve Smith (Australia): Smith had a great year as well, scoring over 1,000 runs in Test cricket and leading Australia to the No. 1 ranking in Test cricket. He was named the ICC ODI Player of the Year.\\n3. Joe Root (England): Root had a strong year, scoring over 1,000 runs in Test cricket and leading England to the No. 2 ranking in Test cricket.\\n4. Kane Williamson (New Zealand): Williamson had a great year, scoring over 1,000 runs in all formats of the game and leading New Zealand to the ICC World T20 final.\\n5. Quinton de Kock (South Africa): De Kock had a great year behind the wickets, scoring over 1,000 runs in all formats of the game and effecting over 100 dismissals.\\n6. David Warner (Australia): Warner had a great year, scoring over 1,000 runs in all formats of the game and leading Australia to the ICC World T20 title.\\n7. AB de Villiers (South Africa): De Villiers had a great year, scoring over 1,000 runs in all formats of the game and effecting over 50 dismissals.\\n8. Chris Gayle (West Indies): Gayle had a great year, scoring over 1,000 runs in all formats of the game and leading the West Indies to the ICC World T20 title.\\n9. Shakib Al Hasan (Bangladesh): Shakib had a great year, scoring over 1,000 runs in all formats of the game and taking over 50 wickets.\\n10', generation_info=None)], [Generation(text=\"\\n\\n  A) LeBron James\\n  B) Kevin Durant\\n  C) Steph Curry\\n  D) James Harden\\n\\nAnswer: C) Steph Curry\\n\\nIn recent years, Curry has established himself as the premier shooter in the NBA, leading the league in three-point shooting and earning back-to-back MVP awards. He's also a strong ball handler and playmaker, making him a threat to score from anywhere on the court. While other players like LeBron James and Kevin Durant are certainly talented, Curry's unique skill set and consistent dominance make him the best basketball player in the league right now.\", generation_info=None)]]\n"
      ]
     }
    ],
@@ -128,7 +158,7 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "Kansas City's weather in December can be quite chilly,\n"
+      "What's the weather like in Kansas City in December? \n"
      ]
     }
    ],
@@ -143,14 +173,20 @@
    "id": "137662a6",
    "metadata": {},
    "source": [
-    "# Create and Run Chain\n",
-    "\n",
-    "Create a prompt template to be used with the LLM Chain. Once this prompt template is created, initialize the chain with the LLM and prompt template, and run the chain with the specified prompts."
+    "# Simple Chain with Non-Chat Model"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "79efa62d",
+   "metadata": {},
+   "source": [
+    "You can use the LangChain Expression Language to create a simple chain with non-chat models."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 11,
    "id": "fd2c6bc1",
    "metadata": {},
    "outputs": [
@@ -159,140 +195,55 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "\n",
-      "Assistant: That's a great question! There are many factors to consider when choosing a name for a company that makes football helmets. Here are a few suggestions:\n",
-      "\n",
-      "1. Gridiron Gear: This name plays off the term \"gridiron,\" which is a slang term for a football field. It also suggests that the company's products are high-quality and durable, like gear used in a gridiron game.\n",
-      "2. Helmet Headquarters: This name is straightforward and to the point. It clearly communicates that the company is a leading manufacturer of football helmets.\n",
-      "3. Tackle Tough: This name plays off the idea of tackling a tough opponent on the football field. It suggests that the company's helmets are designed to protect players from even the toughest hits.\n",
-      "4. Block Breakthrough: This name is a play on words that suggests the company's helmets are breaking through the competition. It also implies that the company is innovative and forward-thinking.\n",
-      "5. First Down Fashion: This name combines the idea of scoring a first down on the football field with the idea of fashionable clothing. It suggests that the company's helmets are not only functional but also stylish.\n",
-      "\n",
-      "I hope these suggestions help you come up with a great name for your company!\n"
+      "A bear walks into a bar and says, \"I'll have a beer and a muffin.\" The bartender says, \"Sorry, we don't serve muffins here.\" The bear says, \"OK, give me a beer and I'll make my own muffin.\"\n",
+      "What do you call a bear with no teeth?\n",
+      "A gummy bear.\n",
+      "What do you call a bear with no teeth and no hair?\n",
+      "\n"
      ]
     }
    ],
    "source": [
-    "human_message_prompt = HumanMessagePromptTemplate.from_template(\"What is a good name for a company that makes {product}?\")\n",
-    "chat_prompt_template = ChatPromptTemplate.from_messages([human_message_prompt])\n",
-    "chat = Fireworks()\n",
-    "chain = LLMChain(llm=chat, prompt=chat_prompt_template)\n",
-    "output = chain.run(\"football helmets\")\n",
+    "from langchain.prompts import PromptTemplate\n",
+    "from langchain.llms.fireworks import Fireworks\n",
     "\n",
-    "print(output)"
+    "llm = Fireworks(model=\"accounts/fireworks/models/llama-v2-13b\", model_kwargs={\"temperature\":0, \"max_tokens\":100, \"top_p\":1.0})\n",
+    "prompt = PromptTemplate.from_template(\"Tell me a joke about {topic}?\")\n",
+    "chain = prompt | llm\n",
+    "\n",
+    "print(chain.invoke({\"topic\": \"bears\"}))"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "25812db3-23a6-41dd-8636-5a49c52bb6eb",
+   "id": "d0a29826",
    "metadata": {},
    "source": [
-    "# Run Stream"
+    "You can stream the output, if you want."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
-   "id": "26d67ecf-9290-4ec2-8b39-ff17fc99620f",
+   "execution_count": 12,
+   "id": "f644ff28",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " Tom Brady, Aaron Rod\n",
-      "gers, or Drew Bre\n",
-      "es?\n",
-      "Some people might\n",
-      " say Tom Brady, who\n",
-      " has won six Super Bowls\n",
-      " and four Super Bowl MVP\n",
-      " awards, is the best quarter\n",
-      "back in the NFL. O\n",
-      "thers might argue that Aaron\n",
-      " Rodgers, who has led\n",
-      " his team to a Super Bowl\n",
-      " victory and has been named the\n",
-      " NFL MVP twice, is\n",
-      " the best. Still, others\n",
-      " might say that Drew Bre\n",
-      "es, who holds the NFL\n",
-      " record for most career passing yards\n",
-      " and has led his team to\n",
-      " a Super Bowl victory, is\n",
-      " the best.\n",
-      "But what\n",
-      " if I told you there'\n",
-      "s actually a fourth quarterback\n",
-      " who could make a strong case\n",
-      " for being the best in the\n",
-      " NFL? Meet Russell Wilson\n",
-      ", the Seattle Seahaw\n",
-      "ks' dynamic signal-call\n",
-      "er who has led his team\n",
-      " to a Super Bowl victory and\n",
-      " has been named the NFL M\n",
-      "VP twice.\n",
-      "Wilson\n",
-      " has a unique combination of physical\n",
-      " and mental skills that set him\n",
-      " apart from other quarterbacks\n",
-      " in the league. He'\n",
-      "s incredibly athletic,\n",
-      " with the ability to make plays\n",
-      " with his feet and his arm\n",
-      ", and he's also\n",
-      " highly intelligent, with a\n",
-      " quick mind and the ability to\n",
-      " read defenses like a pro\n",
-      ".\n",
-      "But what really\n",
-      " sets Wilson apart is his\n",
-      " leadership ability. He'\n",
-      "s a natural-born\n",
-      " leader who has a way\n",
-      " of inspiring his team\n",
-      "mates and getting them\n",
-      " to buy into his vision\n",
-      " for the game. He\n",
-      "'s also an excellent\n",
-      " communicator, who can\n",
-      " articulate his strategy\n",
-      " and game plan in a\n",
-      " way that his teamm\n",
-      "ates can understand and execute\n",
-      ".\n",
-      "So, who\n",
-      "'s the best quarter\n",
-      "back in the NFL?\n",
-      " It's hard to\n",
-      " say for sure, but\n",
-      " if you ask me,\n",
-      " Russell Wilson is definitely in\n",
-      " the conversation. He'\n",
-      "s got the physical skills\n",
-      ", the mental skills,\n",
-      " and the leadership ability to\n",
-      " be the best of the\n",
-      " best.\n"
+      "\n",
+      "A bear walks into a bar and says, \"I'll have a beer and a muffin.\" The bartender says, \"Sorry, we don't serve muffins here.\" The bear says, \"OK, give me a beer and I'll make my own muffin.\"\n",
+      "What do you call a bear with no teeth?\n",
+      "A gummy bear.\n",
+      "What do you call a bear with no teeth and no hair?\n"
      ]
     }
    ],
    "source": [
-    "llm = Fireworks()\n",
-    "generator = llm.stream(\"Who's the best quarterback in the NFL?\")\n",
-    "\n",
-    "for token in generator:\n",
-    "    print(token)"
+    "for token in chain.stream({\"topic\": \"bears\"}):\n",
+    "    print(token, end='', flush=True)"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "e3a35e0b-c875-493a-8143-d802d273247c",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -311,7 +262,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.9.16"
   }
  },
  "nbformat": 4,

docs/extras/integrations/llms/index.mdx

@@ -39,8 +39,8 @@ Databricks|✅|❌|❌|❌|❌|❌
 DeepInfra|✅|❌|❌|❌|❌|❌
 DeepSparse|✅|❌|❌|❌|❌|❌
 EdenAI|✅|✅|❌|❌|❌|❌
-Fireworks|✅|✅|❌|❌|✅|✅
-FireworksChat|✅|✅|❌|❌|✅|✅
+Fireworks|✅|✅|✅|✅|❌|❌
+Fireworks|✅|✅|✅|✅|✅|✅
 ForefrontAI|✅|❌|❌|❌|❌|❌
 GPT4All|✅|❌|❌|❌|❌|❌
 GooglePalm|✅|❌|❌|❌|✅|❌
@@ -48,7 +48,7 @@ GooseAI|✅|❌|❌|❌|❌|❌
 GradientLLM|✅|✅|❌|❌|❌|❌
 HuggingFaceEndpoint|✅|❌|❌|❌|❌|❌
 HuggingFaceHub|✅|❌|❌|❌|❌|❌
-HuggingFacePipeline|✅|❌|❌|❌|❌|❌
+HuggingFacePipeline|✅|❌|❌|❌|✅|❌
 HuggingFaceTextGenInference|✅|✅|✅|✅|❌|❌
 HumanInputLLM|✅|❌|❌|❌|❌|❌
 JavelinAIGateway|✅|✅|❌|❌|❌|❌

docs/extras/integrations/llms/modal.ipynb

@@ -52,7 +52,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "The [`langchain.llms.modal.Modal`](https://github.com/hwchase17/langchain/blame/master/langchain/llms/modal.py) integration class requires that you deploy a Modal application with a web endpoint that complies with the following JSON interface:\n",
+    "The [`langchain.llms.modal.Modal`](https://github.com/langchain-ai/langchain/blame/master/langchain/llms/modal.py) integration class requires that you deploy a Modal application with a web endpoint that complies with the following JSON interface:\n",
     "\n",
     "1. The LLM prompt is accepted as a `str` value under the key `\"prompt\"`\n",
     "2. The LLM response returned as a `str` value under the key `\"prompt\"`\n",

docs/extras/integrations/llms/ollama.ipynb

@@ -51,15 +51,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain.llms import Ollama\n",
     "from langchain.callbacks.manager import CallbackManager\n",
     "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler                                  \n",
-    "llm = Ollama(base_url=\"http://localhost:11434\", \n",
-    "             model=\"llama2\", \n",
+    "llm = Ollama(model=\"llama2\", \n",
     "             callback_manager = CallbackManager([StreamingStdOutCallbackHandler()]))"
    ]
   },
@@ -72,36 +71,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "Great! The history of Artificial Intelligence (AI) is a fascinating and complex topic that spans several decades. Here's a brief overview:\n",
-      "\n",
-      "1. Early Years (1950s-1960s): The term \"Artificial Intelligence\" was coined in 1956 by computer scientist John McCarthy. However, the concept of AI dates back to ancient Greece, where mythical creatures like Talos and Hephaestus were created to perform tasks without any human intervention. In the 1950s and 1960s, researchers began exploring ways to replicate human intelligence using computers, leading to the development of simple AI programs like ELIZA (1966) and PARRY (1972).\n",
-      "2. Rule-Based Systems (1970s-1980s): As computing power increased, researchers developed rule-based systems, such as Mycin (1976), which could diagnose medical conditions based on a set of rules. This period also saw the rise of expert systems, like EDICT (1985), which mimicked human experts in specific domains.\n",
-      "3. Machine Learning (1990s-2000s): With the advent of big data and machine learning algorithms, AI evolved to include neural networks, decision trees, and other techniques for training models on large datasets. This led to the development of applications like speech recognition (e.g., Siri, Alexa), image recognition (e.g., Google Image Search), and natural language processing (e.g., chatbots).\n",
-      "4. Deep Learning (2010s-present): The rise of deep learning techniques, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), has enabled AI to perform complex tasks like image and speech recognition, natural language processing, and even autonomous driving. Companies like Google, Facebook, and Baidu have invested heavily in deep learning research, leading to breakthroughs in areas like facial recognition, object detection, and machine translation.\n",
-      "5. Current Trends (present-future): AI is currently being applied to various industries, including healthcare, finance, education, and entertainment. With the growth of cloud computing, edge AI, and autonomous systems, we can expect to see more sophisticated AI applications in the near future. However, there are also concerns about the ethical implications of AI, such as data privacy, algorithmic bias, and job displacement.\n",
-      "\n",
-      "Remember, AI has a long history, and its development is an ongoing process. As technology advances, we can expect to see even more innovative applications of AI in various fields."
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'\\nGreat! The history of Artificial Intelligence (AI) is a fascinating and complex topic that spans several decades. Here\\'s a brief overview:\\n\\n1. Early Years (1950s-1960s): The term \"Artificial Intelligence\" was coined in 1956 by computer scientist John McCarthy. However, the concept of AI dates back to ancient Greece, where mythical creatures like Talos and Hephaestus were created to perform tasks without any human intervention. In the 1950s and 1960s, researchers began exploring ways to replicate human intelligence using computers, leading to the development of simple AI programs like ELIZA (1966) and PARRY (1972).\\n2. Rule-Based Systems (1970s-1980s): As computing power increased, researchers developed rule-based systems, such as Mycin (1976), which could diagnose medical conditions based on a set of rules. This period also saw the rise of expert systems, like EDICT (1985), which mimicked human experts in specific domains.\\n3. Machine Learning (1990s-2000s): With the advent of big data and machine learning algorithms, AI evolved to include neural networks, decision trees, and other techniques for training models on large datasets. This led to the development of applications like speech recognition (e.g., Siri, Alexa), image recognition (e.g., Google Image Search), and natural language processing (e.g., chatbots).\\n4. Deep Learning (2010s-present): The rise of deep learning techniques, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), has enabled AI to perform complex tasks like image and speech recognition, natural language processing, and even autonomous driving. Companies like Google, Facebook, and Baidu have invested heavily in deep learning research, leading to breakthroughs in areas like facial recognition, object detection, and machine translation.\\n5. Current Trends (present-future): AI is currently being applied to various industries, including healthcare, finance, education, and entertainment. With the growth of cloud computing, edge AI, and autonomous systems, we can expect to see more sophisticated AI applications in the near future. However, there are also concerns about the ethical implications of AI, such as data privacy, algorithmic bias, and job displacement.\\n\\nRemember, AI has a long history, and its development is an ongoing process. As technology advances, we can expect to see even more innovative applications of AI in various fields.'"
-      ]
-     },
-     "execution_count": 40,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "llm(\"Tell me about the history of AI\")"
    ]
@@ -121,7 +93,6 @@
    "source": [
     "from langchain.embeddings import OllamaEmbeddings\n",
     "oembed = OllamaEmbeddings(base_url=\"http://localhost:11434\", model=\"llama2\")\n",
-    "\n",
     "oembed.embed_query(\"Llamas are social animals and live with others as a herd.\")"
    ]
   },
@@ -153,34 +124,60 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 60,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
+    "# Load web page\n",
     "from langchain.document_loaders import WebBaseLoader\n",
     "loader = WebBaseLoader(\"https://lilianweng.github.io/posts/2023-06-23-agent/\")\n",
-    "data = loader.load()\n",
-    "\n",
+    "data = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Split into chunks \n",
     "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
-    "text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)\n",
+    "text_splitter = RecursiveCharacterTextSplitter(chunk_size=1500, chunk_overlap=100)\n",
     "all_splits = text_splitter.split_documents(data)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Found model file at  /Users/rlm/.cache/gpt4all/ggml-all-MiniLM-L6-v2-f16.bin\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "objc[77472]: Class GGMLMetalClass is implemented in both /Users/rlm/miniforge3/envs/llama2/lib/python3.9/site-packages/gpt4all/llmodel_DO_NOT_MODIFY/build/libreplit-mainline-metal.dylib (0x17f754208) and /Users/rlm/miniforge3/envs/llama2/lib/python3.9/site-packages/gpt4all/llmodel_DO_NOT_MODIFY/build/libllamamodel-mainline-metal.dylib (0x17fb80208). One of the two will be used. Which one is undefined.\n"
+     ]
+    }
+   ],
    "source": [
+    "# Embed and store\n",
     "from langchain.vectorstores import Chroma\n",
-    "from langchain.embeddings import OllamaEmbeddings\n",
-    "\n",
-    "vectorstore = Chroma.from_documents(documents=all_splits, embedding=OllamaEmbeddings())"
+    "from langchain.embeddings import GPT4AllEmbeddings\n",
+    "from langchain.embeddings import OllamaEmbeddings # We can also try Ollama embeddings\n",
+    "vectorstore = Chroma.from_documents(documents=all_splits,\n",
+    "                                    embedding=GPT4AllEmbeddings())"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 62,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -189,41 +186,32 @@
        "4"
       ]
      },
-     "execution_count": 62,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "question = \"What are the approaches to Task Decomposition?\"\n",
+    "# Retrieve\n",
+    "question = \"How can Task Decomposition be done?\"\n",
     "docs = vectorstore.similarity_search(question)\n",
     "len(docs)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.prompts import PromptTemplate\n",
-    "\n",
-    "# Prompt\n",
-    "template = \"\"\"Use the following pieces of context to answer the question at the end. \n",
-    "If you don't know the answer, just say that you don't know, don't try to make up an answer. \n",
-    "Use three sentences maximum and keep the answer as concise as possible. \n",
-    "{context}\n",
-    "Question: {question}\n",
-    "Helpful Answer:\"\"\"\n",
-    "QA_CHAIN_PROMPT = PromptTemplate(\n",
-    "    input_variables=[\"context\", \"question\"],\n",
-    "    template=template,\n",
-    ")\n"
+    "# RAG prompt\n",
+    "from langchain import hub\n",
+    "QA_CHAIN_PROMPT = hub.pull(\"rlm/rag-prompt-llama\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 69,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -231,15 +219,14 @@
     "from langchain.llms import Ollama\n",
     "from langchain.callbacks.manager import CallbackManager\n",
     "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
-    "llm = Ollama(base_url=\"http://localhost:11434\",\n",
-    "             model=\"llama2\",\n",
+    "llm = Ollama(model=\"llama2\",\n",
     "             verbose=True,\n",
     "             callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]))"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 66,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -254,18 +241,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 70,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Task decomposition can be approached in different ways for AI agents, including:\n",
+      " There are several approaches to task decomposition for AI agents, including:\n",
       "\n",
-      "1. Using simple prompts like \"Steps for XYZ.\" or \"What are the subgoals for achieving XYZ?\" to guide the LLM.\n",
-      "2. Providing task-specific instructions, such as \"Write a story outline\" for writing a novel.\n",
-      "3. Utilizing human inputs to help the AI agent understand the task and break it down into smaller steps."
+      "1. Chain of thought (CoT): This involves instructing the model to \"think step by step\" and use more test-time computation to decompose hard tasks into smaller and simpler steps.\n",
+      "2. Tree of thoughts (ToT): This extends CoT by exploring multiple reasoning possibilities at each step, creating a tree structure. The search process can be BFS or DFS with each state evaluated by a classifier or majority vote.\n",
+      "3. Using task-specific instructions: For example, \"Write a story outline.\" for writing a novel.\n",
+      "4. Human inputs: The agent can receive input from a human operator to perform tasks that require creativity and domain expertise.\n",
+      "\n",
+      "These approaches allow the agent to break down complex tasks into manageable subgoals, enabling efficient handling of tasks and improving the quality of final results through self-reflection and refinement."
      ]
     }
    ],
@@ -283,17 +273,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 56,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Task decomposition can be approached in three ways: (1) using simple prompting like \"Steps for XYZ.\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions, or (3) with human inputs.{'model': 'llama2', 'created_at': '2023-08-08T04:01:09.005367Z', 'done': True, 'context': [1, 29871, 1, 13, 9314, 14816, 29903, 6778, 13, 13, 3492, 526, 263, 8444, 29892, 3390, 1319, 322, 15993, 20255, 29889, 29849, 1234, 408, 1371, 3730, 408, 1950, 29892, 1550, 1641, 9109, 29889, 3575, 6089, 881, 451, 3160, 738, 10311, 1319, 29892, 443, 621, 936, 29892, 11021, 391, 29892, 7916, 391, 29892, 304, 27375, 29892, 18215, 29892, 470, 27302, 2793, 29889, 3529, 9801, 393, 596, 20890, 526, 5374, 635, 443, 5365, 1463, 322, 6374, 297, 5469, 29889, 13, 13, 3644, 263, 1139, 947, 451, 1207, 738, 4060, 29892, 470, 338, 451, 2114, 1474, 16165, 261, 296, 29892, 5649, 2020, 2012, 310, 22862, 1554, 451, 1959, 29889, 960, 366, 1016, 29915, 29873, 1073, 278, 1234, 304, 263, 1139, 29892, 3113, 1016, 29915, 29873, 6232, 2089, 2472, 29889, 13, 13, 29966, 829, 14816, 29903, 6778, 13, 13, 29961, 25580, 29962, 4803, 278, 1494, 12785, 310, 3030, 304, 1234, 278, 1139, 472, 278, 1095, 29889, 29871, 13, 3644, 366, 1016, 29915, 29873, 1073, 278, 1234, 29892, 925, 1827, 393, 366, 1016, 29915, 29873, 1073, 29892, 1016, 29915, 29873, 1018, 304, 1207, 701, 385, 1234, 29889, 29871, 13, 11403, 2211, 25260, 7472, 322, 3013, 278, 1234, 408, 3022, 895, 408, 1950, 29889, 29871, 13, 5398, 26227, 508, 367, 2309, 313, 29896, 29897, 491, 365, 26369, 411, 2560, 9508, 292, 763, 376, 7789, 567, 363, 1060, 29979, 29999, 7790, 29876, 29896, 19602, 376, 5618, 526, 278, 1014, 1484, 1338, 363, 3657, 15387, 1060, 29979, 29999, 29973, 613, 313, 29906, 29897, 491, 773, 3414, 29899, 14940, 11994, 29936, 321, 29889, 29887, 29889, 376, 6113, 263, 5828, 27887, 1213, 363, 5007, 263, 9554, 29892, 470, 313, 29941, 29897, 411, 5199, 10970, 29889, 13, 13, 5398, 26227, 508, 367, 2309, 313, 29896, 29897, 491, 365, 26369, 411, 2560, 9508, 292, 763, 376, 7789, 567, 363, 1060, 29979, 29999, 7790, 29876, 29896, 19602, 376, 5618, 526, 278, 1014, 1484, 1338, 363, 3657, 15387, 1060, 29979, 29999, 29973, 613, 313, 29906, 29897, 491, 773, 3414, 29899, 14940, 11994, 29936, 321, 29889, 29887, 29889, 376, 6113, 263, 5828, 27887, 1213, 363, 5007, 263, 9554, 29892, 470, 313, 29941, 29897, 411, 5199, 10970, 29889, 13, 13, 5398, 26227, 508, 367, 2309, 313, 29896, 29897, 491, 365, 26369, 411, 2560, 9508, 292, 763, 376, 7789, 567, 363, 1060, 29979, 29999, 7790, 29876, 29896, 19602, 376, 5618, 526, 278, 1014, 1484, 1338, 363, 3657, 15387, 1060, 29979, 29999, 29973, 613, 313, 29906, 29897, 491, 773, 3414, 29899, 14940, 11994, 29936, 321, 29889, 29887, 29889, 376, 6113, 263, 5828, 27887, 1213, 363, 5007, 263, 9554, 29892, 470, 313, 29941, 29897, 411, 5199, 10970, 29889, 13, 13, 1451, 16047, 267, 297, 1472, 29899, 8489, 18987, 322, 3414, 26227, 29901, 1858, 9450, 975, 263, 3309, 29891, 4955, 322, 17583, 3902, 8253, 278, 1650, 2913, 3933, 18066, 292, 29889, 365, 26369, 29879, 21117, 304, 10365, 13900, 746, 20050, 411, 15668, 4436, 29892, 3907, 963, 3109, 16424, 9401, 304, 25618, 1058, 5110, 515, 14260, 322, 1059, 29889, 13, 16492, 29901, 1724, 526, 278, 13501, 304, 9330, 897, 510, 3283, 29973, 13, 29648, 1319, 673, 29901, 518, 29914, 25580, 29962, 13, 5398, 26227, 508, 367, 26733, 297, 2211, 5837, 29901, 313, 29896, 29897, 773, 2560, 9508, 292, 763, 376, 7789, 567, 363, 1060, 29979, 29999, 7790, 29876, 29896, 19602, 376, 5618, 526, 278, 1014, 1484, 1338, 363, 3657, 15387, 1060, 29979, 29999, 29973, 613, 313, 29906, 29897, 491, 773, 3414, 29899, 14940, 11994, 29892, 470, 313, 29941, 29897, 411, 5199, 10970, 29889, 2], 'total_duration': 1364428708, 'load_duration': 1246375, 'sample_count': 62, 'sample_duration': 44859000, 'prompt_eval_count': 1, 'eval_count': 62, 'eval_duration': 1313002000}\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "from langchain.schema import LLMResult\n",
     "from langchain.callbacks.base import BaseCallbackHandler\n",
@@ -345,6 +327,78 @@
    "source": [
     "62 / (1313002000/1000/1000/1000)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Using the Hub for prompt management\n",
+    " \n",
+    "Open source models often benefit from specific prompts. \n",
+    "\n",
+    "For example, [Mistral 7b](https://mistral.ai/news/announcing-mistral-7b/) was fine-tuned for chat using the prompt format shown [here](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1).\n",
+    "\n",
+    "Get the model: `ollama pull mistral:7b-instruct`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# LLM\n",
+    "from langchain.llms import Ollama\n",
+    "from langchain.callbacks.manager import CallbackManager\n",
+    "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
+    "llm = Ollama(model=\"mistral:7b-instruct\",\n",
+    "             verbose=True,\n",
+    "             callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain import hub\n",
+    "QA_CHAIN_PROMPT = hub.pull(\"rlm/rag-prompt-mistral\")\n",
+    "\n",
+    "# QA chain\n",
+    "from langchain.chains import RetrievalQA\n",
+    "qa_chain = RetrievalQA.from_chain_type(\n",
+    "    llm,\n",
+    "    retriever=vectorstore.as_retriever(),\n",
+    "    chain_type_kwargs={\"prompt\": QA_CHAIN_PROMPT},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "There are different approaches to Task Decomposition for AI Agents such as Chain of thought (CoT) and Tree of Thoughts (ToT). CoT breaks down big tasks into multiple manageable tasks and generates multiple thoughts per step, while ToT explores multiple reasoning possibilities at each step. Task decomposition can be done by LLM with simple prompting or using task-specific instructions or human inputs."
+     ]
+    }
+   ],
+   "source": [
+    "question = \"What are the various approaches to Task Decomposition for AI Agents?\"\n",
+    "result = qa_chain({\"query\": question})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -363,9 +417,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.5"
+   "version": "3.9.16"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

docs/extras/integrations/llms/titan_takeoff.ipynb

@@ -17,7 +17,7 @@
    "source": [
     "## Installation\n",
     "\n",
-    "To get started with Iris Takeoff, all you need is to have docker and python installed on your local system. If you wish to use the server with gpu suport, then you will need to install docker with cuda support.\n",
+    "To get started with Iris Takeoff, all you need is to have docker and python installed on your local system. If you wish to use the server with gpu support, then you will need to install docker with cuda support.\n",
     "\n",
     "For Mac and Windows users, make sure you have the docker daemon running! You can check this by running docker ps in your terminal. To start the daemon, open the docker desktop app.\n",
     "\n",
@@ -157,7 +157,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.prompts import PromptTemplate\nfrom langchain.chains import LLMChain\n",
+    "from langchain.prompts import PromptTemplate\n",
+    "from langchain.chains import LLMChain\n",
     "\n",
     "llm = TitanTakeoff()\n",
     "\n",

docs/extras/integrations/memory/aws_dynamodb.ipynb

@@ -0,0 +1,371 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "91c6a7ef",
+   "metadata": {},
+   "source": [
+    "# AWS DynamoDB\n",
+    "\n",
+    ">[Amazon AWS DynamoDB](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/dynamodb/index.html) is a fully managed `NoSQL` database service that provides fast and predictable performance with seamless scalability.\n",
+    "\n",
+    "This notebook goes over how to use `DynamoDB` to store chat message history."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3f608be0",
+   "metadata": {},
+   "source": [
+    "First make sure you have correctly configured the [AWS CLI](https://docs.aws.amazon.com/cli/latest/userguide/cli-chap-configure.html). Then make sure you have installed `boto3`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3a7e89c2-4c55-4a66-91ec-9bf9a37467eb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install boto3"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "030d784f",
+   "metadata": {},
+   "source": [
+    "Next, create the `DynamoDB` Table where we will be storing messages:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "93ce1811",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0\n"
+     ]
+    }
+   ],
+   "source": [
+    "import boto3\n",
+    "\n",
+    "# Get the service resource.\n",
+    "dynamodb = boto3.resource(\"dynamodb\")\n",
+    "\n",
+    "# Create the DynamoDB table.\n",
+    "table = dynamodb.create_table(\n",
+    "    TableName=\"SessionTable\",\n",
+    "    KeySchema=[{\"AttributeName\": \"SessionId\", \"KeyType\": \"HASH\"}],\n",
+    "    AttributeDefinitions=[{\"AttributeName\": \"SessionId\", \"AttributeType\": \"S\"}],\n",
+    "    BillingMode=\"PAY_PER_REQUEST\",\n",
+    ")\n",
+    "\n",
+    "# Wait until the table exists.\n",
+    "table.meta.client.get_waiter(\"table_exists\").wait(TableName=\"SessionTable\")\n",
+    "\n",
+    "# Print out some data about the table.\n",
+    "print(table.item_count)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1a9b310b",
+   "metadata": {},
+   "source": [
+    "## DynamoDBChatMessageHistory"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "d15e3302",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.memory.chat_message_histories import DynamoDBChatMessageHistory\n",
+    "\n",
+    "history = DynamoDBChatMessageHistory(table_name=\"SessionTable\", session_id=\"0\")\n",
+    "\n",
+    "history.add_user_message(\"hi!\")\n",
+    "\n",
+    "history.add_ai_message(\"whats up?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "64fc465e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[HumanMessage(content='hi!', additional_kwargs={}, example=False),\n",
+       " AIMessage(content='whats up?', additional_kwargs={}, example=False),\n",
+       " HumanMessage(content='hi!', additional_kwargs={}, example=False),\n",
+       " AIMessage(content='whats up?', additional_kwargs={}, example=False)]"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "history.messages"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "955f1b15",
+   "metadata": {},
+   "source": [
+    "## DynamoDBChatMessageHistory with Custom Endpoint URL\n",
+    "\n",
+    "Sometimes it is useful to specify the URL to the AWS endpoint to connect to. For instance, when you are running locally against [Localstack](https://localstack.cloud/). For those cases you can specify the URL via the `endpoint_url` parameter in the constructor."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "225713c8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.memory.chat_message_histories import DynamoDBChatMessageHistory\n",
+    "\n",
+    "history = DynamoDBChatMessageHistory(\n",
+    "    table_name=\"SessionTable\",\n",
+    "    session_id=\"0\",\n",
+    "    endpoint_url=\"http://localhost.localstack.cloud:4566\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "97f8578a",
+   "metadata": {},
+   "source": [
+    "## DynamoDBChatMessageHistory With Different Keys Composite Keys\n",
+    "The default key for DynamoDBChatMessageHistory is ```{\"SessionId\": self.session_id}```, but you can modify this to match your table design.\n",
+    "\n",
+    "### Primary Key Name\n",
+    "You may modify the primary key by passing in a primary_key_name value in the constructor, resulting in the following:\n",
+    "```{self.primary_key_name: self.session_id}```\n",
+    "\n",
+    "### Composite Keys\n",
+    "When using an existing DynamoDB table, you may need to modify the key structure from the default of to something including a Sort Key. To do this you may use the ```key``` parameter.\n",
+    "\n",
+    "Passing a value for key will override the primary_key parameter, and the resulting key structure will be the passed value.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "088c037c",
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[HumanMessage(content='hello, composite dynamodb table!', additional_kwargs={}, example=False)]"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.memory.chat_message_histories import DynamoDBChatMessageHistory\n",
+    "\n",
+    "composite_table = dynamodb.create_table(\n",
+    "    TableName=\"CompositeTable\",\n",
+    "    KeySchema=[{\"AttributeName\": \"PK\", \"KeyType\": \"HASH\"}, {\"AttributeName\": \"SK\", \"KeyType\": \"RANGE\"}],\n",
+    "    AttributeDefinitions=[{\"AttributeName\": \"PK\", \"AttributeType\": \"S\"}, {\"AttributeName\": \"SK\", \"AttributeType\": \"S\"}],\n",
+    "    BillingMode=\"PAY_PER_REQUEST\",\n",
+    ")\n",
+    "\n",
+    "# Wait until the table exists.\n",
+    "composite_table.meta.client.get_waiter(\"table_exists\").wait(TableName=\"CompositeTable\")\n",
+    "\n",
+    "# Print out some data about the table.\n",
+    "print(composite_table.item_count)\n",
+    "\n",
+    "my_key = {\n",
+    "    \"PK\": \"session_id::0\",\n",
+    "    \"SK\":  \"langchain_history\",\n",
+    "}\n",
+    "\n",
+    "composite_key_history = DynamoDBChatMessageHistory(\n",
+    "    table_name=\"CompositeTable\",\n",
+    "    session_id=\"0\",\n",
+    "    endpoint_url=\"http://localhost.localstack.cloud:4566\",\n",
+    "    key=my_key,\n",
+    ")\n",
+    "\n",
+    "composite_key_history.add_user_message(\"hello, composite dynamodb table!\")\n",
+    "\n",
+    "composite_key_history.messages"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3b33c988",
+   "metadata": {},
+   "source": [
+    "## Agent with DynamoDB Memory"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "f92d9499",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.agents import Tool\n",
+    "from langchain.memory import ConversationBufferMemory\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.agents import initialize_agent\n",
+    "from langchain.agents import AgentType\n",
+    "from langchain.utilities import PythonREPL\n",
+    "from getpass import getpass\n",
+    "\n",
+    "message_history = DynamoDBChatMessageHistory(table_name=\"SessionTable\", session_id=\"1\")\n",
+    "memory = ConversationBufferMemory(\n",
+    "    memory_key=\"chat_history\", chat_memory=message_history, return_messages=True\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "1167eeba",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "python_repl = PythonREPL()\n",
+    "\n",
+    "# You can create the tool to pass to an agent\n",
+    "tools = [\n",
+    "    Tool(\n",
+    "        name=\"python_repl\",\n",
+    "        description=\"A Python shell. Use this to execute python commands. Input should be a valid python command. If you want to see the output of a value, you should print it out with `print(...)`.\",\n",
+    "        func=python_repl.run,\n",
+    "    )\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "fce085c5",
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "ValidationError",
+     "evalue": "1 validation error for ChatOpenAI\n__root__\n  Did not find openai_api_key, please add an environment variable `OPENAI_API_KEY` which contains it, or pass  `openai_api_key` as a named parameter. (type=value_error)",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mValidationError\u001b[0m                           Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[17], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m llm \u001b[38;5;241m=\u001b[39m \u001b[43mChatOpenAI\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtemperature\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m      2\u001b[0m agent_chain \u001b[38;5;241m=\u001b[39m initialize_agent(\n\u001b[1;32m      3\u001b[0m     tools,\n\u001b[1;32m      4\u001b[0m     llm,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m      7\u001b[0m     memory\u001b[38;5;241m=\u001b[39mmemory,\n\u001b[1;32m      8\u001b[0m )\n",
+      "File \u001b[0;32m~/Documents/projects/langchain/libs/langchain/langchain/load/serializable.py:74\u001b[0m, in \u001b[0;36mSerializable.__init__\u001b[0;34m(self, **kwargs)\u001b[0m\n\u001b[1;32m     73\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__init__\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m---> 74\u001b[0m     \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[38;5;21;43m__init__\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     75\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_lc_kwargs \u001b[38;5;241m=\u001b[39m kwargs\n",
+      "File \u001b[0;32m~/Documents/projects/langchain/.venv/lib/python3.9/site-packages/pydantic/main.py:341\u001b[0m, in \u001b[0;36mpydantic.main.BaseModel.__init__\u001b[0;34m()\u001b[0m\n",
+      "\u001b[0;31mValidationError\u001b[0m: 1 validation error for ChatOpenAI\n__root__\n  Did not find openai_api_key, please add an environment variable `OPENAI_API_KEY` which contains it, or pass  `openai_api_key` as a named parameter. (type=value_error)"
+     ]
+    }
+   ],
+   "source": [
+    "llm = ChatOpenAI(temperature=0)\n",
+    "agent_chain = initialize_agent(\n",
+    "    tools,\n",
+    "    llm,\n",
+    "    agent=AgentType.CHAT_CONVERSATIONAL_REACT_DESCRIPTION,\n",
+    "    verbose=True,\n",
+    "    memory=memory,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "952a3103",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agent_chain.run(input=\"Hello!\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "54c4aaf4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agent_chain.run(input=\"Who owns Twitter?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f9013118",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agent_chain.run(input=\"My name is Bob.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "405e5315",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agent_chain.run(input=\"Who am I?\")\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/extras/integrations/memory/cassandra_chat_message_history.ipynb

@@ -5,15 +5,24 @@
    "id": "90cd3ded",
    "metadata": {},
    "source": [
-    "# Cassandra Chat Message History\n",
+    "# Cassandra \n",
     "\n",
-    ">[Apache Cassandra®](https://cassandra.apache.org) is a NoSQL, row-oriented, highly scalable and highly available database, well suited for storing large amounts of data.\n",
+    ">[Apache Cassandra®](https://cassandra.apache.org) is a `NoSQL`, row-oriented, highly scalable and highly available database, well suited for storing large amounts of data.\n",
     "\n",
-    "Cassandra is a good choice for storing chat message history because it is easy to scale and can handle a large number of writes.\n",
+    ">`Cassandra` is a good choice for storing chat message history because it is easy to scale and can handle a large number of writes.\n",
     "\n",
     "This notebook goes over how to use Cassandra to store chat message history.\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f507f58b-bf22-4a48-8daf-68d869bcd1ba",
+   "metadata": {},
+   "source": [
+    "## Setting up\n",
     "\n",
-    "To run this notebook you need either a running Cassandra cluster or a DataStax Astra DB instance running in the cloud (you can get one for free at [datastax.com](https://astra.datastax.com)). Check [cassio.org](https://cassio.org/start_here/) for more information."
+    "To run this notebook you need either a running `Cassandra` cluster or a `DataStax Astra DB` instance running in the cloud (you can get one for free at [datastax.com](https://astra.datastax.com)). Check [cassio.org](https://cassio.org/start_here/) for more information."
    ]
   },
   {
@@ -31,7 +40,7 @@
    "id": "e3d97b65",
    "metadata": {},
    "source": [
-    "### Please provide database connection parameters and secrets:"
+    "### Set up the database connection parameters and secrets"
    ]
   },
   {
@@ -63,7 +72,7 @@
    "id": "55860b2d",
    "metadata": {},
    "source": [
-    "#### depending on whether local or cloud-based Astra DB, create the corresponding database connection \"Session\" object"
+    "Depending on whether local or cloud-based Astra DB, create the corresponding database connection \"Session\" object."
    ]
   },
   {
@@ -105,7 +114,7 @@
    "id": "36c163e8",
    "metadata": {},
    "source": [
-    "### Creation and usage of the Chat Message History"
+    "## Example"
    ]
   },
   {

docs/extras/integrations/memory/dynamodb_chat_message_history.ipynb

@@ -1,352 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "id": "91c6a7ef",
-      "metadata": {},
-      "source": [
-        "# Dynamodb Chat Message History\n",
-        "\n",
-        "This notebook goes over how to use Dynamodb to store chat message history."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "3f608be0",
-      "metadata": {},
-      "source": [
-        "First make sure you have correctly configured the [AWS CLI](https://docs.aws.amazon.com/cli/latest/userguide/cli-chap-configure.html). Then make sure you have installed boto3."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "030d784f",
-      "metadata": {},
-      "source": [
-        "Next, create the DynamoDB Table where we will be storing messages:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 10,
-      "id": "93ce1811",
-      "metadata": {},
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "0\n"
-          ]
-        }
-      ],
-      "source": [
-        "import boto3\n",
-        "\n",
-        "# Get the service resource.\n",
-        "dynamodb = boto3.resource(\"dynamodb\")\n",
-        "\n",
-        "# Create the DynamoDB table.\n",
-        "table = dynamodb.create_table(\n",
-        "    TableName=\"SessionTable\",\n",
-        "    KeySchema=[{\"AttributeName\": \"SessionId\", \"KeyType\": \"HASH\"}],\n",
-        "    AttributeDefinitions=[{\"AttributeName\": \"SessionId\", \"AttributeType\": \"S\"}],\n",
-        "    BillingMode=\"PAY_PER_REQUEST\",\n",
-        ")\n",
-        "\n",
-        "# Wait until the table exists.\n",
-        "table.meta.client.get_waiter(\"table_exists\").wait(TableName=\"SessionTable\")\n",
-        "\n",
-        "# Print out some data about the table.\n",
-        "print(table.item_count)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "1a9b310b",
-      "metadata": {},
-      "source": [
-        "## DynamoDBChatMessageHistory"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 11,
-      "id": "d15e3302",
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from langchain.memory.chat_message_histories import DynamoDBChatMessageHistory\n",
-        "\n",
-        "history = DynamoDBChatMessageHistory(table_name=\"SessionTable\", session_id=\"0\")\n",
-        "\n",
-        "history.add_user_message(\"hi!\")\n",
-        "\n",
-        "history.add_ai_message(\"whats up?\")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 12,
-      "id": "64fc465e",
-      "metadata": {},
-      "outputs": [
-        {
-          "data": {
-            "text/plain": "[HumanMessage(content='hi!', additional_kwargs={}, example=False),\n AIMessage(content='whats up?', additional_kwargs={}, example=False),\n HumanMessage(content='hi!', additional_kwargs={}, example=False),\n AIMessage(content='whats up?', additional_kwargs={}, example=False)]"
-          },
-          "execution_count": 12,
-          "metadata": {},
-          "output_type": "execute_result"
-        }
-      ],
-      "source": [
-        "history.messages"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "955f1b15",
-      "metadata": {},
-      "source": [
-        "## DynamoDBChatMessageHistory with Custom Endpoint URL\n",
-        "\n",
-        "Sometimes it is useful to specify the URL to the AWS endpoint to connect to. For instance, when you are running locally against [Localstack](https://localstack.cloud/). For those cases you can specify the URL via the `endpoint_url` parameter in the constructor."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 13,
-      "id": "225713c8",
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from langchain.memory.chat_message_histories import DynamoDBChatMessageHistory\n",
-        "\n",
-        "history = DynamoDBChatMessageHistory(\n",
-        "    table_name=\"SessionTable\",\n",
-        "    session_id=\"0\",\n",
-        "    endpoint_url=\"http://localhost.localstack.cloud:4566\",\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "## DynamoDBChatMessageHistory With Different Keys Composite Keys\n",
-        "The default key for DynamoDBChatMessageHistory is ```{\"SessionId\": self.session_id}```, but you can modify this to match your table design.\n",
-        "\n",
-        "### Primary Key Name\n",
-        "You may modify the primary key by passing in a primary_key_name value in the constructor, resulting in the following:\n",
-        "```{self.primary_key_name: self.session_id}```\n",
-        "\n",
-        "### Composite Keys\n",
-        "When using an existing DynamoDB table, you may need to modify the key structure from the default of to something including a Sort Key. To do this you may use the ```key``` parameter.\n",
-        "\n",
-        "Passing a value for key will override the primary_key parameter, and the resulting key structure will be the passed value.\n"
-      ],
-      "metadata": {
-        "collapsed": false
-      },
-      "id": "c9bc0693"
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 14,
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "0\n"
-          ]
-        },
-        {
-          "data": {
-            "text/plain": "[HumanMessage(content='hello, composite dynamodb table!', additional_kwargs={}, example=False)]"
-          },
-          "execution_count": 14,
-          "metadata": {},
-          "output_type": "execute_result"
-        }
-      ],
-      "source": [
-        "from langchain.memory.chat_message_histories import DynamoDBChatMessageHistory\n",
-        "\n",
-        "composite_table = dynamodb.create_table(\n",
-        "    TableName=\"CompositeTable\",\n",
-        "    KeySchema=[{\"AttributeName\": \"PK\", \"KeyType\": \"HASH\"}, {\"AttributeName\": \"SK\", \"KeyType\": \"RANGE\"}],\n",
-        "    AttributeDefinitions=[{\"AttributeName\": \"PK\", \"AttributeType\": \"S\"}, {\"AttributeName\": \"SK\", \"AttributeType\": \"S\"}],\n",
-        "    BillingMode=\"PAY_PER_REQUEST\",\n",
-        ")\n",
-        "\n",
-        "# Wait until the table exists.\n",
-        "composite_table.meta.client.get_waiter(\"table_exists\").wait(TableName=\"CompositeTable\")\n",
-        "\n",
-        "# Print out some data about the table.\n",
-        "print(composite_table.item_count)\n",
-        "\n",
-        "my_key = {\n",
-        "    \"PK\": \"session_id::0\",\n",
-        "    \"SK\":  \"langchain_history\",\n",
-        "}\n",
-        "\n",
-        "composite_key_history = DynamoDBChatMessageHistory(\n",
-        "    table_name=\"CompositeTable\",\n",
-        "    session_id=\"0\",\n",
-        "    endpoint_url=\"http://localhost.localstack.cloud:4566\",\n",
-        "    key=my_key,\n",
-        ")\n",
-        "\n",
-        "composite_key_history.add_user_message(\"hello, composite dynamodb table!\")\n",
-        "\n",
-        "composite_key_history.messages"
-      ],
-      "metadata": {
-        "collapsed": false
-      },
-      "id": "a7fa0331"
-    },
-    {
-      "attachments": {},
-      "cell_type": "markdown",
-      "id": "3b33c988",
-      "metadata": {},
-      "source": [
-        "## Agent with DynamoDB Memory"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 15,
-      "id": "f92d9499",
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from langchain.agents import Tool\n",
-        "from langchain.memory import ConversationBufferMemory\n",
-        "from langchain.chat_models import ChatOpenAI\n",
-        "from langchain.agents import initialize_agent\n",
-        "from langchain.agents import AgentType\n",
-        "from langchain.utilities import PythonREPL\n",
-        "from getpass import getpass\n",
-        "\n",
-        "message_history = DynamoDBChatMessageHistory(table_name=\"SessionTable\", session_id=\"1\")\n",
-        "memory = ConversationBufferMemory(\n",
-        "    memory_key=\"chat_history\", chat_memory=message_history, return_messages=True\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 16,
-      "id": "1167eeba",
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "python_repl = PythonREPL()\n",
-        "\n",
-        "# You can create the tool to pass to an agent\n",
-        "tools = [\n",
-        "    Tool(\n",
-        "        name=\"python_repl\",\n",
-        "        description=\"A Python shell. Use this to execute python commands. Input should be a valid python command. If you want to see the output of a value, you should print it out with `print(...)`.\",\n",
-        "        func=python_repl.run,\n",
-        "    )\n",
-        "]"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 17,
-      "id": "fce085c5",
-      "metadata": {},
-      "outputs": [
-        {
-          "ename": "ValidationError",
-          "evalue": "1 validation error for ChatOpenAI\n__root__\n  Did not find openai_api_key, please add an environment variable `OPENAI_API_KEY` which contains it, or pass  `openai_api_key` as a named parameter. (type=value_error)",
-          "output_type": "error",
-          "traceback": [
-            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-            "\u001b[0;31mValidationError\u001b[0m                           Traceback (most recent call last)",
-            "Cell \u001b[0;32mIn[17], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m llm \u001b[38;5;241m=\u001b[39m \u001b[43mChatOpenAI\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtemperature\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m      2\u001b[0m agent_chain \u001b[38;5;241m=\u001b[39m initialize_agent(\n\u001b[1;32m      3\u001b[0m     tools,\n\u001b[1;32m      4\u001b[0m     llm,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m      7\u001b[0m     memory\u001b[38;5;241m=\u001b[39mmemory,\n\u001b[1;32m      8\u001b[0m )\n",
-            "File \u001b[0;32m~/Documents/projects/langchain/libs/langchain/langchain/load/serializable.py:74\u001b[0m, in \u001b[0;36mSerializable.__init__\u001b[0;34m(self, **kwargs)\u001b[0m\n\u001b[1;32m     73\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__init__\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m---> 74\u001b[0m     \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[38;5;21;43m__init__\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     75\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_lc_kwargs \u001b[38;5;241m=\u001b[39m kwargs\n",
-            "File \u001b[0;32m~/Documents/projects/langchain/.venv/lib/python3.9/site-packages/pydantic/main.py:341\u001b[0m, in \u001b[0;36mpydantic.main.BaseModel.__init__\u001b[0;34m()\u001b[0m\n",
-            "\u001b[0;31mValidationError\u001b[0m: 1 validation error for ChatOpenAI\n__root__\n  Did not find openai_api_key, please add an environment variable `OPENAI_API_KEY` which contains it, or pass  `openai_api_key` as a named parameter. (type=value_error)"
-          ]
-        }
-      ],
-      "source": [
-        "llm = ChatOpenAI(temperature=0)\n",
-        "agent_chain = initialize_agent(\n",
-        "    tools,\n",
-        "    llm,\n",
-        "    agent=AgentType.CHAT_CONVERSATIONAL_REACT_DESCRIPTION,\n",
-        "    verbose=True,\n",
-        "    memory=memory,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "id": "952a3103",
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "agent_chain.run(input=\"Hello!\")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "id": "54c4aaf4",
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "agent_chain.run(input=\"Who owns Twitter?\")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "id": "f9013118",
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "agent_chain.run(input=\"My name is Bob.\")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "id": "405e5315",
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "agent_chain.run(input=\"Who am I?\")\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": "3.11.3"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 5
-}

docs/extras/integrations/memory/momento_chat_message_history.ipynb

@@ -5,9 +5,13 @@
    "id": "91c6a7ef",
    "metadata": {},
    "source": [
-    "# Momento Chat Message History\n",
+    "# Momento Cache\n",
     "\n",
-    "This notebook goes over how to use [Momento Cache](https://gomomento.com) to store chat message history using the `MomentoChatMessageHistory` class. See the Momento [docs](https://docs.momentohq.com/getting-started) for more detail on how to get set up with Momento.\n",
+    ">[Momento Cache](https://docs.momentohq.com/) is the world's first truly serverless caching service. It provides instant elasticity, scale-to-zero \n",
+    "> capability, and blazing-fast performance.  \n",
+    "\n",
+    "\n",
+    "This notebook goes over how to use [Momento Cache](https://www.gomomento.com/services/cache) to store chat message history using the `MomentoChatMessageHistory` class. See the Momento [docs](https://docs.momentohq.com/getting-started) for more detail on how to get set up with Momento.\n",
     "\n",
     "Note that, by default we will create a cache if one with the given name doesn't already exist.\n",
     "\n",
@@ -78,7 +82,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/extras/integrations/memory/mongodb_chat_message_history.ipynb

@@ -1,18 +1,35 @@
 {
  "cells": [
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "91c6a7ef",
    "metadata": {},
    "source": [
-    "# Mongodb Chat Message History\n",
+    "# MongodDB\n",
     "\n",
-    "This notebook goes over how to use Mongodb to store chat message history.\n",
+    ">`MongoDB` is a source-available cross-platform document-oriented database program. Classified as a NoSQL database program, `MongoDB` uses `JSON`-like documents with optional schemas.\n",
+    ">\n",
+    ">`MongoDB` is developed by MongoDB Inc. and licensed under the Server Side Public License (SSPL). - [Wikipedia](https://en.wikipedia.org/wiki/MongoDB)\n",
     "\n",
-    "MongoDB is a source-available cross-platform document-oriented database program. Classified as a NoSQL database program, MongoDB uses JSON-like documents with optional schemas.\n",
-    "\n",
-    "MongoDB is developed by MongoDB Inc. and licensed under the Server Side Public License (SSPL). - [Wikipedia](https://en.wikipedia.org/wiki/MongoDB)"
+    "This notebook goes over how to use Mongodb to store chat message history.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2d6ed3c8-b70a-498c-bc9e-41b91797d3b7",
+   "metadata": {},
+   "source": [
+    "## Setting up"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5a7f3b3f-d9b8-4577-a7ef-bdd8ecaedb70",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install pymongo"
    ]
   },
   {
@@ -26,6 +43,14 @@
     "connection_string = \"mongodb://mongo_user:password123@mongo:27017\""
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "a8e63850-3e14-46fe-a59e-be6d6bf8fe61",
+   "metadata": {},
+   "source": [
+    "## Example"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 4,
@@ -83,7 +108,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/extras/integrations/memory/motorhead_memory.ipynb

@@ -4,13 +4,29 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Motörhead Memory\n",
-    "[Motörhead](https://github.com/getmetal/motorhead) is a memory server implemented in Rust. It automatically handles incremental summarization in the background and allows for stateless applications.\n",
+    "# Motörhead\n",
+    "\n",
+    ">[Motörhead](https://github.com/getmetal/motorhead) is a memory server implemented in Rust. It automatically handles incremental summarization in the background and allows for stateless applications.\n",
     "\n",
     "## Setup\n",
     "\n",
-    "See instructions at [Motörhead](https://github.com/getmetal/motorhead) for running the server locally.\n",
-    "\n"
+    "See instructions at [Motörhead](https://github.com/getmetal/motorhead) for running the server locally."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.memory.motorhead_memory import MotorheadMemory"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Example"
    ]
   },
   {
@@ -19,7 +35,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.memory.motorhead_memory import MotorheadMemory\n",
     "from langchain.llms import OpenAI\nfrom langchain.chains import LLMChain\nfrom langchain.prompts import PromptTemplate\n",
     "\n",
     "template = \"\"\"You are a chatbot having a conversation with a human.\n",

docs/extras/integrations/memory/motorhead_memory_managed.ipynb

@@ -1,198 +0,0 @@
-{
- "cells": [
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Motörhead Memory (Managed)\n",
-    "[Motörhead](https://github.com/getmetal/motorhead) is a memory server implemented in Rust. It automatically handles incremental summarization in the background and allows for stateless applications.\n",
-    "\n",
-    "## Setup\n",
-    "\n",
-    "See instructions at [Motörhead](https://docs.getmetal.io/motorhead/introduction) for running the managed version of Motorhead. You can retrieve your `api_key` and `client_id` by creating an account on [Metal](https://getmetal.io).\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.memory.motorhead_memory import MotorheadMemory\n",
-    "from langchain.llms import OpenAI\nfrom langchain.chains import LLMChain\nfrom langchain.prompts import PromptTemplate\n",
-    "\n",
-    "template = \"\"\"You are a chatbot having a conversation with a human.\n",
-    "\n",
-    "{chat_history}\n",
-    "Human: {human_input}\n",
-    "AI:\"\"\"\n",
-    "\n",
-    "prompt = PromptTemplate(\n",
-    "    input_variables=[\"chat_history\", \"human_input\"], \n",
-    "    template=template\n",
-    ")\n",
-    "memory = MotorheadMemory(\n",
-    "    api_key=\"YOUR_API_KEY\",\n",
-    "    client_id=\"YOUR_CLIENT_ID\"\n",
-    "    session_id=\"testing-1\",\n",
-    "    memory_key=\"chat_history\"\n",
-    ")\n",
-    "\n",
-    "await memory.init();  # loads previous state from Motörhead 🤘\n",
-    "\n",
-    "llm_chain = LLMChain(\n",
-    "    llm=OpenAI(), \n",
-    "    prompt=prompt, \n",
-    "    verbose=True, \n",
-    "    memory=memory,\n",
-    ")\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
-      "Prompt after formatting:\n",
-      "\u001b[32;1m\u001b[1;3mYou are a chatbot having a conversation with a human.\n",
-      "\n",
-      "\n",
-      "Human: hi im bob\n",
-      "AI:\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "' Hi Bob, nice to meet you! How are you doing today?'"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "llm_chain.run(\"hi im bob\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
-      "Prompt after formatting:\n",
-      "\u001b[32;1m\u001b[1;3mYou are a chatbot having a conversation with a human.\n",
-      "\n",
-      "Human: hi im bob\n",
-      "AI:  Hi Bob, nice to meet you! How are you doing today?\n",
-      "Human: whats my name?\n",
-      "AI:\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "' You said your name is Bob. Is that correct?'"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "llm_chain.run(\"whats my name?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
-      "Prompt after formatting:\n",
-      "\u001b[32;1m\u001b[1;3mYou are a chatbot having a conversation with a human.\n",
-      "\n",
-      "Human: hi im bob\n",
-      "AI:  Hi Bob, nice to meet you! How are you doing today?\n",
-      "Human: whats my name?\n",
-      "AI:  You said your name is Bob. Is that correct?\n",
-      "Human: whats for dinner?\n",
-      "AI:\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "\"  I'm sorry, I'm not sure what you're asking. Could you please rephrase your question?\""
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "llm_chain.run(\"whats for dinner?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.9.1"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

docs/extras/integrations/memory/postgres_chat_message_history.ipynb

@@ -1,12 +1,13 @@
 {
  "cells": [
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "91c6a7ef",
    "metadata": {},
    "source": [
-    "# Postgres Chat Message History\n",
+    "# Postgres\n",
+    "\n",
+    ">[PostgreSQL](https://en.wikipedia.org/wiki/PostgreSQL) also known as `Postgres`, is a free and open-source relational database management system (RDBMS) emphasizing extensibility and SQL compliance.\n",
     "\n",
     "This notebook goes over how to use Postgres to store chat message history."
    ]
@@ -57,7 +58,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.2"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/extras/integrations/memory/redis_chat_message_history.ipynb

@@ -5,9 +5,11 @@
    "id": "91c6a7ef",
    "metadata": {},
    "source": [
-    "# Redis Chat Message History\n",
+    "# Redis\n",
     "\n",
-    "This notebook goes over how to use Redis to store chat message history."
+    ">[Redis (Remote Dictionary Server)](https://en.wikipedia.org/wiki/Redis) is an open-source in-memory storage, used as a distributed, in-memory key–value database, cache and message broker, with optional durability. Because it holds all data in memory and because of its design, `Redis` offers low-latency reads and writes, making it particularly suitable for use cases that require a cache. Redis is the most popular NoSQL database, and one of the most popular databases overall.\n",
+    "\n",
+    "This notebook goes over how to use `Redis` to store chat message history."
    ]
   },
   {
@@ -73,7 +75,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/extras/integrations/memory/rockset_chat_message_history.ipynb

@@ -1,17 +1,47 @@
 {
  "cells": [
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Rockset Chat Message History\n",
+    "# Rockset\n",
     "\n",
-    "This notebook goes over how to use [Rockset](https://rockset.com/docs) to store chat message history. \n",
+    ">[Rockset](https://rockset.com/product/) is a real-time analytics database service for serving low latency, high concurrency analytical queries at scale. It builds a Converged Index™ on structured and semi-structured data with an efficient store for vector embeddings. Its support for running SQL on schemaless data makes it a perfect choice for running vector search with metadata filters. \n",
     "\n",
+    "\n",
+    "This notebook goes over how to use [Rockset](https://rockset.com/docs) to store chat message history. \n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setting up"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install rockset"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
     "To begin, with get your API key from the [Rockset console](https://console.rockset.com/apikeys). Find your API region for the Rockset [API reference](https://rockset.com/docs/rest-api#introduction)."
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Example"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -40,7 +70,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -57,11 +86,24 @@
   }
  ],
  "metadata": {
-  "language_info": {
-   "name": "python"
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
   },
-  "orig_nbformat": 4
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
+  }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

docs/extras/integrations/memory/sql_chat_message_history.ipynb

@@ -2,36 +2,58 @@
  "cells": [
   {
    "cell_type": "markdown",
+   "id": "f22eab3f84cbeb37",
+   "metadata": {},
    "source": [
-    "# SQL Chat Message History\n",
+    "# SQL (SQLAlchemy)\n",
     "\n",
-    "This notebook goes over a **SQLChatMessageHistory** class that allows to store chat history in any database supported by SQLAlchemy.\n",
+    ">[Structured Query Language (SQL)](https://en.wikipedia.org/wiki/SQL) is a domain-specific language used in programming and designed for managing data held in a relational database management system (RDBMS), or for stream processing in a relational data stream management system (RDSMS). It is particularly useful in handling structured data, i.e., data incorporating relations among entities and variables.\n",
     "\n",
-    "Please note that to use it with databases other than SQLite, you will need to install the corresponding database driver."
-   ],
-   "metadata": {
-    "collapsed": false
-   },
-   "id": "f22eab3f84cbeb37"
+    ">[SQLAlchemy](https://github.com/sqlalchemy/sqlalchemy) is an open-source `SQL` toolkit and object-relational mapper (ORM) for the Python programming language released under the MIT License.\n",
+    "\n",
+    "This notebook goes over a `SQLChatMessageHistory` class that allows to store chat history in any database supported by `SQLAlchemy`.\n",
+    "\n",
+    "Please note that to use it with databases other than `SQLite`, you will need to install the corresponding database driver."
+   ]
   },
   {
    "cell_type": "markdown",
+   "id": "f8f2830ee9ca1e01",
+   "metadata": {},
    "source": [
-    "### Basic Usage\n",
+    "## Basic Usage\n",
     "\n",
     "To use the storage you need to provide only 2 things:\n",
     "\n",
     "1. Session Id - a unique identifier of the session, like user name, email, chat id etc.\n",
-    "2. Connection string - a string that specifies the database connection. It will be passed to SQLAlchemy create_engine function."
-   ],
-   "metadata": {
-    "collapsed": false
-   },
-   "id": "f8f2830ee9ca1e01"
+    "2. Connection string - a string that specifies the database connection. It will be passed to SQLAlchemy create_engine function.\n",
+    "3. Install `SQLAlchemy` python package."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ab016290-3823-4e1b-9610-ae9a1b71cb07",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install SQLAlchemy"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 1,
+   "id": "4576e914a866fb40",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-08-28T10:04:38.077748Z",
+     "start_time": "2023-08-28T10:04:36.105894Z"
+    },
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
    "outputs": [],
    "source": [
     "from langchain.memory.chat_message_histories import SQLChatMessageHistory\n",
@@ -43,23 +65,29 @@
     "\n",
     "chat_message_history.add_user_message('Hello')\n",
     "chat_message_history.add_ai_message('Hi')"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "ExecuteTime": {
-     "end_time": "2023-08-28T10:04:38.077748Z",
-     "start_time": "2023-08-28T10:04:36.105894Z"
-    }
-   },
-   "id": "4576e914a866fb40"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 2,
+   "id": "b476688cbb32ba90",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-08-28T10:04:38.929396Z",
+     "start_time": "2023-08-28T10:04:38.915727Z"
+    },
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
    "outputs": [
     {
      "data": {
-      "text/plain": "[HumanMessage(content='Hello', additional_kwargs={}, example=False),\n AIMessage(content='Hi', additional_kwargs={}, example=False)]"
+      "text/plain": [
+       "[HumanMessage(content='Hello', additional_kwargs={}, example=False),\n",
+       " AIMessage(content='Hi', additional_kwargs={}, example=False)]"
+      ]
      },
      "execution_count": 2,
      "metadata": {},
@@ -68,35 +96,36 @@
    ],
    "source": [
     "chat_message_history.messages"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "ExecuteTime": {
-     "end_time": "2023-08-28T10:04:38.929396Z",
-     "start_time": "2023-08-28T10:04:38.915727Z"
-    }
-   },
-   "id": "b476688cbb32ba90"
+   ]
   },
   {
    "cell_type": "markdown",
+   "id": "2e5337719d5614fd",
+   "metadata": {},
    "source": [
-    "### Custom Storage Format\n",
+    "## Custom Storage Format\n",
     "\n",
     "By default, only the session id and message dictionary are stored in the table.\n",
     "\n",
     "However, sometimes you might want to store some additional information, like message date, author, language etc.\n",
     "\n",
     "To do that, you can create a custom message converter, by implementing **BaseMessageConverter** interface."
-   ],
-   "metadata": {
-    "collapsed": false
-   },
-   "id": "2e5337719d5614fd"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 3,
+   "id": "fdfde84c07d071bb",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-08-28T10:04:41.510498Z",
+     "start_time": "2023-08-28T10:04:41.494912Z"
+    },
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
    "outputs": [],
    "source": [
     "from datetime import datetime\n",
@@ -165,23 +194,29 @@
     "\n",
     "chat_message_history.add_user_message('Hello')\n",
     "chat_message_history.add_ai_message('Hi')"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "ExecuteTime": {
-     "end_time": "2023-08-28T10:04:41.510498Z",
-     "start_time": "2023-08-28T10:04:41.494912Z"
-    }
-   },
-   "id": "fdfde84c07d071bb"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 4,
+   "id": "4a6a54d8a9e2856f",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-08-28T10:04:43.497990Z",
+     "start_time": "2023-08-28T10:04:43.492517Z"
+    },
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
    "outputs": [
     {
      "data": {
-      "text/plain": "[HumanMessage(content='Hello', additional_kwargs={}, example=False),\n AIMessage(content='Hi', additional_kwargs={}, example=False)]"
+      "text/plain": [
+       "[HumanMessage(content='Hello', additional_kwargs={}, example=False),\n",
+       " AIMessage(content='Hi', additional_kwargs={}, example=False)]"
+      ]
      },
      "execution_count": 4,
      "metadata": {},
@@ -190,44 +225,34 @@
    ],
    "source": [
     "chat_message_history.messages"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "ExecuteTime": {
-     "end_time": "2023-08-28T10:04:43.497990Z",
-     "start_time": "2023-08-28T10:04:43.492517Z"
-    }
-   },
-   "id": "4a6a54d8a9e2856f"
+   ]
   },
   {
    "cell_type": "markdown",
+   "id": "622aded629a1adeb",
+   "metadata": {},
    "source": [
     "You also might want to change the name of session_id column. In this case you'll need to specify `session_id_field_name` parameter."
-   ],
-   "metadata": {
-    "collapsed": false
-   },
-   "id": "622aded629a1adeb"
+   ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
     "name": "ipython",
-    "version": 2
+    "version": 3
    },
    "file_extension": ".py",
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython2",
-   "version": "2.7.6"
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/extras/integrations/memory/sqlite.ipynb

@@ -2,19 +2,32 @@
  "cells": [
   {
    "cell_type": "markdown",
+   "id": "d464a12a",
    "metadata": {
     "id": "eg0Hwptz9g5q"
    },
    "source": [
-    "# Entity Memory with SQLite storage\n",
+    "# SQLite\n",
     "\n",
-    "In this walkthrough we'll create a simple conversation chain which uses ConversationEntityMemory backed by a SqliteEntityStore."
-   ],
-   "id": "d464a12a"
+    ">[SQLite](https://en.wikipedia.org/wiki/SQLite) is a database engine written in the C programming language. It is not a standalone app; rather, it is a library that software developers embed in their apps. As such, it belongs to the family of embedded databases. It is the most widely deployed database engine, as it is used by several of the top web browsers, operating systems, mobile phones, and other embedded systems.\n",
+    "\n",
+    "In this walkthrough we'll create a simple conversation chain which uses `ConversationEntityMemory` backed by a `SqliteEntityStore`."
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 1,
+   "id": "d0a07a30-028f-4e16-8b11-45b2416f7b0f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#!pip install sqlite3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "db59b901",
    "metadata": {
     "id": "2wUMSUoF8ffn"
    },
@@ -25,12 +38,12 @@
     "from langchain.memory import ConversationEntityMemory\n",
     "from langchain.memory.entity import SQLiteEntityStore\n",
     "from langchain.memory.prompt import ENTITY_MEMORY_CONVERSATION_TEMPLATE"
-   ],
-   "id": "db59b901"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 2,
+   "id": "ca6dee29",
    "metadata": {
     "id": "8TpJZti99gxV"
    },
@@ -45,22 +58,22 @@
     "    memory=memory,\n",
     "    verbose=True,\n",
     ")"
-   ],
-   "id": "ca6dee29"
+   ]
   },
   {
    "cell_type": "markdown",
+   "id": "f9b4c3a0",
    "metadata": {
     "id": "HEAHG1L79ca1"
    },
    "source": [
     "Notice the usage of `EntitySqliteStore` as parameter to `entity_store` on the `memory` property."
-   ],
-   "id": "f9b4c3a0"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 3,
+   "id": "297e78a6",
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -111,12 +124,12 @@
    ],
    "source": [
     "conversation.run(\"Deven & Sam are working on a hackathon project\")"
-   ],
-   "id": "297e78a6"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 4,
+   "id": "7e71f1dc",
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -139,12 +152,12 @@
    ],
    "source": [
     "conversation.memory.entity_store.get(\"Deven\")"
-   ],
-   "id": "7e71f1dc"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 5,
+   "id": "316f2e8d",
    "metadata": {},
    "outputs": [
     {
@@ -160,16 +173,15 @@
    ],
    "source": [
     "conversation.memory.entity_store.get(\"Sam\")"
-   ],
-   "id": "316f2e8d"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "b85f8427",
    "metadata": {},
    "outputs": [],
-   "source": [],
-   "id": "b85f8427"
+   "source": []
   }
  ],
  "metadata": {
@@ -177,9 +189,9 @@
    "provenance": []
   },
   "kernelspec": {
-   "display_name": "venv",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
-   "name": "venv"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -191,9 +203,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,
  "nbformat_minor": 5
-}
+}

docs/extras/integrations/memory/streamlit_chat_message_history.ipynb

@@ -5,13 +5,17 @@
    "id": "91c6a7ef",
    "metadata": {},
    "source": [
-    "# Streamlit Chat Message History\n",
+    "# Streamlit\n",
     "\n",
-    "This notebook goes over how to store and use chat message history in a Streamlit app. StreamlitChatMessageHistory will store messages in\n",
+    ">[Streamlit](https://docs.streamlit.io/) is an open-source Python library that makes it easy to create and share beautiful, \n",
+    "custom web apps for machine learning and data science.\n",
+    "\n",
+    "\n",
+    "This notebook goes over how to store and use chat message history in a `Streamlit` app. `StreamlitChatMessageHistory` will store messages in\n",
     "[Streamlit session state](https://docs.streamlit.io/library/api-reference/session-state)\n",
     "at the specified `key=`. The default key is `\"langchain_messages\"`.\n",
     "\n",
-    "- Note, StreamlitChatMessageHistory only works when run in a Streamlit app.\n",
+    "- Note, `StreamlitChatMessageHistory` only works when run in a Streamlit app.\n",
     "- You may also be interested in [StreamlitCallbackHandler](/docs/integrations/callbacks/streamlit) for LangChain.\n",
     "- For more on Streamlit check out their\n",
     "[getting started documentation](https://docs.streamlit.io/library/get-started).\n",
@@ -50,7 +54,7 @@
    "id": "b60dc735",
    "metadata": {},
    "source": [
-    "You can integrate StreamlitChatMessageHistory into ConversationBufferMemory and chains or agents as usual. The history will be persisted across re-runs of the Streamlit app within a given user session. A given StreamlitChatMessageHistory will NOT be persisted or shared across user sessions."
+    "You can integrate `StreamlitChatMessageHistory` into `ConversationBufferMemory` and chains or agents as usual. The history will be persisted across re-runs of the Streamlit app within a given user session. A given `StreamlitChatMessageHistory` will NOT be persisted or shared across user sessions."
    ]
   },
   {
@@ -132,9 +136,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "poetry-venv",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
-   "name": "poetry-venv"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -146,7 +150,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/extras/integrations/memory/xata_chat_message_history.ipynb

@@ -4,9 +4,9 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Xata chat memory\n",
+    "# Xata\n",
     "\n",
-    "[Xata](https://xata.io) is a serverless data platform, based on PostgreSQL and Elasticsearch. It provides a Python SDK for interacting with your database, and a UI for managing your data. With the `XataChatMessageHistory` class, you can use Xata databases for longer-term persistence of chat sessions.\n",
+    ">[Xata](https://xata.io) is a serverless data platform, based on `PostgreSQL` and `Elasticsearch`. It provides a Python SDK for interacting with your database, and a UI for managing your data. With the `XataChatMessageHistory` class, you can use Xata databases for longer-term persistence of chat sessions.\n",
     "\n",
     "This notebook covers:\n",
     "\n",
@@ -318,7 +318,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/extras/integrations/memory/zep_memory.ipynb

@@ -1,26 +1,14 @@
 {
  "cells": [
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Zep Memory\n",
+    "# Zep\n",
     "\n",
-    "## REACT Agent Chat Message History with Zep - A long-term memory store for LLM applications.\n",
-    "\n",
-    "This notebook demonstrates how to use the [Zep Long-term Memory Store](https://docs.getzep.com/) as memory for your chatbot.\n",
-    "\n",
-    "We'll demonstrate:\n",
-    "\n",
-    "1. Adding conversation history to the Zep memory store.\n",
-    "2. Running an agent and having message automatically added to the store.\n",
-    "3. Viewing the enriched messages.\n",
-    "4. Vector search over the conversation history.\n",
-    "\n",
-    "### More on Zep:\n",
-    "\n",
-    "Zep stores, summarizes, embeds, indexes, and enriches conversational AI chat histories, and exposes them via simple, low-latency APIs.\n",
+    ">[Zep](https://docs.getzep.com/) is a long-term memory store for LLM applications.\n",
+    ">\n",
+    ">`Zep` stores, summarizes, embeds, indexes, and enriches conversational AI chat histories, and exposes them via simple, low-latency APIs.\n",
     "\n",
     "Key Features:\n",
     "\n",
@@ -32,8 +20,21 @@
     "- **Auto-token counting** of memories and summaries, allowing finer-grained control over prompt assembly.\n",
     "- Python and JavaScript SDKs.\n",
     "\n",
-    "Zep project: [https://github.com/getzep/zep](https://github.com/getzep/zep)\n",
-    "Docs: [https://docs.getzep.com/](https://docs.getzep.com/)\n"
+    "`Zep` project: [https://github.com/getzep/zep](https://github.com/getzep/zep)\n",
+    "Docs: [https://docs.getzep.com/](https://docs.getzep.com/)\n",
+    "\n",
+    "\n",
+    "## Example\n",
+    "\n",
+    "This notebook demonstrates how to use the [Zep Long-term Memory Store](https://docs.getzep.com/) as memory for your chatbot.\n",
+    "REACT Agent Chat Message History with Zep - A long-term memory store for LLM applications.\n",
+    "\n",
+    "We'll demonstrate:\n",
+    "\n",
+    "1. Adding conversation history to the Zep memory store.\n",
+    "2. Running an agent and having message automatically added to the store.\n",
+    "3. Viewing the enriched messages.\n",
+    "4. Vector search over the conversation history."
    ]
   },
   {
@@ -96,7 +97,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -143,7 +143,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -232,7 +231,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -257,16 +255,18 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new  chain...\u001B[0m\n",
-      "\u001B[32;1m\u001B[1;3mThought: Do I need to use a tool? No\n",
-      "AI: Parable of the Sower is a prescient novel that speaks to the challenges facing contemporary society, such as climate change, inequality, and violence. It is a cautionary tale that warns of the dangers of unchecked greed and the need for individuals to take responsibility for their own lives and the lives of those around them.\u001B[0m\n",
+      "\u001b[1m> Entering new  chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: Do I need to use a tool? No\n",
+      "AI: Parable of the Sower is a prescient novel that speaks to the challenges facing contemporary society, such as climate change, inequality, and violence. It is a cautionary tale that warns of the dangers of unchecked greed and the need for individuals to take responsibility for their own lives and the lives of those around them.\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished chain.\u001B[0m\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
      "data": {
-      "text/plain": "'Parable of the Sower is a prescient novel that speaks to the challenges facing contemporary society, such as climate change, inequality, and violence. It is a cautionary tale that warns of the dangers of unchecked greed and the need for individuals to take responsibility for their own lives and the lives of those around them.'"
+      "text/plain": [
+       "'Parable of the Sower is a prescient novel that speaks to the challenges facing contemporary society, such as climate change, inequality, and violence. It is a cautionary tale that warns of the dangers of unchecked greed and the need for individuals to take responsibility for their own lives and the lives of those around them.'"
+      ]
      },
      "execution_count": 6,
      "metadata": {},
@@ -280,7 +280,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -341,7 +340,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -391,11 +389,14 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "outputs": [],
-   "source": [],
    "metadata": {
-    "collapsed": false
-   }
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -414,7 +415,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/extras/integrations/providers/aws_dynamodb.mdx

@@ -0,0 +1,23 @@
+# AWS DynamoDB
+
+>[AWS DynamoDB](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/dynamodb/index.html) 
+> is a fully managed `NoSQL` database service that provides fast and predictable performance with seamless scalability.
+ 
+## Installation and Setup
+
+We have to configur the [AWS CLI](https://docs.aws.amazon.com/cli/latest/userguide/cli-chap-configure.html). 
+
+We need to install the `boto3` library.
+
+```bash
+pip install boto3
+```
+
+
+## Memory
+
+See a [usage example](/docs/integrations/memory/aws_dynamodb).
+
+```python
+from langchain.memory import DynamoDBChatMessageHistory
+```

docs/extras/integrations/providers/beautiful_soup.mdx

@@ -0,0 +1,20 @@
+# Beautiful Soup
+
+>[Beautiful Soup](https://www.crummy.com/software/BeautifulSoup/) is a Python package for parsing 
+> HTML and XML documents (including having malformed markup, i.e. non-closed tags, so named after tag soup). 
+> It creates a parse tree for parsed pages that can be used to extract data from HTML,[3] which 
+> is useful for web scraping.
+
+## Installation and Setup
+
+```bash
+pip install beautifulsoup4
+```
+
+## Document Transformer
+
+See a [usage example](/docs/integrations/document_transformers/beautiful_soup).
+
+```python
+from langchain.document_loaders import BeautifulSoupTransformer
+```

docs/extras/integrations/providers/clarifai.mdx

@@ -43,10 +43,10 @@ For more details, the docs on the Clarifai Embeddings wrapper provide a [detaile
 
 Clarifai's vector DB was launched in 2016 and has been optimized to support live search queries. With workflows in the Clarifai platform, you data is automatically indexed by am embedding model and optionally other models as well to index that information in the DB for search. You can query the DB not only via the vectors but also filter by metadata matches, other AI predicted concepts, and even do geo-coordinate search. Simply create an application, select the appropriate base workflow for your type of data, and upload it (through the API as [documented here](https://docs.clarifai.com/api-guide/data/create-get-update-delete) or the UIs at clarifai.com).
 
-You an also add data directly from LangChain as well, and the auto-indexing will take place for you. You'll notice this is a little different than other vectorstores where you need to provde an embedding model in their constructor and have LangChain coordinate getting the embeddings from text and writing those to the index. Not only is it more convenient, but it's much more scalable to use Clarifai's distributed cloud to do all the index in the background.
+You can also add data directly from LangChain as well, and the auto-indexing will take place for you. You'll notice this is a little different than other vectorstores where you need to provide an embedding model in their constructor and have LangChain coordinate getting the embeddings from text and writing those to the index. Not only is it more convenient, but it's much more scalable to use Clarifai's distributed cloud to do all the index in the background.
 
 ```python
 from langchain.vectorstores import Clarifai
 clarifai_vector_db = Clarifai.from_texts(user_id=USER_ID, app_id=APP_ID, texts=texts, pat=CLARIFAI_PAT, number_of_docs=NUMBER_OF_DOCS, metadatas = metadatas)
 ```
-For more details, the docs on the Clarifai vector store provide a [detailed walkthrough](/docs/integrations/text_embedding/clarifai.html).
+For more details, the docs on the Clarifai vector store provide a [detailed walkthrough](/docs/integrations/vectorstores/clarifai.ipynb).

docs/extras/integrations/providers/doctran.mdx

@@ -0,0 +1,37 @@
+# Doctran
+
+>[Doctran](https://github.com/psychic-api/doctran) is a python package. It uses LLMs and open source 
+> NLP libraries to transform raw text into clean, structured, information-dense documents 
+> that are optimized for vector space retrieval. You can think of `Doctran` as a black box where 
+> messy strings go in and nice, clean, labelled strings come out.
+
+
+## Installation and Setup
+
+```bash
+pip install doctran
+```
+
+## Document Transformers
+
+### Document Interrogator
+
+See a [usage example for DoctranQATransformer](/docs/integrations/document_transformers/doctran_interrogate_document).
+
+```python
+from langchain.document_loaders import DoctranQATransformer
+```
+### Property Extractor
+
+See a [usage example for DoctranPropertyExtractor](/docs/integrations/document_transformers/doctran_extract_properties).
+
+```python
+from langchain.document_loaders import DoctranPropertyExtractor
+```
+### Document Translator
+
+See a [usage example for DoctranTextTranslator](/docs/integrations/document_transformers/doctran_translate_document).
+
+```python
+from langchain.document_loaders import DoctranTextTranslator
+```

docs/extras/integrations/providers/google_document_ai.mdx

@@ -0,0 +1,28 @@
+# Google Document AI
+
+>[Document AI](https://cloud.google.com/document-ai/docs/overview) is a `Google Cloud Platform` 
+> service to transform unstructured data from documents into structured data, making it easier 
+> to understand, analyze, and consume.  
+
+
+## Installation and Setup
+
+You need to set up a [`GCS` bucket and create your own OCR processor](https://cloud.google.com/document-ai/docs/create-processor)  
+The `GCS_OUTPUT_PATH` should be a path to a folder on GCS (starting with `gs://`) 
+and a processor name should look like `projects/PROJECT_NUMBER/locations/LOCATION/processors/PROCESSOR_ID`.
+You can get it either programmatically or copy from the `Prediction endpoint` section of the `Processor details`
+tab in the Google Cloud Console.
+
+```bash
+pip install google-cloud-documentai
+pip install google-cloud-documentai-toolbox
+```
+
+## Document Transformer
+
+See a [usage example](/docs/integrations/document_transformers/docai).
+
+```python
+from langchain.document_loaders.blob_loaders import Blob
+from langchain.document_loaders.parsers import DocAIParser
+```

docs/extras/integrations/providers/html2text.mdx

@@ -0,0 +1,19 @@
+# HTML to text
+
+>[html2text](https://github.com/Alir3z4/html2text/) is a Python package that converts a page of `HTML` into clean, easy-to-read plain `ASCII text`. 
+
+The ASCII also happens to be a valid `Markdown` (a text-to-HTML format).
+
+## Installation and Setup
+
+```bash
+pip install html2text
+```
+
+## Document Transformer
+
+See a [usage example](/docs/integrations/document_transformers/html2text).
+
+```python
+from langchain.document_loaders import Html2TextTransformer
+```

docs/extras/integrations/providers/jina.mdx

@@ -62,7 +62,7 @@ Deploy on Jina AI Cloud with `lc-serve deploy jcloud app`. Once deployed, we can
 ```bash
 curl -X 'POST' 'https://<your-app>.wolf.jina.ai/ask' \
  -d '{
-  "input": "Your Quesion here?",
+  "input": "Your Question here?",
   "envs": {
      "OPENAI_API_KEY": "sk-***"
   }

docs/extras/integrations/providers/motorhead.mdx

@@ -0,0 +1,16 @@
+# Motörhead
+
+>[Motörhead](https://github.com/getmetal/motorhead) is a memory server implemented in Rust. It automatically handles incremental summarization in the background and allows for stateless applications.
+
+## Installation and Setup
+
+See instructions at [Motörhead](https://github.com/getmetal/motorhead) for running the server locally.
+
+
+## Memory
+
+See a [usage example](/docs/integrations/memory/motorhead_memory).
+
+```python
+from langchain.memory import MotorheadMemory
+```

docs/extras/integrations/providers/nuclia.mdx

@@ -0,0 +1,37 @@
+# Nuclia
+
+>[Nuclia](https://nuclia.com) automatically indexes your unstructured data from any internal
+> and external source, providing optimized search results and generative answers. 
+> It can handle video and audio transcription, image content extraction, and document parsing.
+
+>`Nuclia Understanding API` document transformer splits text into paragraphs and sentences, 
+> identifies entities, provides a summary of the text and generates embeddings for all the sentences.
+
+
+## Installation and Setup
+
+We need to install the `nucliadb-protos` package to use the `Nuclia Understanding API`.
+```bash
+pip install nucliadb-protos
+```
+
+To use the `Nuclia Understanding API`, we need to have a `Nuclia account`. 
+We can create one for free at [https://nuclia.cloud](https://nuclia.cloud), 
+and then [create a NUA key](https://docs.nuclia.dev/docs/docs/using/understanding/intro).
+
+To use the Nuclia document transformer, we need to instantiate a `NucliaUnderstandingAPI`
+tool with `enable_ml` set to `True`:
+
+```python
+from langchain.tools.nuclia import NucliaUnderstandingAPI
+
+nua = NucliaUnderstandingAPI(enable_ml=True)
+```
+
+## Document Transformer
+
+See a [usage example](/docs/integrations/document_transformers/nuclia_transformer).
+
+```python
+from langchain.document_transformers.nuclia_text_transform import NucliaTextTransformer
+```

docs/extras/integrations/providers/predibase.md

@@ -3,7 +3,7 @@
 Learn how to use LangChain with models on Predibase. 
 
 ## Setup
-- Create a [Predibase](hhttps://predibase.com/) account and [API key](https://docs.predibase.com/sdk-guide/intro).
+- Create a [Predibase](https://predibase.com/) account and [API key](https://docs.predibase.com/sdk-guide/intro).
 - Install the Predibase Python client with `pip install predibase`
 - Use your API key to authenticate
 

docs/extras/integrations/providers/redis.mdx

@@ -1,7 +1,10 @@
 # Redis
 
->[Redis](https://redis.com) is an open-source key-value store that can be used as a cache, 
-> message broker, database, vector database and more.
+>[Redis (Remote Dictionary Server)](https://en.wikipedia.org/wiki/Redis) is an open-source in-memory storage, 
+> used as a distributed, in-memory key–value database, cache and message broker, with optional durability. 
+> Because it holds all data in memory and because of its design, `Redis` offers low-latency reads and writes, 
+> making it particularly suitable for use cases that require a cache. Redis is the most popular NoSQL database, 
+> and one of the most popular databases overall.
 
 This page covers how to use the [Redis](https://redis.com) ecosystem within LangChain.
 It is broken into two parts: installation and setup, and then references to specific Redis wrappers.
@@ -111,7 +114,7 @@ Redis can be used to persist LLM conversations.
 
 #### Vector Store Retriever Memory
 
-For a more detailed walkthrough of the `VectorStoreRetrieverMemory` wrapper, see [this notebook](/docs/modules/memory/integrations/vectorstore_retriever_memory.html).
+For a more detailed walkthrough of the `VectorStoreRetrieverMemory` wrapper, see [this notebook](/docs/modules/memory/types/vectorstore_retriever_memory.html).
 
 #### Chat Message History Memory
 For a detailed example of Redis to cache conversation message history, see [this notebook](/docs/integrations/memory/redis_chat_message_history.html).

docs/extras/integrations/providers/searchapi.mdx

@@ -0,0 +1,80 @@
+# SearchApi
+
+This page covers how to use the [SearchApi](https://www.searchapi.io/) Google Search API within LangChain. SearchApi is a real-time SERP API for easy SERP scraping.
+
+## Setup
+
+- Go to [https://www.searchapi.io/](https://www.searchapi.io/) to sign up for a free account
+- Get the api key and set it as an environment variable (`SEARCHAPI_API_KEY`)
+
+## Wrappers
+
+### Utility
+
+There is a SearchApiAPIWrapper utility which wraps this API. To import this utility:
+
+```python
+from langchain.utilities import SearchApiAPIWrapper
+```
+
+You can use it as part of a Self Ask chain:
+
+```python
+from langchain.utilities import SearchApiAPIWrapper
+from langchain.llms.openai import OpenAI
+from langchain.agents import initialize_agent, Tool
+from langchain.agents import AgentType
+
+import os
+
+os.environ["SEARCHAPI_API_KEY"] = ""
+os.environ['OPENAI_API_KEY'] = ""
+
+llm = OpenAI(temperature=0)
+search = SearchApiAPIWrapper()
+tools = [
+    Tool(
+        name="Intermediate Answer",
+        func=search.run,
+        description="useful for when you need to ask with search"
+    )
+]
+
+self_ask_with_search = initialize_agent(tools, llm, agent=AgentType.SELF_ASK_WITH_SEARCH, verbose=True)
+self_ask_with_search.run("Who lived longer: Plato, Socrates, or Aristotle?")
+```
+
+#### Output
+
+```
+> Entering new AgentExecutor chain...
+ Yes.
+Follow up: How old was Plato when he died?
+Intermediate answer: eighty
+Follow up: How old was Socrates when he died?
+Intermediate answer: | Socrates | 
+| -------- | 
+| Born | c. 470 BC Deme Alopece, Athens | 
+| Died | 399 BC (aged approximately 71) Athens | 
+| Cause of death | Execution by forced suicide by poisoning | 
+| Spouse(s) | Xanthippe, Myrto | 
+
+Follow up: How old was Aristotle when he died?
+Intermediate answer: 62 years
+So the final answer is: Plato
+
+> Finished chain.
+'Plato'
+```
+
+### Tool
+
+You can also easily load this wrapper as a Tool (to use with an Agent).
+You can do this with:
+
+```python
+from langchain.agents import load_tools
+tools = load_tools(["searchapi"])
+```
+
+For more information on tools, see [this page](/docs/modules/agents/tools/).

docs/extras/integrations/providers/vectara/index.mdx

@@ -5,7 +5,7 @@
 
 **Vectara Overview:**
 - `Vectara` is developer-first API platform for building GenAI applications
-- To use Vectara - first [sign up](https://console.vectara.com/signup) and create an account. Then create a corpus and an API key for indexing and searching.
+- To use Vectara - first [sign up](https://vectara.com/integrations/langchain) and create an account. Then create a corpus and an API key for indexing and searching.
 - You can use Vectara's [indexing API](https://docs.vectara.com/docs/indexing-apis/indexing) to add documents into Vectara's index
 - You can use Vectara's [Search API](https://docs.vectara.com/docs/search-apis/search) to query Vectara's index (which also supports Hybrid search implicitly).
 - You can use Vectara's integration with LangChain as a Vector store or using the Retriever abstraction.
@@ -13,7 +13,7 @@
 ## Installation and Setup
 
 To use `Vectara` with LangChain no special installation steps are required. 
-To get started, follow our [quickstart](https://docs.vectara.com/docs/quickstart) guide to create an account, a corpus and an API key. 
+To get started, [sign up](https://vectara.com/integrations/langchain) and follow our [quickstart](https://docs.vectara.com/docs/quickstart) guide to create a corpus and an API key. 
 Once you have these, you can provide them as arguments to the Vectara vectorstore, or you can set them as environment variables.
 
 - export `VECTARA_CUSTOMER_ID`="your_customer_id"