x

.devcontainer/README.md

@@ -10,7 +10,7 @@ You can use the dev container configuration in this folder to build and run the
 You may use the button above, or follow these steps to open this repo in a Codespace:
 1. Click the **Code** drop-down menu at the top of https://github.com/langchain-ai/langchain.
 1. Click on the **Codespaces** tab.
-1. Click **Create codespace on master**.
+1. Click **Create codespace on master** .
 
 For more info, check out the [GitHub documentation](https://docs.github.com/en/free-pro-team@latest/github/developing-online-with-codespaces/creating-a-codespace#creating-a-codespace).
   

.devcontainer/devcontainer.json

@@ -12,7 +12,7 @@
 
 	// The optional 'workspaceFolder' property is the path VS Code should open by default when
 	// connected. This is typically a file mount in .devcontainer/docker-compose.yml
-	"workspaceFolder": "/workspaces/langchain",
+	"workspaceFolder": "/workspaces/${localWorkspaceFolderBasename}",
 
 	// Prevent the container from shutting down
 	"overrideCommand": true

.devcontainer/docker-compose.yaml

@@ -6,7 +6,7 @@ services:
       context: ..
     volumes:
    # Update this to wherever you want VS Code to mount the folder of your project
-      - ..:/workspaces/langchain:cached
+      - ..:/workspaces:cached
     networks:
       - langchain-network 
   #   environment:

.github/ISSUE_TEMPLATE/documentation.yml

@@ -26,13 +26,6 @@ body:
       [LangChain Github Discussions](https://github.com/langchain-ai/langchain/discussions),
       [LangChain Github Issues](https://github.com/langchain-ai/langchain/issues?q=is%3Aissue),
       [LangChain ChatBot](https://chat.langchain.com/)
-- type: input
-  id: url
-  attributes:
-    label: URL
-    description: URL to documentation
-  validations:
-    required: false
 - type: checkboxes
   id: checks
   attributes:
@@ -55,4 +48,4 @@ body:
     label: "Idea or request for content:"
     description: >
       Please describe as clearly as possible what topics you think are missing
-      from the current documentation.
+      from the current documentation.

.github/PULL_REQUEST_TEMPLATE.md

@@ -26,4 +26,4 @@ Additional guidelines:
 - Changes should be backwards compatible.
 - If you are adding something to community, do not re-import it in langchain.
 
-If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
+If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, hwchase17.

.github/actions/people/app/main.py

@@ -537,9 +537,7 @@ if __name__ == "__main__":
         "nfcampos",
         "efriis",
         "eyurtsev",
-        "rlancemartin",
-        "ccurme",
-        "vbarda",
+        "rlancemartin"
     }
     hidden_logins = {
         "dev2049",

.github/scripts/check_diff.py

@@ -6,8 +6,8 @@ from typing import Dict
 LANGCHAIN_DIRS = [
     "libs/core",
     "libs/text-splitters",
-    "libs/langchain",
     "libs/community",
+    "libs/langchain",
     "libs/experimental",
 ]
 
@@ -19,7 +19,6 @@ if __name__ == "__main__":
         "test": set(),
         "extended-test": set(),
     }
-    docs_edited = False
 
     if len(files) == 300:
         # max diff length is 300 files - there are likely files missing
@@ -48,17 +47,6 @@ if __name__ == "__main__":
                     found = True
                 if found:
                     dirs_to_run["extended-test"].add(dir_)
-        elif file.startswith("libs/standard-tests"):
-            # TODO: update to include all packages that rely on standard-tests (all partner packages)
-            # note: won't run on external repo partners
-            dirs_to_run["lint"].add("libs/standard-tests")
-            dirs_to_run["test"].add("libs/partners/mistralai")
-            dirs_to_run["test"].add("libs/partners/openai")
-            dirs_to_run["test"].add("libs/partners/anthropic")
-            dirs_to_run["test"].add("libs/partners/ai21")
-            dirs_to_run["test"].add("libs/partners/fireworks")
-            dirs_to_run["test"].add("libs/partners/groq")
-
         elif file.startswith("libs/cli"):
             # todo: add cli makefile
             pass
@@ -77,8 +65,6 @@ if __name__ == "__main__":
                 "an update for this new library!"
             )
         elif any(file.startswith(p) for p in ["docs/", "templates/", "cookbook/"]):
-            if file.startswith("docs/"):
-                docs_edited = True
             dirs_to_run["lint"].add(".")
 
     outputs = {
@@ -87,8 +73,7 @@ if __name__ == "__main__":
         ),
         "dirs-to-test": list(dirs_to_run["test"] | dirs_to_run["extended-test"]),
         "dirs-to-extended-test": list(dirs_to_run["extended-test"]),
-        "docs-edited": "true" if docs_edited else "",
     }
     for key, value in outputs.items():
         json_output = json.dumps(value)
-        print(f"{key}={json_output}")
+        print(f"{key}={json_output}")  # noqa: T201

.github/scripts/get_min_versions.py

@@ -13,16 +13,13 @@ MIN_VERSION_LIBS = [
 
 
 def get_min_version(version: str) -> str:
-    # base regex for x.x.x with cases for rc/post/etc
-    # valid strings: https://peps.python.org/pep-0440/#public-version-identifiers
-    vstring = r"\d+(?:\.\d+){0,2}(?:(?:a|b|rc|\.post|\.dev)\d+)?"
     # case ^x.x.x
-    _match = re.match(f"^\\^({vstring})$", version)
+    _match = re.match(r"^\^(\d+(?:\.\d+){0,2})$", version)
     if _match:
         return _match.group(1)
 
     # case >=x.x.x,<y.y.y
-    _match = re.match(f"^>=({vstring}),<({vstring})$", version)
+    _match = re.match(r"^>=(\d+(?:\.\d+){0,2}),<(\d+(?:\.\d+){0,2})$", version)
     if _match:
         _min = _match.group(1)
         _max = _match.group(2)
@@ -30,7 +27,7 @@ def get_min_version(version: str) -> str:
         return _min
 
     # case x.x.x
-    _match = re.match(f"^({vstring})$", version)
+    _match = re.match(r"^(\d+(?:\.\d+){0,2})$", version)
     if _match:
         return _match.group(1)
 
@@ -55,9 +52,6 @@ def get_min_version_from_toml(toml_path: str):
             # Get the version string
             version_string = dependencies[lib]
 
-            if isinstance(version_string, dict):
-                version_string = version_string["version"]
-
             # Use parse_version to get the minimum supported version from version_string
             min_version = get_min_version(version_string)
 
@@ -76,4 +70,4 @@ if __name__ == "__main__":
 
     print(
         " ".join([f"{lib}=={version}" for lib, version in min_versions.items()])
-    )
+    )  # noqa: T201

.github/workflows/.codespell-exclude

@@ -1,7 +0,0 @@
-libs/community/langchain_community/llms/yuan2.py
-"NotIn": "not in",
-- `/checkin`: Check-in
-docs/docs/integrations/providers/trulens.mdx
-self.assertIn(
-from trulens_eval import Tru
-tru = Tru()

.github/workflows/_compile_integration_test.yml

@@ -24,7 +24,6 @@ jobs:
           - "3.9"
           - "3.10"
           - "3.11"
-          - "3.12"
     name: "poetry run pytest -m compile tests/integration_tests #${{ matrix.python-version }}"
     steps:
       - uses: actions/checkout@v4

.github/workflows/_dependencies.yml

@@ -28,7 +28,6 @@ jobs:
           - "3.9"
           - "3.10"
           - "3.11"
-          - "3.12"
     name: dependency checks ${{ matrix.python-version }}
     steps:
       - uses: actions/checkout@v4

.github/workflows/_integration_test.yml

@@ -58,7 +58,6 @@ jobs:
           MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
           TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
           NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
           GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
           GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
@@ -78,7 +77,6 @@ jobs:
           MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
           VOYAGE_API_KEY: ${{ secrets.VOYAGE_API_KEY }}
           COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
-          UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
         run: |
           make integration_tests
 

.github/workflows/_lint.yml

@@ -34,7 +34,7 @@ jobs:
         # so linting on fewer versions makes CI faster.
         python-version:
           - "3.8"
-          - "3.12"
+          - "3.11"
     steps:
       - uses: actions/checkout@v4
 

.github/workflows/_release.yml

@@ -13,11 +13,6 @@ on:
         required: true
         type: string
         default: 'libs/langchain'
-      dangerous-nonmaster-release:
-        required: false
-        type: boolean
-        default: false
-        description: "Release from a non-master branch (danger!)"
 
 env:
   PYTHON_VERSION: "3.11"
@@ -25,7 +20,7 @@ env:
 
 jobs:
   build:
-    if: github.ref == 'refs/heads/master' || inputs.dangerous-nonmaster-release
+    if: github.ref == 'refs/heads/master'
     environment: Scheduled testing
     runs-on: ubuntu-latest
 
@@ -72,78 +67,19 @@ jobs:
         run: |
           echo pkg-name="$(poetry version | cut -d ' ' -f 1)" >> $GITHUB_OUTPUT
           echo version="$(poetry version --short)" >> $GITHUB_OUTPUT
-  release-notes:
-    needs:
-      - build
-    runs-on: ubuntu-latest
-    outputs:
-      release-body: ${{ steps.generate-release-body.outputs.release-body }}
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          repository: langchain-ai/langchain
-          path: langchain
-          sparse-checkout: | # this only grabs files for relevant dir
-            ${{ inputs.working-directory }}
-          ref: master # this scopes to just master branch
-          fetch-depth: 0 # this fetches entire commit history
-      - name: Check Tags
-        id: check-tags
-        shell: bash
-        working-directory: langchain/${{ inputs.working-directory }}
-        env:
-          PKG_NAME: ${{ needs.build.outputs.pkg-name }}
-          VERSION: ${{ needs.build.outputs.version }}
-        run: |
-          REGEX="^$PKG_NAME==\\d+\\.\\d+\\.\\d+\$"
-          echo $REGEX
-          PREV_TAG=$(git tag --sort=-creatordate | grep -P $REGEX || true | head -1)
-          TAG="${PKG_NAME}==${VERSION}"
-          if [ "$TAG" == "$PREV_TAG" ]; then
-            echo "No new version to release"
-            exit 1
-          fi
-          echo tag="$TAG" >> $GITHUB_OUTPUT
-          echo prev-tag="$PREV_TAG" >> $GITHUB_OUTPUT
-      - name: Generate release body
-        id: generate-release-body
-        working-directory: langchain
-        env:
-          WORKING_DIR: ${{ inputs.working-directory }}
-          PKG_NAME: ${{ needs.build.outputs.pkg-name }}
-          TAG: ${{ steps.check-tags.outputs.tag }}
-          PREV_TAG: ${{ steps.check-tags.outputs.prev-tag }}
-        run: |
-          PREAMBLE="Changes since $PREV_TAG"
-          # if PREV_TAG is empty, then we are releasing the first version
-          if [ -z "$PREV_TAG" ]; then
-            PREAMBLE="Initial release"
-            PREV_TAG=$(git rev-list --max-parents=0 HEAD)
-          fi
-          {
-            echo 'release-body<<EOF'
-            echo "# Release $TAG"
-            echo $PREAMBLE
-            echo
-            git log --format="%s" "$PREV_TAG"..HEAD -- $WORKING_DIR
-            echo EOF
-          } >> "$GITHUB_OUTPUT"
 
   test-pypi-publish:
     needs:
       - build
-      - release-notes
     uses:
       ./.github/workflows/_test_release.yml
     with:
       working-directory: ${{ inputs.working-directory }}
-      dangerous-nonmaster-release: ${{ inputs.dangerous-nonmaster-release }}
     secrets: inherit
 
   pre-release-checks:
     needs:
       - build
-      - release-notes
       - test-pypi-publish
     runs-on: ubuntu-latest
     steps:
@@ -176,7 +112,7 @@ jobs:
           PKG_NAME: ${{ needs.build.outputs.pkg-name }}
           VERSION: ${{ needs.build.outputs.version }}
         # Here we use:
-        # - The default regular PyPI index as the *primary* index, meaning
+        # - The default regular PyPI index as the *primary* index, meaning 
         #   that it takes priority (https://pypi.org/simple)
         # - The test PyPI index as an extra index, so that any dependencies that
         #   are not found on test PyPI can be resolved and installed anyway.
@@ -235,7 +171,7 @@ jobs:
         env:
           MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
         run: |
-          poetry run pip install --force-reinstall $MIN_VERSIONS --editable .
+          poetry run pip install $MIN_VERSIONS
           make tests
         working-directory: ${{ inputs.working-directory }}
 
@@ -279,15 +215,12 @@ jobs:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # for airbyte
           MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
           VOYAGE_API_KEY: ${{ secrets.VOYAGE_API_KEY }}
-          UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
-          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
         run: make integration_tests
         working-directory: ${{ inputs.working-directory }}
 
   publish:
     needs:
       - build
-      - release-notes
       - test-pypi-publish
       - pre-release-checks
     runs-on: ubuntu-latest
@@ -329,7 +262,6 @@ jobs:
   mark-release:
     needs:
       - build
-      - release-notes
       - test-pypi-publish
       - pre-release-checks
       - publish
@@ -358,14 +290,14 @@ jobs:
         with:
           name: dist
           path: ${{ inputs.working-directory }}/dist/
-          
-      - name: Create Tag
+
+      - name: Create Release
         uses: ncipollo/release-action@v1
+        if: ${{ inputs.working-directory == 'libs/langchain' }}
         with:
           artifacts: "dist/*"
           token: ${{ secrets.GITHUB_TOKEN }}
-          generateReleaseNotes: false
-          tag: ${{needs.build.outputs.pkg-name}}==${{ needs.build.outputs.version }}
-          body: ${{ needs.release-notes.outputs.release-body }}
-          commit: ${{ github.sha }}
-          makeLatest: ${{ needs.build.outputs.pkg-name == 'langchain-core'}}
+          draft: false
+          generateReleaseNotes: true
+          tag: v${{ needs.build.outputs.version }}
+          commit: master

.github/workflows/_test.yml

@@ -28,7 +28,6 @@ jobs:
           - "3.9"
           - "3.10"
           - "3.11"
-          - "3.12"
     name: "make test #${{ matrix.python-version }}"
     steps:
       - uses: actions/checkout@v4

.github/workflows/_test_doc_imports.yml

@@ -12,7 +12,7 @@ jobs:
     strategy:
       matrix:
         python-version:
-          - "3.12"
+          - "3.11"
     name: "check doc imports #${{ matrix.python-version }}"
     steps:
       - uses: actions/checkout@v4

.github/workflows/_test_release.yml

@@ -7,11 +7,6 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
-      dangerous-nonmaster-release:
-        required: false
-        type: boolean
-        default: false
-        description: "Release from a non-master branch (danger!)"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -19,7 +14,7 @@ env:
 
 jobs:
   build:
-    if: github.ref == 'refs/heads/master' || inputs.dangerous-nonmaster-release
+    if: github.ref == 'refs/heads/master'
     runs-on: ubuntu-latest
 
     outputs:

.github/workflows/check-broken-links.yml

@@ -7,7 +7,6 @@ on:
 
 jobs:
   check-links:
-    if: github.repository_owner == 'langchain-ai'
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4

.github/workflows/check_diffs.yml

@@ -36,7 +36,6 @@ jobs:
       dirs-to-lint: ${{ steps.set-matrix.outputs.dirs-to-lint }}
       dirs-to-test: ${{ steps.set-matrix.outputs.dirs-to-test }}
       dirs-to-extended-test: ${{ steps.set-matrix.outputs.dirs-to-extended-test }}
-      docs-edited: ${{ steps.set-matrix.outputs.docs-edited }}
   lint:
     name: cd ${{ matrix.working-directory }}
     needs: [ build ]
@@ -61,9 +60,9 @@ jobs:
       working-directory: ${{ matrix.working-directory }}
     secrets: inherit
 
-  test-doc-imports:
+  test_doc_imports:
     needs: [ build ]
-    if: ${{ needs.build.outputs.dirs-to-test != '[]' || needs.build.outputs.docs-edited }}
+    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
     uses: ./.github/workflows/_test_doc_imports.yml
     secrets: inherit
 
@@ -104,7 +103,6 @@ jobs:
           - "3.9"
           - "3.10"
           - "3.11"
-          - "3.12"
     runs-on: ubuntu-latest
     defaults:
       run:
@@ -124,9 +122,7 @@ jobs:
         shell: bash
         run: |
           echo "Running extended tests, installing dependencies with poetry..."
-          poetry install --with test
-          poetry run pip install uv
-          poetry run uv pip install -r extended_testing_deps.txt
+          poetry install -E extended_testing --with test
 
       - name: Run extended tests
         run: make extended_tests
@@ -144,7 +140,7 @@ jobs:
           echo "$STATUS" | grep 'nothing to commit, working tree clean'
   ci_success:
     name: "CI Success"
-    needs: [build, lint, test, compile-integration-tests, dependencies, extended-tests, test-doc-imports]
+    needs: [build, lint, test, compile-integration-tests, dependencies, extended-tests]
     if: |
       always()
     runs-on: ubuntu-latest

.github/workflows/check_new_docs.yml

@@ -1,31 +0,0 @@
----
-name: Integration docs lint
-
-on:
-  push:
-    branches: [master]
-  pull_request:
-
-# If another push to the same PR or branch happens while this workflow is still running,
-# cancel the earlier run in favor of the next run.
-#
-# There's no point in testing an outdated version of the code. GitHub only allows
-# a limited number of job runners to be active at the same time, so it's better to cancel
-# pointless jobs early so that more useful jobs can run sooner.
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
-        with:
-          python-version: '3.10'
-      - id: files
-        uses: Ana06/get-changed-files@v2.2.0
-      - name: Check new docs
-        run: |
-          python docs/scripts/check_templates.py ${{ steps.files.outputs.added }}

.github/workflows/codespell.yml

@@ -3,9 +3,9 @@ name: CI / cd . / make spell_check
 
 on:
   push:
-    branches: [master, v0.1]
+    branches: [master]
   pull_request:
-    branches: [master, v0.1]
+    branches: [master]
 
 permissions:
   contents: read
@@ -29,9 +29,9 @@ jobs:
           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,*.ambr,./cookbook/data/imdb_top_1000.csv,*.lock
-#          ignore_words_list: ${{ steps.extract_ignore_words.outputs.ignore_words_list }}
-#          exclude_file: ./.github/workflows/codespell-exclude
+      - name: Codespell
+        uses: codespell-project/actions-codespell@v2
+        with:
+          skip: guide_imports.json,*.ambr,./cookbook/data/imdb_top_1000.csv,*.lock
+          ignore_words_list: ${{ steps.extract_ignore_words.outputs.ignore_words_list }}
+          exclude_file: libs/community/langchain_community/llms/yuan2.py

.github/workflows/extract_ignored_words_list.py

@@ -7,4 +7,4 @@ ignore_words_list = (
     pyproject_toml.get("tool", {}).get("codespell", {}).get("ignore-words-list")
 )
 
-print(f"::set-output name=ignore_words_list::{ignore_words_list}")
+print(f"::set-output name=ignore_words_list::{ignore_words_list}")  # noqa: T201

.github/workflows/scheduled_test.yml

@@ -10,69 +10,28 @@ env:
 
 jobs:
   build:
-    if: github.repository_owner == 'langchain-ai'
-    name: Python ${{ matrix.python-version }} - ${{ matrix.working-directory }}
+    defaults:
+      run:
+        working-directory: libs/langchain
     runs-on: ubuntu-latest
+    environment: Scheduled testing
     strategy:
-      fail-fast: false
       matrix:
         python-version:
           - "3.8"
+          - "3.9"
+          - "3.10"
           - "3.11"
-        working-directory:
-          - "libs/partners/openai"
-          - "libs/partners/anthropic"
-          - "libs/partners/ai21"
-          - "libs/partners/fireworks"
-          - "libs/partners/groq"
-          - "libs/partners/mistralai"
-          - "libs/partners/together"
-          - "libs/partners/cohere"
-          - "libs/partners/google-vertexai"
-          - "libs/partners/google-genai"
-          - "libs/partners/aws"
-          - "libs/partners/nvidia-ai-endpoints"
-
+    name: Python ${{ matrix.python-version }}
     steps:
       - uses: actions/checkout@v4
-        with:
-          path: langchain
-      - uses: actions/checkout@v4
-        with:
-          repository: langchain-ai/langchain-google
-          path: langchain-google
-      - uses: actions/checkout@v4
-        with:
-          repository: langchain-ai/langchain-nvidia
-          path: langchain-nvidia
-      - uses: actions/checkout@v4
-        with:
-          repository: langchain-ai/langchain-cohere
-          path: langchain-cohere
-      - uses: actions/checkout@v4
-        with:
-          repository: langchain-ai/langchain-aws
-          path: langchain-aws
-
-      - name: Move libs
-        run: |
-          rm -rf \
-            langchain/libs/partners/google-genai \
-            langchain/libs/partners/google-vertexai \
-            langchain/libs/partners/nvidia-ai-endpoints \
-            langchain/libs/partners/cohere
-          mv langchain-google/libs/genai langchain/libs/partners/google-genai
-          mv langchain-google/libs/vertexai langchain/libs/partners/google-vertexai
-          mv langchain-nvidia/libs/ai-endpoints langchain/libs/partners/nvidia-ai-endpoints
-          mv langchain-cohere/libs/cohere langchain/libs/partners/cohere
-          mv langchain-aws/libs/aws langchain/libs/partners/aws
 
       - name: Set up Python ${{ matrix.python-version }}
-        uses: "./langchain/.github/actions/poetry_setup"
+        uses: "./.github/actions/poetry_setup"
         with:
           python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: langchain/${{ matrix.working-directory }}
+          working-directory: libs/langchain
           cache-key: scheduled
 
       - name: 'Authenticate to Google Cloud'
@@ -86,15 +45,22 @@ jobs:
         with:
           aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
           aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-          aws-region: ${{ secrets.AWS_REGION }}
+          aws-region: ${{ vars.AWS_REGION }}
 
       - name: Install dependencies
+        working-directory: libs/langchain
+        shell: bash
         run: |
           echo "Running scheduled tests, installing dependencies with poetry..."
-          cd langchain/${{ matrix.working-directory }}
           poetry install --with=test_integration,test
 
-      - name: Run integration tests
+      - name: Install deps outside pyproject
+        if: ${{ startsWith(inputs.working-directory, 'libs/community/') }}
+        shell: bash
+        run: poetry run pip install "boto3<2" "google-cloud-aiplatform<2"
+
+      - name: Run tests
+        shell: bash
         env:
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
           ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
@@ -104,31 +70,12 @@ jobs:
           AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
           AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
           AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
-          AI21_API_KEY: ${{ secrets.AI21_API_KEY }}
           FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
-          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
-          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
-          TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
-          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
-          NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
-          GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
-          GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
-          GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
         run: |
-          cd langchain/${{ matrix.working-directory }}
-          make integration_tests
-
-      - name: Remove external libraries
-        run: | 
-          rm -rf \
-            langchain/libs/partners/google-genai \
-            langchain/libs/partners/google-vertexai \
-            langchain/libs/partners/nvidia-ai-endpoints \
-            langchain/libs/partners/cohere \
-            langchain/libs/partners/aws
+          make scheduled_tests
 
       - name: Ensure the tests did not create any additional files
-        working-directory: langchain
+        shell: bash
         run: |
           set -eu
 

.gitignore

@@ -133,7 +133,6 @@ env.bak/
 
 # mypy
 .mypy_cache/
-.mypy_cache_test/
 .dmypy.json
 dmypy.json
 
@@ -179,4 +178,3 @@ _dist
 docs/docs/templates
 
 prof
-virtualenv/

Makefile

@@ -3,7 +3,7 @@
 ## help: Show this help info.
 help: Makefile
 	@printf "\n\033[1mUsage: make <TARGETS> ...\033[0m\n\n\033[1mTargets:\033[0m\n\n"
-	@sed -n 's/^## //p' $< | awk -F':' '{printf "\033[36m%-30s\033[0m %s\n", $$1, $$2}' | sort | sed -e 's/^/  /'
+	@sed -n 's/^##//p' $< | awk -F':' '{printf "\033[36m%-30s\033[0m %s\n", $$1, $$2}' | sort | sed -e 's/^/ /'
 
 ## all: Default target, shows help.
 all: help
@@ -17,11 +17,16 @@ clean: docs_clean api_docs_clean
 
 ## docs_build: Build the documentation.
 docs_build:
-	cd docs && make build
+	docs/.local_build.sh
 
 ## docs_clean: Clean the documentation build artifacts.
 docs_clean:
-	cd docs && make clean
+	@if [ -d _dist ]; then \
+		rm -r _dist; \
+		echo "Directory _dist has been cleaned."; \
+	else \
+		echo "Nothing to clean."; \
+	fi
 
 ## docs_linkcheck: Run linkchecker on the documentation.
 docs_linkcheck:
@@ -32,19 +37,10 @@ api_docs_build:
 	poetry run python docs/api_reference/create_api_rst.py
 	cd docs/api_reference && poetry run make html
 
-API_PKG ?= text-splitters
-
-api_docs_quick_preview:
-	poetry run pip install "pydantic<2"
-	poetry run python docs/api_reference/create_api_rst.py $(API_PKG)
-	cd docs/api_reference && poetry run make html
-	open docs/api_reference/_build/html/$(shell echo $(API_PKG) | sed 's/-/_/g')_api_reference.html
-
 ## api_docs_clean: Clean the API Reference documentation build artifacts.
 api_docs_clean:
 	find ./docs/api_reference -name '*_api_reference.rst' -delete
-	git clean -fdX ./docs/api_reference
-	
+	cd docs/api_reference && poetry run make clean
 
 ## api_docs_linkcheck: Run linkchecker on the API Reference documentation.
 api_docs_linkcheck:
@@ -64,12 +60,12 @@ spell_fix:
 
 ## lint: Run linting on the project.
 lint lint_package lint_tests:
-	poetry run ruff check docs templates cookbook
+	poetry run ruff docs templates cookbook
 	poetry run ruff format docs templates cookbook --diff
-	poetry run ruff check --select I docs templates cookbook
+	poetry run ruff --select I docs templates cookbook
 	git grep 'from langchain import' docs/docs templates cookbook | grep -vE 'from langchain import (hub)' && exit 1 || exit 0
 
 ## format: Format the project files.
 format format_diff:
 	poetry run ruff format docs templates cookbook
-	poetry run ruff check --select I --fix docs templates cookbook
+	poetry run ruff --select I --fix docs templates cookbook

README.md

@@ -2,17 +2,17 @@
 
 ⚡ Build context-aware reasoning applications ⚡
 
-[![Release Notes](https://img.shields.io/github/release/langchain-ai/langchain?style=flat-square)](https://github.com/langchain-ai/langchain/releases)
+[![Release Notes](https://img.shields.io/github/release/langchain-ai/langchain)](https://github.com/langchain-ai/langchain/releases)
 [![CI](https://github.com/langchain-ai/langchain/actions/workflows/check_diffs.yml/badge.svg)](https://github.com/langchain-ai/langchain/actions/workflows/check_diffs.yml)
-[![PyPI - License](https://img.shields.io/pypi/l/langchain-core?style=flat-square)](https://opensource.org/licenses/MIT)
-[![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-core?style=flat-square)](https://pypistats.org/packages/langchain-core)
-[![GitHub star chart](https://img.shields.io/github/stars/langchain-ai/langchain?style=flat-square)](https://star-history.com/#langchain-ai/langchain)
-[![Dependency Status](https://img.shields.io/librariesio/github/langchain-ai/langchain?style=flat-square)](https://libraries.io/github/langchain-ai/langchain)
-[![Open Issues](https://img.shields.io/github/issues-raw/langchain-ai/langchain?style=flat-square)](https://github.com/langchain-ai/langchain/issues)
-[![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode&style=flat-square)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchain)
-[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/langchain-ai/langchain)
-[![](https://dcbadge.vercel.app/api/server/6adMQxSpJS?compact=true&style=flat)](https://discord.gg/6adMQxSpJS)
+[![Downloads](https://static.pepy.tech/badge/langchain/month)](https://pepy.tech/project/langchain)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai)
+[![](https://dcbadge.vercel.app/api/server/6adMQxSpJS?compact=true&style=flat)](https://discord.gg/6adMQxSpJS)
+[![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchain)
+[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/langchain-ai/langchain)
+[![GitHub star chart](https://img.shields.io/github/stars/langchain-ai/langchain?style=social)](https://star-history.com/#langchain-ai/langchain)
+[![Dependency Status](https://img.shields.io/librariesio/github/langchain-ai/langchain)](https://libraries.io/github/langchain-ai/langchain)
+[![Open Issues](https://img.shields.io/github/issues-raw/langchain-ai/langchain)](https://github.com/langchain-ai/langchain/issues)
 
 Looking for the JS/TS library? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
 
@@ -38,22 +38,22 @@ conda install langchain -c conda-forge
 
 For these applications, LangChain simplifies the entire application lifecycle:
 
-- **Open-source libraries**: Build your applications using LangChain's [modular building blocks](https://python.langchain.com/v0.2/docs/concepts/#langchain-expression-language-lcel) and [components](https://python.langchain.com/v0.2/docs/concepts/#components). Integrate with hundreds of [third-party providers](https://python.langchain.com/v0.2/docs/integrations/platforms/).
-- **Productionization**: Inspect, monitor, and evaluate your apps with [LangSmith](https://docs.smith.langchain.com/) so that you can constantly optimize and deploy with confidence.
-- **Deployment**: Turn any chain into a REST API with [LangServe](https://python.langchain.com/v0.2/docs/langserve/).
+- **Open-source libraries**: Build your applications using LangChain's [modular building blocks](https://python.langchain.com/docs/expression_language/) and [components](https://python.langchain.com/docs/modules/). Integrate with hundreds of [third-party providers](https://python.langchain.com/docs/integrations/platforms/).
+- **Productionization**: Inspect, monitor, and evaluate your apps with [LangSmith](https://python.langchain.com/docs/langsmith/) so that you can constantly optimize and deploy with confidence.
+- **Deployment**: Turn any chain into a REST API with [LangServe](https://python.langchain.com/docs/langserve).
 
 ### Open-source libraries
 - **`langchain-core`**: Base abstractions and LangChain Expression Language.
 - **`langchain-community`**: Third party integrations.
   - Some integrations have been further split into **partner packages** that only rely on **`langchain-core`**. Examples include **`langchain_openai`** and **`langchain_anthropic`**.
 - **`langchain`**: Chains, agents, and retrieval strategies that make up an application's cognitive architecture.
-- **[`LangGraph`](https://langchain-ai.github.io/langgraph/)**: A library for building robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph.
+- **`[LangGraph](https://python.langchain.com/docs/langgraph)`**: A library for building robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph.
 
 ### Productionization:
-- **[LangSmith](https://docs.smith.langchain.com/)**: A developer platform that lets you debug, test, evaluate, and monitor chains built on any LLM framework and seamlessly integrates with LangChain.
+- **[LangSmith](https://python.langchain.com/docs/langsmith)**: A developer platform that lets you debug, test, evaluate, and monitor chains built on any LLM framework and seamlessly integrates with LangChain.
 
 ### Deployment:
-- **[LangServe](https://python.langchain.com/v0.2/docs/langserve/)**: A library for deploying LangChain chains as REST APIs.
+- **[LangServe](https://python.langchain.com/docs/langserve)**: A library for deploying LangChain chains as REST APIs.
 
 ![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](docs/static/svg/langchain_stack.svg "LangChain Architecture Overview")
 
@@ -61,20 +61,20 @@ For these applications, LangChain simplifies the entire application lifecycle:
 
 **❓ Question answering with RAG**
 
-- [Documentation](https://python.langchain.com/v0.2/docs/tutorials/rag/)
+- [Documentation](https://python.langchain.com/docs/use_cases/question_answering/)
 - End-to-end Example: [Chat LangChain](https://chat.langchain.com) and [repo](https://github.com/langchain-ai/chat-langchain)
 
 **🧱 Extracting structured output**
 
-- [Documentation](https://python.langchain.com/v0.2/docs/tutorials/extraction/)
+- [Documentation](https://python.langchain.com/docs/use_cases/extraction/)
 - End-to-end Example: [SQL Llama2 Template](https://github.com/langchain-ai/langchain-extract/)
 
 **🤖 Chatbots**
 
-- [Documentation](https://python.langchain.com/v0.2/docs/tutorials/chatbot/)
+- [Documentation](https://python.langchain.com/docs/use_cases/chatbots)
 - End-to-end Example: [Web LangChain (web researcher chatbot)](https://weblangchain.vercel.app) and [repo](https://github.com/langchain-ai/weblangchain)
 
-And much more! Head to the [Tutorials](https://python.langchain.com/v0.2/docs/tutorials/) section of the docs for more.
+And much more! Head to the [Use cases](https://python.langchain.com/docs/use_cases/) section of the docs for more.
 
 ## 🚀 How does LangChain help?
 The main value props of the LangChain libraries are:
@@ -87,50 +87,49 @@ Off-the-shelf chains make it easy to get started. Components make it easy to cus
 
 LCEL is the foundation of many of LangChain's components, and is a declarative way to compose chains. LCEL was designed from day 1 to support putting prototypes in production, with no code changes, from the simplest “prompt + LLM” chain to the most complex chains.
 
-- **[Overview](https://python.langchain.com/v0.2/docs/concepts/#langchain-expression-language-lcel)**: LCEL and its benefits
-- **[Interface](https://python.langchain.com/v0.2/docs/concepts/#runnable-interface)**: The standard Runnable interface for LCEL objects
-- **[Primitives](https://python.langchain.com/v0.2/docs/how_to/#langchain-expression-language-lcel)**: More on the primitives LCEL includes
-- **[Cheatsheet](https://python.langchain.com/v0.2/docs/how_to/lcel_cheatsheet/)**: Quick overview of the most common usage patterns
+- **[Overview](https://python.langchain.com/docs/expression_language/)**: LCEL and its benefits
+- **[Interface](https://python.langchain.com/docs/expression_language/interface)**: The standard interface for LCEL objects
+- **[Primitives](https://python.langchain.com/docs/expression_language/primitives)**: More on the primitives LCEL includes
 
 ## Components
 
 Components fall into the following **modules**:
 
-**📃 Model I/O**
+**📃 Model I/O:**
 
-This includes [prompt management](https://python.langchain.com/v0.2/docs/concepts/#prompt-templates), [prompt optimization](https://python.langchain.com/v0.2/docs/concepts/#example-selectors), a generic interface for [chat models](https://python.langchain.com/v0.2/docs/concepts/#chat-models) and [LLMs](https://python.langchain.com/v0.2/docs/concepts/#llms), and common utilities for working with [model outputs](https://python.langchain.com/v0.2/docs/concepts/#output-parsers).
+This includes [prompt management](https://python.langchain.com/docs/modules/model_io/prompts/), [prompt optimization](https://python.langchain.com/docs/modules/model_io/prompts/example_selectors/), a generic interface for [chat models](https://python.langchain.com/docs/modules/model_io/chat/) and [LLMs](https://python.langchain.com/docs/modules/model_io/llms/), and common utilities for working with [model outputs](https://python.langchain.com/docs/modules/model_io/output_parsers/).
 
-**📚 Retrieval**
+**📚 Retrieval:**
 
-Retrieval Augmented Generation involves [loading data](https://python.langchain.com/v0.2/docs/concepts/#document-loaders) from a variety of sources, [preparing it](https://python.langchain.com/v0.2/docs/concepts/#text-splitters), then [searching over (a.k.a. retrieving from)](https://python.langchain.com/v0.2/docs/concepts/#retrievers) it for use in the generation step.
+Retrieval Augmented Generation involves [loading data](https://python.langchain.com/docs/modules/data_connection/document_loaders/) from a variety of sources, [preparing it](https://python.langchain.com/docs/modules/data_connection/document_loaders/), [then retrieving it](https://python.langchain.com/docs/modules/data_connection/retrievers/) for use in the generation step.
 
-**🤖 Agents**
+**🤖 Agents:**
 
-Agents allow an LLM autonomy over how a task is accomplished. Agents make decisions about which Actions to take, then take that Action, observe the result, and repeat until the task is complete. LangChain provides a [standard interface for agents](https://python.langchain.com/v0.2/docs/concepts/#agents) along with the [LangGraph](https://github.com/langchain-ai/langgraph) extension for building custom agents.
+Agents allow an LLM autonomy over how a task is accomplished. Agents make decisions about which Actions to take, then take that Action, observe the result, and repeat until the task is complete done. LangChain provides a [standard interface for agents](https://python.langchain.com/docs/modules/agents/), a [selection of agents](https://python.langchain.com/docs/modules/agents/agent_types/) to choose from, and examples of end-to-end agents.
 
 ## 📖 Documentation
 
 Please see [here](https://python.langchain.com) for full documentation, which includes:
 
-- [Introduction](https://python.langchain.com/v0.2/docs/introduction/): Overview of the framework and the structure of the docs.
-- [Tutorials](https://python.langchain.com/docs/use_cases/): If you're looking to build something specific or are more of a hands-on learner, check out our tutorials. This is the best place to get started.
-- [How-to guides](https://python.langchain.com/v0.2/docs/how_to/): Answers to “How do I….?” type questions. These guides are goal-oriented and concrete; they're meant to help you complete a specific task.
-- [Conceptual guide](https://python.langchain.com/v0.2/docs/concepts/): Conceptual explanations of the key parts of the framework.
-- [API Reference](https://api.python.langchain.com): Thorough documentation of every class and method.
+- [Getting started](https://python.langchain.com/docs/get_started/introduction): installation, setting up the environment, simple examples
+- [Use case](https://python.langchain.com/docs/use_cases/) walkthroughs and best practice [guides](https://python.langchain.com/docs/guides/)
+- Overviews of the [interfaces](https://python.langchain.com/docs/expression_language/), [components](https://python.langchain.com/docs/modules/), and [integrations](https://python.langchain.com/docs/integrations/providers)
+
+You can also check out the full [API Reference docs](https://api.python.langchain.com).
 
 ## 🌐 Ecosystem
 
-- [🦜🛠️ LangSmith](https://docs.smith.langchain.com/): Tracing and evaluating your language model applications and intelligent agents to help you move from prototype to production.
-- [🦜🕸️ LangGraph](https://langchain-ai.github.io/langgraph/): Creating stateful, multi-actor applications with LLMs, built on top of (and intended to be used with) LangChain primitives.
+- [🦜🛠️ LangSmith](https://python.langchain.com/docs/langsmith/): Tracing and evaluating your language model applications and intelligent agents to help you move from prototype to production.
+- [🦜🕸️ LangGraph](https://python.langchain.com/docs/langgraph): Creating stateful, multi-actor applications with LLMs, built on top of (and intended to be used with) LangChain primitives.
 - [🦜🏓 LangServe](https://python.langchain.com/docs/langserve): Deploying LangChain runnables and chains as REST APIs.
-  - [LangChain Templates](https://python.langchain.com/v0.2/docs/templates/): Example applications hosted with LangServe.
+  - [LangChain Templates](https://python.langchain.com/docs/templates/): Example applications hosted with LangServe.
 
 
 ## 💁 Contributing
 
 As an open-source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infrastructure, or better documentation.
 
-For detailed information on how to contribute, see [here](https://python.langchain.com/v0.2/docs/contributing/).
+For detailed information on how to contribute, see [here](https://python.langchain.com/docs/contributing/).
 
 ## 🌟 Contributors
 

cookbook/Multi_modal_RAG.ipynb

@@ -464,8 +464,8 @@
     "    Check if the base64 data is an image by looking at the start of the data\n",
     "    \"\"\"\n",
     "    image_signatures = {\n",
-    "        b\"\\xff\\xd8\\xff\": \"jpg\",\n",
-    "        b\"\\x89\\x50\\x4e\\x47\\x0d\\x0a\\x1a\\x0a\": \"png\",\n",
+    "        b\"\\xFF\\xD8\\xFF\": \"jpg\",\n",
+    "        b\"\\x89\\x50\\x4E\\x47\\x0D\\x0A\\x1A\\x0A\": \"png\",\n",
     "        b\"\\x47\\x49\\x46\\x38\": \"gif\",\n",
     "        b\"\\x52\\x49\\x46\\x46\": \"webp\",\n",
     "    }\n",
@@ -604,7 +604,7 @@
    "source": [
     "# Check retrieval\n",
     "query = \"Give me company names that are interesting investments based on EV / NTM and NTM rev growth. Consider EV / NTM multiples vs historical?\"\n",
-    "docs = retriever_multi_vector_img.invoke(query, limit=6)\n",
+    "docs = retriever_multi_vector_img.get_relevant_documents(query, limit=6)\n",
     "\n",
     "# We get 4 docs\n",
     "len(docs)"
@@ -630,7 +630,7 @@
    "source": [
     "# Check retrieval\n",
     "query = \"What are the EV / NTM and NTM rev growth for MongoDB, Cloudflare, and Datadog?\"\n",
-    "docs = retriever_multi_vector_img.invoke(query, limit=6)\n",
+    "docs = retriever_multi_vector_img.get_relevant_documents(query, limit=6)\n",
     "\n",
     "# We get 4 docs\n",
     "len(docs)"

cookbook/Multi_modal_RAG_google.ipynb

@@ -185,7 +185,7 @@
     "    )\n",
     "    # Text summary chain\n",
     "    model = VertexAI(\n",
-    "        temperature=0, model_name=\"gemini-pro\", max_tokens=1024\n",
+    "        temperature=0, model_name=\"gemini-pro\", max_output_tokens=1024\n",
     "    ).with_fallbacks([empty_response])\n",
     "    summarize_chain = {\"element\": lambda x: x} | prompt | model | StrOutputParser()\n",
     "\n",
@@ -254,9 +254,9 @@
     "\n",
     "def image_summarize(img_base64, prompt):\n",
     "    \"\"\"Make image summary\"\"\"\n",
-    "    model = ChatVertexAI(model=\"gemini-pro-vision\", max_tokens=1024)\n",
+    "    model = ChatVertexAI(model_name=\"gemini-pro-vision\", max_output_tokens=1024)\n",
     "\n",
-    "    msg = model.invoke(\n",
+    "    msg = model(\n",
     "        [\n",
     "            HumanMessage(\n",
     "                content=[\n",
@@ -462,8 +462,8 @@
     "    Check if the base64 data is an image by looking at the start of the data\n",
     "    \"\"\"\n",
     "    image_signatures = {\n",
-    "        b\"\\xff\\xd8\\xff\": \"jpg\",\n",
-    "        b\"\\x89\\x50\\x4e\\x47\\x0d\\x0a\\x1a\\x0a\": \"png\",\n",
+    "        b\"\\xFF\\xD8\\xFF\": \"jpg\",\n",
+    "        b\"\\x89\\x50\\x4E\\x47\\x0D\\x0A\\x1A\\x0A\": \"png\",\n",
     "        b\"\\x47\\x49\\x46\\x38\": \"gif\",\n",
     "        b\"\\x52\\x49\\x46\\x46\": \"webp\",\n",
     "    }\n",
@@ -553,7 +553,9 @@
     "    \"\"\"\n",
     "\n",
     "    # Multi-modal LLM\n",
-    "    model = ChatVertexAI(temperature=0, model_name=\"gemini-pro-vision\", max_tokens=1024)\n",
+    "    model = ChatVertexAI(\n",
+    "        temperature=0, model_name=\"gemini-pro-vision\", max_output_tokens=1024\n",
+    "    )\n",
     "\n",
     "    # RAG pipeline\n",
     "    chain = (\n",
@@ -602,7 +604,7 @@
    ],
    "source": [
     "query = \"What are the EV / NTM and NTM rev growth for MongoDB, Cloudflare, and Datadog?\"\n",
-    "docs = retriever_multi_vector_img.invoke(query, limit=1)\n",
+    "docs = retriever_multi_vector_img.get_relevant_documents(query, limit=1)\n",
     "\n",
     "# We get 2 docs\n",
     "len(docs)"

cookbook/RAPTOR.ipynb

@@ -535,9 +535,9 @@
     "    print(f\"--Generated {len(all_clusters)} clusters--\")\n",
     "\n",
     "    # Summarization\n",
-    "    template = \"\"\"Here is a sub-set of LangChain Expression Language doc. \n",
+    "    template = \"\"\"Here is a sub-set of LangChain Expression Langauge doc. \n",
     "    \n",
-    "    LangChain Expression Language provides a way to compose chain in LangChain.\n",
+    "    LangChain Expression Langauge provides a way to compose chain in LangChain.\n",
     "    \n",
     "    Give a detailed summary of the documentation provided.\n",
     "    \n",

cookbook/README.md

@@ -47,7 +47,6 @@ Notebook | Description
 [press_releases.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/press_releases.ipynb) | Retrieve and query company press release data powered by [Kay.ai](https://kay.ai).
 [program_aided_language_model.i...](https://github.com/langchain-ai/langchain/tree/master/cookbook/program_aided_language_model.ipynb) | Implement program-aided language models as described in the provided research paper.
 [qa_citations.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/qa_citations.ipynb) | Different ways to get a model to cite its sources.
-[rag_upstage_layout_analysis_groundedness_check.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/rag_upstage_layout_analysis_groundedness_check.ipynb) | End-to-end RAG example using Upstage Layout Analysis and Groundedness Check.
 [retrieval_in_sql.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/retrieval_in_sql.ipynb) | Perform retrieval-augmented-generation (rag) on a PostgreSQL database using pgvector.
 [sales_agent_with_context.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/sales_agent_with_context.ipynb) | Implement a context-aware ai sales agent, salesgpt, that can have natural sales conversations, interact with other systems, and use a product knowledge base to discuss a company's offerings.
 [self_query_hotel_search.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/self_query_hotel_search.ipynb) | Build a hotel room search feature with self-querying retrieval, using a specific hotel recommendation dataset.
@@ -57,4 +56,3 @@ Notebook | Description
 [two_agent_debate_tools.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/two_agent_debate_tools.ipynb) | Simulate multi-agent dialogues where the agents can utilize various tools.
 [two_player_dnd.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/two_player_dnd.ipynb) | Simulate a two-player dungeons & dragons game, where a dialogue simulator class is used to coordinate the dialogue between the protagonist and the dungeon master.
 [wikibase_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/wikibase_agent.ipynb) | Create a simple wikibase agent that utilizes sparql generation, with testing done on http://wikidata.org.
-[oracleai_demo.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/oracleai_demo.ipynb) | This guide outlines how to utilize Oracle AI Vector Search alongside Langchain for an end-to-end RAG pipeline, providing step-by-step examples. The process includes loading documents from various sources using OracleDocLoader, summarizing them either within or outside the database with OracleSummary, and generating embeddings similarly through OracleEmbeddings. It also covers chunking documents according to specific requirements using Advanced Oracle Capabilities from OracleTextSplitter, and finally, storing and indexing these documents in a Vector Store for querying with OracleVS.

cookbook/Semi_Structured_RAG.ipynb

@@ -75,7 +75,7 @@
     "\n",
     "Apply to the [`LLaMA2`](https://arxiv.org/pdf/2307.09288.pdf) paper. \n",
     "\n",
-    "We use the Unstructured [`partition_pdf`](https://unstructured-io.github.io/unstructured/core/partition.html#partition-pdf), which segments a PDF document by using a layout model. \n",
+    "We use the Unstructured [`partition_pdf`](https://unstructured-io.github.io/unstructured/bricks/partition.html#partition-pdf), which segments a PDF document by using a layout model. \n",
     "\n",
     "This layout model makes it possible to extract elements, such as tables, from pdfs. \n",
     "\n",

cookbook/Semi_structured_and_multi_modal_RAG.ipynb

@@ -562,7 +562,9 @@
    ],
    "source": [
     "# We can retrieve this table\n",
-    "retriever.invoke(\"What are results for LLaMA across across domains / subjects?\")[1]"
+    "retriever.get_relevant_documents(\n",
+    "    \"What are results for LLaMA across across domains / subjects?\"\n",
+    ")[1]"
    ]
   },
   {
@@ -612,7 +614,9 @@
     }
    ],
    "source": [
-    "retriever.invoke(\"Images / figures with playful and creative examples\")[1]"
+    "retriever.get_relevant_documents(\"Images / figures with playful and creative examples\")[\n",
+    "    1\n",
+    "]"
    ]
   },
   {

cookbook/Semi_structured_multi_modal_RAG_LLaMA2.ipynb

@@ -501,7 +501,9 @@
     }
    ],
    "source": [
-    "retriever.invoke(\"Images / figures with playful and creative examples\")[0]"
+    "retriever.get_relevant_documents(\"Images / figures with playful and creative examples\")[\n",
+    "    0\n",
+    "]"
    ]
   },
   {

cookbook/advanced_rag_eval.ipynb

@@ -342,7 +342,7 @@
     "# Testing on retrieval\n",
     "query = \"What percentage of CPI is dedicated to Housing, and how does it compare to the combined percentage of Medical Care, Apparel, and Other Goods and Services?\"\n",
     "suffix_for_images = \" Include any pie charts, graphs, or tables.\"\n",
-    "docs = retriever_multi_vector_img.invoke(query + suffix_for_images)"
+    "docs = retriever_multi_vector_img.get_relevant_documents(query + suffix_for_images)"
    ]
   },
   {
@@ -532,8 +532,8 @@
     "def is_image_data(b64data):\n",
     "    \"\"\"Check if the base64 data is an image by looking at the start of the data.\"\"\"\n",
     "    image_signatures = {\n",
-    "        b\"\\xff\\xd8\\xff\": \"jpg\",\n",
-    "        b\"\\x89\\x50\\x4e\\x47\\x0d\\x0a\\x1a\\x0a\": \"png\",\n",
+    "        b\"\\xFF\\xD8\\xFF\": \"jpg\",\n",
+    "        b\"\\x89\\x50\\x4E\\x47\\x0D\\x0A\\x1A\\x0A\": \"png\",\n",
     "        b\"\\x47\\x49\\x46\\x38\": \"gif\",\n",
     "        b\"\\x52\\x49\\x46\\x46\": \"webp\",\n",
     "    }\n",

cookbook/autogpt/marathon_times.ipynb

@@ -46,7 +46,7 @@
     "from langchain_experimental.autonomous_agents import AutoGPT\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "# Needed since jupyter runs an async eventloop\n",
+    "# Needed synce jupyter runs an async eventloop\n",
     "nest_asyncio.apply()"
    ]
   },

cookbook/camel_role_playing.ipynb

@@ -90,7 +90,7 @@
     "    ) -> AIMessage:\n",
     "        messages = self.update_messages(input_message)\n",
     "\n",
-    "        output_message = self.model.invoke(messages)\n",
+    "        output_message = self.model(messages)\n",
     "        self.update_messages(output_message)\n",
     "\n",
     "        return output_message"

cookbook/cql_agent.ipynb

@@ -1,557 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup Environment"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Python Modules"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Install the following Python modules:\n",
-    "\n",
-    "```bash\n",
-    "pip install ipykernel python-dotenv cassio pandas langchain_openai langchain langchain-community langchainhub langchain_experimental openai-multi-tool-use-parallel-patch\n",
-    "```"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Load the `.env` File"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Connection is via `cassio` using `auto=True` parameter, and the notebook uses OpenAI. You should create a `.env` file accordingly.\n",
-    "\n",
-    "For Casssandra, set:\n",
-    "```bash\n",
-    "CASSANDRA_CONTACT_POINTS\n",
-    "CASSANDRA_USERNAME\n",
-    "CASSANDRA_PASSWORD\n",
-    "CASSANDRA_KEYSPACE\n",
-    "```\n",
-    "\n",
-    "For Astra, set:\n",
-    "```bash\n",
-    "ASTRA_DB_APPLICATION_TOKEN\n",
-    "ASTRA_DB_DATABASE_ID\n",
-    "ASTRA_DB_KEYSPACE\n",
-    "```\n",
-    "\n",
-    "For example:\n",
-    "\n",
-    "```bash\n",
-    "# Connection to Astra:\n",
-    "ASTRA_DB_DATABASE_ID=a1b2c3d4-...\n",
-    "ASTRA_DB_APPLICATION_TOKEN=AstraCS:...\n",
-    "ASTRA_DB_KEYSPACE=notebooks\n",
-    "\n",
-    "# Also set \n",
-    "OPENAI_API_KEY=sk-....\n",
-    "```\n",
-    "\n",
-    "(You may also modify the below code to directly connect with `cassio`.)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from dotenv import load_dotenv\n",
-    "\n",
-    "load_dotenv(override=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Connect to Cassandra"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "\n",
-    "import cassio\n",
-    "\n",
-    "cassio.init(auto=True)\n",
-    "session = cassio.config.resolve_session()\n",
-    "if not session:\n",
-    "    raise Exception(\n",
-    "        \"Check environment configuration or manually configure cassio connection parameters\"\n",
-    "    )\n",
-    "\n",
-    "keyspace = os.environ.get(\n",
-    "    \"ASTRA_DB_KEYSPACE\", os.environ.get(\"CASSANDRA_KEYSPACE\", None)\n",
-    ")\n",
-    "if not keyspace:\n",
-    "    raise ValueError(\"a KEYSPACE environment variable must be set\")\n",
-    "\n",
-    "session.set_keyspace(keyspace)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup Database"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "This needs to be done one time only!"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Download Data"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The dataset used is from Kaggle, the [Environmental Sensor Telemetry Data](https://www.kaggle.com/datasets/garystafford/environmental-sensor-data-132k?select=iot_telemetry_data.csv). The next cell will download and unzip the data into a Pandas dataframe. The following cell is instructions to download manually. \n",
-    "\n",
-    "The net result of this section is you should have a Pandas dataframe variable `df`."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Download Automatically"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from io import BytesIO\n",
-    "from zipfile import ZipFile\n",
-    "\n",
-    "import pandas as pd\n",
-    "import requests\n",
-    "\n",
-    "datasetURL = \"https://storage.googleapis.com/kaggle-data-sets/788816/1355729/bundle/archive.zip?X-Goog-Algorithm=GOOG4-RSA-SHA256&X-Goog-Credential=gcp-kaggle-com%40kaggle-161607.iam.gserviceaccount.com%2F20240404%2Fauto%2Fstorage%2Fgoog4_request&X-Goog-Date=20240404T115828Z&X-Goog-Expires=259200&X-Goog-SignedHeaders=host&X-Goog-Signature=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\"\n",
-    "\n",
-    "response = requests.get(datasetURL)\n",
-    "if response.status_code == 200:\n",
-    "    zip_file = ZipFile(BytesIO(response.content))\n",
-    "    csv_file_name = zip_file.namelist()[0]\n",
-    "else:\n",
-    "    print(\"Failed to download the file\")\n",
-    "\n",
-    "with zip_file.open(csv_file_name) as csv_file:\n",
-    "    df = pd.read_csv(csv_file)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Download Manually"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can download the `.zip` file and unpack the `.csv` contained within. Comment in the next line, and adjust the path to this `.csv` file appropriately."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# df = pd.read_csv(\"/path/to/iot_telemetry_data.csv\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Load Data into Cassandra"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "This section assumes the existence of a dataframe `df`, the following cell validates its structure. The Download section above creates this object."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "assert df is not None, \"Dataframe 'df' must be set\"\n",
-    "expected_columns = [\n",
-    "    \"ts\",\n",
-    "    \"device\",\n",
-    "    \"co\",\n",
-    "    \"humidity\",\n",
-    "    \"light\",\n",
-    "    \"lpg\",\n",
-    "    \"motion\",\n",
-    "    \"smoke\",\n",
-    "    \"temp\",\n",
-    "]\n",
-    "assert all(\n",
-    "    [column in df.columns for column in expected_columns]\n",
-    "), \"DataFrame does not have the expected columns\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Create and load tables:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from datetime import UTC, datetime\n",
-    "\n",
-    "from cassandra.query import BatchStatement\n",
-    "\n",
-    "# Create sensors table\n",
-    "table_query = \"\"\"\n",
-    "CREATE TABLE IF NOT EXISTS iot_sensors (\n",
-    "    device text,\n",
-    "    conditions text,\n",
-    "    room text,\n",
-    "    PRIMARY KEY (device)\n",
-    ")\n",
-    "WITH COMMENT = 'Environmental IoT room sensor metadata.';\n",
-    "\"\"\"\n",
-    "session.execute(table_query)\n",
-    "\n",
-    "pstmt = session.prepare(\n",
-    "    \"\"\"\n",
-    "INSERT INTO iot_sensors (device, conditions, room)\n",
-    "VALUES (?, ?, ?)\n",
-    "\"\"\"\n",
-    ")\n",
-    "\n",
-    "devices = [\n",
-    "    (\"00:0f:00:70:91:0a\", \"stable conditions, cooler and more humid\", \"room 1\"),\n",
-    "    (\"1c:bf:ce:15:ec:4d\", \"highly variable temperature and humidity\", \"room 2\"),\n",
-    "    (\"b8:27:eb:bf:9d:51\", \"stable conditions, warmer and dryer\", \"room 3\"),\n",
-    "]\n",
-    "\n",
-    "for device, conditions, room in devices:\n",
-    "    session.execute(pstmt, (device, conditions, room))\n",
-    "\n",
-    "print(\"Sensors inserted successfully.\")\n",
-    "\n",
-    "# Create data table\n",
-    "table_query = \"\"\"\n",
-    "CREATE TABLE IF NOT EXISTS iot_data (\n",
-    "    day text,\n",
-    "    device text,\n",
-    "    ts timestamp,\n",
-    "    co double,\n",
-    "    humidity double,\n",
-    "    light boolean,\n",
-    "    lpg double,\n",
-    "    motion boolean,\n",
-    "    smoke double,\n",
-    "    temp double,\n",
-    "    PRIMARY KEY ((day, device), ts)\n",
-    ")\n",
-    "WITH COMMENT = 'Data from environmental IoT room sensors. Columns include device identifier, timestamp (ts) of the data collection, carbon monoxide level (co), relative humidity, light presence, LPG concentration, motion detection, smoke concentration, and temperature (temp). Data is partitioned by day and device.';\n",
-    "\"\"\"\n",
-    "session.execute(table_query)\n",
-    "\n",
-    "pstmt = session.prepare(\n",
-    "    \"\"\"\n",
-    "INSERT INTO iot_data (day, device, ts, co, humidity, light, lpg, motion, smoke, temp)\n",
-    "VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)\n",
-    "\"\"\"\n",
-    ")\n",
-    "\n",
-    "\n",
-    "def insert_data_batch(name, group):\n",
-    "    batch = BatchStatement()\n",
-    "    day, device = name\n",
-    "    print(f\"Inserting batch for day: {day}, device: {device}\")\n",
-    "\n",
-    "    for _, row in group.iterrows():\n",
-    "        timestamp = datetime.fromtimestamp(row[\"ts\"], UTC)\n",
-    "        batch.add(\n",
-    "            pstmt,\n",
-    "            (\n",
-    "                day,\n",
-    "                row[\"device\"],\n",
-    "                timestamp,\n",
-    "                row[\"co\"],\n",
-    "                row[\"humidity\"],\n",
-    "                row[\"light\"],\n",
-    "                row[\"lpg\"],\n",
-    "                row[\"motion\"],\n",
-    "                row[\"smoke\"],\n",
-    "                row[\"temp\"],\n",
-    "            ),\n",
-    "        )\n",
-    "\n",
-    "    session.execute(batch)\n",
-    "\n",
-    "\n",
-    "# Convert columns to appropriate types\n",
-    "df[\"light\"] = df[\"light\"] == \"true\"\n",
-    "df[\"motion\"] = df[\"motion\"] == \"true\"\n",
-    "df[\"ts\"] = df[\"ts\"].astype(float)\n",
-    "df[\"day\"] = df[\"ts\"].apply(\n",
-    "    lambda x: datetime.fromtimestamp(x, UTC).strftime(\"%Y-%m-%d\")\n",
-    ")\n",
-    "\n",
-    "grouped_df = df.groupby([\"day\", \"device\"])\n",
-    "\n",
-    "for name, group in grouped_df:\n",
-    "    insert_data_batch(name, group)\n",
-    "\n",
-    "print(\"Data load complete\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "print(session.keyspace)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Load the Tools"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Python `import` statements for the demo:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.agents import AgentExecutor, create_openai_tools_agent\n",
-    "from langchain_community.agent_toolkits.cassandra_database.toolkit import (\n",
-    "    CassandraDatabaseToolkit,\n",
-    ")\n",
-    "from langchain_community.tools.cassandra_database.prompt import QUERY_PATH_PROMPT\n",
-    "from langchain_community.tools.cassandra_database.tool import (\n",
-    "    GetSchemaCassandraDatabaseTool,\n",
-    "    GetTableDataCassandraDatabaseTool,\n",
-    "    QueryCassandraDatabaseTool,\n",
-    ")\n",
-    "from langchain_community.utilities.cassandra_database import CassandraDatabase\n",
-    "from langchain_openai import ChatOpenAI"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The `CassandraDatabase` object is loaded from `cassio`, though it does accept a `Session`-type parameter as an alternative."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Create a CassandraDatabase instance\n",
-    "db = CassandraDatabase(include_tables=[\"iot_sensors\", \"iot_data\"])\n",
-    "\n",
-    "# Create the Cassandra Database tools\n",
-    "query_tool = QueryCassandraDatabaseTool(db=db)\n",
-    "schema_tool = GetSchemaCassandraDatabaseTool(db=db)\n",
-    "select_data_tool = GetTableDataCassandraDatabaseTool(db=db)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The tools can be invoked directly:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Test the tools\n",
-    "print(\"Executing a CQL query:\")\n",
-    "query = \"SELECT * FROM iot_sensors LIMIT 5;\"\n",
-    "result = query_tool.run({\"query\": query})\n",
-    "print(result)\n",
-    "\n",
-    "print(\"\\nGetting the schema for a keyspace:\")\n",
-    "schema = schema_tool.run({\"keyspace\": keyspace})\n",
-    "print(schema)\n",
-    "\n",
-    "print(\"\\nGetting data from a table:\")\n",
-    "table = \"iot_data\"\n",
-    "predicate = \"day = '2020-07-14' and device = 'b8:27:eb:bf:9d:51'\"\n",
-    "data = select_data_tool.run(\n",
-    "    {\"keyspace\": keyspace, \"table\": table, \"predicate\": predicate, \"limit\": 5}\n",
-    ")\n",
-    "print(data)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Agent Configuration"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.agents import Tool\n",
-    "from langchain_experimental.utilities import PythonREPL\n",
-    "\n",
-    "python_repl = PythonREPL()\n",
-    "\n",
-    "repl_tool = 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",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain import hub\n",
-    "\n",
-    "llm = ChatOpenAI(temperature=0, model=\"gpt-4-1106-preview\")\n",
-    "toolkit = CassandraDatabaseToolkit(db=db)\n",
-    "\n",
-    "# context = toolkit.get_context()\n",
-    "# tools = toolkit.get_tools()\n",
-    "tools = [schema_tool, select_data_tool, repl_tool]\n",
-    "\n",
-    "input = (\n",
-    "    QUERY_PATH_PROMPT\n",
-    "    + f\"\"\"\n",
-    "\n",
-    "Here is your task: In the {keyspace} keyspace, find the total number of times the temperature of each device has exceeded 23 degrees on July 14, 2020.\n",
-    " Create a summary report including the name of the room. Use Pandas if helpful.\n",
-    "\"\"\"\n",
-    ")\n",
-    "\n",
-    "prompt = hub.pull(\"hwchase17/openai-tools-agent\")\n",
-    "\n",
-    "# messages = [\n",
-    "#     HumanMessagePromptTemplate.from_template(input),\n",
-    "#     AIMessage(content=QUERY_PATH_PROMPT),\n",
-    "#     MessagesPlaceholder(variable_name=\"agent_scratchpad\"),\n",
-    "# ]\n",
-    "\n",
-    "# prompt = ChatPromptTemplate.from_messages(messages)\n",
-    "# print(prompt)\n",
-    "\n",
-    "# Choose the LLM that will drive the agent\n",
-    "# Only certain models support this\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-1106\", temperature=0)\n",
-    "\n",
-    "# Construct the OpenAI Tools agent\n",
-    "agent = create_openai_tools_agent(llm, tools, prompt)\n",
-    "\n",
-    "print(\"Available tools:\")\n",
-    "for tool in tools:\n",
-    "    print(\"\\t\" + tool.name + \" - \" + tool.description + \" - \" + str(tool))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)\n",
-    "\n",
-    "response = agent_executor.invoke({\"input\": input})\n",
-    "\n",
-    "print(response[\"output\"])"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.9.1"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

cookbook/custom_agent_with_plugin_retrieval.ipynb

@@ -169,7 +169,7 @@
     "\n",
     "def get_tools(query):\n",
     "    # Get documents, which contain the Plugins to use\n",
-    "    docs = retriever.invoke(query)\n",
+    "    docs = retriever.get_relevant_documents(query)\n",
     "    # Get the toolkits, one for each plugin\n",
     "    tool_kits = [toolkits_dict[d.metadata[\"plugin_name\"]] for d in docs]\n",
     "    # Get the tools: a separate NLAChain for each endpoint\n",

cookbook/custom_agent_with_plugin_retrieval_using_plugnplai.ipynb

@@ -193,7 +193,7 @@
     "\n",
     "def get_tools(query):\n",
     "    # Get documents, which contain the Plugins to use\n",
-    "    docs = retriever.invoke(query)\n",
+    "    docs = retriever.get_relevant_documents(query)\n",
     "    # Get the toolkits, one for each plugin\n",
     "    tool_kits = [toolkits_dict[d.metadata[\"plugin_name\"]] for d in docs]\n",
     "    # Get the tools: a separate NLAChain for each endpoint\n",

cookbook/custom_agent_with_tool_retrieval.ipynb

@@ -142,7 +142,7 @@
     "\n",
     "\n",
     "def get_tools(query):\n",
-    "    docs = retriever.invoke(query)\n",
+    "    docs = retriever.get_relevant_documents(query)\n",
     "    return [ALL_TOOLS[d.metadata[\"index\"]] for d in docs]"
    ]
   },

cookbook/forward_looking_retrieval_augmented_generation.ipynb

@@ -362,7 +362,7 @@
    ],
    "source": [
     "llm = OpenAI()\n",
-    "llm.invoke(query)"
+    "llm(query)"
    ]
   },
   {

cookbook/gymnasium_agent_simulation.ipynb

@@ -108,7 +108,7 @@
     "        return obs_message\n",
     "\n",
     "    def _act(self):\n",
-    "        act_message = self.model.invoke(self.message_history)\n",
+    "        act_message = self.model(self.message_history)\n",
     "        self.message_history.append(act_message)\n",
     "        action = int(self.action_parser.parse(act_message.content)[\"action\"])\n",
     "        return action\n",

cookbook/langgraph_crag.ipynb

@@ -206,7 +206,7 @@
     "    print(\"---RETRIEVE---\")\n",
     "    state_dict = state[\"keys\"]\n",
     "    question = state_dict[\"question\"]\n",
-    "    documents = retriever.invoke(question)\n",
+    "    documents = retriever.get_relevant_documents(question)\n",
     "    return {\"keys\": {\"documents\": documents, \"question\": question}}\n",
     "\n",
     "\n",

cookbook/langgraph_self_rag.ipynb

@@ -213,7 +213,7 @@
     "    print(\"---RETRIEVE---\")\n",
     "    state_dict = state[\"keys\"]\n",
     "    question = state_dict[\"question\"]\n",
-    "    documents = retriever.invoke(question)\n",
+    "    documents = retriever.get_relevant_documents(question)\n",
     "    return {\"keys\": {\"documents\": documents, \"question\": question}}\n",
     "\n",
     "\n",

cookbook/mongodb-langchain-cache-memory.ipynb

@@ -1,818 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "70b333e6",
-   "metadata": {},
-   "source": [
-    "[![View Article](https://img.shields.io/badge/View%20Article-blue)](https://www.mongodb.com/developer/products/atlas/advanced-rag-langchain-mongodb/)\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "d84a72ea",
-   "metadata": {},
-   "source": [
-    "# Adding Semantic Caching and Memory to your RAG Application using MongoDB and LangChain\n",
-    "\n",
-    "In this notebook, we will see how to use the new MongoDBCache and MongoDBChatMessageHistory in your RAG application.\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "65527202",
-   "metadata": {},
-   "source": [
-    "## Step 1: Install required libraries\n",
-    "\n",
-    "- **datasets**: Python library to get access to datasets available on Hugging Face Hub\n",
-    "\n",
-    "- **langchain**: Python toolkit for LangChain\n",
-    "\n",
-    "- **langchain-mongodb**: Python package to use MongoDB as a vector store, semantic cache, chat history store etc. in LangChain\n",
-    "\n",
-    "- **langchain-openai**: Python package to use OpenAI models with LangChain\n",
-    "\n",
-    "- **pymongo**: Python toolkit for MongoDB\n",
-    "\n",
-    "- **pandas**: Python library for data analysis, exploration, and manipulation"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "cbc22fa4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "! pip install -qU datasets langchain langchain-mongodb langchain-openai pymongo pandas"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "39c41e87",
-   "metadata": {},
-   "source": [
-    "## Step 2: Setup pre-requisites\n",
-    "\n",
-    "* Set the MongoDB connection string. Follow the steps [here](https://www.mongodb.com/docs/manual/reference/connection-string/) to get the connection string from the Atlas UI.\n",
-    "\n",
-    "* Set the OpenAI API key. Steps to obtain an API key as [here](https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "b56412ae",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import getpass"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "16a20d7a",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Enter your MongoDB connection string:········\n"
-     ]
-    }
-   ],
-   "source": [
-    "MONGODB_URI = getpass.getpass(\"Enter your MongoDB connection string:\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "978682d4",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Enter your OpenAI API key:········\n"
-     ]
-    }
-   ],
-   "source": [
-    "OPENAI_API_KEY = getpass.getpass(\"Enter your OpenAI API key:\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "606081c5",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "········\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Optional-- If you want to enable Langsmith -- good for debugging\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f6b8302c",
-   "metadata": {},
-   "source": [
-    "## Step 3: Download the dataset\n",
-    "\n",
-    "We will be using MongoDB's [embedded_movies](https://huggingface.co/datasets/MongoDB/embedded_movies) dataset"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "1a3433a6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import pandas as pd\n",
-    "from datasets import load_dataset"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "aee5311b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Ensure you have an HF_TOKEN in your development enviornment:\n",
-    "# access tokens can be created or copied from the Hugging Face platform (https://huggingface.co/docs/hub/en/security-tokens)\n",
-    "\n",
-    "# Load MongoDB's embedded_movies dataset from Hugging Face\n",
-    "# https://huggingface.co/datasets/MongoDB/airbnb_embeddings\n",
-    "\n",
-    "data = load_dataset(\"MongoDB/embedded_movies\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "1d630a26",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df = pd.DataFrame(data[\"train\"])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "a1f94f43",
-   "metadata": {},
-   "source": [
-    "## Step 4: Data analysis\n",
-    "\n",
-    "Make sure length of the dataset is what we expect, drop Nones etc."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "b276df71",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>fullplot</th>\n",
-       "      <th>type</th>\n",
-       "      <th>plot_embedding</th>\n",
-       "      <th>num_mflix_comments</th>\n",
-       "      <th>runtime</th>\n",
-       "      <th>writers</th>\n",
-       "      <th>imdb</th>\n",
-       "      <th>countries</th>\n",
-       "      <th>rated</th>\n",
-       "      <th>plot</th>\n",
-       "      <th>title</th>\n",
-       "      <th>languages</th>\n",
-       "      <th>metacritic</th>\n",
-       "      <th>directors</th>\n",
-       "      <th>awards</th>\n",
-       "      <th>genres</th>\n",
-       "      <th>poster</th>\n",
-       "      <th>cast</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>Young Pauline is left a lot of money when her ...</td>\n",
-       "      <td>movie</td>\n",
-       "      <td>[0.00072939653, -0.026834568, 0.013515796, -0....</td>\n",
-       "      <td>0</td>\n",
-       "      <td>199.0</td>\n",
-       "      <td>[Charles W. Goddard (screenplay), Basil Dickey...</td>\n",
-       "      <td>{'id': 4465, 'rating': 7.6, 'votes': 744}</td>\n",
-       "      <td>[USA]</td>\n",
-       "      <td>None</td>\n",
-       "      <td>Young Pauline is left a lot of money when her ...</td>\n",
-       "      <td>The Perils of Pauline</td>\n",
-       "      <td>[English]</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[Louis J. Gasnier, Donald MacKenzie]</td>\n",
-       "      <td>{'nominations': 0, 'text': '1 win.', 'wins': 1}</td>\n",
-       "      <td>[Action]</td>\n",
-       "      <td>https://m.media-amazon.com/images/M/MV5BMzgxOD...</td>\n",
-       "      <td>[Pearl White, Crane Wilbur, Paul Panzer, Edwar...</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                                            fullplot   type  \\\n",
-       "0  Young Pauline is left a lot of money when her ...  movie   \n",
-       "\n",
-       "                                      plot_embedding  num_mflix_comments  \\\n",
-       "0  [0.00072939653, -0.026834568, 0.013515796, -0....                   0   \n",
-       "\n",
-       "   runtime                                            writers  \\\n",
-       "0    199.0  [Charles W. Goddard (screenplay), Basil Dickey...   \n",
-       "\n",
-       "                                        imdb countries rated  \\\n",
-       "0  {'id': 4465, 'rating': 7.6, 'votes': 744}     [USA]  None   \n",
-       "\n",
-       "                                                plot                  title  \\\n",
-       "0  Young Pauline is left a lot of money when her ...  The Perils of Pauline   \n",
-       "\n",
-       "   languages  metacritic                             directors  \\\n",
-       "0  [English]         NaN  [Louis J. Gasnier, Donald MacKenzie]   \n",
-       "\n",
-       "                                            awards    genres  \\\n",
-       "0  {'nominations': 0, 'text': '1 win.', 'wins': 1}  [Action]   \n",
-       "\n",
-       "                                              poster  \\\n",
-       "0  https://m.media-amazon.com/images/M/MV5BMzgxOD...   \n",
-       "\n",
-       "                                                cast  \n",
-       "0  [Pearl White, Crane Wilbur, Paul Panzer, Edwar...  "
-      ]
-     },
-     "execution_count": 10,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Previewing the contents of the data\n",
-    "df.head(1)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "22ab375d",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Only keep records where the fullplot field is not null\n",
-    "df = df[df[\"fullplot\"].notna()]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "fceed99a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Renaming the embedding field to \"embedding\" -- required by LangChain\n",
-    "df.rename(columns={\"plot_embedding\": \"embedding\"}, inplace=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "aedec13a",
-   "metadata": {},
-   "source": [
-    "## Step 5: Create a simple RAG chain using MongoDB as the vector store"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "11d292f3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_mongodb import MongoDBAtlasVectorSearch\n",
-    "from pymongo import MongoClient\n",
-    "\n",
-    "# Initialize MongoDB python client\n",
-    "client = MongoClient(MONGODB_URI, appname=\"devrel.content.python\")\n",
-    "\n",
-    "DB_NAME = \"langchain_chatbot\"\n",
-    "COLLECTION_NAME = \"data\"\n",
-    "ATLAS_VECTOR_SEARCH_INDEX_NAME = \"vector_index\"\n",
-    "collection = client[DB_NAME][COLLECTION_NAME]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "d8292d53",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "DeleteResult({'n': 1000, 'electionId': ObjectId('7fffffff00000000000000f6'), 'opTime': {'ts': Timestamp(1710523288, 1033), 't': 246}, 'ok': 1.0, '$clusterTime': {'clusterTime': Timestamp(1710523288, 1042), 'signature': {'hash': b\"i\\xa8\\xe9'\\x1ed\\xf2u\\xf3L\\xff\\xb1\\xf5\\xbfA\\x90\\xabJ\\x12\\x83\", 'keyId': 7299545392000008318}}, 'operationTime': Timestamp(1710523288, 1033)}, acknowledged=True)"
-      ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Delete any existing records in the collection\n",
-    "collection.delete_many({})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "36c68914",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Data ingestion into MongoDB completed\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Data Ingestion\n",
-    "records = df.to_dict(\"records\")\n",
-    "collection.insert_many(records)\n",
-    "\n",
-    "print(\"Data ingestion into MongoDB completed\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "cbfca0b8",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_openai import OpenAIEmbeddings\n",
-    "\n",
-    "# Using the text-embedding-ada-002 since that's what was used to create embeddings in the movies dataset\n",
-    "embeddings = OpenAIEmbeddings(\n",
-    "    openai_api_key=OPENAI_API_KEY, model=\"text-embedding-ada-002\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "id": "798e176c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Vector Store Creation\n",
-    "vector_store = MongoDBAtlasVectorSearch.from_connection_string(\n",
-    "    connection_string=MONGODB_URI,\n",
-    "    namespace=DB_NAME + \".\" + COLLECTION_NAME,\n",
-    "    embedding=embeddings,\n",
-    "    index_name=ATLAS_VECTOR_SEARCH_INDEX_NAME,\n",
-    "    text_key=\"fullplot\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 49,
-   "id": "c71cd087",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Using the MongoDB vector store as a retriever in a RAG chain\n",
-    "retriever = vector_store.as_retriever(search_type=\"similarity\", search_kwargs={\"k\": 5})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 25,
-   "id": "b6588cd3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_core.runnables import RunnablePassthrough\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "# Generate context using the retriever, and pass the user question through\n",
-    "retrieve = {\n",
-    "    \"context\": retriever | (lambda docs: \"\\n\\n\".join([d.page_content for d in docs])),\n",
-    "    \"question\": RunnablePassthrough(),\n",
-    "}\n",
-    "template = \"\"\"Answer the question based only on the following context: \\\n",
-    "{context}\n",
-    "\n",
-    "Question: {question}\n",
-    "\"\"\"\n",
-    "# Defining the chat prompt\n",
-    "prompt = ChatPromptTemplate.from_template(template)\n",
-    "# Defining the model to be used for chat completion\n",
-    "model = ChatOpenAI(temperature=0, openai_api_key=OPENAI_API_KEY)\n",
-    "# Parse output as a string\n",
-    "parse_output = StrOutputParser()\n",
-    "\n",
-    "# Naive RAG chain\n",
-    "naive_rag_chain = retrieve | prompt | model | parse_output"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 26,
-   "id": "aaae21f5",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Once a Thief'"
-      ]
-     },
-     "execution_count": 26,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "naive_rag_chain.invoke(\"What is the best movie to watch when sad?\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "75f929ef",
-   "metadata": {},
-   "source": [
-    "## Step 6: Create a RAG chain with chat history"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 27,
-   "id": "94e7bd4a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.prompts import MessagesPlaceholder\n",
-    "from langchain_core.runnables.history import RunnableWithMessageHistory\n",
-    "from langchain_mongodb.chat_message_histories import MongoDBChatMessageHistory"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 29,
-   "id": "5bb30860",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def get_session_history(session_id: str) -> MongoDBChatMessageHistory:\n",
-    "    return MongoDBChatMessageHistory(\n",
-    "        MONGODB_URI, session_id, database_name=DB_NAME, collection_name=\"history\"\n",
-    "    )"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 50,
-   "id": "f51d0f35",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Given a follow-up question and history, create a standalone question\n",
-    "standalone_system_prompt = \"\"\"\n",
-    "Given a chat history and a follow-up question, rephrase the follow-up question to be a standalone question. \\\n",
-    "Do NOT answer the question, just reformulate it if needed, otherwise return it as is. \\\n",
-    "Only return the final standalone question. \\\n",
-    "\"\"\"\n",
-    "standalone_question_prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", standalone_system_prompt),\n",
-    "        MessagesPlaceholder(variable_name=\"history\"),\n",
-    "        (\"human\", \"{question}\"),\n",
-    "    ]\n",
-    ")\n",
-    "\n",
-    "question_chain = standalone_question_prompt | model | parse_output"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 51,
-   "id": "f3ef3354",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Generate context by passing output of the question_chain i.e. the standalone question to the retriever\n",
-    "retriever_chain = RunnablePassthrough.assign(\n",
-    "    context=question_chain\n",
-    "    | retriever\n",
-    "    | (lambda docs: \"\\n\\n\".join([d.page_content for d in docs]))\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 55,
-   "id": "5afb7345",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Create a prompt that includes the context, history and the follow-up question\n",
-    "rag_system_prompt = \"\"\"Answer the question based only on the following context: \\\n",
-    "{context}\n",
-    "\"\"\"\n",
-    "rag_prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", rag_system_prompt),\n",
-    "        MessagesPlaceholder(variable_name=\"history\"),\n",
-    "        (\"human\", \"{question}\"),\n",
-    "    ]\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 56,
-   "id": "f95f47d0",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# RAG chain\n",
-    "rag_chain = retriever_chain | rag_prompt | model | parse_output"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 57,
-   "id": "9618d395",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'The best movie to watch when feeling down could be \"Last Action Hero.\" It\\'s a fun and action-packed film that blends reality and fantasy, offering an escape from the real world and providing an entertaining distraction.'"
-      ]
-     },
-     "execution_count": 57,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# RAG chain with history\n",
-    "with_message_history = RunnableWithMessageHistory(\n",
-    "    rag_chain,\n",
-    "    get_session_history,\n",
-    "    input_messages_key=\"question\",\n",
-    "    history_messages_key=\"history\",\n",
-    ")\n",
-    "with_message_history.invoke(\n",
-    "    {\"question\": \"What is the best movie to watch when sad?\"},\n",
-    "    {\"configurable\": {\"session_id\": \"1\"}},\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 58,
-   "id": "6e3080d1",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'I apologize for the confusion. Another movie that might lift your spirits when you\\'re feeling sad is \"Smilla\\'s Sense of Snow.\" It\\'s a mystery thriller that could engage your mind and distract you from your sadness with its intriguing plot and suspenseful storyline.'"
-      ]
-     },
-     "execution_count": 58,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "with_message_history.invoke(\n",
-    "    {\n",
-    "        \"question\": \"Hmmm..I don't want to watch that one. Can you suggest something else?\"\n",
-    "    },\n",
-    "    {\"configurable\": {\"session_id\": \"1\"}},\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 59,
-   "id": "daea2953",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'For a lighter movie option, you might enjoy \"Cousins.\" It\\'s a comedy film set in Barcelona with action and humor, offering a fun and entertaining escape from reality. The storyline is engaging and filled with comedic moments that could help lift your spirits.'"
-      ]
-     },
-     "execution_count": 59,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "with_message_history.invoke(\n",
-    "    {\"question\": \"How about something more light?\"},\n",
-    "    {\"configurable\": {\"session_id\": \"1\"}},\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0de23a88",
-   "metadata": {},
-   "source": [
-    "## Step 7: Get faster responses using Semantic Cache\n",
-    "\n",
-    "**NOTE:** Semantic cache only caches the input to the LLM. When using it in retrieval chains, remember that documents retrieved can change between runs resulting in cache misses for semantically similar queries."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 61,
-   "id": "5d6b6741",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.globals import set_llm_cache\n",
-    "from langchain_mongodb.cache import MongoDBAtlasSemanticCache\n",
-    "\n",
-    "set_llm_cache(\n",
-    "    MongoDBAtlasSemanticCache(\n",
-    "        connection_string=MONGODB_URI,\n",
-    "        embedding=embeddings,\n",
-    "        collection_name=\"semantic_cache\",\n",
-    "        database_name=DB_NAME,\n",
-    "        index_name=ATLAS_VECTOR_SEARCH_INDEX_NAME,\n",
-    "        wait_until_ready=True,  # Optional, waits until the cache is ready to be used\n",
-    "    )\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 62,
-   "id": "9825bc7b",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "CPU times: user 87.8 ms, sys: 670 µs, total: 88.5 ms\n",
-      "Wall time: 1.24 s\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'Once a Thief'"
-      ]
-     },
-     "execution_count": 62,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "%%time\n",
-    "naive_rag_chain.invoke(\"What is the best movie to watch when sad?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 63,
-   "id": "a5e518cf",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "CPU times: user 43.5 ms, sys: 4.16 ms, total: 47.7 ms\n",
-      "Wall time: 255 ms\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'Once a Thief'"
-      ]
-     },
-     "execution_count": 63,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "%%time\n",
-    "naive_rag_chain.invoke(\"What is the best movie to watch when sad?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 64,
-   "id": "3d3d3ad3",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "CPU times: user 115 ms, sys: 171 µs, total: 115 ms\n",
-      "Wall time: 1.38 s\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'I would recommend watching \"Last Action Hero\" when sad, as it is a fun and action-packed film that can help lift your spirits.'"
-      ]
-     },
-     "execution_count": 64,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "%%time\n",
-    "naive_rag_chain.invoke(\"Which movie do I watch when sad?\")"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "conda_pytorch_p310",
-   "language": "python",
-   "name": "conda_pytorch_p310"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.13"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/multi_modal_RAG_chroma.ipynb

@@ -435,7 +435,7 @@
     "    display(HTML(image_html))\n",
     "\n",
     "\n",
-    "docs = retriever.invoke(\"Woman with children\", k=10)\n",
+    "docs = retriever.get_relevant_documents(\"Woman with children\", k=10)\n",
     "for doc in docs:\n",
     "    if is_base64(doc.page_content):\n",
     "        plt_img_base64(doc.page_content)\n",

cookbook/multi_modal_RAG_vdms.ipynb

@@ -443,7 +443,7 @@
     "\n",
     "\n",
     "query = \"Woman with children\"\n",
-    "docs = retriever.invoke(query, k=10)\n",
+    "docs = retriever.get_relevant_documents(query, k=10)\n",
     "\n",
     "for doc in docs:\n",
     "    if is_base64(doc.page_content):\n",

cookbook/multi_player_dnd.ipynb

@@ -74,7 +74,7 @@
     "        Applies the chatmodel to the message history\n",
     "        and returns the message string\n",
     "        \"\"\"\n",
-    "        message = self.model.invoke(\n",
+    "        message = self.model(\n",
     "            [\n",
     "                self.system_message,\n",
     "                HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",

cookbook/multiagent_authoritarian.ipynb

@@ -79,7 +79,7 @@
     "        Applies the chatmodel to the message history\n",
     "        and returns the message string\n",
     "        \"\"\"\n",
-    "        message = self.model.invoke(\n",
+    "        message = self.model(\n",
     "            [\n",
     "                self.system_message,\n",
     "                HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",
@@ -234,7 +234,7 @@
     "            termination_clause=self.termination_clause if self.stop else \"\",\n",
     "        )\n",
     "\n",
-    "        self.response = self.model.invoke(\n",
+    "        self.response = self.model(\n",
     "            [\n",
     "                self.system_message,\n",
     "                HumanMessage(content=response_prompt),\n",
@@ -263,7 +263,7 @@
     "            speaker_names=speaker_names,\n",
     "        )\n",
     "\n",
-    "        choice_string = self.model.invoke(\n",
+    "        choice_string = self.model(\n",
     "            [\n",
     "                self.system_message,\n",
     "                HumanMessage(content=choice_prompt),\n",
@@ -299,7 +299,7 @@
     "                ),\n",
     "                next_speaker=self.next_speaker,\n",
     "            )\n",
-    "            message = self.model.invoke(\n",
+    "            message = self.model(\n",
     "                [\n",
     "                    self.system_message,\n",
     "                    HumanMessage(content=next_prompt),\n",

cookbook/multiagent_bidding.ipynb

@@ -71,7 +71,7 @@
     "        Applies the chatmodel to the message history\n",
     "        and returns the message string\n",
     "        \"\"\"\n",
-    "        message = self.model.invoke(\n",
+    "        message = self.model(\n",
     "            [\n",
     "                self.system_message,\n",
     "                HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",
@@ -164,7 +164,7 @@
     "            message_history=\"\\n\".join(self.message_history),\n",
     "            recent_message=self.message_history[-1],\n",
     "        )\n",
-    "        bid_string = self.model.invoke([SystemMessage(content=prompt)]).content\n",
+    "        bid_string = self.model([SystemMessage(content=prompt)]).content\n",
     "        return bid_string"
    ]
   },

cookbook/nomic_multimodal_rag.ipynb

@@ -1,497 +0,0 @@
-{
- "cells": [
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "id": "9fc3897d-176f-4729-8fd1-cfb4add53abd",
-   "metadata": {},
-   "source": [
-    "## Nomic multi-modal RAG\n",
-    "\n",
-    "Many documents contain a mixture of content types, including text and images. \n",
-    "\n",
-    "Yet, information captured in images is lost in most RAG applications.\n",
-    "\n",
-    "With the emergence of multimodal LLMs, like [GPT-4V](https://openai.com/research/gpt-4v-system-card), it is worth considering how to utilize images in RAG:\n",
-    "\n",
-    "In this demo we\n",
-    "\n",
-    "* Use multimodal embeddings from Nomic Embed [Vision](https://huggingface.co/nomic-ai/nomic-embed-vision-v1.5) and [Text](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5) to embed images and text\n",
-    "* Retrieve both using similarity search\n",
-    "* Pass raw images and text chunks to a multimodal LLM for answer synthesis \n",
-    "\n",
-    "## Signup\n",
-    "\n",
-    "Get your API token, then run:\n",
-    "```\n",
-    "! nomic login\n",
-    "```\n",
-    "\n",
-    "Then run with your generated API token \n",
-    "```\n",
-    "! nomic login < token > \n",
-    "```\n",
-    "\n",
-    "## Packages\n",
-    "\n",
-    "For `unstructured`, you will also need `poppler` ([installation instructions](https://pdf2image.readthedocs.io/en/latest/installation.html)) and `tesseract` ([installation instructions](https://tesseract-ocr.github.io/tessdoc/Installation.html)) in your system."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "54926b9b-75c2-4cd4-8f14-b3882a0d370b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "! nomic login token"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "febbc459-ebba-4c1a-a52b-fed7731593f8",
-   "metadata": {
-    "scrolled": true
-   },
-   "outputs": [],
-   "source": [
-    "! pip install -U langchain-nomic langchain_community tiktoken langchain-openai chromadb langchain # (newest versions required for multi-modal)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "acbdc603-39e2-4a5f-836c-2bbaecd46b0b",
-   "metadata": {
-    "scrolled": true
-   },
-   "outputs": [],
-   "source": [
-    "# lock to 0.10.19 due to a persistent bug in more recent versions\n",
-    "! pip install \"unstructured[all-docs]==0.10.19\" pillow pydantic lxml pillow matplotlib tiktoken"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "1e94b3fb-8e3e-4736-be0a-ad881626c7bd",
-   "metadata": {},
-   "source": [
-    "## Data Loading\n",
-    "\n",
-    "### Partition PDF text and images\n",
-    "  \n",
-    "Let's look at an example pdfs containing interesting images.\n",
-    "\n",
-    "1/ Art from the J Paul Getty museum:\n",
-    "\n",
-    " * Here is a [zip file](https://drive.google.com/file/d/18kRKbq2dqAhhJ3DfZRnYcTBEUfYxe1YR/view?usp=sharing) with the PDF and the already extracted images. \n",
-    "* https://www.getty.edu/publications/resources/virtuallibrary/0892360224.pdf\n",
-    "\n",
-    "2/ Famous photographs from library of congress:\n",
-    "\n",
-    "* https://www.loc.gov/lcm/pdf/LCM_2020_1112.pdf\n",
-    "* We'll use this as an example below\n",
-    "\n",
-    "We can use `partition_pdf` below from [Unstructured](https://unstructured-io.github.io/unstructured/introduction.html#key-concepts) to extract text and images.\n",
-    "\n",
-    "To supply this to extract the images:\n",
-    "```\n",
-    "extract_images_in_pdf=True\n",
-    "```\n",
-    "\n",
-    "\n",
-    "\n",
-    "If using this zip file, then you can simply process the text only with:\n",
-    "```\n",
-    "extract_images_in_pdf=False\n",
-    "```"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "9646b524-71a7-4b2a-bdc8-0b81f77e968f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Folder with pdf and extracted images\n",
-    "from pathlib import Path\n",
-    "\n",
-    "# replace with actual path to images\n",
-    "path = Path(\"../art\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "77f096ab-a933-41d0-8f4e-1efc83998fc3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "path.resolve()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "bc4839c0-8773-4a07-ba59-5364501269b2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Extract images, tables, and chunk text\n",
-    "from unstructured.partition.pdf import partition_pdf\n",
-    "\n",
-    "raw_pdf_elements = partition_pdf(\n",
-    "    filename=str(path.resolve()) + \"/getty.pdf\",\n",
-    "    extract_images_in_pdf=False,\n",
-    "    infer_table_structure=True,\n",
-    "    chunking_strategy=\"by_title\",\n",
-    "    max_characters=4000,\n",
-    "    new_after_n_chars=3800,\n",
-    "    combine_text_under_n_chars=2000,\n",
-    "    image_output_dir_path=path,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "969545ad",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Categorize text elements by type\n",
-    "tables = []\n",
-    "texts = []\n",
-    "for element in raw_pdf_elements:\n",
-    "    if \"unstructured.documents.elements.Table\" in str(type(element)):\n",
-    "        tables.append(str(element))\n",
-    "    elif \"unstructured.documents.elements.CompositeElement\" in str(type(element)):\n",
-    "        texts.append(str(element))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "5d8e6349-1547-4cbf-9c6f-491d8610ec10",
-   "metadata": {},
-   "source": [
-    "## Multi-modal embeddings with our document\n",
-    "\n",
-    "We will use [nomic-embed-vision-v1.5](https://huggingface.co/nomic-ai/nomic-embed-vision-v1.5) embeddings. This model is aligned \n",
-    "to [nomic-embed-text-v1.5](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5) allowing for multimodal semantic search and Multimodal RAG!"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "4bc15842-cb95-4f84-9eb5-656b0282a800",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "import uuid\n",
-    "\n",
-    "import chromadb\n",
-    "import numpy as np\n",
-    "from langchain_community.vectorstores import Chroma\n",
-    "from langchain_nomic import NomicEmbeddings\n",
-    "from PIL import Image as _PILImage\n",
-    "\n",
-    "# Create chroma\n",
-    "text_vectorstore = Chroma(\n",
-    "    collection_name=\"mm_rag_clip_photos_text\",\n",
-    "    embedding_function=NomicEmbeddings(\n",
-    "        vision_model=\"nomic-embed-vision-v1.5\", model=\"nomic-embed-text-v1.5\"\n",
-    "    ),\n",
-    ")\n",
-    "image_vectorstore = Chroma(\n",
-    "    collection_name=\"mm_rag_clip_photos_image\",\n",
-    "    embedding_function=NomicEmbeddings(\n",
-    "        vision_model=\"nomic-embed-vision-v1.5\", model=\"nomic-embed-text-v1.5\"\n",
-    "    ),\n",
-    ")\n",
-    "\n",
-    "# Get image URIs with .jpg extension only\n",
-    "image_uris = sorted(\n",
-    "    [\n",
-    "        os.path.join(path, image_name)\n",
-    "        for image_name in os.listdir(path)\n",
-    "        if image_name.endswith(\".jpg\")\n",
-    "    ]\n",
-    ")\n",
-    "\n",
-    "# Add images\n",
-    "image_vectorstore.add_images(uris=image_uris)\n",
-    "\n",
-    "# Add documents\n",
-    "text_vectorstore.add_texts(texts=texts)\n",
-    "\n",
-    "# Make retriever\n",
-    "image_retriever = image_vectorstore.as_retriever()\n",
-    "text_retriever = text_vectorstore.as_retriever()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "02a186d0-27e0-4820-8092-63b5349dd25d",
-   "metadata": {},
-   "source": [
-    "## RAG\n",
-    "\n",
-    "`vectorstore.add_images` will store / retrieve images as base64 encoded strings.\n",
-    "\n",
-    "These can be passed to [GPT-4V](https://platform.openai.com/docs/guides/vision)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "344f56a8-0dc3-433e-851c-3f7600c7a72b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import base64\n",
-    "import io\n",
-    "from io import BytesIO\n",
-    "\n",
-    "import numpy as np\n",
-    "from PIL import Image\n",
-    "\n",
-    "\n",
-    "def resize_base64_image(base64_string, size=(128, 128)):\n",
-    "    \"\"\"\n",
-    "    Resize an image encoded as a Base64 string.\n",
-    "\n",
-    "    Args:\n",
-    "    base64_string (str): Base64 string of the original image.\n",
-    "    size (tuple): Desired size of the image as (width, height).\n",
-    "\n",
-    "    Returns:\n",
-    "    str: Base64 string of the resized image.\n",
-    "    \"\"\"\n",
-    "    # Decode the Base64 string\n",
-    "    img_data = base64.b64decode(base64_string)\n",
-    "    img = Image.open(io.BytesIO(img_data))\n",
-    "\n",
-    "    # Resize the image\n",
-    "    resized_img = img.resize(size, Image.LANCZOS)\n",
-    "\n",
-    "    # Save the resized image to a bytes buffer\n",
-    "    buffered = io.BytesIO()\n",
-    "    resized_img.save(buffered, format=img.format)\n",
-    "\n",
-    "    # Encode the resized image to Base64\n",
-    "    return base64.b64encode(buffered.getvalue()).decode(\"utf-8\")\n",
-    "\n",
-    "\n",
-    "def is_base64(s):\n",
-    "    \"\"\"Check if a string is Base64 encoded\"\"\"\n",
-    "    try:\n",
-    "        return base64.b64encode(base64.b64decode(s)) == s.encode()\n",
-    "    except Exception:\n",
-    "        return False\n",
-    "\n",
-    "\n",
-    "def split_image_text_types(docs):\n",
-    "    \"\"\"Split numpy array images and texts\"\"\"\n",
-    "    images = []\n",
-    "    text = []\n",
-    "    for doc in docs:\n",
-    "        doc = doc.page_content  # Extract Document contents\n",
-    "        if is_base64(doc):\n",
-    "            # Resize image to avoid OAI server error\n",
-    "            images.append(\n",
-    "                resize_base64_image(doc, size=(250, 250))\n",
-    "            )  # base64 encoded str\n",
-    "        else:\n",
-    "            text.append(doc)\n",
-    "    return {\"images\": images, \"texts\": text}"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "23a2c1d8-fea6-4152-b184-3172dd46c735",
-   "metadata": {},
-   "source": [
-    "Currently, we format the inputs using a `RunnableLambda` while we add image support to `ChatPromptTemplates`.\n",
-    "\n",
-    "Our runnable follows the classic RAG flow - \n",
-    "\n",
-    "* We first compute the context (both \"texts\" and \"images\" in this case) and the question (just a RunnablePassthrough here) \n",
-    "* Then we pass this into our prompt template, which is a custom function that formats the message for the gpt-4-vision-preview model. \n",
-    "* And finally we parse the output as a string."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "5d8919dc-c238-4746-86ba-45d940a7d260",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = \"\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "4c93fab3-74c4-4f1d-958a-0bc4cdd0797e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from operator import itemgetter\n",
-    "\n",
-    "from langchain_core.messages import HumanMessage, SystemMessage\n",
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.runnables import RunnableLambda, RunnablePassthrough\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "\n",
-    "def prompt_func(data_dict):\n",
-    "    # Joining the context texts into a single string\n",
-    "    formatted_texts = \"\\n\".join(data_dict[\"text_context\"][\"texts\"])\n",
-    "    messages = []\n",
-    "\n",
-    "    # Adding image(s) to the messages if present\n",
-    "    if data_dict[\"image_context\"][\"images\"]:\n",
-    "        image_message = {\n",
-    "            \"type\": \"image_url\",\n",
-    "            \"image_url\": {\n",
-    "                \"url\": f\"data:image/jpeg;base64,{data_dict['image_context']['images'][0]}\"\n",
-    "            },\n",
-    "        }\n",
-    "        messages.append(image_message)\n",
-    "\n",
-    "    # Adding the text message for analysis\n",
-    "    text_message = {\n",
-    "        \"type\": \"text\",\n",
-    "        \"text\": (\n",
-    "            \"As an expert art critic and historian, your task is to analyze and interpret images, \"\n",
-    "            \"considering their historical and cultural significance. Alongside the images, you will be \"\n",
-    "            \"provided with related text to offer context. Both will be retrieved from a vectorstore based \"\n",
-    "            \"on user-input keywords. Please use your extensive knowledge and analytical skills to provide a \"\n",
-    "            \"comprehensive summary that includes:\\n\"\n",
-    "            \"- A detailed description of the visual elements in the image.\\n\"\n",
-    "            \"- The historical and cultural context of the image.\\n\"\n",
-    "            \"- An interpretation of the image's symbolism and meaning.\\n\"\n",
-    "            \"- Connections between the image and the related text.\\n\\n\"\n",
-    "            f\"User-provided keywords: {data_dict['question']}\\n\\n\"\n",
-    "            \"Text and / or tables:\\n\"\n",
-    "            f\"{formatted_texts}\"\n",
-    "        ),\n",
-    "    }\n",
-    "    messages.append(text_message)\n",
-    "\n",
-    "    return [HumanMessage(content=messages)]\n",
-    "\n",
-    "\n",
-    "model = ChatOpenAI(temperature=0, model=\"gpt-4-vision-preview\", max_tokens=1024)\n",
-    "\n",
-    "# RAG pipeline\n",
-    "chain = (\n",
-    "    {\n",
-    "        \"text_context\": text_retriever | RunnableLambda(split_image_text_types),\n",
-    "        \"image_context\": image_retriever | RunnableLambda(split_image_text_types),\n",
-    "        \"question\": RunnablePassthrough(),\n",
-    "    }\n",
-    "    | RunnableLambda(prompt_func)\n",
-    "    | model\n",
-    "    | StrOutputParser()\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "1566096d-97c2-4ddc-ba4a-6ef88c525e4e",
-   "metadata": {},
-   "source": [
-    "## Test retrieval and run RAG"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "90121e56-674b-473b-871d-6e4753fd0c45",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from IPython.display import HTML, display\n",
-    "\n",
-    "\n",
-    "def plt_img_base64(img_base64):\n",
-    "    # Create an HTML img tag with the base64 string as the source\n",
-    "    image_html = f'<img src=\"data:image/jpeg;base64,{img_base64}\" />'\n",
-    "\n",
-    "    # Display the image by rendering the HTML\n",
-    "    display(HTML(image_html))\n",
-    "\n",
-    "\n",
-    "docs = text_retriever.invoke(\"Women with children\", k=5)\n",
-    "for doc in docs:\n",
-    "    if is_base64(doc.page_content):\n",
-    "        plt_img_base64(doc.page_content)\n",
-    "    else:\n",
-    "        print(doc.page_content)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "44eaa532-f035-4c04-b578-02339d42554c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "docs = image_retriever.invoke(\"Women with children\", k=5)\n",
-    "for doc in docs:\n",
-    "    if is_base64(doc.page_content):\n",
-    "        plt_img_base64(doc.page_content)\n",
-    "    else:\n",
-    "        print(doc.page_content)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "69fb15fd-76fc-49b4-806d-c4db2990027d",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain.invoke(\"Women with children\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "227f08b8-e732-4089-b65c-6eb6f9e48f15",
-   "metadata": {},
-   "source": [
-    "We can see the images retrieved in the LangSmith trace:\n",
-    "\n",
-    "LangSmith [trace](https://smith.langchain.com/public/69c558a5-49dc-4c60-a49b-3adbb70f74c5/r/e872c2c8-528c-468f-aefd-8b5cd730a673)."
-   ]
-  }
- ],
- "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": "3.11.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/oracleai_demo.ipynb

@@ -1,880 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Oracle AI Vector Search with Document Processing\n",
-    "Oracle AI Vector Search is designed for Artificial Intelligence (AI) workloads that allows you to query data based on semantics, rather than keywords.\n",
-    "One of the biggest benefits of Oracle AI Vector Search is that semantic search on unstructured data can be combined with relational search on business data in one single system.\n",
-    "This is not only powerful but also significantly more effective because you don't need to add a specialized vector database, eliminating the pain of data fragmentation between multiple systems.\n",
-    "\n",
-    "In addition, your vectors can benefit from all of Oracle Database’s most powerful features, like the following:\n",
-    "\n",
-    " * [Partitioning Support](https://www.oracle.com/database/technologies/partitioning.html)\n",
-    " * [Real Application Clusters scalability](https://www.oracle.com/database/real-application-clusters/)\n",
-    " * [Exadata smart scans](https://www.oracle.com/database/technologies/exadata/software/smartscan/)\n",
-    " * [Shard processing across geographically distributed databases](https://www.oracle.com/database/distributed-database/)\n",
-    " * [Transactions](https://docs.oracle.com/en/database/oracle/oracle-database/23/cncpt/transactions.html)\n",
-    " * [Parallel SQL](https://docs.oracle.com/en/database/oracle/oracle-database/21/vldbg/parallel-exec-intro.html#GUID-D28717E4-0F77-44F5-BB4E-234C31D4E4BA)\n",
-    " * [Disaster recovery](https://www.oracle.com/database/data-guard/)\n",
-    " * [Security](https://www.oracle.com/security/database-security/)\n",
-    " * [Oracle Machine Learning](https://www.oracle.com/artificial-intelligence/database-machine-learning/)\n",
-    " * [Oracle Graph Database](https://www.oracle.com/database/integrated-graph-database/)\n",
-    " * [Oracle Spatial and Graph](https://www.oracle.com/database/spatial/)\n",
-    " * [Oracle Blockchain](https://docs.oracle.com/en/database/oracle/oracle-database/23/arpls/dbms_blockchain_table.html#GUID-B469E277-978E-4378-A8C1-26D3FF96C9A6)\n",
-    " * [JSON](https://docs.oracle.com/en/database/oracle/oracle-database/23/adjsn/json-in-oracle-database.html)\n",
-    "\n",
-    "This guide demonstrates how Oracle AI Vector Search can be used with Langchain to serve an end-to-end RAG pipeline. This guide goes through examples of:\n",
-    "\n",
-    " * Loading the documents from various sources using OracleDocLoader\n",
-    " * Summarizing them within/outside the database using OracleSummary\n",
-    " * Generating embeddings for them within/outside the database using OracleEmbeddings\n",
-    " * Chunking them according to different requirements using Advanced Oracle Capabilities from OracleTextSplitter\n",
-    " * Storing and Indexing them in a Vector Store and querying them for queries in OracleVS"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "If you are just starting with Oracle Database, consider exploring the [free Oracle 23 AI](https://www.oracle.com/database/free/#resources) which provides a great introduction to setting up your database environment. While working with the database, it is often advisable to avoid using the system user by default; instead, you can create your own user for enhanced security and customization. For detailed steps on user creation, refer to our [end-to-end guide](https://github.com/langchain-ai/langchain/blob/master/cookbook/oracleai_demo.ipynb) which also shows how to set up a user in Oracle. Additionally, understanding user privileges is crucial for managing database security effectively. You can learn more about this topic in the official [Oracle guide](https://docs.oracle.com/en/database/oracle/oracle-database/19/admqs/administering-user-accounts-and-security.html#GUID-36B21D72-1BBB-46C9-A0C9-F0D2A8591B8D) on administering user accounts and security."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Prerequisites\n",
-    "\n",
-    "Please install Oracle Python Client driver to use Langchain with Oracle AI Vector Search. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# pip install oracledb"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Create Demo User\n",
-    "First, create a demo user with all the required privileges. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 37,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Connection successful!\n",
-      "User setup done!\n"
-     ]
-    }
-   ],
-   "source": [
-    "import sys\n",
-    "\n",
-    "import oracledb\n",
-    "\n",
-    "# Update with your username, password, hostname, and service_name\n",
-    "username = \"\"\n",
-    "password = \"\"\n",
-    "dsn = \"\"\n",
-    "\n",
-    "try:\n",
-    "    conn = oracledb.connect(user=username, password=password, dsn=dsn)\n",
-    "    print(\"Connection successful!\")\n",
-    "\n",
-    "    cursor = conn.cursor()\n",
-    "    try:\n",
-    "        cursor.execute(\n",
-    "            \"\"\"\n",
-    "            begin\n",
-    "                -- Drop user\n",
-    "                begin\n",
-    "                    execute immediate 'drop user testuser cascade';\n",
-    "                exception\n",
-    "                    when others then\n",
-    "                        dbms_output.put_line('Error dropping user: ' || SQLERRM);\n",
-    "                end;\n",
-    "                \n",
-    "                -- Create user and grant privileges\n",
-    "                execute immediate 'create user testuser identified by testuser';\n",
-    "                execute immediate 'grant connect, unlimited tablespace, create credential, create procedure, create any index to testuser';\n",
-    "                execute immediate 'create or replace directory DEMO_PY_DIR as ''/scratch/hroy/view_storage/hroy_devstorage/demo/orachain''';\n",
-    "                execute immediate 'grant read, write on directory DEMO_PY_DIR to public';\n",
-    "                execute immediate 'grant create mining model to testuser';\n",
-    "                \n",
-    "                -- Network access\n",
-    "                begin\n",
-    "                    DBMS_NETWORK_ACL_ADMIN.APPEND_HOST_ACE(\n",
-    "                        host => '*',\n",
-    "                        ace => xs$ace_type(privilege_list => xs$name_list('connect'),\n",
-    "                                           principal_name => 'testuser',\n",
-    "                                           principal_type => xs_acl.ptype_db)\n",
-    "                    );\n",
-    "                end;\n",
-    "            end;\n",
-    "            \"\"\"\n",
-    "        )\n",
-    "        print(\"User setup done!\")\n",
-    "    except Exception as e:\n",
-    "        print(f\"User setup failed with error: {e}\")\n",
-    "    finally:\n",
-    "        cursor.close()\n",
-    "    conn.close()\n",
-    "except Exception as e:\n",
-    "    print(f\"Connection failed with error: {e}\")\n",
-    "    sys.exit(1)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Process Documents using Oracle AI\n",
-    "Consider the following scenario: users possess documents stored either in an Oracle Database or a file system and intend to utilize this data with Oracle AI Vector Search powered by Langchain.\n",
-    "\n",
-    "To prepare the documents for analysis, a comprehensive preprocessing workflow is necessary. Initially, the documents must be retrieved, summarized (if required), and chunked as needed. Subsequent steps involve generating embeddings for these chunks and integrating them into the Oracle AI Vector Store. Users can then conduct semantic searches on this data.\n",
-    "\n",
-    "The Oracle AI Vector Search Langchain library encompasses a suite of document processing tools that facilitate document loading, chunking, summary generation, and embedding creation.\n",
-    "\n",
-    "In the sections that follow, we will detail the utilization of Oracle AI Langchain APIs to effectively implement each of these processes."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Connect to Demo User\n",
-    "The following sample code will show how to connect to Oracle Database. By default, python-oracledb runs in a ‘Thin’ mode which connects directly to Oracle Database. This mode does not need Oracle Client libraries. However, some additional functionality is available when python-oracledb uses them. Python-oracledb is said to be in ‘Thick’ mode when Oracle Client libraries are used. Both modes have comprehensive functionality supporting the Python Database API v2.0 Specification. See the following [guide](https://python-oracledb.readthedocs.io/en/latest/user_guide/appendix_a.html#featuresummary) that talks about features supported in each mode. You might want to switch to thick-mode if you are unable to use thin-mode."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 45,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Connection successful!\n"
-     ]
-    }
-   ],
-   "source": [
-    "import sys\n",
-    "\n",
-    "import oracledb\n",
-    "\n",
-    "# please update with your username, password, hostname and service_name\n",
-    "username = \"\"\n",
-    "password = \"\"\n",
-    "dsn = \"\"\n",
-    "\n",
-    "try:\n",
-    "    conn = oracledb.connect(user=username, password=password, dsn=dsn)\n",
-    "    print(\"Connection successful!\")\n",
-    "except Exception as e:\n",
-    "    print(\"Connection failed!\")\n",
-    "    sys.exit(1)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Populate a Demo Table\n",
-    "Create a demo table and insert some sample documents."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 46,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Table created and populated.\n"
-     ]
-    }
-   ],
-   "source": [
-    "try:\n",
-    "    cursor = conn.cursor()\n",
-    "\n",
-    "    drop_table_sql = \"\"\"drop table demo_tab\"\"\"\n",
-    "    cursor.execute(drop_table_sql)\n",
-    "\n",
-    "    create_table_sql = \"\"\"create table demo_tab (id number, data clob)\"\"\"\n",
-    "    cursor.execute(create_table_sql)\n",
-    "\n",
-    "    insert_row_sql = \"\"\"insert into demo_tab values (:1, :2)\"\"\"\n",
-    "    rows_to_insert = [\n",
-    "        (\n",
-    "            1,\n",
-    "            \"If the answer to any preceding questions is yes, then the database stops the search and allocates space from the specified tablespace; otherwise, space is allocated from the database default shared temporary tablespace.\",\n",
-    "        ),\n",
-    "        (\n",
-    "            2,\n",
-    "            \"A tablespace can be online (accessible) or offline (not accessible) whenever the database is open.\\nA tablespace is usually online so that its data is available to users. The SYSTEM tablespace and temporary tablespaces cannot be taken offline.\",\n",
-    "        ),\n",
-    "        (\n",
-    "            3,\n",
-    "            \"The database stores LOBs differently from other data types. Creating a LOB column implicitly creates a LOB segment and a LOB index. The tablespace containing the LOB segment and LOB index, which are always stored together, may be different from the tablespace containing the table.\\nSometimes the database can store small amounts of LOB data in the table itself rather than in a separate LOB segment.\",\n",
-    "        ),\n",
-    "    ]\n",
-    "    cursor.executemany(insert_row_sql, rows_to_insert)\n",
-    "\n",
-    "    conn.commit()\n",
-    "\n",
-    "    print(\"Table created and populated.\")\n",
-    "    cursor.close()\n",
-    "except Exception as e:\n",
-    "    print(\"Table creation failed.\")\n",
-    "    cursor.close()\n",
-    "    conn.close()\n",
-    "    sys.exit(1)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "With the inclusion of a demo user and a populated sample table, the remaining configuration involves setting up embedding and summary functionalities. Users are presented with multiple provider options, including local database solutions and third-party services such as Ocigenai, Hugging Face, and OpenAI. Should users opt for a third-party provider, they are required to establish credentials containing the necessary authentication details. Conversely, if selecting a database as the provider for embeddings, it is necessary to upload an ONNX model to the Oracle Database. No additional setup is required for summary functionalities when using the database option."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Load ONNX Model\n",
-    "\n",
-    "Oracle accommodates a variety of embedding providers, enabling users to choose between proprietary database solutions and third-party services such as OCIGENAI and HuggingFace. This selection dictates the methodology for generating and managing embeddings.\n",
-    "\n",
-    "***Important*** : Should users opt for the database option, they must upload an ONNX model into the Oracle Database. Conversely, if a third-party provider is selected for embedding generation, uploading an ONNX model to Oracle Database is not required.\n",
-    "\n",
-    "A significant advantage of utilizing an ONNX model directly within Oracle is the enhanced security and performance it offers by eliminating the need to transmit data to external parties. Additionally, this method avoids the latency typically associated with network or REST API calls.\n",
-    "\n",
-    "Below is the example code to upload an ONNX model into Oracle Database:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 47,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "ONNX model loaded.\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_community.embeddings.oracleai import OracleEmbeddings\n",
-    "\n",
-    "# please update with your related information\n",
-    "# make sure that you have onnx file in the system\n",
-    "onnx_dir = \"DEMO_PY_DIR\"\n",
-    "onnx_file = \"tinybert.onnx\"\n",
-    "model_name = \"demo_model\"\n",
-    "\n",
-    "try:\n",
-    "    OracleEmbeddings.load_onnx_model(conn, onnx_dir, onnx_file, model_name)\n",
-    "    print(\"ONNX model loaded.\")\n",
-    "except Exception as e:\n",
-    "    print(\"ONNX model loading failed!\")\n",
-    "    sys.exit(1)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Create Credential\n",
-    "\n",
-    "When selecting third-party providers for generating embeddings, users are required to establish credentials to securely access the provider's endpoints.\n",
-    "\n",
-    "***Important:*** No credentials are necessary when opting for the 'database' provider to generate embeddings. However, should users decide to utilize a third-party provider, they must create credentials specific to the chosen provider.\n",
-    "\n",
-    "Below is an illustrative example:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "try:\n",
-    "    cursor = conn.cursor()\n",
-    "    cursor.execute(\n",
-    "        \"\"\"\n",
-    "       declare\n",
-    "           jo json_object_t;\n",
-    "       begin\n",
-    "           -- HuggingFace\n",
-    "           dbms_vector_chain.drop_credential(credential_name  => 'HF_CRED');\n",
-    "           jo := json_object_t();\n",
-    "           jo.put('access_token', '<access_token>');\n",
-    "           dbms_vector_chain.create_credential(\n",
-    "               credential_name   =>  'HF_CRED',\n",
-    "               params            => json(jo.to_string));\n",
-    "\n",
-    "           -- OCIGENAI\n",
-    "           dbms_vector_chain.drop_credential(credential_name  => 'OCI_CRED');\n",
-    "           jo := json_object_t();\n",
-    "           jo.put('user_ocid','<user_ocid>');\n",
-    "           jo.put('tenancy_ocid','<tenancy_ocid>');\n",
-    "           jo.put('compartment_ocid','<compartment_ocid>');\n",
-    "           jo.put('private_key','<private_key>');\n",
-    "           jo.put('fingerprint','<fingerprint>');\n",
-    "           dbms_vector_chain.create_credential(\n",
-    "               credential_name   => 'OCI_CRED',\n",
-    "               params            => json(jo.to_string));\n",
-    "       end;\n",
-    "       \"\"\"\n",
-    "    )\n",
-    "    cursor.close()\n",
-    "    print(\"Credentials created.\")\n",
-    "except Exception as ex:\n",
-    "    cursor.close()\n",
-    "    raise"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Load Documents\n",
-    "Users have the flexibility to load documents from either the Oracle Database, a file system, or both, by appropriately configuring the loader parameters. For comprehensive details on these parameters, please consult the [Oracle AI Vector Search Guide](https://docs.oracle.com/en/database/oracle/oracle-database/23/arpls/dbms_vector_chain1.html#GUID-73397E89-92FB-48ED-94BB-1AD960C4EA1F).\n",
-    "\n",
-    "A significant advantage of utilizing OracleDocLoader is its capability to process over 150 distinct file formats, eliminating the need for multiple loaders for different document types. For a complete list of the supported formats, please refer to the [Oracle Text Supported Document Formats](https://docs.oracle.com/en/database/oracle/oracle-database/23/ccref/oracle-text-supported-document-formats.html).\n",
-    "\n",
-    "Below is a sample code snippet that demonstrates how to use OracleDocLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 48,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Number of docs loaded: 3\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_community.document_loaders.oracleai import OracleDocLoader\n",
-    "from langchain_core.documents import Document\n",
-    "\n",
-    "# loading from Oracle Database table\n",
-    "# make sure you have the table with this specification\n",
-    "loader_params = {}\n",
-    "loader_params = {\n",
-    "    \"owner\": \"testuser\",\n",
-    "    \"tablename\": \"demo_tab\",\n",
-    "    \"colname\": \"data\",\n",
-    "}\n",
-    "\n",
-    "\"\"\" load the docs \"\"\"\n",
-    "loader = OracleDocLoader(conn=conn, params=loader_params)\n",
-    "docs = loader.load()\n",
-    "\n",
-    "\"\"\" verify \"\"\"\n",
-    "print(f\"Number of docs loaded: {len(docs)}\")\n",
-    "# print(f\"Document-0: {docs[0].page_content}\") # content"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Generate Summary\n",
-    "Now that the user loaded the documents, they may want to generate a summary for each document. The Oracle AI Vector Search Langchain library offers a suite of APIs designed for document summarization. It supports multiple summarization providers such as Database, OCIGENAI, HuggingFace, among others, allowing users to select the provider that best meets their needs. To utilize these capabilities, users must configure the summary parameters as specified. For detailed information on these parameters, please consult the [Oracle AI Vector Search Guide book](https://docs.oracle.com/en/database/oracle/oracle-database/23/arpls/dbms_vector_chain1.html#GUID-EC9DDB58-6A15-4B36-BA66-ECBA20D2CE57)."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "***Note:*** The users may need to set proxy if they want to use some 3rd party summary generation providers other than Oracle's in-house and default provider: 'database'. If you don't have proxy, please remove the proxy parameter when you instantiate the OracleSummary."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# proxy to be used when we instantiate summary and embedder object\n",
-    "proxy = \"\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The following sample code will show how to generate summary:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 49,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Number of Summaries: 3\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_community.utilities.oracleai import OracleSummary\n",
-    "from langchain_core.documents import Document\n",
-    "\n",
-    "# using 'database' provider\n",
-    "summary_params = {\n",
-    "    \"provider\": \"database\",\n",
-    "    \"glevel\": \"S\",\n",
-    "    \"numParagraphs\": 1,\n",
-    "    \"language\": \"english\",\n",
-    "}\n",
-    "\n",
-    "# get the summary instance\n",
-    "# Remove proxy if not required\n",
-    "summ = OracleSummary(conn=conn, params=summary_params, proxy=proxy)\n",
-    "\n",
-    "list_summary = []\n",
-    "for doc in docs:\n",
-    "    summary = summ.get_summary(doc.page_content)\n",
-    "    list_summary.append(summary)\n",
-    "\n",
-    "\"\"\" verify \"\"\"\n",
-    "print(f\"Number of Summaries: {len(list_summary)}\")\n",
-    "# print(f\"Summary-0: {list_summary[0]}\") #content"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Split Documents\n",
-    "The documents may vary in size, ranging from small to very large. Users often prefer to chunk their documents into smaller sections to facilitate the generation of embeddings. A wide array of customization options is available for this splitting process. For comprehensive details regarding these parameters, please consult the [Oracle AI Vector Search Guide](https://docs.oracle.com/en/database/oracle/oracle-database/23/arpls/dbms_vector_chain1.html#GUID-4E145629-7098-4C7C-804F-FC85D1F24240).\n",
-    "\n",
-    "Below is a sample code illustrating how to implement this:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 50,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Number of Chunks: 3\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_community.document_loaders.oracleai import OracleTextSplitter\n",
-    "from langchain_core.documents import Document\n",
-    "\n",
-    "# split by default parameters\n",
-    "splitter_params = {\"normalize\": \"all\"}\n",
-    "\n",
-    "\"\"\" get the splitter instance \"\"\"\n",
-    "splitter = OracleTextSplitter(conn=conn, params=splitter_params)\n",
-    "\n",
-    "list_chunks = []\n",
-    "for doc in docs:\n",
-    "    chunks = splitter.split_text(doc.page_content)\n",
-    "    list_chunks.extend(chunks)\n",
-    "\n",
-    "\"\"\" verify \"\"\"\n",
-    "print(f\"Number of Chunks: {len(list_chunks)}\")\n",
-    "# print(f\"Chunk-0: {list_chunks[0]}\") # content"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Generate Embeddings\n",
-    "Now that the documents are chunked as per requirements, the users may want to generate embeddings for these chunks. Oracle AI Vector Search provides multiple methods for generating embeddings, utilizing either locally hosted ONNX models or third-party APIs. For comprehensive instructions on configuring these alternatives, please refer to the [Oracle AI Vector Search Guide](https://docs.oracle.com/en/database/oracle/oracle-database/23/arpls/dbms_vector_chain1.html#GUID-C6439E94-4E86-4ECD-954E-4B73D53579DE)."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "***Note:*** Users may need to configure a proxy to utilize third-party embedding generation providers, excluding the 'database' provider that utilizes an ONNX model."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# proxy to be used when we instantiate summary and embedder object\n",
-    "proxy = \"\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The following sample code will show how to generate embeddings:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 51,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Number of embeddings: 3\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_community.embeddings.oracleai import OracleEmbeddings\n",
-    "from langchain_core.documents import Document\n",
-    "\n",
-    "# using ONNX model loaded to Oracle Database\n",
-    "embedder_params = {\"provider\": \"database\", \"model\": \"demo_model\"}\n",
-    "\n",
-    "# get the embedding instance\n",
-    "# Remove proxy if not required\n",
-    "embedder = OracleEmbeddings(conn=conn, params=embedder_params, proxy=proxy)\n",
-    "\n",
-    "embeddings = []\n",
-    "for doc in docs:\n",
-    "    chunks = splitter.split_text(doc.page_content)\n",
-    "    for chunk in chunks:\n",
-    "        embed = embedder.embed_query(chunk)\n",
-    "        embeddings.append(embed)\n",
-    "\n",
-    "\"\"\" verify \"\"\"\n",
-    "print(f\"Number of embeddings: {len(embeddings)}\")\n",
-    "# print(f\"Embedding-0: {embeddings[0]}\") # content"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Create Oracle AI Vector Store\n",
-    "Now that you know how to use Oracle AI Langchain library APIs individually to process the documents, let us show how to integrate with Oracle AI Vector Store to facilitate the semantic searches."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "First, let's import all the dependencies."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 52,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import sys\n",
-    "\n",
-    "import oracledb\n",
-    "from langchain_community.document_loaders.oracleai import (\n",
-    "    OracleDocLoader,\n",
-    "    OracleTextSplitter,\n",
-    ")\n",
-    "from langchain_community.embeddings.oracleai import OracleEmbeddings\n",
-    "from langchain_community.utilities.oracleai import OracleSummary\n",
-    "from langchain_community.vectorstores import oraclevs\n",
-    "from langchain_community.vectorstores.oraclevs import OracleVS\n",
-    "from langchain_community.vectorstores.utils import DistanceStrategy\n",
-    "from langchain_core.documents import Document"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Next, let's combine all document processing stages together. Here is the sample code below:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 53,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Connection successful!\n",
-      "ONNX model loaded.\n",
-      "Number of total chunks with metadata: 3\n"
-     ]
-    }
-   ],
-   "source": [
-    "\"\"\"\n",
-    "In this sample example, we will use 'database' provider for both summary and embeddings.\n",
-    "So, we don't need to do the followings:\n",
-    "    - set proxy for 3rd party providers\n",
-    "    - create credential for 3rd party providers\n",
-    "\n",
-    "If you choose to use 3rd party provider, \n",
-    "please follow the necessary steps for proxy and credential.\n",
-    "\"\"\"\n",
-    "\n",
-    "# oracle connection\n",
-    "# please update with your username, password, hostname, and service_name\n",
-    "username = \"\"\n",
-    "password = \"\"\n",
-    "dsn = \"\"\n",
-    "\n",
-    "try:\n",
-    "    conn = oracledb.connect(user=username, password=password, dsn=dsn)\n",
-    "    print(\"Connection successful!\")\n",
-    "except Exception as e:\n",
-    "    print(\"Connection failed!\")\n",
-    "    sys.exit(1)\n",
-    "\n",
-    "\n",
-    "# load onnx model\n",
-    "# please update with your related information\n",
-    "onnx_dir = \"DEMO_PY_DIR\"\n",
-    "onnx_file = \"tinybert.onnx\"\n",
-    "model_name = \"demo_model\"\n",
-    "try:\n",
-    "    OracleEmbeddings.load_onnx_model(conn, onnx_dir, onnx_file, model_name)\n",
-    "    print(\"ONNX model loaded.\")\n",
-    "except Exception as e:\n",
-    "    print(\"ONNX model loading failed!\")\n",
-    "    sys.exit(1)\n",
-    "\n",
-    "\n",
-    "# params\n",
-    "# please update necessary fields with related information\n",
-    "loader_params = {\n",
-    "    \"owner\": \"testuser\",\n",
-    "    \"tablename\": \"demo_tab\",\n",
-    "    \"colname\": \"data\",\n",
-    "}\n",
-    "summary_params = {\n",
-    "    \"provider\": \"database\",\n",
-    "    \"glevel\": \"S\",\n",
-    "    \"numParagraphs\": 1,\n",
-    "    \"language\": \"english\",\n",
-    "}\n",
-    "splitter_params = {\"normalize\": \"all\"}\n",
-    "embedder_params = {\"provider\": \"database\", \"model\": \"demo_model\"}\n",
-    "\n",
-    "# instantiate loader, summary, splitter, and embedder\n",
-    "loader = OracleDocLoader(conn=conn, params=loader_params)\n",
-    "summary = OracleSummary(conn=conn, params=summary_params)\n",
-    "splitter = OracleTextSplitter(conn=conn, params=splitter_params)\n",
-    "embedder = OracleEmbeddings(conn=conn, params=embedder_params)\n",
-    "\n",
-    "# process the documents\n",
-    "chunks_with_mdata = []\n",
-    "for id, doc in enumerate(docs, start=1):\n",
-    "    summ = summary.get_summary(doc.page_content)\n",
-    "    chunks = splitter.split_text(doc.page_content)\n",
-    "    for ic, chunk in enumerate(chunks, start=1):\n",
-    "        chunk_metadata = doc.metadata.copy()\n",
-    "        chunk_metadata[\"id\"] = chunk_metadata[\"_oid\"] + \"$\" + str(id) + \"$\" + str(ic)\n",
-    "        chunk_metadata[\"document_id\"] = str(id)\n",
-    "        chunk_metadata[\"document_summary\"] = str(summ[0])\n",
-    "        chunks_with_mdata.append(\n",
-    "            Document(page_content=str(chunk), metadata=chunk_metadata)\n",
-    "        )\n",
-    "\n",
-    "\"\"\" verify \"\"\"\n",
-    "print(f\"Number of total chunks with metadata: {len(chunks_with_mdata)}\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "At this point, we have processed the documents and generated chunks with metadata. Next, we will create Oracle AI Vector Store with those chunks.\n",
-    "\n",
-    "Here is the sample code how to do that:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 55,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Vector Store Table: oravs\n"
-     ]
-    }
-   ],
-   "source": [
-    "# create Oracle AI Vector Store\n",
-    "vectorstore = OracleVS.from_documents(\n",
-    "    chunks_with_mdata,\n",
-    "    embedder,\n",
-    "    client=conn,\n",
-    "    table_name=\"oravs\",\n",
-    "    distance_strategy=DistanceStrategy.DOT_PRODUCT,\n",
-    ")\n",
-    "\n",
-    "\"\"\" verify \"\"\"\n",
-    "print(f\"Vector Store Table: {vectorstore.table_name}\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The example provided illustrates the creation of a vector store using the DOT_PRODUCT distance strategy. Users have the flexibility to employ various distance strategies with the Oracle AI Vector Store, as detailed in our [comprehensive guide](https://python.langchain.com/v0.1/docs/integrations/vectorstores/oracle/)."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "With embeddings now stored in vector stores, it is advisable to establish an index to enhance semantic search performance during query execution.\n",
-    "\n",
-    "***Note*** Should you encounter an \"insufficient memory\" error, it is recommended to increase the  ***vector_memory_size*** in your database configuration\n",
-    "\n",
-    "Below is a sample code snippet for creating an index:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 56,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "oraclevs.create_index(\n",
-    "    conn, vectorstore, params={\"idx_name\": \"hnsw_oravs\", \"idx_type\": \"HNSW\"}\n",
-    ")\n",
-    "\n",
-    "print(\"Index created.\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "This example demonstrates the creation of a default HNSW index on embeddings within the 'oravs' table. Users may adjust various parameters according to their specific needs. For detailed information on these parameters, please consult the [Oracle AI Vector Search Guide book](https://docs.oracle.com/en/database/oracle/oracle-database/23/vecse/manage-different-categories-vector-indexes.html).\n",
-    "\n",
-    "Additionally, various types of vector indices can be created to meet diverse requirements. More details can be found in our [comprehensive guide](https://python.langchain.com/v0.1/docs/integrations/vectorstores/oracle/).\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Perform Semantic Search\n",
-    "All set!\n",
-    "\n",
-    "We have successfully processed the documents and stored them in the vector store, followed by the creation of an index to enhance query performance. We are now prepared to proceed with semantic searches.\n",
-    "\n",
-    "Below is the sample code for this process:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 58,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[Document(page_content='The database stores LOBs differently from other data types. Creating a LOB column implicitly creates a LOB segment and a LOB index. The tablespace containing the LOB segment and LOB index, which are always stored together, may be different from the tablespace containing the table. Sometimes the database can store small amounts of LOB data in the table itself rather than in a separate LOB segment.', metadata={'_oid': '662f2f257677f3c2311a8ff999fd34e5', '_rowid': 'AAAR/xAAEAAAAAnAAC', 'id': '662f2f257677f3c2311a8ff999fd34e5$3$1', 'document_id': '3', 'document_summary': 'Sometimes the database can store small amounts of LOB data in the table itself rather than in a separate LOB segment.\\n\\n'})]\n",
-      "[]\n",
-      "[(Document(page_content='The database stores LOBs differently from other data types. Creating a LOB column implicitly creates a LOB segment and a LOB index. The tablespace containing the LOB segment and LOB index, which are always stored together, may be different from the tablespace containing the table. Sometimes the database can store small amounts of LOB data in the table itself rather than in a separate LOB segment.', metadata={'_oid': '662f2f257677f3c2311a8ff999fd34e5', '_rowid': 'AAAR/xAAEAAAAAnAAC', 'id': '662f2f257677f3c2311a8ff999fd34e5$3$1', 'document_id': '3', 'document_summary': 'Sometimes the database can store small amounts of LOB data in the table itself rather than in a separate LOB segment.\\n\\n'}), 0.055675752460956573)]\n",
-      "[]\n",
-      "[Document(page_content='If the answer to any preceding questions is yes, then the database stops the search and allocates space from the specified tablespace; otherwise, space is allocated from the database default shared temporary tablespace.', metadata={'_oid': '662f2f253acf96b33b430b88699490a2', '_rowid': 'AAAR/xAAEAAAAAnAAA', 'id': '662f2f253acf96b33b430b88699490a2$1$1', 'document_id': '1', 'document_summary': 'If the answer to any preceding questions is yes, then the database stops the search and allocates space from the specified tablespace; otherwise, space is allocated from the database default shared temporary tablespace.\\n\\n'})]\n",
-      "[Document(page_content='If the answer to any preceding questions is yes, then the database stops the search and allocates space from the specified tablespace; otherwise, space is allocated from the database default shared temporary tablespace.', metadata={'_oid': '662f2f253acf96b33b430b88699490a2', '_rowid': 'AAAR/xAAEAAAAAnAAA', 'id': '662f2f253acf96b33b430b88699490a2$1$1', 'document_id': '1', 'document_summary': 'If the answer to any preceding questions is yes, then the database stops the search and allocates space from the specified tablespace; otherwise, space is allocated from the database default shared temporary tablespace.\\n\\n'})]\n"
-     ]
-    }
-   ],
-   "source": [
-    "query = \"What is Oracle AI Vector Store?\"\n",
-    "filter = {\"document_id\": [\"1\"]}\n",
-    "\n",
-    "# Similarity search without a filter\n",
-    "print(vectorstore.similarity_search(query, 1))\n",
-    "\n",
-    "# Similarity search with a filter\n",
-    "print(vectorstore.similarity_search(query, 1, filter=filter))\n",
-    "\n",
-    "# Similarity search with relevance score\n",
-    "print(vectorstore.similarity_search_with_score(query, 1))\n",
-    "\n",
-    "# Similarity search with relevance score with filter\n",
-    "print(vectorstore.similarity_search_with_score(query, 1, filter=filter))\n",
-    "\n",
-    "# Max marginal relevance search\n",
-    "print(vectorstore.max_marginal_relevance_search(query, 1, fetch_k=20, lambda_mult=0.5))\n",
-    "\n",
-    "# Max marginal relevance search with filter\n",
-    "print(\n",
-    "    vectorstore.max_marginal_relevance_search(\n",
-    "        query, 1, fetch_k=20, lambda_mult=0.5, filter=filter\n",
-    "    )\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": "3.11.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

cookbook/petting_zoo.ipynb

@@ -129,7 +129,7 @@
     "        return obs_message\n",
     "\n",
     "    def _act(self):\n",
-    "        act_message = self.model.invoke(self.message_history)\n",
+    "        act_message = self.model(self.message_history)\n",
     "        self.message_history.append(act_message)\n",
     "        action = int(self.action_parser.parse(act_message.content)[\"action\"])\n",
     "        return action\n",

cookbook/rag_semantic_chunking_azureaidocintelligence.ipynb

@@ -168,7 +168,7 @@
     "\n",
     "retriever = vector_store.as_retriever(search_type=\"similarity\", search_kwargs={\"k\": 3})\n",
     "\n",
-    "retrieved_docs = retriever.invoke(\"<your question>\")\n",
+    "retrieved_docs = retriever.get_relevant_documents(\"<your question>\")\n",
     "\n",
     "print(retrieved_docs[0].page_content)\n",
     "\n",

cookbook/rag_upstage_layout_analysis_groundedness_check.ipynb

@@ -1,82 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# RAG using Upstage Layout Analysis and Groundedness Check\n",
-    "This example illustrates RAG using [Upstage](https://python.langchain.com/docs/integrations/providers/upstage/) Layout Analysis and Groundedness Check."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from typing import List\n",
-    "\n",
-    "from langchain_community.vectorstores import DocArrayInMemorySearch\n",
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_core.runnables import RunnablePassthrough\n",
-    "from langchain_core.runnables.base import RunnableSerializable\n",
-    "from langchain_upstage import (\n",
-    "    ChatUpstage,\n",
-    "    UpstageEmbeddings,\n",
-    "    UpstageGroundednessCheck,\n",
-    "    UpstageLayoutAnalysisLoader,\n",
-    ")\n",
-    "\n",
-    "model = ChatUpstage()\n",
-    "\n",
-    "files = [\"/PATH/TO/YOUR/FILE.pdf\", \"/PATH/TO/YOUR/FILE2.pdf\"]\n",
-    "\n",
-    "loader = UpstageLayoutAnalysisLoader(file_path=files, split=\"element\")\n",
-    "\n",
-    "docs = loader.load()\n",
-    "\n",
-    "vectorstore = DocArrayInMemorySearch.from_documents(\n",
-    "    docs, embedding=UpstageEmbeddings(model=\"solar-embedding-1-large\")\n",
-    ")\n",
-    "retriever = vectorstore.as_retriever()\n",
-    "\n",
-    "template = \"\"\"Answer the question based only on the following context:\n",
-    "{context}\n",
-    "\n",
-    "Question: {question}\n",
-    "\"\"\"\n",
-    "prompt = ChatPromptTemplate.from_template(template)\n",
-    "output_parser = StrOutputParser()\n",
-    "\n",
-    "retrieved_docs = retriever.get_relevant_documents(\"How many parameters in SOLAR model?\")\n",
-    "\n",
-    "groundedness_check = UpstageGroundednessCheck()\n",
-    "groundedness = \"\"\n",
-    "while groundedness != \"grounded\":\n",
-    "    chain: RunnableSerializable = RunnablePassthrough() | prompt | model | output_parser\n",
-    "\n",
-    "    result = chain.invoke(\n",
-    "        {\n",
-    "            \"context\": retrieved_docs,\n",
-    "            \"question\": \"How many parameters in SOLAR model?\",\n",
-    "        }\n",
-    "    )\n",
-    "\n",
-    "    groundedness = groundedness_check.invoke(\n",
-    "        {\n",
-    "            \"context\": retrieved_docs,\n",
-    "            \"answer\": result,\n",
-    "        }\n",
-    "    )"
-   ]
-  }
- ],
- "metadata": {
-  "language_info": {
-   "name": "python"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

cookbook/rag_with_quantized_embeddings.ipynb

@@ -39,10 +39,12 @@
     "from langchain_community.document_loaders.recursive_url_loader import (\n",
     "    RecursiveUrlLoader,\n",
     ")\n",
+    "\n",
+    "# noqa\n",
     "from langchain_community.vectorstores import Chroma\n",
     "\n",
     "# For our example, we'll load docs from the web\n",
-    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter  # noqa\n",
     "\n",
     "DOCSTORE_DIR = \".\"\n",
     "DOCSTORE_ID_KEY = \"doc_id\""

cookbook/self_query_hotel_search.ipynb

@@ -355,15 +355,15 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "attribute_info[-2][\"description\"] += (\n",
-    "    f\". Valid values are {sorted(latest_price['starrating'].value_counts().index.tolist())}\"\n",
-    ")\n",
-    "attribute_info[3][\"description\"] += (\n",
-    "    f\". Valid values are {sorted(latest_price['maxoccupancy'].value_counts().index.tolist())}\"\n",
-    ")\n",
-    "attribute_info[-3][\"description\"] += (\n",
-    "    f\". Valid values are {sorted(latest_price['country'].value_counts().index.tolist())}\"\n",
-    ")"
+    "attribute_info[-2][\n",
+    "    \"description\"\n",
+    "] += f\". Valid values are {sorted(latest_price['starrating'].value_counts().index.tolist())}\"\n",
+    "attribute_info[3][\n",
+    "    \"description\"\n",
+    "] += f\". Valid values are {sorted(latest_price['maxoccupancy'].value_counts().index.tolist())}\"\n",
+    "attribute_info[-3][\n",
+    "    \"description\"\n",
+    "] += f\". Valid values are {sorted(latest_price['country'].value_counts().index.tolist())}\""
    ]
   },
   {
@@ -688,9 +688,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "attribute_info[-3][\"description\"] += (\n",
-    "    \". NOTE: Only use the 'eq' operator if a specific country is mentioned. If a region is mentioned, include all relevant countries in filter.\"\n",
-    ")\n",
+    "attribute_info[-3][\n",
+    "    \"description\"\n",
+    "] += \". NOTE: Only use the 'eq' operator if a specific country is mentioned. If a region is mentioned, include all relevant countries in filter.\"\n",
     "chain = load_query_constructor_runnable(\n",
     "    ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0),\n",
     "    doc_contents,\n",
@@ -1227,7 +1227,7 @@
     }
    ],
    "source": [
-    "results = retriever.invoke(\n",
+    "results = retriever.get_relevant_documents(\n",
     "    \"I want to stay somewhere highly rated along the coast. I want a room with a patio and a fireplace.\"\n",
     ")\n",
     "for res in results:\n",

cookbook/sharedmemory_for_tools.ipynb

@@ -22,8 +22,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain import hub\n",
-    "from langchain.agents import AgentExecutor, Tool, ZeroShotAgent, create_react_agent\n",
+    "from langchain.agents import AgentExecutor, Tool, ZeroShotAgent\n",
     "from langchain.chains import LLMChain\n",
     "from langchain.memory import ConversationBufferMemory, ReadOnlySharedMemory\n",
     "from langchain.prompts import PromptTemplate\n",
@@ -85,7 +84,19 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "prompt = hub.pull(\"hwchase17/react\")"
+    "prefix = \"\"\"Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:\"\"\"\n",
+    "suffix = \"\"\"Begin!\"\n",
+    "\n",
+    "{chat_history}\n",
+    "Question: {input}\n",
+    "{agent_scratchpad}\"\"\"\n",
+    "\n",
+    "prompt = ZeroShotAgent.create_prompt(\n",
+    "    tools,\n",
+    "    prefix=prefix,\n",
+    "    suffix=suffix,\n",
+    "    input_variables=[\"input\", \"chat_history\", \"agent_scratchpad\"],\n",
+    ")"
    ]
   },
   {
@@ -103,14 +114,16 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "model = OpenAI()\n",
-    "agent = create_react_agent(model, tools, prompt)\n",
-    "agent_executor = AgentExecutor(agent=agent, tools=tools, memory=memory)"
+    "llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=prompt)\n",
+    "agent = ZeroShotAgent(llm_chain=llm_chain, tools=tools, verbose=True)\n",
+    "agent_chain = AgentExecutor.from_agent_and_tools(\n",
+    "    agent=agent, tools=tools, verbose=True, memory=memory\n",
+    ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 6,
    "id": "ca4bc1fb",
    "metadata": {},
    "outputs": [
@@ -120,15 +133,15 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
-      "\u001B[32;1m\u001B[1;3mThought: I should research ChatGPT to answer this question.\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I should research ChatGPT to answer this question.\n",
       "Action: Search\n",
-      "Action Input: \"ChatGPT\"\u001B[0m\n",
-      "Observation: \u001B[36;1m\u001B[1;3mNov 30, 2022 ... We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... ChatGPT. We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... Feb 2, 2023 ... ChatGPT, the popular chatbot from OpenAI, is estimated to have reached 100 million monthly active users in January, just two months after ... 2 days ago ... ChatGPT recently launched a new version of its own plagiarism detection tool, with hopes that it will squelch some of the criticism around how ... An API for accessing new AI models developed by OpenAI. Feb 19, 2023 ... ChatGPT is an AI chatbot system that OpenAI released in November to show off and test what a very large, powerful AI system can accomplish. You ... ChatGPT is fine-tuned from GPT-3.5, a language model trained to produce text. ChatGPT was optimized for dialogue by using Reinforcement Learning with Human ... 3 days ago ... Visual ChatGPT connects ChatGPT and a series of Visual Foundation Models to enable sending and receiving images during chatting. Dec 1, 2022 ... ChatGPT is a natural language processing tool driven by AI technology that allows you to have human-like conversations and much more with a ...\u001B[0m\n",
-      "Thought:\u001B[32;1m\u001B[1;3m I now know the final answer.\n",
-      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\u001B[0m\n",
+      "Action Input: \"ChatGPT\"\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mNov 30, 2022 ... We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... ChatGPT. We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... Feb 2, 2023 ... ChatGPT, the popular chatbot from OpenAI, is estimated to have reached 100 million monthly active users in January, just two months after ... 2 days ago ... ChatGPT recently launched a new version of its own plagiarism detection tool, with hopes that it will squelch some of the criticism around how ... An API for accessing new AI models developed by OpenAI. Feb 19, 2023 ... ChatGPT is an AI chatbot system that OpenAI released in November to show off and test what a very large, powerful AI system can accomplish. You ... ChatGPT is fine-tuned from GPT-3.5, a language model trained to produce text. ChatGPT was optimized for dialogue by using Reinforcement Learning with Human ... 3 days ago ... Visual ChatGPT connects ChatGPT and a series of Visual Foundation Models to enable sending and receiving images during chatting. Dec 1, 2022 ... ChatGPT is a natural language processing tool driven by AI technology that allows you to have human-like conversations and much more with a ...\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished chain.\u001B[0m\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
@@ -140,40 +153,10 @@
      "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
-    },
-    {
-     "ename": "KeyboardInterrupt",
-     "evalue": "",
-     "output_type": "error",
-     "traceback": [
-      "\u001B[0;31m---------------------------------------------------------------------------\u001B[0m",
-      "\u001B[0;31mKeyboardInterrupt\u001B[0m                         Traceback (most recent call last)",
-      "Cell \u001B[0;32mIn[36], line 1\u001B[0m\n\u001B[0;32m----> 1\u001B[0m \u001B[43magent_executor\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43minvoke\u001B[49m\u001B[43m(\u001B[49m\u001B[43m{\u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43minput\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mWhat is ChatGPT?\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m}\u001B[49m\u001B[43m)\u001B[49m\n",
-      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/chains/base.py:163\u001B[0m, in \u001B[0;36mChain.invoke\u001B[0;34m(self, input, config, **kwargs)\u001B[0m\n\u001B[1;32m    161\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m \u001B[38;5;167;01mBaseException\u001B[39;00m \u001B[38;5;28;01mas\u001B[39;00m e:\n\u001B[1;32m    162\u001B[0m     run_manager\u001B[38;5;241m.\u001B[39mon_chain_error(e)\n\u001B[0;32m--> 163\u001B[0m     \u001B[38;5;28;01mraise\u001B[39;00m e\n\u001B[1;32m    164\u001B[0m run_manager\u001B[38;5;241m.\u001B[39mon_chain_end(outputs)\n\u001B[1;32m    166\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m include_run_info:\n",
-      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/chains/base.py:153\u001B[0m, in \u001B[0;36mChain.invoke\u001B[0;34m(self, input, config, **kwargs)\u001B[0m\n\u001B[1;32m    150\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[1;32m    151\u001B[0m     \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_validate_inputs(inputs)\n\u001B[1;32m    152\u001B[0m     outputs \u001B[38;5;241m=\u001B[39m (\n\u001B[0;32m--> 153\u001B[0m         \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_call\u001B[49m\u001B[43m(\u001B[49m\u001B[43minputs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mrun_manager\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mrun_manager\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m    154\u001B[0m         \u001B[38;5;28;01mif\u001B[39;00m new_arg_supported\n\u001B[1;32m    155\u001B[0m         \u001B[38;5;28;01melse\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_call(inputs)\n\u001B[1;32m    156\u001B[0m     )\n\u001B[1;32m    158\u001B[0m     final_outputs: Dict[\u001B[38;5;28mstr\u001B[39m, Any] \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mprep_outputs(\n\u001B[1;32m    159\u001B[0m         inputs, outputs, return_only_outputs\n\u001B[1;32m    160\u001B[0m     )\n\u001B[1;32m    161\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m \u001B[38;5;167;01mBaseException\u001B[39;00m \u001B[38;5;28;01mas\u001B[39;00m e:\n",
-      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/agents/agent.py:1432\u001B[0m, in \u001B[0;36mAgentExecutor._call\u001B[0;34m(self, inputs, run_manager)\u001B[0m\n\u001B[1;32m   1430\u001B[0m \u001B[38;5;66;03m# We now enter the agent loop (until it returns something).\u001B[39;00m\n\u001B[1;32m   1431\u001B[0m \u001B[38;5;28;01mwhile\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_should_continue(iterations, time_elapsed):\n\u001B[0;32m-> 1432\u001B[0m     next_step_output \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_take_next_step\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m   1433\u001B[0m \u001B[43m        \u001B[49m\u001B[43mname_to_tool_map\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1434\u001B[0m \u001B[43m        \u001B[49m\u001B[43mcolor_mapping\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1435\u001B[0m \u001B[43m        \u001B[49m\u001B[43minputs\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1436\u001B[0m \u001B[43m        \u001B[49m\u001B[43mintermediate_steps\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1437\u001B[0m \u001B[43m        \u001B[49m\u001B[43mrun_manager\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mrun_manager\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1438\u001B[0m \u001B[43m    \u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1439\u001B[0m     \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28misinstance\u001B[39m(next_step_output, AgentFinish):\n\u001B[1;32m   1440\u001B[0m         \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_return(\n\u001B[1;32m   1441\u001B[0m             next_step_output, intermediate_steps, run_manager\u001B[38;5;241m=\u001B[39mrun_manager\n\u001B[1;32m   1442\u001B[0m         )\n",
-      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/agents/agent.py:1138\u001B[0m, in \u001B[0;36mAgentExecutor._take_next_step\u001B[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001B[0m\n\u001B[1;32m   1129\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m \u001B[38;5;21m_take_next_step\u001B[39m(\n\u001B[1;32m   1130\u001B[0m     \u001B[38;5;28mself\u001B[39m,\n\u001B[1;32m   1131\u001B[0m     name_to_tool_map: Dict[\u001B[38;5;28mstr\u001B[39m, BaseTool],\n\u001B[0;32m   (...)\u001B[0m\n\u001B[1;32m   1135\u001B[0m     run_manager: Optional[CallbackManagerForChainRun] \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;01mNone\u001B[39;00m,\n\u001B[1;32m   1136\u001B[0m ) \u001B[38;5;241m-\u001B[39m\u001B[38;5;241m>\u001B[39m Union[AgentFinish, List[Tuple[AgentAction, \u001B[38;5;28mstr\u001B[39m]]]:\n\u001B[1;32m   1137\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_consume_next_step(\n\u001B[0;32m-> 1138\u001B[0m         [\n\u001B[1;32m   1139\u001B[0m             a\n\u001B[1;32m   1140\u001B[0m             \u001B[38;5;28;01mfor\u001B[39;00m a \u001B[38;5;129;01min\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_iter_next_step(\n\u001B[1;32m   1141\u001B[0m                 name_to_tool_map,\n\u001B[1;32m   1142\u001B[0m                 color_mapping,\n\u001B[1;32m   1143\u001B[0m                 inputs,\n\u001B[1;32m   1144\u001B[0m                 intermediate_steps,\n\u001B[1;32m   1145\u001B[0m                 run_manager,\n\u001B[1;32m   1146\u001B[0m             )\n\u001B[1;32m   1147\u001B[0m         ]\n\u001B[1;32m   1148\u001B[0m     )\n",
-      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/agents/agent.py:1138\u001B[0m, in \u001B[0;36m<listcomp>\u001B[0;34m(.0)\u001B[0m\n\u001B[1;32m   1129\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m \u001B[38;5;21m_take_next_step\u001B[39m(\n\u001B[1;32m   1130\u001B[0m     \u001B[38;5;28mself\u001B[39m,\n\u001B[1;32m   1131\u001B[0m     name_to_tool_map: Dict[\u001B[38;5;28mstr\u001B[39m, BaseTool],\n\u001B[0;32m   (...)\u001B[0m\n\u001B[1;32m   1135\u001B[0m     run_manager: Optional[CallbackManagerForChainRun] \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;01mNone\u001B[39;00m,\n\u001B[1;32m   1136\u001B[0m ) \u001B[38;5;241m-\u001B[39m\u001B[38;5;241m>\u001B[39m Union[AgentFinish, List[Tuple[AgentAction, \u001B[38;5;28mstr\u001B[39m]]]:\n\u001B[1;32m   1137\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_consume_next_step(\n\u001B[0;32m-> 1138\u001B[0m         [\n\u001B[1;32m   1139\u001B[0m             a\n\u001B[1;32m   1140\u001B[0m             \u001B[38;5;28;01mfor\u001B[39;00m a \u001B[38;5;129;01min\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_iter_next_step(\n\u001B[1;32m   1141\u001B[0m                 name_to_tool_map,\n\u001B[1;32m   1142\u001B[0m                 color_mapping,\n\u001B[1;32m   1143\u001B[0m                 inputs,\n\u001B[1;32m   1144\u001B[0m                 intermediate_steps,\n\u001B[1;32m   1145\u001B[0m                 run_manager,\n\u001B[1;32m   1146\u001B[0m             )\n\u001B[1;32m   1147\u001B[0m         ]\n\u001B[1;32m   1148\u001B[0m     )\n",
-      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/agents/agent.py:1223\u001B[0m, in \u001B[0;36mAgentExecutor._iter_next_step\u001B[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001B[0m\n\u001B[1;32m   1221\u001B[0m     \u001B[38;5;28;01myield\u001B[39;00m agent_action\n\u001B[1;32m   1222\u001B[0m \u001B[38;5;28;01mfor\u001B[39;00m agent_action \u001B[38;5;129;01min\u001B[39;00m actions:\n\u001B[0;32m-> 1223\u001B[0m     \u001B[38;5;28;01myield\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_perform_agent_action\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m   1224\u001B[0m \u001B[43m        \u001B[49m\u001B[43mname_to_tool_map\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mcolor_mapping\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43magent_action\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mrun_manager\u001B[49m\n\u001B[1;32m   1225\u001B[0m \u001B[43m    \u001B[49m\u001B[43m)\u001B[49m\n",
-      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/agents/agent.py:1245\u001B[0m, in \u001B[0;36mAgentExecutor._perform_agent_action\u001B[0;34m(self, name_to_tool_map, color_mapping, agent_action, run_manager)\u001B[0m\n\u001B[1;32m   1243\u001B[0m         tool_run_kwargs[\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mllm_prefix\u001B[39m\u001B[38;5;124m\"\u001B[39m] \u001B[38;5;241m=\u001B[39m \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124m\"\u001B[39m\n\u001B[1;32m   1244\u001B[0m     \u001B[38;5;66;03m# We then call the tool on the tool input to get an observation\u001B[39;00m\n\u001B[0;32m-> 1245\u001B[0m     observation \u001B[38;5;241m=\u001B[39m \u001B[43mtool\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mrun\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m   1246\u001B[0m \u001B[43m        \u001B[49m\u001B[43magent_action\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mtool_input\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1247\u001B[0m \u001B[43m        \u001B[49m\u001B[43mverbose\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mverbose\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1248\u001B[0m \u001B[43m        \u001B[49m\u001B[43mcolor\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mcolor\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1249\u001B[0m \u001B[43m        \u001B[49m\u001B[43mcallbacks\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mrun_manager\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mget_child\u001B[49m\u001B[43m(\u001B[49m\u001B[43m)\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;28;43;01mif\u001B[39;49;00m\u001B[43m \u001B[49m\u001B[43mrun_manager\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;28;43;01melse\u001B[39;49;00m\u001B[43m \u001B[49m\u001B[38;5;28;43;01mNone\u001B[39;49;00m\u001B[43m,\u001B[49m\n\u001B[1;32m   1250\u001B[0m \u001B[43m        \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mtool_run_kwargs\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1251\u001B[0m \u001B[43m    \u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1252\u001B[0m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[1;32m   1253\u001B[0m     tool_run_kwargs \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39magent\u001B[38;5;241m.\u001B[39mtool_run_logging_kwargs()\n",
-      "File \u001B[0;32m~/code/langchain/libs/core/langchain_core/tools.py:422\u001B[0m, in \u001B[0;36mBaseTool.run\u001B[0;34m(self, tool_input, verbose, start_color, color, callbacks, tags, metadata, run_name, run_id, **kwargs)\u001B[0m\n\u001B[1;32m    420\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m (\u001B[38;5;167;01mException\u001B[39;00m, \u001B[38;5;167;01mKeyboardInterrupt\u001B[39;00m) \u001B[38;5;28;01mas\u001B[39;00m e:\n\u001B[1;32m    421\u001B[0m     run_manager\u001B[38;5;241m.\u001B[39mon_tool_error(e)\n\u001B[0;32m--> 422\u001B[0m     \u001B[38;5;28;01mraise\u001B[39;00m e\n\u001B[1;32m    423\u001B[0m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[1;32m    424\u001B[0m     run_manager\u001B[38;5;241m.\u001B[39mon_tool_end(observation, color\u001B[38;5;241m=\u001B[39mcolor, name\u001B[38;5;241m=\u001B[39m\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mname, \u001B[38;5;241m*\u001B[39m\u001B[38;5;241m*\u001B[39mkwargs)\n",
-      "File \u001B[0;32m~/code/langchain/libs/core/langchain_core/tools.py:381\u001B[0m, in \u001B[0;36mBaseTool.run\u001B[0;34m(self, tool_input, verbose, start_color, color, callbacks, tags, metadata, run_name, run_id, **kwargs)\u001B[0m\n\u001B[1;32m    378\u001B[0m     parsed_input \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_parse_input(tool_input)\n\u001B[1;32m    379\u001B[0m     tool_args, tool_kwargs \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_to_args_and_kwargs(parsed_input)\n\u001B[1;32m    380\u001B[0m     observation \u001B[38;5;241m=\u001B[39m (\n\u001B[0;32m--> 381\u001B[0m         \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_run\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mtool_args\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mrun_manager\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mrun_manager\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mtool_kwargs\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m    382\u001B[0m         \u001B[38;5;28;01mif\u001B[39;00m new_arg_supported\n\u001B[1;32m    383\u001B[0m         \u001B[38;5;28;01melse\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_run(\u001B[38;5;241m*\u001B[39mtool_args, \u001B[38;5;241m*\u001B[39m\u001B[38;5;241m*\u001B[39mtool_kwargs)\n\u001B[1;32m    384\u001B[0m     )\n\u001B[1;32m    385\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m ValidationError \u001B[38;5;28;01mas\u001B[39;00m e:\n\u001B[1;32m    386\u001B[0m     \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mhandle_validation_error:\n",
-      "File \u001B[0;32m~/code/langchain/libs/core/langchain_core/tools.py:588\u001B[0m, in \u001B[0;36mTool._run\u001B[0;34m(self, run_manager, *args, **kwargs)\u001B[0m\n\u001B[1;32m    579\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mfunc:\n\u001B[1;32m    580\u001B[0m     new_argument_supported \u001B[38;5;241m=\u001B[39m signature(\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mfunc)\u001B[38;5;241m.\u001B[39mparameters\u001B[38;5;241m.\u001B[39mget(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mcallbacks\u001B[39m\u001B[38;5;124m\"\u001B[39m)\n\u001B[1;32m    581\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m (\n\u001B[1;32m    582\u001B[0m         \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mfunc(\n\u001B[1;32m    583\u001B[0m             \u001B[38;5;241m*\u001B[39margs,\n\u001B[1;32m    584\u001B[0m             callbacks\u001B[38;5;241m=\u001B[39mrun_manager\u001B[38;5;241m.\u001B[39mget_child() \u001B[38;5;28;01mif\u001B[39;00m run_manager \u001B[38;5;28;01melse\u001B[39;00m \u001B[38;5;28;01mNone\u001B[39;00m,\n\u001B[1;32m    585\u001B[0m             \u001B[38;5;241m*\u001B[39m\u001B[38;5;241m*\u001B[39mkwargs,\n\u001B[1;32m    586\u001B[0m         )\n\u001B[1;32m    587\u001B[0m         \u001B[38;5;28;01mif\u001B[39;00m new_argument_supported\n\u001B[0;32m--> 588\u001B[0m         \u001B[38;5;28;01melse\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mfunc\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[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    589\u001B[0m     )\n\u001B[1;32m    590\u001B[0m \u001B[38;5;28;01mraise\u001B[39;00m \u001B[38;5;167;01mNotImplementedError\u001B[39;00m(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mTool does not support sync\u001B[39m\u001B[38;5;124m\"\u001B[39m)\n",
-      "File \u001B[0;32m~/code/langchain/libs/community/langchain_community/utilities/google_search.py:94\u001B[0m, in \u001B[0;36mGoogleSearchAPIWrapper.run\u001B[0;34m(self, query)\u001B[0m\n\u001B[1;32m     92\u001B[0m \u001B[38;5;250m\u001B[39m\u001B[38;5;124;03m\"\"\"Run query through GoogleSearch and parse result.\"\"\"\u001B[39;00m\n\u001B[1;32m     93\u001B[0m snippets \u001B[38;5;241m=\u001B[39m []\n\u001B[0;32m---> 94\u001B[0m results \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_google_search_results\u001B[49m\u001B[43m(\u001B[49m\u001B[43mquery\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mnum\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mk\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m     95\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mlen\u001B[39m(results) \u001B[38;5;241m==\u001B[39m \u001B[38;5;241m0\u001B[39m:\n\u001B[1;32m     96\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mNo good Google Search Result was found\u001B[39m\u001B[38;5;124m\"\u001B[39m\n",
-      "File \u001B[0;32m~/code/langchain/libs/community/langchain_community/utilities/google_search.py:62\u001B[0m, in \u001B[0;36mGoogleSearchAPIWrapper._google_search_results\u001B[0;34m(self, search_term, **kwargs)\u001B[0m\n\u001B[1;32m     60\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39msiterestrict:\n\u001B[1;32m     61\u001B[0m     cse \u001B[38;5;241m=\u001B[39m cse\u001B[38;5;241m.\u001B[39msiterestrict()\n\u001B[0;32m---> 62\u001B[0m res \u001B[38;5;241m=\u001B[39m \u001B[43mcse\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mlist\u001B[49m\u001B[43m(\u001B[49m\u001B[43mq\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43msearch_term\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mcx\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mgoogle_cse_id\u001B[49m\u001B[43m,\u001B[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\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mexecute\u001B[49m\u001B[43m(\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m     63\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m res\u001B[38;5;241m.\u001B[39mget(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mitems\u001B[39m\u001B[38;5;124m\"\u001B[39m, [])\n",
-      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/googleapiclient/_helpers.py:130\u001B[0m, in \u001B[0;36mpositional.<locals>.positional_decorator.<locals>.positional_wrapper\u001B[0;34m(*args, **kwargs)\u001B[0m\n\u001B[1;32m    128\u001B[0m     \u001B[38;5;28;01melif\u001B[39;00m positional_parameters_enforcement \u001B[38;5;241m==\u001B[39m POSITIONAL_WARNING:\n\u001B[1;32m    129\u001B[0m         logger\u001B[38;5;241m.\u001B[39mwarning(message)\n\u001B[0;32m--> 130\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mwrapped\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[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",
-      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/googleapiclient/http.py:923\u001B[0m, in \u001B[0;36mHttpRequest.execute\u001B[0;34m(self, http, num_retries)\u001B[0m\n\u001B[1;32m    920\u001B[0m     \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mheaders[\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mcontent-length\u001B[39m\u001B[38;5;124m\"\u001B[39m] \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mstr\u001B[39m(\u001B[38;5;28mlen\u001B[39m(\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mbody))\n\u001B[1;32m    922\u001B[0m \u001B[38;5;66;03m# Handle retries for server-side errors.\u001B[39;00m\n\u001B[0;32m--> 923\u001B[0m resp, content \u001B[38;5;241m=\u001B[39m \u001B[43m_retry_request\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m    924\u001B[0m \u001B[43m    \u001B[49m\u001B[43mhttp\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    925\u001B[0m \u001B[43m    \u001B[49m\u001B[43mnum_retries\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    926\u001B[0m \u001B[43m    \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mrequest\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m,\u001B[49m\n\u001B[1;32m    927\u001B[0m \u001B[43m    \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_sleep\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    928\u001B[0m \u001B[43m    \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_rand\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    929\u001B[0m \u001B[43m    \u001B[49m\u001B[38;5;28;43mstr\u001B[39;49m\u001B[43m(\u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43muri\u001B[49m\u001B[43m)\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    930\u001B[0m \u001B[43m    \u001B[49m\u001B[43mmethod\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mstr\u001B[39;49m\u001B[43m(\u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mmethod\u001B[49m\u001B[43m)\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    931\u001B[0m \u001B[43m    \u001B[49m\u001B[43mbody\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mbody\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    932\u001B[0m \u001B[43m    \u001B[49m\u001B[43mheaders\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mheaders\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    933\u001B[0m \u001B[43m\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m    935\u001B[0m \u001B[38;5;28;01mfor\u001B[39;00m callback \u001B[38;5;129;01min\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mresponse_callbacks:\n\u001B[1;32m    936\u001B[0m     callback(resp)\n",
-      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/googleapiclient/http.py:191\u001B[0m, in \u001B[0;36m_retry_request\u001B[0;34m(http, num_retries, req_type, sleep, rand, uri, method, *args, **kwargs)\u001B[0m\n\u001B[1;32m    189\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[1;32m    190\u001B[0m     exception \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;01mNone\u001B[39;00m\n\u001B[0;32m--> 191\u001B[0m     resp, content \u001B[38;5;241m=\u001B[39m \u001B[43mhttp\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mrequest\u001B[49m\u001B[43m(\u001B[49m\u001B[43muri\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mmethod\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[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    192\u001B[0m \u001B[38;5;66;03m# Retry on SSL errors and socket timeout errors.\u001B[39;00m\n\u001B[1;32m    193\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m _ssl_SSLError \u001B[38;5;28;01mas\u001B[39;00m ssl_error:\n",
-      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/httplib2/__init__.py:1724\u001B[0m, in \u001B[0;36mHttp.request\u001B[0;34m(self, uri, method, body, headers, redirections, connection_type)\u001B[0m\n\u001B[1;32m   1722\u001B[0m             content \u001B[38;5;241m=\u001B[39m \u001B[38;5;124mb\u001B[39m\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124m\"\u001B[39m\n\u001B[1;32m   1723\u001B[0m         \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[0;32m-> 1724\u001B[0m             (response, content) \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_request\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m   1725\u001B[0m \u001B[43m                \u001B[49m\u001B[43mconn\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mauthority\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43muri\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mrequest_uri\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mmethod\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mbody\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mheaders\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mredirections\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mcachekey\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1726\u001B[0m \u001B[43m            \u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1727\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m \u001B[38;5;167;01mException\u001B[39;00m \u001B[38;5;28;01mas\u001B[39;00m e:\n\u001B[1;32m   1728\u001B[0m     is_timeout \u001B[38;5;241m=\u001B[39m \u001B[38;5;28misinstance\u001B[39m(e, socket\u001B[38;5;241m.\u001B[39mtimeout)\n",
-      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/httplib2/__init__.py:1444\u001B[0m, in \u001B[0;36mHttp._request\u001B[0;34m(self, conn, host, absolute_uri, request_uri, method, body, headers, redirections, cachekey)\u001B[0m\n\u001B[1;32m   1441\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m auth:\n\u001B[1;32m   1442\u001B[0m     auth\u001B[38;5;241m.\u001B[39mrequest(method, request_uri, headers, body)\n\u001B[0;32m-> 1444\u001B[0m (response, content) \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_conn_request\u001B[49m\u001B[43m(\u001B[49m\u001B[43mconn\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mrequest_uri\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mmethod\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mbody\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mheaders\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1446\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m auth:\n\u001B[1;32m   1447\u001B[0m     \u001B[38;5;28;01mif\u001B[39;00m auth\u001B[38;5;241m.\u001B[39mresponse(response, body):\n",
-      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/httplib2/__init__.py:1366\u001B[0m, in \u001B[0;36mHttp._conn_request\u001B[0;34m(self, conn, request_uri, method, body, headers)\u001B[0m\n\u001B[1;32m   1364\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[1;32m   1365\u001B[0m     \u001B[38;5;28;01mif\u001B[39;00m conn\u001B[38;5;241m.\u001B[39msock \u001B[38;5;129;01mis\u001B[39;00m \u001B[38;5;28;01mNone\u001B[39;00m:\n\u001B[0;32m-> 1366\u001B[0m         \u001B[43mconn\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mconnect\u001B[49m\u001B[43m(\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1367\u001B[0m     conn\u001B[38;5;241m.\u001B[39mrequest(method, request_uri, body, headers)\n\u001B[1;32m   1368\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m socket\u001B[38;5;241m.\u001B[39mtimeout:\n",
-      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/httplib2/__init__.py:1156\u001B[0m, in \u001B[0;36mHTTPSConnectionWithTimeout.connect\u001B[0;34m(self)\u001B[0m\n\u001B[1;32m   1154\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m has_timeout(\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mtimeout):\n\u001B[1;32m   1155\u001B[0m     sock\u001B[38;5;241m.\u001B[39msettimeout(\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mtimeout)\n\u001B[0;32m-> 1156\u001B[0m \u001B[43msock\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mconnect\u001B[49m\u001B[43m(\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mhost\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mport\u001B[49m\u001B[43m)\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1158\u001B[0m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39msock \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_context\u001B[38;5;241m.\u001B[39mwrap_socket(sock, server_hostname\u001B[38;5;241m=\u001B[39m\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mhost)\n\u001B[1;32m   1160\u001B[0m \u001B[38;5;66;03m# Python 3.3 compatibility: emulate the check_hostname behavior\u001B[39;00m\n",
-      "\u001B[0;31mKeyboardInterrupt\u001B[0m: "
-     ]
     }
    ],
    "source": [
-    "agent_executor.invoke({\"input\": \"What is ChatGPT?\"})"
+    "agent_chain.run(input=\"What is ChatGPT?\")"
    ]
   },
   {
@@ -196,15 +179,15 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
-      "\u001B[32;1m\u001B[1;3mThought: I need to find out who developed ChatGPT\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to find out who developed ChatGPT\n",
       "Action: Search\n",
-      "Action Input: Who developed ChatGPT\u001B[0m\n",
-      "Observation: \u001B[36;1m\u001B[1;3mChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... Feb 15, 2023 ... Who owns Chat GPT? Chat GPT is owned and developed by AI research and deployment company, OpenAI. The organization is headquartered in San ... Feb 8, 2023 ... ChatGPT is an AI chatbot developed by San Francisco-based startup OpenAI. OpenAI was co-founded in 2015 by Elon Musk and Sam Altman and is ... Dec 7, 2022 ... ChatGPT is an AI chatbot designed and developed by OpenAI. The bot works by generating text responses based on human-user input, like questions ... Jan 12, 2023 ... In 2019, Microsoft invested $1 billion in OpenAI, the tiny San Francisco company that designed ChatGPT. And in the years since, it has quietly ... Jan 25, 2023 ... The inside story of ChatGPT: How OpenAI founder Sam Altman built the world's hottest technology with billions from Microsoft. Dec 3, 2022 ... ChatGPT went viral on social media for its ability to do anything from code to write essays. · The company that created the AI chatbot has a ... Jan 17, 2023 ... While many Americans were nursing hangovers on New Year's Day, 22-year-old Edward Tian was working feverishly on a new app to combat misuse ... ChatGPT is a language model created by OpenAI, an artificial intelligence research laboratory consisting of a team of researchers and engineers focused on ... 1 day ago ... Everyone is talking about ChatGPT, developed by OpenAI. This is such a great tool that has helped to make AI more accessible to a wider ...\u001B[0m\n",
-      "Thought:\u001B[32;1m\u001B[1;3m I now know the final answer\n",
-      "Final Answer: ChatGPT was developed by OpenAI.\u001B[0m\n",
+      "Action Input: Who developed ChatGPT\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... Feb 15, 2023 ... Who owns Chat GPT? Chat GPT is owned and developed by AI research and deployment company, OpenAI. The organization is headquartered in San ... Feb 8, 2023 ... ChatGPT is an AI chatbot developed by San Francisco-based startup OpenAI. OpenAI was co-founded in 2015 by Elon Musk and Sam Altman and is ... Dec 7, 2022 ... ChatGPT is an AI chatbot designed and developed by OpenAI. The bot works by generating text responses based on human-user input, like questions ... Jan 12, 2023 ... In 2019, Microsoft invested $1 billion in OpenAI, the tiny San Francisco company that designed ChatGPT. And in the years since, it has quietly ... Jan 25, 2023 ... The inside story of ChatGPT: How OpenAI founder Sam Altman built the world's hottest technology with billions from Microsoft. Dec 3, 2022 ... ChatGPT went viral on social media for its ability to do anything from code to write essays. · The company that created the AI chatbot has a ... Jan 17, 2023 ... While many Americans were nursing hangovers on New Year's Day, 22-year-old Edward Tian was working feverishly on a new app to combat misuse ... ChatGPT is a language model created by OpenAI, an artificial intelligence research laboratory consisting of a team of researchers and engineers focused on ... 1 day ago ... Everyone is talking about ChatGPT, developed by OpenAI. This is such a great tool that has helped to make AI more accessible to a wider ...\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: ChatGPT was developed by OpenAI.\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished chain.\u001B[0m\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
@@ -219,7 +202,7 @@
     }
    ],
    "source": [
-    "agent_executor.invoke({\"input\": \"Who developed it?\"})"
+    "agent_chain.run(input=\"Who developed it?\")"
    ]
   },
   {
@@ -234,14 +217,14 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
-      "\u001B[32;1m\u001B[1;3mThought: I need to simplify the conversation for a 5 year old.\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to simplify the conversation for a 5 year old.\n",
       "Action: Summary\n",
-      "Action Input: My daughter 5 years old\u001B[0m\n",
+      "Action Input: My daughter 5 years old\u001b[0m\n",
       "\n",
-      "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
       "Prompt after formatting:\n",
-      "\u001B[32;1m\u001B[1;3mThis is a conversation between a human and a bot:\n",
+      "\u001b[32;1m\u001b[1;3mThis is a conversation between a human and a bot:\n",
       "\n",
       "Human: What is ChatGPT?\n",
       "AI: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\n",
@@ -249,16 +232,16 @@
       "AI: ChatGPT was developed by OpenAI.\n",
       "\n",
       "Write a summary of the conversation for My daughter 5 years old:\n",
-      "\u001B[0m\n",
+      "\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished chain.\u001B[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
       "\n",
-      "Observation: \u001B[33;1m\u001B[1;3m\n",
-      "The conversation was about ChatGPT, an artificial intelligence chatbot. It was created by OpenAI and can send and receive images while chatting.\u001B[0m\n",
-      "Thought:\u001B[32;1m\u001B[1;3m I now know the final answer.\n",
-      "Final Answer: ChatGPT is an artificial intelligence chatbot created by OpenAI that can send and receive images while chatting.\u001B[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3m\n",
+      "The conversation was about ChatGPT, an artificial intelligence chatbot. It was created by OpenAI and can send and receive images while chatting.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: ChatGPT is an artificial intelligence chatbot created by OpenAI that can send and receive images while chatting.\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished chain.\u001B[0m\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
@@ -273,8 +256,8 @@
     }
    ],
    "source": [
-    "agent_executor.invoke(\n",
-    "    {\"input\": \"Thanks. Summarize the conversation, for my daughter 5 years old.\"}\n",
+    "agent_chain.run(\n",
+    "    input=\"Thanks. Summarize the conversation, for my daughter 5 years old.\"\n",
     ")"
    ]
   },
@@ -306,17 +289,9 @@
     }
    ],
    "source": [
-    "print(agent_executor.memory.buffer)"
+    "print(agent_chain.memory.buffer)"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "84ca95c30e262e00",
-   "metadata": {
-    "collapsed": false
-   },
-   "source": []
-  },
   {
    "cell_type": "markdown",
    "id": "cc3d0aa4",
@@ -365,9 +340,25 @@
     "    ),\n",
     "]\n",
     "\n",
-    "prompt = hub.pull(\"hwchase17/react\")\n",
-    "agent = create_react_agent(model, tools, prompt)\n",
-    "agent_executor = AgentExecutor(agent=agent, tools=tools, memory=memory)"
+    "prefix = \"\"\"Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:\"\"\"\n",
+    "suffix = \"\"\"Begin!\"\n",
+    "\n",
+    "{chat_history}\n",
+    "Question: {input}\n",
+    "{agent_scratchpad}\"\"\"\n",
+    "\n",
+    "prompt = ZeroShotAgent.create_prompt(\n",
+    "    tools,\n",
+    "    prefix=prefix,\n",
+    "    suffix=suffix,\n",
+    "    input_variables=[\"input\", \"chat_history\", \"agent_scratchpad\"],\n",
+    ")\n",
+    "\n",
+    "llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=prompt)\n",
+    "agent = ZeroShotAgent(llm_chain=llm_chain, tools=tools, verbose=True)\n",
+    "agent_chain = AgentExecutor.from_agent_and_tools(\n",
+    "    agent=agent, tools=tools, verbose=True, memory=memory\n",
+    ")"
    ]
   },
   {
@@ -382,15 +373,15 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
-      "\u001B[32;1m\u001B[1;3mThought: I should research ChatGPT to answer this question.\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I should research ChatGPT to answer this question.\n",
       "Action: Search\n",
-      "Action Input: \"ChatGPT\"\u001B[0m\n",
-      "Observation: \u001B[36;1m\u001B[1;3mNov 30, 2022 ... We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... ChatGPT. We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... Feb 2, 2023 ... ChatGPT, the popular chatbot from OpenAI, is estimated to have reached 100 million monthly active users in January, just two months after ... 2 days ago ... ChatGPT recently launched a new version of its own plagiarism detection tool, with hopes that it will squelch some of the criticism around how ... An API for accessing new AI models developed by OpenAI. Feb 19, 2023 ... ChatGPT is an AI chatbot system that OpenAI released in November to show off and test what a very large, powerful AI system can accomplish. You ... ChatGPT is fine-tuned from GPT-3.5, a language model trained to produce text. ChatGPT was optimized for dialogue by using Reinforcement Learning with Human ... 3 days ago ... Visual ChatGPT connects ChatGPT and a series of Visual Foundation Models to enable sending and receiving images during chatting. Dec 1, 2022 ... ChatGPT is a natural language processing tool driven by AI technology that allows you to have human-like conversations and much more with a ...\u001B[0m\n",
-      "Thought:\u001B[32;1m\u001B[1;3m I now know the final answer.\n",
-      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\u001B[0m\n",
+      "Action Input: \"ChatGPT\"\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mNov 30, 2022 ... We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... ChatGPT. We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... Feb 2, 2023 ... ChatGPT, the popular chatbot from OpenAI, is estimated to have reached 100 million monthly active users in January, just two months after ... 2 days ago ... ChatGPT recently launched a new version of its own plagiarism detection tool, with hopes that it will squelch some of the criticism around how ... An API for accessing new AI models developed by OpenAI. Feb 19, 2023 ... ChatGPT is an AI chatbot system that OpenAI released in November to show off and test what a very large, powerful AI system can accomplish. You ... ChatGPT is fine-tuned from GPT-3.5, a language model trained to produce text. ChatGPT was optimized for dialogue by using Reinforcement Learning with Human ... 3 days ago ... Visual ChatGPT connects ChatGPT and a series of Visual Foundation Models to enable sending and receiving images during chatting. Dec 1, 2022 ... ChatGPT is a natural language processing tool driven by AI technology that allows you to have human-like conversations and much more with a ...\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished chain.\u001B[0m\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
@@ -405,7 +396,7 @@
     }
    ],
    "source": [
-    "agent_executor.invoke({\"input\": \"What is ChatGPT?\"})"
+    "agent_chain.run(input=\"What is ChatGPT?\")"
    ]
   },
   {
@@ -420,15 +411,15 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
-      "\u001B[32;1m\u001B[1;3mThought: I need to find out who developed ChatGPT\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to find out who developed ChatGPT\n",
       "Action: Search\n",
-      "Action Input: Who developed ChatGPT\u001B[0m\n",
-      "Observation: \u001B[36;1m\u001B[1;3mChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... Feb 15, 2023 ... Who owns Chat GPT? Chat GPT is owned and developed by AI research and deployment company, OpenAI. The organization is headquartered in San ... Feb 8, 2023 ... ChatGPT is an AI chatbot developed by San Francisco-based startup OpenAI. OpenAI was co-founded in 2015 by Elon Musk and Sam Altman and is ... Dec 7, 2022 ... ChatGPT is an AI chatbot designed and developed by OpenAI. The bot works by generating text responses based on human-user input, like questions ... Jan 12, 2023 ... In 2019, Microsoft invested $1 billion in OpenAI, the tiny San Francisco company that designed ChatGPT. And in the years since, it has quietly ... Jan 25, 2023 ... The inside story of ChatGPT: How OpenAI founder Sam Altman built the world's hottest technology with billions from Microsoft. Dec 3, 2022 ... ChatGPT went viral on social media for its ability to do anything from code to write essays. · The company that created the AI chatbot has a ... Jan 17, 2023 ... While many Americans were nursing hangovers on New Year's Day, 22-year-old Edward Tian was working feverishly on a new app to combat misuse ... ChatGPT is a language model created by OpenAI, an artificial intelligence research laboratory consisting of a team of researchers and engineers focused on ... 1 day ago ... Everyone is talking about ChatGPT, developed by OpenAI. This is such a great tool that has helped to make AI more accessible to a wider ...\u001B[0m\n",
-      "Thought:\u001B[32;1m\u001B[1;3m I now know the final answer\n",
-      "Final Answer: ChatGPT was developed by OpenAI.\u001B[0m\n",
+      "Action Input: Who developed ChatGPT\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... Feb 15, 2023 ... Who owns Chat GPT? Chat GPT is owned and developed by AI research and deployment company, OpenAI. The organization is headquartered in San ... Feb 8, 2023 ... ChatGPT is an AI chatbot developed by San Francisco-based startup OpenAI. OpenAI was co-founded in 2015 by Elon Musk and Sam Altman and is ... Dec 7, 2022 ... ChatGPT is an AI chatbot designed and developed by OpenAI. The bot works by generating text responses based on human-user input, like questions ... Jan 12, 2023 ... In 2019, Microsoft invested $1 billion in OpenAI, the tiny San Francisco company that designed ChatGPT. And in the years since, it has quietly ... Jan 25, 2023 ... The inside story of ChatGPT: How OpenAI founder Sam Altman built the world's hottest technology with billions from Microsoft. Dec 3, 2022 ... ChatGPT went viral on social media for its ability to do anything from code to write essays. · The company that created the AI chatbot has a ... Jan 17, 2023 ... While many Americans were nursing hangovers on New Year's Day, 22-year-old Edward Tian was working feverishly on a new app to combat misuse ... ChatGPT is a language model created by OpenAI, an artificial intelligence research laboratory consisting of a team of researchers and engineers focused on ... 1 day ago ... Everyone is talking about ChatGPT, developed by OpenAI. This is such a great tool that has helped to make AI more accessible to a wider ...\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: ChatGPT was developed by OpenAI.\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished chain.\u001B[0m\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
@@ -443,7 +434,7 @@
     }
    ],
    "source": [
-    "agent_executor.invoke({\"input\": \"Who developed it?\"})"
+    "agent_chain.run(input=\"Who developed it?\")"
    ]
   },
   {
@@ -458,14 +449,14 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
-      "\u001B[32;1m\u001B[1;3mThought: I need to simplify the conversation for a 5 year old.\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to simplify the conversation for a 5 year old.\n",
       "Action: Summary\n",
-      "Action Input: My daughter 5 years old\u001B[0m\n",
+      "Action Input: My daughter 5 years old\u001b[0m\n",
       "\n",
-      "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
       "Prompt after formatting:\n",
-      "\u001B[32;1m\u001B[1;3mThis is a conversation between a human and a bot:\n",
+      "\u001b[32;1m\u001b[1;3mThis is a conversation between a human and a bot:\n",
       "\n",
       "Human: What is ChatGPT?\n",
       "AI: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\n",
@@ -473,16 +464,16 @@
       "AI: ChatGPT was developed by OpenAI.\n",
       "\n",
       "Write a summary of the conversation for My daughter 5 years old:\n",
-      "\u001B[0m\n",
+      "\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished chain.\u001B[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
       "\n",
-      "Observation: \u001B[33;1m\u001B[1;3m\n",
-      "The conversation was about ChatGPT, an artificial intelligence chatbot developed by OpenAI. It is designed to have conversations with humans and can also send and receive images.\u001B[0m\n",
-      "Thought:\u001B[32;1m\u001B[1;3m I now know the final answer.\n",
-      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI that can have conversations with humans and send and receive images.\u001B[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3m\n",
+      "The conversation was about ChatGPT, an artificial intelligence chatbot developed by OpenAI. It is designed to have conversations with humans and can also send and receive images.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI that can have conversations with humans and send and receive images.\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished chain.\u001B[0m\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
@@ -497,8 +488,8 @@
     }
    ],
    "source": [
-    "agent_executor.invoke(\n",
-    "    {\"input\": \"Thanks. Summarize the conversation, for my daughter 5 years old.\"}\n",
+    "agent_chain.run(\n",
+    "    input=\"Thanks. Summarize the conversation, for my daughter 5 years old.\"\n",
     ")"
    ]
   },
@@ -533,7 +524,7 @@
     }
    ],
    "source": [
-    "print(agent_executor.memory.buffer)"
+    "print(agent_chain.memory.buffer)"
    ]
   }
  ],

cookbook/sql_db_qa.mdx

@@ -647,7 +647,7 @@ Sometimes you may not have the luxury of using OpenAI or other service-hosted la
 import logging
 import torch
 from transformers import AutoTokenizer, GPT2TokenizerFast, pipeline, AutoModelForSeq2SeqLM, AutoModelForCausalLM
-from langchain_huggingface import HuggingFacePipeline
+from langchain_community.llms import HuggingFacePipeline
 
 # Note: This model requires a large GPU, e.g. an 80GB A100. See documentation for other ways to run private non-OpenAI models.
 model_id = "google/flan-ul2"
@@ -992,7 +992,7 @@ Now that you have some examples (with manually corrected output SQL), you can do
 ```python
 from langchain.prompts import FewShotPromptTemplate, PromptTemplate
 from langchain.chains.sql_database.prompt import _sqlite_prompt, PROMPT_SUFFIX
-from langchain_huggingface import HuggingFaceEmbeddings
+from langchain_community.embeddings.huggingface import HuggingFaceEmbeddings
 from langchain.prompts.example_selector.semantic_similarity import SemanticSimilarityExampleSelector
 from langchain_community.vectorstores import Chroma
 

cookbook/tool_call_messages.ipynb

@@ -1,199 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "c48812ed-35bd-4fbe-9a2c-6c7335e5645e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_anthropic import ChatAnthropic\n",
-    "from langchain_core.runnables import ConfigurableField\n",
-    "from langchain_core.tools import tool\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "\n",
-    "@tool\n",
-    "def multiply(x: float, y: float) -> float:\n",
-    "    \"\"\"Multiply 'x' times 'y'.\"\"\"\n",
-    "    return x * y\n",
-    "\n",
-    "\n",
-    "@tool\n",
-    "def exponentiate(x: float, y: float) -> float:\n",
-    "    \"\"\"Raise 'x' to the 'y'.\"\"\"\n",
-    "    return x**y\n",
-    "\n",
-    "\n",
-    "@tool\n",
-    "def add(x: float, y: float) -> float:\n",
-    "    \"\"\"Add 'x' and 'y'.\"\"\"\n",
-    "    return x + y\n",
-    "\n",
-    "\n",
-    "tools = [multiply, exponentiate, add]\n",
-    "\n",
-    "gpt35 = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0).bind_tools(tools)\n",
-    "claude3 = ChatAnthropic(model=\"claude-3-sonnet-20240229\").bind_tools(tools)\n",
-    "llm_with_tools = gpt35.configurable_alternatives(\n",
-    "    ConfigurableField(id=\"llm\"), default_key=\"gpt35\", claude3=claude3\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "9c186263-1b98-4cb2-b6d1-71f65eb0d811",
-   "metadata": {},
-   "source": [
-    "# LangGraph"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "28fc2c60-7dbc-428a-8983-1a6a15ea30d2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, Sequence, TypedDict\n",
-    "\n",
-    "from langchain_core.messages import AIMessage, BaseMessage, HumanMessage, ToolMessage\n",
-    "from langchain_core.runnables import RunnableLambda\n",
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    messages: Annotated[Sequence[BaseMessage], operator.add]\n",
-    "\n",
-    "\n",
-    "def should_continue(state):\n",
-    "    return \"continue\" if state[\"messages\"][-1].tool_calls else \"end\"\n",
-    "\n",
-    "\n",
-    "def call_model(state, config):\n",
-    "    return {\"messages\": [llm_with_tools.invoke(state[\"messages\"], config=config)]}\n",
-    "\n",
-    "\n",
-    "def _invoke_tool(tool_call):\n",
-    "    tool = {tool.name: tool for tool in tools}[tool_call[\"name\"]]\n",
-    "    return ToolMessage(tool.invoke(tool_call[\"args\"]), tool_call_id=tool_call[\"id\"])\n",
-    "\n",
-    "\n",
-    "tool_executor = RunnableLambda(_invoke_tool)\n",
-    "\n",
-    "\n",
-    "def call_tools(state):\n",
-    "    last_message = state[\"messages\"][-1]\n",
-    "    return {\"messages\": tool_executor.batch(last_message.tool_calls)}\n",
-    "\n",
-    "\n",
-    "workflow = StateGraph(AgentState)\n",
-    "workflow.add_node(\"agent\", call_model)\n",
-    "workflow.add_node(\"action\", call_tools)\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "workflow.add_conditional_edges(\n",
-    "    \"agent\",\n",
-    "    should_continue,\n",
-    "    {\n",
-    "        \"continue\": \"action\",\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "graph = workflow.compile()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "3710e724-2595-4625-ba3a-effb81e66e4a",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'messages': [HumanMessage(content=\"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\"),\n",
-       "  AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_6yMU2WsS4Bqgi1WxFHxtfJRc', 'function': {'arguments': '{\"x\": 8, \"y\": 2.743}', 'name': 'exponentiate'}, 'type': 'function'}, {'id': 'call_GAL3dQiKFF9XEV0RrRLPTvVp', 'function': {'arguments': '{\"x\": 17.24, \"y\": -918.1241}', 'name': 'add'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 58, 'prompt_tokens': 168, 'total_tokens': 226}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_b28b39ffa8', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-528302fc-7acf-4c11-82c4-119ccf40c573-0', tool_calls=[{'name': 'exponentiate', 'args': {'x': 8, 'y': 2.743}, 'id': 'call_6yMU2WsS4Bqgi1WxFHxtfJRc'}, {'name': 'add', 'args': {'x': 17.24, 'y': -918.1241}, 'id': 'call_GAL3dQiKFF9XEV0RrRLPTvVp'}]),\n",
-       "  ToolMessage(content='300.03770462067547', tool_call_id='call_6yMU2WsS4Bqgi1WxFHxtfJRc'),\n",
-       "  ToolMessage(content='-900.8841', tool_call_id='call_GAL3dQiKFF9XEV0RrRLPTvVp'),\n",
-       "  AIMessage(content='The result of \\\\(3 + 5^{2.743}\\\\) is approximately 300.04, and the result of \\\\(17.24 - 918.1241\\\\) is approximately -900.88.', response_metadata={'token_usage': {'completion_tokens': 44, 'prompt_tokens': 251, 'total_tokens': 295}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_b28b39ffa8', 'finish_reason': 'stop', 'logprobs': None}, id='run-d1161669-ed09-4b18-94bd-6d8530df5aa8-0')]}"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "graph.invoke(\n",
-    "    {\n",
-    "        \"messages\": [\n",
-    "            HumanMessage(\n",
-    "                \"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\"\n",
-    "            )\n",
-    "        ]\n",
-    "    }\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "073c074e-d722-42e0-85ec-c62c079207e4",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'messages': [HumanMessage(content=\"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\"),\n",
-       "  AIMessage(content=[{'text': \"Okay, let's break this down into two parts:\", 'type': 'text'}, {'id': 'toolu_01DEhqcXkXTtzJAiZ7uMBeDC', 'input': {'x': 3, 'y': 5}, 'name': 'add', 'type': 'tool_use'}], response_metadata={'id': 'msg_01AkLGH8sxMHaH15yewmjwkF', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 450, 'output_tokens': 81}}, id='run-f35bfae8-8ded-4f8a-831b-0940d6ad16b6-0', tool_calls=[{'name': 'add', 'args': {'x': 3, 'y': 5}, 'id': 'toolu_01DEhqcXkXTtzJAiZ7uMBeDC'}]),\n",
-       "  ToolMessage(content='8.0', tool_call_id='toolu_01DEhqcXkXTtzJAiZ7uMBeDC'),\n",
-       "  AIMessage(content=[{'id': 'toolu_013DyMLrvnrto33peAKMGMr1', 'input': {'x': 8.0, 'y': 2.743}, 'name': 'exponentiate', 'type': 'tool_use'}], response_metadata={'id': 'msg_015Fmp8aztwYcce2JDAFfce3', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 545, 'output_tokens': 75}}, id='run-48aaeeeb-a1e5-48fd-a57a-6c3da2907b47-0', tool_calls=[{'name': 'exponentiate', 'args': {'x': 8.0, 'y': 2.743}, 'id': 'toolu_013DyMLrvnrto33peAKMGMr1'}]),\n",
-       "  ToolMessage(content='300.03770462067547', tool_call_id='toolu_013DyMLrvnrto33peAKMGMr1'),\n",
-       "  AIMessage(content=[{'text': 'So 3 plus 5 raised to the 2.743 power is 300.04.\\n\\nFor the second part:', 'type': 'text'}, {'id': 'toolu_01UTmMrGTmLpPrPCF1rShN46', 'input': {'x': 17.24, 'y': -918.1241}, 'name': 'add', 'type': 'tool_use'}], response_metadata={'id': 'msg_015TkhfRBENPib2RWAxkieH6', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 638, 'output_tokens': 105}}, id='run-45fb62e3-d102-4159-881d-241c5dbadeed-0', tool_calls=[{'name': 'add', 'args': {'x': 17.24, 'y': -918.1241}, 'id': 'toolu_01UTmMrGTmLpPrPCF1rShN46'}]),\n",
-       "  ToolMessage(content='-900.8841', tool_call_id='toolu_01UTmMrGTmLpPrPCF1rShN46'),\n",
-       "  AIMessage(content='Therefore, 17.24 - 918.1241 = -900.8841', response_metadata={'id': 'msg_01LgKnRuUcSyADCpxv9tPoYD', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 759, 'output_tokens': 24}}, id='run-1008254e-ccd1-497c-8312-9550dd77bd08-0')]}"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "graph.invoke(\n",
-    "    {\n",
-    "        \"messages\": [\n",
-    "            HumanMessage(\n",
-    "                \"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\"\n",
-    "            )\n",
-    "        ]\n",
-    "    },\n",
-    "    config={\"configurable\": {\"llm\": \"claude3\"}},\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": "3.10.4"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/two_agent_debate_tools.ipynb

@@ -84,7 +84,7 @@
     "        Applies the chatmodel to the message history\n",
     "        and returns the message string\n",
     "        \"\"\"\n",
-    "        message = self.model.invoke(\n",
+    "        message = self.model(\n",
     "            [\n",
     "                self.system_message,\n",
     "                HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",

cookbook/two_player_dnd.ipynb

@@ -70,7 +70,7 @@
     "        Applies the chatmodel to the message history\n",
     "        and returns the message string\n",
     "        \"\"\"\n",
-    "        message = self.model.invoke(\n",
+    "        message = self.model(\n",
     "            [\n",
     "                self.system_message,\n",
     "                HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",

docs/.gitignore

@@ -1,3 +1,2 @@
 /.quarto/
 src/supabase.d.ts
-build

docs/.local_build.sh

@@ -0,0 +1,24 @@
+#!/usr/bin/env bash
+
+set -o errexit
+set -o nounset
+set -o pipefail
+set -o xtrace
+
+SCRIPT_DIR="$(cd "$(dirname "$0")"; pwd)"
+cd "${SCRIPT_DIR}"
+
+mkdir -p ../_dist
+rsync -ruv --exclude node_modules --exclude api_reference --exclude .venv --exclude .docusaurus . ../_dist
+cd ../_dist
+poetry run python scripts/model_feat_table.py
+cp ../cookbook/README.md src/pages/cookbook.mdx
+mkdir -p docs/templates
+cp ../templates/docs/INDEX.md docs/templates/index.md
+poetry run python scripts/copy_templates.py
+wget -q https://raw.githubusercontent.com/langchain-ai/langserve/main/README.md -O docs/langserve.md
+wget -q https://raw.githubusercontent.com/langchain-ai/langgraph/main/README.md -O docs/langgraph.md
+
+yarn
+
+poetry run quarto preview docs

docs/Makefile

@@ -1,80 +0,0 @@
-# we build the docs in these stages:
-# 1. install vercel and python dependencies
-# 2. copy files from "source dir" to "intermediate dir"
-# 2. generate files like model feat table, etc in "intermediate dir"
-# 3. copy files to their right spots (e.g. langserve readme) in "intermediate dir"
-# 4. build the docs from "intermediate dir" to "output dir"
-
-SOURCE_DIR = docs/
-INTERMEDIATE_DIR = build/intermediate/docs
-
-OUTPUT_NEW_DIR = build/output-new
-OUTPUT_NEW_DOCS_DIR = $(OUTPUT_NEW_DIR)/docs
-
-PYTHON = .venv/bin/python
-
-PARTNER_DEPS_LIST := $(shell find ../libs/partners -mindepth 1 -maxdepth 1 -type d -exec test -e "{}/pyproject.toml" \; -print | grep -vE "airbyte|ibm" | tr '\n' ' ')
-
-PORT ?= 3001
-
-clean:
-	rm -rf build
-
-install-vercel-deps:
-	yum -y update
-	yum install gcc bzip2-devel libffi-devel zlib-devel wget tar gzip rsync -y
-
-install-py-deps:
-	python3 -m venv .venv
-	$(PYTHON) -m pip install --upgrade pip
-	$(PYTHON) -m pip install --upgrade uv
-	$(PYTHON) -m uv pip install -r vercel_requirements.txt
-	$(PYTHON) -m uv pip install --editable $(PARTNER_DEPS_LIST)
-
-generate-files:
-	mkdir -p $(INTERMEDIATE_DIR)
-	cp -r $(SOURCE_DIR)/* $(INTERMEDIATE_DIR)
-	mkdir -p $(INTERMEDIATE_DIR)/templates
-
-	$(PYTHON) scripts/model_feat_table.py $(INTERMEDIATE_DIR)
-
-	$(PYTHON) scripts/copy_templates.py $(INTERMEDIATE_DIR)
-
-	wget -q https://raw.githubusercontent.com/langchain-ai/langserve/main/README.md -O $(INTERMEDIATE_DIR)/langserve.md
-	$(PYTHON) scripts/resolve_local_links.py $(INTERMEDIATE_DIR)/langserve.md https://github.com/langchain-ai/langserve/tree/main/
-
-copy-infra:
-	mkdir -p $(OUTPUT_NEW_DIR)
-	cp -r src $(OUTPUT_NEW_DIR)
-	cp vercel.json $(OUTPUT_NEW_DIR)
-	cp babel.config.js $(OUTPUT_NEW_DIR)
-	cp -r data $(OUTPUT_NEW_DIR)
-	cp docusaurus.config.js $(OUTPUT_NEW_DIR)
-	cp package.json $(OUTPUT_NEW_DIR)
-	cp sidebars.js $(OUTPUT_NEW_DIR)
-	cp -r static $(OUTPUT_NEW_DIR)
-	cp yarn.lock $(OUTPUT_NEW_DIR)
-
-render:
-	$(PYTHON) scripts/notebook_convert.py $(INTERMEDIATE_DIR) $(OUTPUT_NEW_DOCS_DIR)
-
-md-sync:
-	rsync -avm --include="*/" --include="*.mdx" --include="*.md" --include="*.png" --exclude="*" $(INTERMEDIATE_DIR)/ $(OUTPUT_NEW_DOCS_DIR)
-
-generate-references:
-	$(PYTHON) scripts/generate_api_reference_links.py --docs_dir $(OUTPUT_NEW_DOCS_DIR)
-
-build: install-py-deps generate-files copy-infra render md-sync
-
-vercel-build: install-vercel-deps build generate-references
-	rm -rf docs
-	mv $(OUTPUT_NEW_DOCS_DIR) docs
-	rm -rf build
-	yarn run docusaurus build
-	mv build v0.2
-	mkdir build
-	mv v0.2 build
-	mv build/v0.2/404.html build
-
-start:
-	cd $(OUTPUT_NEW_DIR) && yarn && yarn start --port=$(PORT)

docs/api_reference/_static/css/custom.css

@@ -12,8 +12,7 @@ pre {
   }
 }
 
-#my-component-root *,
-#headlessui-portal-root * {
+#my-component-root *, #headlessui-portal-root * {
   z-index: 10000;
 }
 

docs/api_reference/create_api_rst.py

@@ -128,11 +128,11 @@ def _load_package_modules(
     of the modules/packages are part of the package vs. 3rd party or built-in.
 
     Parameters:
-        package_directory (Union[str, Path]): Path to the package directory.
-        submodule (Optional[str]): Optional name of submodule to load.
+        package_directory: Path to the package directory.
+        submodule: Optional name of submodule to load.
 
     Returns:
-        Dict[str, ModuleMembers]: A dictionary where keys are module names and values are ModuleMembers objects.
+        list: A list of loaded module objects.
     """
     package_path = (
         Path(package_directory)
@@ -187,7 +187,7 @@ def _load_package_modules(
             modules_by_namespace[top_namespace] = _module_members
 
         except ImportError as e:
-            print(f"Error: Unable to import module '{namespace}' with error: {e}")
+            print(f"Error: Unable to import module '{namespace}' with error: {e}")  # noqa: T201
 
     return modules_by_namespace
 
@@ -359,14 +359,9 @@ def main(dirs: Optional[list] = None) -> None:
         dirs = [
             dir_
             for dir_ in os.listdir(ROOT_DIR / "libs")
-            if dir_ not in ("cli", "partners", "standard-tests")
-        ]
-        dirs += [
-            dir_
-            for dir_ in os.listdir(ROOT_DIR / "libs" / "partners")
-            if os.path.isdir(ROOT_DIR / "libs" / "partners" / dir_)
-            and "pyproject.toml" in os.listdir(ROOT_DIR / "libs" / "partners" / dir_)
+            if dir_ not in ("cli", "partners")
         ]
+        dirs += os.listdir(ROOT_DIR / "libs" / "partners")
     for dir_ in dirs:
         # Skip any hidden directories
         # Some of these could be present by mistake in the code base

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

@@ -1398,20 +1398,3 @@ table.sk-sponsor-table td {
 .highlight .vi { color: #bb60d5 } /* Name.Variable.Instance */
 .highlight .vm { color: #bb60d5 } /* Name.Variable.Magic */
 .highlight .il { color: #208050 } /* Literal.Number.Integer.Long */
-
-/** Custom styles overriding certain values */
-
-div.sk-sidebar-toc-wrapper {
-  width: unset;
-  overflow-x: auto;
-}
-
-div.sk-sidebar-toc-wrapper > [aria-label="rellinks"] {
-  position: sticky;
-  left: 0;
-}
-
-.navbar-nav .dropdown-menu {
-  max-height: 80vh;
-  overflow-y: auto;
-}

docs/code-block-loader.js

@@ -0,0 +1,76 @@
+/* eslint-disable prefer-template */
+/* eslint-disable no-param-reassign */
+// eslint-disable-next-line import/no-extraneous-dependencies
+const babel = require("@babel/core");
+const path = require("path");
+const fs = require("fs");
+
+/**
+ *
+ * @param {string|Buffer} content Content of the resource file
+ * @param {object} [map] SourceMap data consumable by https://github.com/mozilla/source-map
+ * @param {any} [meta] Meta data, could be anything
+ */
+async function webpackLoader(content, map, meta) {
+  const cb = this.async();
+
+  if (!this.resourcePath.endsWith(".ts")) {
+    cb(null, JSON.stringify({ content, imports: [] }), map, meta);
+    return;
+  }
+
+  try {
+    const result = await babel.parseAsync(content, {
+      sourceType: "module",
+      filename: this.resourcePath,
+    });
+
+    const imports = [];
+
+    result.program.body.forEach((node) => {
+      if (node.type === "ImportDeclaration") {
+        const source = node.source.value;
+
+        if (!source.startsWith("langchain")) {
+          return;
+        }
+
+        node.specifiers.forEach((specifier) => {
+          if (specifier.type === "ImportSpecifier") {
+            const local = specifier.local.name;
+            const imported = specifier.imported.name;
+            imports.push({ local, imported, source });
+          } else {
+            throw new Error("Unsupported import type");
+          }
+        });
+      }
+    });
+
+    imports.forEach((imp) => {
+      const { imported, source } = imp;
+      const moduleName = source.split("/").slice(1).join("_");
+      const docsPath = path.resolve(__dirname, "docs", "api", moduleName);
+      const available = fs.readdirSync(docsPath, { withFileTypes: true });
+      const found = available.find(
+        (dirent) =>
+          dirent.isDirectory() &&
+          fs.existsSync(path.resolve(docsPath, dirent.name, imported + ".md"))
+      );
+      if (found) {
+        imp.docs =
+          "/" + path.join("docs", "api", moduleName, found.name, imported);
+      } else {
+        throw new Error(
+          `Could not find docs for ${source}.${imported} in docs/api/`
+        );
+      }
+    });
+
+    cb(null, JSON.stringify({ content, imports }), map, meta);
+  } catch (err) {
+    cb(err);
+  }
+}
+
+module.exports = webpackLoader;

docs/docs/additional_resources/arxiv_references.mdx

@@ -1,876 +0,0 @@
-# arXiv
-            
-LangChain implements the latest research in the field of Natural Language Processing.
-This page contains `arXiv` papers referenced in the LangChain Documentation, API Reference,
- Templates, and Cookbooks.
-
-From the opposite direction, scientists use LangChain in research and reference LangChain in the research papers. 
-Here you find [such papers](https://arxiv.org/search/?query=langchain&searchtype=all&source=header).
-
-## Summary
-
-| arXiv id / Title | Authors | Published date 🔻 | LangChain Documentation|
-|------------------|---------|-------------------|------------------------|
-| `2402.03620v1` [Self-Discover: Large Language Models Self-Compose Reasoning Structures](http://arxiv.org/abs/2402.03620v1) | Pei Zhou, Jay Pujara, Xiang Ren,  et al. | 2024-02-06 | `Cookbook:` [self-discover](https://github.com/langchain-ai/langchain/blob/master/cookbook/self-discover.ipynb)
-| `2401.18059v1` [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](http://arxiv.org/abs/2401.18059v1) | Parth Sarthi, Salman Abdullah, Aditi Tuli,  et al. | 2024-01-31 | `Cookbook:` [RAPTOR](https://github.com/langchain-ai/langchain/blob/master/cookbook/RAPTOR.ipynb)
-| `2401.15884v2` [Corrective Retrieval Augmented Generation](http://arxiv.org/abs/2401.15884v2) | Shi-Qi Yan, Jia-Chen Gu, Yun Zhu,  et al. | 2024-01-29 | `Cookbook:` [langgraph_crag](https://github.com/langchain-ai/langchain/blob/master/cookbook/langgraph_crag.ipynb)
-| `2401.04088v1` [Mixtral of Experts](http://arxiv.org/abs/2401.04088v1) | Albert Q. Jiang, Alexandre Sablayrolles, Antoine Roux,  et al. | 2024-01-08 | `Cookbook:` [together_ai](https://github.com/langchain-ai/langchain/blob/master/cookbook/together_ai.ipynb)
-| `2312.06648v2` [Dense X Retrieval: What Retrieval Granularity Should We Use?](http://arxiv.org/abs/2312.06648v2) | Tong Chen, Hongwei Wang, Sihao Chen,  et al. | 2023-12-11 | `Template:` [propositional-retrieval](https://python.langchain.com/docs/templates/propositional-retrieval)
-| `2311.09210v1` [Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models](http://arxiv.org/abs/2311.09210v1) | Wenhao Yu, Hongming Zhang, Xiaoman Pan,  et al. | 2023-11-15 | `Template:` [chain-of-note-wiki](https://python.langchain.com/docs/templates/chain-of-note-wiki)
-| `2310.11511v1` [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](http://arxiv.org/abs/2310.11511v1) | Akari Asai, Zeqiu Wu, Yizhong Wang,  et al. | 2023-10-17 | `Cookbook:` [langgraph_self_rag](https://github.com/langchain-ai/langchain/blob/master/cookbook/langgraph_self_rag.ipynb)
-| `2310.06117v2` [Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models](http://arxiv.org/abs/2310.06117v2) | Huaixiu Steven Zheng, Swaroop Mishra, Xinyun Chen,  et al. | 2023-10-09 | `Template:` [stepback-qa-prompting](https://python.langchain.com/docs/templates/stepback-qa-prompting), `Cookbook:` [stepback-qa](https://github.com/langchain-ai/langchain/blob/master/cookbook/stepback-qa.ipynb)
-| `2307.09288v2` [Llama 2: Open Foundation and Fine-Tuned Chat Models](http://arxiv.org/abs/2307.09288v2) | Hugo Touvron, Louis Martin, Kevin Stone,  et al. | 2023-07-18 | `Cookbook:` [Semi_Structured_RAG](https://github.com/langchain-ai/langchain/blob/master/cookbook/Semi_Structured_RAG.ipynb)
-| `2305.14283v3` [Query Rewriting for Retrieval-Augmented Large Language Models](http://arxiv.org/abs/2305.14283v3) | Xinbei Ma, Yeyun Gong, Pengcheng He,  et al. | 2023-05-23 | `Template:` [rewrite-retrieve-read](https://python.langchain.com/docs/templates/rewrite-retrieve-read), `Cookbook:` [rewrite](https://github.com/langchain-ai/langchain/blob/master/cookbook/rewrite.ipynb)
-| `2305.08291v1` [Large Language Model Guided Tree-of-Thought](http://arxiv.org/abs/2305.08291v1) | Jieyi Long | 2023-05-15 | `API:` [langchain_experimental.tot](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.tot), `Cookbook:` [tree_of_thought](https://github.com/langchain-ai/langchain/blob/master/cookbook/tree_of_thought.ipynb)
-| `2305.04091v3` [Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models](http://arxiv.org/abs/2305.04091v3) | Lei Wang, Wanyu Xu, Yihuai Lan,  et al. | 2023-05-06 | `Cookbook:` [plan_and_execute_agent](https://github.com/langchain-ai/langchain/blob/master/cookbook/plan_and_execute_agent.ipynb)
-| `2304.08485v2` [Visual Instruction Tuning](http://arxiv.org/abs/2304.08485v2) | Haotian Liu, Chunyuan Li, Qingyang Wu,  et al. | 2023-04-17 | `Cookbook:` [Semi_structured_and_multi_modal_RAG](https://github.com/langchain-ai/langchain/blob/master/cookbook/Semi_structured_and_multi_modal_RAG.ipynb), [Semi_structured_multi_modal_RAG_LLaMA2](https://github.com/langchain-ai/langchain/blob/master/cookbook/Semi_structured_multi_modal_RAG_LLaMA2.ipynb)
-| `2304.03442v2` [Generative Agents: Interactive Simulacra of Human Behavior](http://arxiv.org/abs/2304.03442v2) | Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai,  et al. | 2023-04-07 | `Cookbook:` [generative_agents_interactive_simulacra_of_human_behavior](https://github.com/langchain-ai/langchain/blob/master/cookbook/generative_agents_interactive_simulacra_of_human_behavior.ipynb), [multiagent_bidding](https://github.com/langchain-ai/langchain/blob/master/cookbook/multiagent_bidding.ipynb)
-| `2303.17760v2` [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](http://arxiv.org/abs/2303.17760v2) | Guohao Li, Hasan Abed Al Kader Hammoud, Hani Itani,  et al. | 2023-03-31 | `Cookbook:` [camel_role_playing](https://github.com/langchain-ai/langchain/blob/master/cookbook/camel_role_playing.ipynb)
-| `2303.17580v4` [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](http://arxiv.org/abs/2303.17580v4) | Yongliang Shen, Kaitao Song, Xu Tan,  et al. | 2023-03-30 | `API:` [langchain_experimental.autonomous_agents](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.autonomous_agents), `Cookbook:` [hugginggpt](https://github.com/langchain-ai/langchain/blob/master/cookbook/hugginggpt.ipynb)
-| `2303.08774v6` [GPT-4 Technical Report](http://arxiv.org/abs/2303.08774v6) | OpenAI, Josh Achiam, Steven Adler,  et al. | 2023-03-15 | `Docs:` [docs/integrations/vectorstores/mongodb_atlas](https://python.langchain.com/docs/integrations/vectorstores/mongodb_atlas)
-| `2301.10226v4` [A Watermark for Large Language Models](http://arxiv.org/abs/2301.10226v4) | John Kirchenbauer, Jonas Geiping, Yuxin Wen,  et al. | 2023-01-24 | `API:` [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference), [langchain_community...OCIModelDeploymentTGI](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentTGI.html#langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentTGI), [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint)
-| `2212.10496v1` [Precise Zero-Shot Dense Retrieval without Relevance Labels](http://arxiv.org/abs/2212.10496v1) | Luyu Gao, Xueguang Ma, Jimmy Lin,  et al. | 2022-12-20 | `API:` [langchain...HypotheticalDocumentEmbedder](https://api.python.langchain.com/en/latest/chains/langchain.chains.hyde.base.HypotheticalDocumentEmbedder.html#langchain.chains.hyde.base.HypotheticalDocumentEmbedder), `Template:` [hyde](https://python.langchain.com/docs/templates/hyde), `Cookbook:` [hypothetical_document_embeddings](https://github.com/langchain-ai/langchain/blob/master/cookbook/hypothetical_document_embeddings.ipynb)
-| `2212.07425v3` [Robust and Explainable Identification of Logical Fallacies in Natural Language Arguments](http://arxiv.org/abs/2212.07425v3) | Zhivar Sourati, Vishnu Priya Prasanna Venkatesh, Darshan Deshpande,  et al. | 2022-12-12 | `API:` [langchain_experimental.fallacy_removal](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.fallacy_removal)
-| `2211.13892v2` [Complementary Explanations for Effective In-Context Learning](http://arxiv.org/abs/2211.13892v2) | Xi Ye, Srinivasan Iyer, Asli Celikyilmaz,  et al. | 2022-11-25 | `API:` [langchain_core...MaxMarginalRelevanceExampleSelector](https://api.python.langchain.com/en/latest/example_selectors/langchain_core.example_selectors.semantic_similarity.MaxMarginalRelevanceExampleSelector.html#langchain_core.example_selectors.semantic_similarity.MaxMarginalRelevanceExampleSelector)
-| `2211.10435v2` [PAL: Program-aided Language Models](http://arxiv.org/abs/2211.10435v2) | Luyu Gao, Aman Madaan, Shuyan Zhou,  et al. | 2022-11-18 | `API:` [langchain_experimental...PALChain](https://api.python.langchain.com/en/latest/pal_chain/langchain_experimental.pal_chain.base.PALChain.html#langchain_experimental.pal_chain.base.PALChain), [langchain_experimental.pal_chain](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.pal_chain), `Cookbook:` [program_aided_language_model](https://github.com/langchain-ai/langchain/blob/master/cookbook/program_aided_language_model.ipynb)
-| `2209.10785v2` [Deep Lake: a Lakehouse for Deep Learning](http://arxiv.org/abs/2209.10785v2) | Sasun Hambardzumyan, Abhinav Tuli, Levon Ghukasyan,  et al. | 2022-09-22 | `Docs:` [docs/integrations/providers/activeloop_deeplake](https://python.langchain.com/docs/integrations/providers/activeloop_deeplake)
-| `2205.12654v1` [Bitext Mining Using Distilled Sentence Representations for Low-Resource Languages](http://arxiv.org/abs/2205.12654v1) | Kevin Heffernan, Onur Çelebi, Holger Schwenk | 2022-05-25 | `API:` [langchain_community...LaserEmbeddings](https://api.python.langchain.com/en/latest/embeddings/langchain_community.embeddings.laser.LaserEmbeddings.html#langchain_community.embeddings.laser.LaserEmbeddings)
-| `2204.00498v1` [Evaluating the Text-to-SQL Capabilities of Large Language Models](http://arxiv.org/abs/2204.00498v1) | Nitarshan Rajkumar, Raymond Li, Dzmitry Bahdanau | 2022-03-15 | `API:` [langchain_community...SparkSQL](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.spark_sql.SparkSQL.html#langchain_community.utilities.spark_sql.SparkSQL), [langchain_community...SQLDatabase](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.sql_database.SQLDatabase.html#langchain_community.utilities.sql_database.SQLDatabase)
-| `2202.00666v5` [Locally Typical Sampling](http://arxiv.org/abs/2202.00666v5) | Clara Meister, Tiago Pimentel, Gian Wiher,  et al. | 2022-02-01 | `API:` [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference), [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint)
-| `2103.00020v1` [Learning Transferable Visual Models From Natural Language Supervision](http://arxiv.org/abs/2103.00020v1) | Alec Radford, Jong Wook Kim, Chris Hallacy,  et al. | 2021-02-26 | `API:` [langchain_experimental.open_clip](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.open_clip)
-| `1909.05858v2` [CTRL: A Conditional Transformer Language Model for Controllable Generation](http://arxiv.org/abs/1909.05858v2) | Nitish Shirish Keskar, Bryan McCann, Lav R. Varshney,  et al. | 2019-09-11 | `API:` [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference), [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint)
-| `1908.10084v1` [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](http://arxiv.org/abs/1908.10084v1) | Nils Reimers, Iryna Gurevych | 2019-08-27 | `Docs:` [docs/integrations/text_embedding/sentence_transformers](https://python.langchain.com/docs/integrations/text_embedding/sentence_transformers)
-
-## Self-Discover: Large Language Models Self-Compose Reasoning Structures
-
-- **arXiv id:** 2402.03620v1
-- **Title:** Self-Discover: Large Language Models Self-Compose Reasoning Structures
-- **Authors:** Pei Zhou, Jay Pujara, Xiang Ren,  et al.
-- **Published Date:** 2024-02-06
-- **URL:** http://arxiv.org/abs/2402.03620v1
-- **LangChain:**
-
-   - **Cookbook:** [self-discover](https://github.com/langchain-ai/langchain/blob/master/cookbook/self-discover.ipynb)
-
-**Abstract:** We introduce SELF-DISCOVER, a general framework for LLMs to self-discover the
-task-intrinsic reasoning structures to tackle complex reasoning problems that
-are challenging for typical prompting methods. Core to the framework is a
-self-discovery process where LLMs select multiple atomic reasoning modules such
-as critical thinking and step-by-step thinking, and compose them into an
-explicit reasoning structure for LLMs to follow during decoding. SELF-DISCOVER
-substantially improves GPT-4 and PaLM 2's performance on challenging reasoning
-benchmarks such as BigBench-Hard, grounded agent reasoning, and MATH, by as
-much as 32% compared to Chain of Thought (CoT). Furthermore, SELF-DISCOVER
-outperforms inference-intensive methods such as CoT-Self-Consistency by more
-than 20%, while requiring 10-40x fewer inference compute. Finally, we show that
-the self-discovered reasoning structures are universally applicable across
-model families: from PaLM 2-L to GPT-4, and from GPT-4 to Llama2, and share
-commonalities with human reasoning patterns.
-                
-## RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
-
-- **arXiv id:** 2401.18059v1
-- **Title:** RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
-- **Authors:** Parth Sarthi, Salman Abdullah, Aditi Tuli,  et al.
-- **Published Date:** 2024-01-31
-- **URL:** http://arxiv.org/abs/2401.18059v1
-- **LangChain:**
-
-   - **Cookbook:** [RAPTOR](https://github.com/langchain-ai/langchain/blob/master/cookbook/RAPTOR.ipynb)
-
-**Abstract:** Retrieval-augmented language models can better adapt to changes in world
-state and incorporate long-tail knowledge. However, most existing methods
-retrieve only short contiguous chunks from a retrieval corpus, limiting
-holistic understanding of the overall document context. We introduce the novel
-approach of recursively embedding, clustering, and summarizing chunks of text,
-constructing a tree with differing levels of summarization from the bottom up.
-At inference time, our RAPTOR model retrieves from this tree, integrating
-information across lengthy documents at different levels of abstraction.
-Controlled experiments show that retrieval with recursive summaries offers
-significant improvements over traditional retrieval-augmented LMs on several
-tasks. On question-answering tasks that involve complex, multi-step reasoning,
-we show state-of-the-art results; for example, by coupling RAPTOR retrieval
-with the use of GPT-4, we can improve the best performance on the QuALITY
-benchmark by 20% in absolute accuracy.
-                
-## Corrective Retrieval Augmented Generation
-
-- **arXiv id:** 2401.15884v2
-- **Title:** Corrective Retrieval Augmented Generation
-- **Authors:** Shi-Qi Yan, Jia-Chen Gu, Yun Zhu,  et al.
-- **Published Date:** 2024-01-29
-- **URL:** http://arxiv.org/abs/2401.15884v2
-- **LangChain:**
-
-   - **Cookbook:** [langgraph_crag](https://github.com/langchain-ai/langchain/blob/master/cookbook/langgraph_crag.ipynb)
-
-**Abstract:** Large language models (LLMs) inevitably exhibit hallucinations since the
-accuracy of generated texts cannot be secured solely by the parametric
-knowledge they encapsulate. Although retrieval-augmented generation (RAG) is a
-practicable complement to LLMs, it relies heavily on the relevance of retrieved
-documents, raising concerns about how the model behaves if retrieval goes
-wrong. To this end, we propose the Corrective Retrieval Augmented Generation
-(CRAG) to improve the robustness of generation. Specifically, a lightweight
-retrieval evaluator is designed to assess the overall quality of retrieved
-documents for a query, returning a confidence degree based on which different
-knowledge retrieval actions can be triggered. Since retrieval from static and
-limited corpora can only return sub-optimal documents, large-scale web searches
-are utilized as an extension for augmenting the retrieval results. Besides, a
-decompose-then-recompose algorithm is designed for retrieved documents to
-selectively focus on key information and filter out irrelevant information in
-them. CRAG is plug-and-play and can be seamlessly coupled with various
-RAG-based approaches. Experiments on four datasets covering short- and
-long-form generation tasks show that CRAG can significantly improve the
-performance of RAG-based approaches.
-                
-## Mixtral of Experts
-
-- **arXiv id:** 2401.04088v1
-- **Title:** Mixtral of Experts
-- **Authors:** Albert Q. Jiang, Alexandre Sablayrolles, Antoine Roux,  et al.
-- **Published Date:** 2024-01-08
-- **URL:** http://arxiv.org/abs/2401.04088v1
-- **LangChain:**
-
-   - **Cookbook:** [together_ai](https://github.com/langchain-ai/langchain/blob/master/cookbook/together_ai.ipynb)
-
-**Abstract:** We introduce Mixtral 8x7B, a Sparse Mixture of Experts (SMoE) language model.
-Mixtral has the same architecture as Mistral 7B, with the difference that each
-layer is composed of 8 feedforward blocks (i.e. experts). For every token, at
-each layer, a router network selects two experts to process the current state
-and combine their outputs. Even though each token only sees two experts, the
-selected experts can be different at each timestep. As a result, each token has
-access to 47B parameters, but only uses 13B active parameters during inference.
-Mixtral was trained with a context size of 32k tokens and it outperforms or
-matches Llama 2 70B and GPT-3.5 across all evaluated benchmarks. In particular,
-Mixtral vastly outperforms Llama 2 70B on mathematics, code generation, and
-multilingual benchmarks. We also provide a model fine-tuned to follow
-instructions, Mixtral 8x7B - Instruct, that surpasses GPT-3.5 Turbo,
-Claude-2.1, Gemini Pro, and Llama 2 70B - chat model on human benchmarks. Both
-the base and instruct models are released under the Apache 2.0 license.
-                
-## Dense X Retrieval: What Retrieval Granularity Should We Use?
-
-- **arXiv id:** 2312.06648v2
-- **Title:** Dense X Retrieval: What Retrieval Granularity Should We Use?
-- **Authors:** Tong Chen, Hongwei Wang, Sihao Chen,  et al.
-- **Published Date:** 2023-12-11
-- **URL:** http://arxiv.org/abs/2312.06648v2
-- **LangChain:**
-
-   - **Template:** [propositional-retrieval](https://python.langchain.com/docs/templates/propositional-retrieval)
-
-**Abstract:** Dense retrieval has become a prominent method to obtain relevant context or
-world knowledge in open-domain NLP tasks. When we use a learned dense retriever
-on a retrieval corpus at inference time, an often-overlooked design choice is
-the retrieval unit in which the corpus is indexed, e.g. document, passage, or
-sentence. We discover that the retrieval unit choice significantly impacts the
-performance of both retrieval and downstream tasks. Distinct from the typical
-approach of using passages or sentences, we introduce a novel retrieval unit,
-proposition, for dense retrieval. Propositions are defined as atomic
-expressions within text, each encapsulating a distinct factoid and presented in
-a concise, self-contained natural language format. We conduct an empirical
-comparison of different retrieval granularity. Our results reveal that
-proposition-based retrieval significantly outperforms traditional passage or
-sentence-based methods in dense retrieval. Moreover, retrieval by proposition
-also enhances the performance of downstream QA tasks, since the retrieved texts
-are more condensed with question-relevant information, reducing the need for
-lengthy input tokens and minimizing the inclusion of extraneous, irrelevant
-information.
-                
-## Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models
-
-- **arXiv id:** 2311.09210v1
-- **Title:** Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models
-- **Authors:** Wenhao Yu, Hongming Zhang, Xiaoman Pan,  et al.
-- **Published Date:** 2023-11-15
-- **URL:** http://arxiv.org/abs/2311.09210v1
-- **LangChain:**
-
-   - **Template:** [chain-of-note-wiki](https://python.langchain.com/docs/templates/chain-of-note-wiki)
-
-**Abstract:** Retrieval-augmented language models (RALMs) represent a substantial
-advancement in the capabilities of large language models, notably in reducing
-factual hallucination by leveraging external knowledge sources. However, the
-reliability of the retrieved information is not always guaranteed. The
-retrieval of irrelevant data can lead to misguided responses, and potentially
-causing the model to overlook its inherent knowledge, even when it possesses
-adequate information to address the query. Moreover, standard RALMs often
-struggle to assess whether they possess adequate knowledge, both intrinsic and
-retrieved, to provide an accurate answer. In situations where knowledge is
-lacking, these systems should ideally respond with "unknown" when the answer is
-unattainable. In response to these challenges, we introduces Chain-of-Noting
-(CoN), a novel approach aimed at improving the robustness of RALMs in facing
-noisy, irrelevant documents and in handling unknown scenarios. The core idea of
-CoN is to generate sequential reading notes for retrieved documents, enabling a
-thorough evaluation of their relevance to the given question and integrating
-this information to formulate the final answer. We employed ChatGPT to create
-training data for CoN, which was subsequently trained on an LLaMa-2 7B model.
-Our experiments across four open-domain QA benchmarks show that RALMs equipped
-with CoN significantly outperform standard RALMs. Notably, CoN achieves an
-average improvement of +7.9 in EM score given entirely noisy retrieved
-documents and +10.5 in rejection rates for real-time questions that fall
-outside the pre-training knowledge scope.
-                
-## Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
-
-- **arXiv id:** 2310.11511v1
-- **Title:** Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
-- **Authors:** Akari Asai, Zeqiu Wu, Yizhong Wang,  et al.
-- **Published Date:** 2023-10-17
-- **URL:** http://arxiv.org/abs/2310.11511v1
-- **LangChain:**
-
-   - **Cookbook:** [langgraph_self_rag](https://github.com/langchain-ai/langchain/blob/master/cookbook/langgraph_self_rag.ipynb)
-
-**Abstract:** Despite their remarkable capabilities, large language models (LLMs) often
-produce responses containing factual inaccuracies due to their sole reliance on
-the parametric knowledge they encapsulate. Retrieval-Augmented Generation
-(RAG), an ad hoc approach that augments LMs with retrieval of relevant
-knowledge, decreases such issues. However, indiscriminately retrieving and
-incorporating a fixed number of retrieved passages, regardless of whether
-retrieval is necessary, or passages are relevant, diminishes LM versatility or
-can lead to unhelpful response generation. We introduce a new framework called
-Self-Reflective Retrieval-Augmented Generation (Self-RAG) that enhances an LM's
-quality and factuality through retrieval and self-reflection. Our framework
-trains a single arbitrary LM that adaptively retrieves passages on-demand, and
-generates and reflects on retrieved passages and its own generations using
-special tokens, called reflection tokens. Generating reflection tokens makes
-the LM controllable during the inference phase, enabling it to tailor its
-behavior to diverse task requirements. Experiments show that Self-RAG (7B and
-13B parameters) significantly outperforms state-of-the-art LLMs and
-retrieval-augmented models on a diverse set of tasks. Specifically, Self-RAG
-outperforms ChatGPT and retrieval-augmented Llama2-chat on Open-domain QA,
-reasoning and fact verification tasks, and it shows significant gains in
-improving factuality and citation accuracy for long-form generations relative
-to these models.
-                
-## Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models
-
-- **arXiv id:** 2310.06117v2
-- **Title:** Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models
-- **Authors:** Huaixiu Steven Zheng, Swaroop Mishra, Xinyun Chen,  et al.
-- **Published Date:** 2023-10-09
-- **URL:** http://arxiv.org/abs/2310.06117v2
-- **LangChain:**
-
-   - **Template:** [stepback-qa-prompting](https://python.langchain.com/docs/templates/stepback-qa-prompting)
-   - **Cookbook:** [stepback-qa](https://github.com/langchain-ai/langchain/blob/master/cookbook/stepback-qa.ipynb)
-
-**Abstract:** We present Step-Back Prompting, a simple prompting technique that enables
-LLMs to do abstractions to derive high-level concepts and first principles from
-instances containing specific details. Using the concepts and principles to
-guide reasoning, LLMs significantly improve their abilities in following a
-correct reasoning path towards the solution. We conduct experiments of
-Step-Back Prompting with PaLM-2L, GPT-4 and Llama2-70B models, and observe
-substantial performance gains on various challenging reasoning-intensive tasks
-including STEM, Knowledge QA, and Multi-Hop Reasoning. For instance, Step-Back
-Prompting improves PaLM-2L performance on MMLU (Physics and Chemistry) by 7%
-and 11% respectively, TimeQA by 27%, and MuSiQue by 7%.
-                
-## Llama 2: Open Foundation and Fine-Tuned Chat Models
-
-- **arXiv id:** 2307.09288v2
-- **Title:** Llama 2: Open Foundation and Fine-Tuned Chat Models
-- **Authors:** Hugo Touvron, Louis Martin, Kevin Stone,  et al.
-- **Published Date:** 2023-07-18
-- **URL:** http://arxiv.org/abs/2307.09288v2
-- **LangChain:**
-
-   - **Cookbook:** [Semi_Structured_RAG](https://github.com/langchain-ai/langchain/blob/master/cookbook/Semi_Structured_RAG.ipynb)
-
-**Abstract:** In this work, we develop and release Llama 2, a collection of pretrained and
-fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70
-billion parameters. Our fine-tuned LLMs, called Llama 2-Chat, are optimized for
-dialogue use cases. Our models outperform open-source chat models on most
-benchmarks we tested, and based on our human evaluations for helpfulness and
-safety, may be a suitable substitute for closed-source models. We provide a
-detailed description of our approach to fine-tuning and safety improvements of
-Llama 2-Chat in order to enable the community to build on our work and
-contribute to the responsible development of LLMs.
-                
-## Query Rewriting for Retrieval-Augmented Large Language Models
-
-- **arXiv id:** 2305.14283v3
-- **Title:** Query Rewriting for Retrieval-Augmented Large Language Models
-- **Authors:** Xinbei Ma, Yeyun Gong, Pengcheng He,  et al.
-- **Published Date:** 2023-05-23
-- **URL:** http://arxiv.org/abs/2305.14283v3
-- **LangChain:**
-
-   - **Template:** [rewrite-retrieve-read](https://python.langchain.com/docs/templates/rewrite-retrieve-read)
-   - **Cookbook:** [rewrite](https://github.com/langchain-ai/langchain/blob/master/cookbook/rewrite.ipynb)
-
-**Abstract:** Large Language Models (LLMs) play powerful, black-box readers in the
-retrieve-then-read pipeline, making remarkable progress in knowledge-intensive
-tasks. This work introduces a new framework, Rewrite-Retrieve-Read instead of
-the previous retrieve-then-read for the retrieval-augmented LLMs from the
-perspective of the query rewriting. Unlike prior studies focusing on adapting
-either the retriever or the reader, our approach pays attention to the
-adaptation of the search query itself, for there is inevitably a gap between
-the input text and the needed knowledge in retrieval. We first prompt an LLM to
-generate the query, then use a web search engine to retrieve contexts.
-Furthermore, to better align the query to the frozen modules, we propose a
-trainable scheme for our pipeline. A small language model is adopted as a
-trainable rewriter to cater to the black-box LLM reader. The rewriter is
-trained using the feedback of the LLM reader by reinforcement learning.
-Evaluation is conducted on downstream tasks, open-domain QA and multiple-choice
-QA. Experiments results show consistent performance improvement, indicating
-that our framework is proven effective and scalable, and brings a new framework
-for retrieval-augmented LLM.
-                
-## Large Language Model Guided Tree-of-Thought
-
-- **arXiv id:** 2305.08291v1
-- **Title:** Large Language Model Guided Tree-of-Thought
-- **Authors:** Jieyi Long
-- **Published Date:** 2023-05-15
-- **URL:** http://arxiv.org/abs/2305.08291v1
-- **LangChain:**
-
-   - **API Reference:** [langchain_experimental.tot](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.tot)
-   - **Cookbook:** [tree_of_thought](https://github.com/langchain-ai/langchain/blob/master/cookbook/tree_of_thought.ipynb)
-
-**Abstract:** In this paper, we introduce the Tree-of-Thought (ToT) framework, a novel
-approach aimed at improving the problem-solving capabilities of auto-regressive
-large language models (LLMs). The ToT technique is inspired by the human mind's
-approach for solving complex reasoning tasks through trial and error. In this
-process, the human mind explores the solution space through a tree-like thought
-process, allowing for backtracking when necessary. To implement ToT as a
-software system, we augment an LLM with additional modules including a prompter
-agent, a checker module, a memory module, and a ToT controller. In order to
-solve a given problem, these modules engage in a multi-round conversation with
-the LLM. The memory module records the conversation and state history of the
-problem solving process, which allows the system to backtrack to the previous
-steps of the thought-process and explore other directions from there. To verify
-the effectiveness of the proposed technique, we implemented a ToT-based solver
-for the Sudoku Puzzle. Experimental results show that the ToT framework can
-significantly increase the success rate of Sudoku puzzle solving. Our
-implementation of the ToT-based Sudoku solver is available on GitHub:
-\url{https://github.com/jieyilong/tree-of-thought-puzzle-solver}.
-                
-## Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models
-
-- **arXiv id:** 2305.04091v3
-- **Title:** Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models
-- **Authors:** Lei Wang, Wanyu Xu, Yihuai Lan,  et al.
-- **Published Date:** 2023-05-06
-- **URL:** http://arxiv.org/abs/2305.04091v3
-- **LangChain:**
-
-   - **Cookbook:** [plan_and_execute_agent](https://github.com/langchain-ai/langchain/blob/master/cookbook/plan_and_execute_agent.ipynb)
-
-**Abstract:** Large language models (LLMs) have recently been shown to deliver impressive
-performance in various NLP tasks. To tackle multi-step reasoning tasks,
-few-shot chain-of-thought (CoT) prompting includes a few manually crafted
-step-by-step reasoning demonstrations which enable LLMs to explicitly generate
-reasoning steps and improve their reasoning task accuracy. To eliminate the
-manual effort, Zero-shot-CoT concatenates the target problem statement with
-"Let's think step by step" as an input prompt to LLMs. Despite the success of
-Zero-shot-CoT, it still suffers from three pitfalls: calculation errors,
-missing-step errors, and semantic misunderstanding errors. To address the
-missing-step errors, we propose Plan-and-Solve (PS) Prompting. It consists of
-two components: first, devising a plan to divide the entire task into smaller
-subtasks, and then carrying out the subtasks according to the plan. To address
-the calculation errors and improve the quality of generated reasoning steps, we
-extend PS prompting with more detailed instructions and derive PS+ prompting.
-We evaluate our proposed prompting strategy on ten datasets across three
-reasoning problems. The experimental results over GPT-3 show that our proposed
-zero-shot prompting consistently outperforms Zero-shot-CoT across all datasets
-by a large margin, is comparable to or exceeds Zero-shot-Program-of-Thought
-Prompting, and has comparable performance with 8-shot CoT prompting on the math
-reasoning problem. The code can be found at
-https://github.com/AGI-Edgerunners/Plan-and-Solve-Prompting.
-                
-## Visual Instruction Tuning
-
-- **arXiv id:** 2304.08485v2
-- **Title:** Visual Instruction Tuning
-- **Authors:** Haotian Liu, Chunyuan Li, Qingyang Wu,  et al.
-- **Published Date:** 2023-04-17
-- **URL:** http://arxiv.org/abs/2304.08485v2
-- **LangChain:**
-
-   - **Cookbook:** [Semi_structured_and_multi_modal_RAG](https://github.com/langchain-ai/langchain/blob/master/cookbook/Semi_structured_and_multi_modal_RAG.ipynb), [Semi_structured_multi_modal_RAG_LLaMA2](https://github.com/langchain-ai/langchain/blob/master/cookbook/Semi_structured_multi_modal_RAG_LLaMA2.ipynb)
-
-**Abstract:** Instruction tuning large language models (LLMs) using machine-generated
-instruction-following data has improved zero-shot capabilities on new tasks,
-but the idea is less explored in the multimodal field. In this paper, we
-present the first attempt to use language-only GPT-4 to generate multimodal
-language-image instruction-following data. By instruction tuning on such
-generated data, we introduce LLaVA: Large Language and Vision Assistant, an
-end-to-end trained large multimodal model that connects a vision encoder and
-LLM for general-purpose visual and language understanding.Our early experiments
-show that LLaVA demonstrates impressive multimodel chat abilities, sometimes
-exhibiting the behaviors of multimodal GPT-4 on unseen images/instructions, and
-yields a 85.1% relative score compared with GPT-4 on a synthetic multimodal
-instruction-following dataset. When fine-tuned on Science QA, the synergy of
-LLaVA and GPT-4 achieves a new state-of-the-art accuracy of 92.53%. We make
-GPT-4 generated visual instruction tuning data, our model and code base
-publicly available.
-                
-## Generative Agents: Interactive Simulacra of Human Behavior
-
-- **arXiv id:** 2304.03442v2
-- **Title:** Generative Agents: Interactive Simulacra of Human Behavior
-- **Authors:** Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai,  et al.
-- **Published Date:** 2023-04-07
-- **URL:** http://arxiv.org/abs/2304.03442v2
-- **LangChain:**
-
-   - **Cookbook:** [generative_agents_interactive_simulacra_of_human_behavior](https://github.com/langchain-ai/langchain/blob/master/cookbook/generative_agents_interactive_simulacra_of_human_behavior.ipynb), [multiagent_bidding](https://github.com/langchain-ai/langchain/blob/master/cookbook/multiagent_bidding.ipynb)
-
-**Abstract:** Believable proxies of human behavior can empower interactive applications
-ranging from immersive environments to rehearsal spaces for interpersonal
-communication to prototyping tools. In this paper, we introduce generative
-agents--computational software agents that simulate believable human behavior.
-Generative agents wake up, cook breakfast, and head to work; artists paint,
-while authors write; they form opinions, notice each other, and initiate
-conversations; they remember and reflect on days past as they plan the next
-day. To enable generative agents, we describe an architecture that extends a
-large language model to store a complete record of the agent's experiences
-using natural language, synthesize those memories over time into higher-level
-reflections, and retrieve them dynamically to plan behavior. We instantiate
-generative agents to populate an interactive sandbox environment inspired by
-The Sims, where end users can interact with a small town of twenty five agents
-using natural language. In an evaluation, these generative agents produce
-believable individual and emergent social behaviors: for example, starting with
-only a single user-specified notion that one agent wants to throw a Valentine's
-Day party, the agents autonomously spread invitations to the party over the
-next two days, make new acquaintances, ask each other out on dates to the
-party, and coordinate to show up for the party together at the right time. We
-demonstrate through ablation that the components of our agent
-architecture--observation, planning, and reflection--each contribute critically
-to the believability of agent behavior. By fusing large language models with
-computational, interactive agents, this work introduces architectural and
-interaction patterns for enabling believable simulations of human behavior.
-                
-## CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
-
-- **arXiv id:** 2303.17760v2
-- **Title:** CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
-- **Authors:** Guohao Li, Hasan Abed Al Kader Hammoud, Hani Itani,  et al.
-- **Published Date:** 2023-03-31
-- **URL:** http://arxiv.org/abs/2303.17760v2
-- **LangChain:**
-
-   - **Cookbook:** [camel_role_playing](https://github.com/langchain-ai/langchain/blob/master/cookbook/camel_role_playing.ipynb)
-
-**Abstract:** The rapid advancement of chat-based language models has led to remarkable
-progress in complex task-solving. However, their success heavily relies on
-human input to guide the conversation, which can be challenging and
-time-consuming. This paper explores the potential of building scalable
-techniques to facilitate autonomous cooperation among communicative agents, and
-provides insight into their "cognitive" processes. To address the challenges of
-achieving autonomous cooperation, we propose a novel communicative agent
-framework named role-playing. Our approach involves using inception prompting
-to guide chat agents toward task completion while maintaining consistency with
-human intentions. We showcase how role-playing can be used to generate
-conversational data for studying the behaviors and capabilities of a society of
-agents, providing a valuable resource for investigating conversational language
-models. In particular, we conduct comprehensive studies on
-instruction-following cooperation in multi-agent settings. Our contributions
-include introducing a novel communicative agent framework, offering a scalable
-approach for studying the cooperative behaviors and capabilities of multi-agent
-systems, and open-sourcing our library to support research on communicative
-agents and beyond: https://github.com/camel-ai/camel.
-                
-## HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
-
-- **arXiv id:** 2303.17580v4
-- **Title:** HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
-- **Authors:** Yongliang Shen, Kaitao Song, Xu Tan,  et al.
-- **Published Date:** 2023-03-30
-- **URL:** http://arxiv.org/abs/2303.17580v4
-- **LangChain:**
-
-   - **API Reference:** [langchain_experimental.autonomous_agents](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.autonomous_agents)
-   - **Cookbook:** [hugginggpt](https://github.com/langchain-ai/langchain/blob/master/cookbook/hugginggpt.ipynb)
-
-**Abstract:** Solving complicated AI tasks with different domains and modalities is a key
-step toward artificial general intelligence. While there are numerous AI models
-available for various domains and modalities, they cannot handle complicated AI
-tasks autonomously. Considering large language models (LLMs) have exhibited
-exceptional abilities in language understanding, generation, interaction, and
-reasoning, we advocate that LLMs could act as a controller to manage existing
-AI models to solve complicated AI tasks, with language serving as a generic
-interface to empower this. Based on this philosophy, we present HuggingGPT, an
-LLM-powered agent that leverages LLMs (e.g., ChatGPT) to connect various AI
-models in machine learning communities (e.g., Hugging Face) to solve AI tasks.
-Specifically, we use ChatGPT to conduct task planning when receiving a user
-request, select models according to their function descriptions available in
-Hugging Face, execute each subtask with the selected AI model, and summarize
-the response according to the execution results. By leveraging the strong
-language capability of ChatGPT and abundant AI models in Hugging Face,
-HuggingGPT can tackle a wide range of sophisticated AI tasks spanning different
-modalities and domains and achieve impressive results in language, vision,
-speech, and other challenging tasks, which paves a new way towards the
-realization of artificial general intelligence.
-                
-## GPT-4 Technical Report
-
-- **arXiv id:** 2303.08774v6
-- **Title:** GPT-4 Technical Report
-- **Authors:** OpenAI, Josh Achiam, Steven Adler,  et al.
-- **Published Date:** 2023-03-15
-- **URL:** http://arxiv.org/abs/2303.08774v6
-- **LangChain:**
-
-   - **Documentation:** [docs/integrations/vectorstores/mongodb_atlas](https://python.langchain.com/docs/integrations/vectorstores/mongodb_atlas)
-
-**Abstract:** We report the development of GPT-4, a large-scale, multimodal model which can
-accept image and text inputs and produce text outputs. While less capable than
-humans in many real-world scenarios, GPT-4 exhibits human-level performance on
-various professional and academic benchmarks, including passing a simulated bar
-exam with a score around the top 10% of test takers. GPT-4 is a
-Transformer-based model pre-trained to predict the next token in a document.
-The post-training alignment process results in improved performance on measures
-of factuality and adherence to desired behavior. A core component of this
-project was developing infrastructure and optimization methods that behave
-predictably across a wide range of scales. This allowed us to accurately
-predict some aspects of GPT-4's performance based on models trained with no
-more than 1/1,000th the compute of GPT-4.
-                
-## A Watermark for Large Language Models
-
-- **arXiv id:** 2301.10226v4
-- **Title:** A Watermark for Large Language Models
-- **Authors:** John Kirchenbauer, Jonas Geiping, Yuxin Wen,  et al.
-- **Published Date:** 2023-01-24
-- **URL:** http://arxiv.org/abs/2301.10226v4
-- **LangChain:**
-
-   - **API Reference:** [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference), [langchain_community...OCIModelDeploymentTGI](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentTGI.html#langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentTGI), [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint)
-
-**Abstract:** Potential harms of large language models can be mitigated by watermarking
-model output, i.e., embedding signals into generated text that are invisible to
-humans but algorithmically detectable from a short span of tokens. We propose a
-watermarking framework for proprietary language models. The watermark can be
-embedded with negligible impact on text quality, and can be detected using an
-efficient open-source algorithm without access to the language model API or
-parameters. The watermark works by selecting a randomized set of "green" tokens
-before a word is generated, and then softly promoting use of green tokens
-during sampling. We propose a statistical test for detecting the watermark with
-interpretable p-values, and derive an information-theoretic framework for
-analyzing the sensitivity of the watermark. We test the watermark using a
-multi-billion parameter model from the Open Pretrained Transformer (OPT)
-family, and discuss robustness and security.
-                
-## Precise Zero-Shot Dense Retrieval without Relevance Labels
-
-- **arXiv id:** 2212.10496v1
-- **Title:** Precise Zero-Shot Dense Retrieval without Relevance Labels
-- **Authors:** Luyu Gao, Xueguang Ma, Jimmy Lin,  et al.
-- **Published Date:** 2022-12-20
-- **URL:** http://arxiv.org/abs/2212.10496v1
-- **LangChain:**
-
-   - **API Reference:** [langchain...HypotheticalDocumentEmbedder](https://api.python.langchain.com/en/latest/chains/langchain.chains.hyde.base.HypotheticalDocumentEmbedder.html#langchain.chains.hyde.base.HypotheticalDocumentEmbedder)
-   - **Template:** [hyde](https://python.langchain.com/docs/templates/hyde)
-   - **Cookbook:** [hypothetical_document_embeddings](https://github.com/langchain-ai/langchain/blob/master/cookbook/hypothetical_document_embeddings.ipynb)
-
-**Abstract:** While dense retrieval has been shown effective and efficient across tasks and
-languages, it remains difficult to create effective fully zero-shot dense
-retrieval systems when no relevance label is available. In this paper, we
-recognize the difficulty of zero-shot learning and encoding relevance. Instead,
-we propose to pivot through Hypothetical Document Embeddings~(HyDE). Given a
-query, HyDE first zero-shot instructs an instruction-following language model
-(e.g. InstructGPT) to generate a hypothetical document. The document captures
-relevance patterns but is unreal and may contain false details. Then, an
-unsupervised contrastively learned encoder~(e.g. Contriever) encodes the
-document into an embedding vector. This vector identifies a neighborhood in the
-corpus embedding space, where similar real documents are retrieved based on
-vector similarity. This second step ground the generated document to the actual
-corpus, with the encoder's dense bottleneck filtering out the incorrect
-details. Our experiments show that HyDE significantly outperforms the
-state-of-the-art unsupervised dense retriever Contriever and shows strong
-performance comparable to fine-tuned retrievers, across various tasks (e.g. web
-search, QA, fact verification) and languages~(e.g. sw, ko, ja).
-                
-## Robust and Explainable Identification of Logical Fallacies in Natural Language Arguments
-
-- **arXiv id:** 2212.07425v3
-- **Title:** Robust and Explainable Identification of Logical Fallacies in Natural Language Arguments
-- **Authors:** Zhivar Sourati, Vishnu Priya Prasanna Venkatesh, Darshan Deshpande,  et al.
-- **Published Date:** 2022-12-12
-- **URL:** http://arxiv.org/abs/2212.07425v3
-- **LangChain:**
-
-   - **API Reference:** [langchain_experimental.fallacy_removal](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.fallacy_removal)
-
-**Abstract:** The spread of misinformation, propaganda, and flawed argumentation has been
-amplified in the Internet era. Given the volume of data and the subtlety of
-identifying violations of argumentation norms, supporting information analytics
-tasks, like content moderation, with trustworthy methods that can identify
-logical fallacies is essential. In this paper, we formalize prior theoretical
-work on logical fallacies into a comprehensive three-stage evaluation framework
-of detection, coarse-grained, and fine-grained classification. We adapt
-existing evaluation datasets for each stage of the evaluation. We employ three
-families of robust and explainable methods based on prototype reasoning,
-instance-based reasoning, and knowledge injection. The methods combine language
-models with background knowledge and explainable mechanisms. Moreover, we
-address data sparsity with strategies for data augmentation and curriculum
-learning. Our three-stage framework natively consolidates prior datasets and
-methods from existing tasks, like propaganda detection, serving as an
-overarching evaluation testbed. We extensively evaluate these methods on our
-datasets, focusing on their robustness and explainability. Our results provide
-insight into the strengths and weaknesses of the methods on different
-components and fallacy classes, indicating that fallacy identification is a
-challenging task that may require specialized forms of reasoning to capture
-various classes. We share our open-source code and data on GitHub to support
-further work on logical fallacy identification.
-                
-## Complementary Explanations for Effective In-Context Learning
-
-- **arXiv id:** 2211.13892v2
-- **Title:** Complementary Explanations for Effective In-Context Learning
-- **Authors:** Xi Ye, Srinivasan Iyer, Asli Celikyilmaz,  et al.
-- **Published Date:** 2022-11-25
-- **URL:** http://arxiv.org/abs/2211.13892v2
-- **LangChain:**
-
-   - **API Reference:** [langchain_core...MaxMarginalRelevanceExampleSelector](https://api.python.langchain.com/en/latest/example_selectors/langchain_core.example_selectors.semantic_similarity.MaxMarginalRelevanceExampleSelector.html#langchain_core.example_selectors.semantic_similarity.MaxMarginalRelevanceExampleSelector)
-
-**Abstract:** Large language models (LLMs) have exhibited remarkable capabilities in
-learning from explanations in prompts, but there has been limited understanding
-of exactly how these explanations function or why they are effective. This work
-aims to better understand the mechanisms by which explanations are used for
-in-context learning. We first study the impact of two different factors on the
-performance of prompts with explanations: the computation trace (the way the
-solution is decomposed) and the natural language used to express the prompt. By
-perturbing explanations on three controlled tasks, we show that both factors
-contribute to the effectiveness of explanations. We further study how to form
-maximally effective sets of explanations for solving a given test query. We
-find that LLMs can benefit from the complementarity of the explanation set:
-diverse reasoning skills shown by different exemplars can lead to better
-performance. Therefore, we propose a maximal marginal relevance-based exemplar
-selection approach for constructing exemplar sets that are both relevant as
-well as complementary, which successfully improves the in-context learning
-performance across three real-world tasks on multiple LLMs.
-                
-## PAL: Program-aided Language Models
-
-- **arXiv id:** 2211.10435v2
-- **Title:** PAL: Program-aided Language Models
-- **Authors:** Luyu Gao, Aman Madaan, Shuyan Zhou,  et al.
-- **Published Date:** 2022-11-18
-- **URL:** http://arxiv.org/abs/2211.10435v2
-- **LangChain:**
-
-   - **API Reference:** [langchain_experimental...PALChain](https://api.python.langchain.com/en/latest/pal_chain/langchain_experimental.pal_chain.base.PALChain.html#langchain_experimental.pal_chain.base.PALChain), [langchain_experimental.pal_chain](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.pal_chain)
-   - **Cookbook:** [program_aided_language_model](https://github.com/langchain-ai/langchain/blob/master/cookbook/program_aided_language_model.ipynb)
-
-**Abstract:** Large language models (LLMs) have recently demonstrated an impressive ability
-to perform arithmetic and symbolic reasoning tasks, when provided with a few
-examples at test time ("few-shot prompting"). Much of this success can be
-attributed to prompting methods such as "chain-of-thought'', which employ LLMs
-for both understanding the problem description by decomposing it into steps, as
-well as solving each step of the problem. While LLMs seem to be adept at this
-sort of step-by-step decomposition, LLMs often make logical and arithmetic
-mistakes in the solution part, even when the problem is decomposed correctly.
-In this paper, we present Program-Aided Language models (PAL): a novel approach
-that uses the LLM to read natural language problems and generate programs as
-the intermediate reasoning steps, but offloads the solution step to a runtime
-such as a Python interpreter. With PAL, decomposing the natural language
-problem into runnable steps remains the only learning task for the LLM, while
-solving is delegated to the interpreter. We demonstrate this synergy between a
-neural LLM and a symbolic interpreter across 13 mathematical, symbolic, and
-algorithmic reasoning tasks from BIG-Bench Hard and other benchmarks. In all
-these natural language reasoning tasks, generating code using an LLM and
-reasoning using a Python interpreter leads to more accurate results than much
-larger models. For example, PAL using Codex achieves state-of-the-art few-shot
-accuracy on the GSM8K benchmark of math word problems, surpassing PaLM-540B
-which uses chain-of-thought by absolute 15% top-1. Our code and data are
-publicly available at http://reasonwithpal.com/ .
-                
-## Deep Lake: a Lakehouse for Deep Learning
-
-- **arXiv id:** 2209.10785v2
-- **Title:** Deep Lake: a Lakehouse for Deep Learning
-- **Authors:** Sasun Hambardzumyan, Abhinav Tuli, Levon Ghukasyan,  et al.
-- **Published Date:** 2022-09-22
-- **URL:** http://arxiv.org/abs/2209.10785v2
-- **LangChain:**
-
-   - **Documentation:** [docs/integrations/providers/activeloop_deeplake](https://python.langchain.com/docs/integrations/providers/activeloop_deeplake)
-
-**Abstract:** Traditional data lakes provide critical data infrastructure for analytical
-workloads by enabling time travel, running SQL queries, ingesting data with
-ACID transactions, and visualizing petabyte-scale datasets on cloud storage.
-They allow organizations to break down data silos, unlock data-driven
-decision-making, improve operational efficiency, and reduce costs. However, as
-deep learning usage increases, traditional data lakes are not well-designed for
-applications such as natural language processing (NLP), audio processing,
-computer vision, and applications involving non-tabular datasets. This paper
-presents Deep Lake, an open-source lakehouse for deep learning applications
-developed at Activeloop. Deep Lake maintains the benefits of a vanilla data
-lake with one key difference: it stores complex data, such as images, videos,
-annotations, as well as tabular data, in the form of tensors and rapidly
-streams the data over the network to (a) Tensor Query Language, (b) in-browser
-visualization engine, or (c) deep learning frameworks without sacrificing GPU
-utilization. Datasets stored in Deep Lake can be accessed from PyTorch,
-TensorFlow, JAX, and integrate with numerous MLOps tools.
-                
-## Bitext Mining Using Distilled Sentence Representations for Low-Resource Languages
-
-- **arXiv id:** 2205.12654v1
-- **Title:** Bitext Mining Using Distilled Sentence Representations for Low-Resource Languages
-- **Authors:** Kevin Heffernan, Onur Çelebi, Holger Schwenk
-- **Published Date:** 2022-05-25
-- **URL:** http://arxiv.org/abs/2205.12654v1
-- **LangChain:**
-
-   - **API Reference:** [langchain_community...LaserEmbeddings](https://api.python.langchain.com/en/latest/embeddings/langchain_community.embeddings.laser.LaserEmbeddings.html#langchain_community.embeddings.laser.LaserEmbeddings)
-
-**Abstract:** Scaling multilingual representation learning beyond the hundred most frequent
-languages is challenging, in particular to cover the long tail of low-resource
-languages. A promising approach has been to train one-for-all multilingual
-models capable of cross-lingual transfer, but these models often suffer from
-insufficient capacity and interference between unrelated languages. Instead, we
-move away from this approach and focus on training multiple language (family)
-specific representations, but most prominently enable all languages to still be
-encoded in the same representational space. To achieve this, we focus on
-teacher-student training, allowing all encoders to be mutually compatible for
-bitext mining, and enabling fast learning of new languages. We introduce a new
-teacher-student training scheme which combines supervised and self-supervised
-training, allowing encoders to take advantage of monolingual training data,
-which is valuable in the low-resource setting.
-  Our approach significantly outperforms the original LASER encoder. We study
-very low-resource languages and handle 50 African languages, many of which are
-not covered by any other model. For these languages, we train sentence
-encoders, mine bitexts, and validate the bitexts by training NMT systems.
-                
-## Evaluating the Text-to-SQL Capabilities of Large Language Models
-
-- **arXiv id:** 2204.00498v1
-- **Title:** Evaluating the Text-to-SQL Capabilities of Large Language Models
-- **Authors:** Nitarshan Rajkumar, Raymond Li, Dzmitry Bahdanau
-- **Published Date:** 2022-03-15
-- **URL:** http://arxiv.org/abs/2204.00498v1
-- **LangChain:**
-
-   - **API Reference:** [langchain_community...SparkSQL](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.spark_sql.SparkSQL.html#langchain_community.utilities.spark_sql.SparkSQL), [langchain_community...SQLDatabase](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.sql_database.SQLDatabase.html#langchain_community.utilities.sql_database.SQLDatabase)
-
-**Abstract:** We perform an empirical evaluation of Text-to-SQL capabilities of the Codex
-language model. We find that, without any finetuning, Codex is a strong
-baseline on the Spider benchmark; we also analyze the failure modes of Codex in
-this setting. Furthermore, we demonstrate on the GeoQuery and Scholar
-benchmarks that a small number of in-domain examples provided in the prompt
-enables Codex to perform better than state-of-the-art models finetuned on such
-few-shot examples.
-                
-## Locally Typical Sampling
-
-- **arXiv id:** 2202.00666v5
-- **Title:** Locally Typical Sampling
-- **Authors:** Clara Meister, Tiago Pimentel, Gian Wiher,  et al.
-- **Published Date:** 2022-02-01
-- **URL:** http://arxiv.org/abs/2202.00666v5
-- **LangChain:**
-
-   - **API Reference:** [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference), [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint)
-
-**Abstract:** Today's probabilistic language generators fall short when it comes to
-producing coherent and fluent text despite the fact that the underlying models
-perform well under standard metrics, e.g., perplexity. This discrepancy has
-puzzled the language generation community for the last few years. In this work,
-we posit that the abstraction of natural language generation as a discrete
-stochastic process--which allows for an information-theoretic analysis--can
-provide new insights into the behavior of probabilistic language generators,
-e.g., why high-probability texts can be dull or repetitive. Humans use language
-as a means of communicating information, aiming to do so in a simultaneously
-efficient and error-minimizing manner; in fact, psycholinguistics research
-suggests humans choose each word in a string with this subconscious goal in
-mind. We formally define the set of strings that meet this criterion: those for
-which each word has an information content close to the expected information
-content, i.e., the conditional entropy of our model. We then propose a simple
-and efficient procedure for enforcing this criterion when generating from
-probabilistic models, which we call locally typical sampling. Automatic and
-human evaluations show that, in comparison to nucleus and top-k sampling,
-locally typical sampling offers competitive performance (in both abstractive
-summarization and story generation) in terms of quality while consistently
-reducing degenerate repetitions.
-                
-## Learning Transferable Visual Models From Natural Language Supervision
-
-- **arXiv id:** 2103.00020v1
-- **Title:** Learning Transferable Visual Models From Natural Language Supervision
-- **Authors:** Alec Radford, Jong Wook Kim, Chris Hallacy,  et al.
-- **Published Date:** 2021-02-26
-- **URL:** http://arxiv.org/abs/2103.00020v1
-- **LangChain:**
-
-   - **API Reference:** [langchain_experimental.open_clip](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.open_clip)
-
-**Abstract:** State-of-the-art computer vision systems are trained to predict a fixed set
-of predetermined object categories. This restricted form of supervision limits
-their generality and usability since additional labeled data is needed to
-specify any other visual concept. Learning directly from raw text about images
-is a promising alternative which leverages a much broader source of
-supervision. We demonstrate that the simple pre-training task of predicting
-which caption goes with which image is an efficient and scalable way to learn
-SOTA image representations from scratch on a dataset of 400 million (image,
-text) pairs collected from the internet. After pre-training, natural language
-is used to reference learned visual concepts (or describe new ones) enabling
-zero-shot transfer of the model to downstream tasks. We study the performance
-of this approach by benchmarking on over 30 different existing computer vision
-datasets, spanning tasks such as OCR, action recognition in videos,
-geo-localization, and many types of fine-grained object classification. The
-model transfers non-trivially to most tasks and is often competitive with a
-fully supervised baseline without the need for any dataset specific training.
-For instance, we match the accuracy of the original ResNet-50 on ImageNet
-zero-shot without needing to use any of the 1.28 million training examples it
-was trained on. We release our code and pre-trained model weights at
-https://github.com/OpenAI/CLIP.
-                
-## CTRL: A Conditional Transformer Language Model for Controllable Generation
-
-- **arXiv id:** 1909.05858v2
-- **Title:** CTRL: A Conditional Transformer Language Model for Controllable Generation
-- **Authors:** Nitish Shirish Keskar, Bryan McCann, Lav R. Varshney,  et al.
-- **Published Date:** 2019-09-11
-- **URL:** http://arxiv.org/abs/1909.05858v2
-- **LangChain:**
-
-   - **API Reference:** [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference), [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint)
-
-**Abstract:** Large-scale language models show promising text generation capabilities, but
-users cannot easily control particular aspects of the generated text. We
-release CTRL, a 1.63 billion-parameter conditional transformer language model,
-trained to condition on control codes that govern style, content, and
-task-specific behavior. Control codes were derived from structure that
-naturally co-occurs with raw text, preserving the advantages of unsupervised
-learning while providing more explicit control over text generation. These
-codes also allow CTRL to predict which parts of the training data are most
-likely given a sequence. This provides a potential method for analyzing large
-amounts of data via model-based source attribution. We have released multiple
-full-sized, pretrained versions of CTRL at https://github.com/salesforce/ctrl.
-                
-## Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
-
-- **arXiv id:** 1908.10084v1
-- **Title:** Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
-- **Authors:** Nils Reimers, Iryna Gurevych
-- **Published Date:** 2019-08-27
-- **URL:** http://arxiv.org/abs/1908.10084v1
-- **LangChain:**
-
-   - **Documentation:** [docs/integrations/text_embedding/sentence_transformers](https://python.langchain.com/docs/integrations/text_embedding/sentence_transformers)
-
-**Abstract:** BERT (Devlin et al., 2018) and RoBERTa (Liu et al., 2019) has set a new
-state-of-the-art performance on sentence-pair regression tasks like semantic
-textual similarity (STS). However, it requires that both sentences are fed into
-the network, which causes a massive computational overhead: Finding the most
-similar pair in a collection of 10,000 sentences requires about 50 million
-inference computations (~65 hours) with BERT. The construction of BERT makes it
-unsuitable for semantic similarity search as well as for unsupervised tasks
-like clustering.
-  In this publication, we present Sentence-BERT (SBERT), a modification of the
-pretrained BERT network that use siamese and triplet network structures to
-derive semantically meaningful sentence embeddings that can be compared using
-cosine-similarity. This reduces the effort for finding the most similar pair
-from 65 hours with BERT / RoBERTa to about 5 seconds with SBERT, while
-maintaining the accuracy from BERT.
-  We evaluate SBERT and SRoBERTa on common STS tasks and transfer learning
-tasks, where it outperforms other state-of-the-art sentence embeddings methods.
-                

docs/docs/additional_resources/tutorials.mdx

@@ -1,10 +1,14 @@
-# 3rd Party Tutorials
+# Tutorials
+
+## Books and Handbooks
+
+- [Generative AI with LangChain](https://www.amazon.com/Generative-AI-LangChain-language-ChatGPT/dp/1835083463/ref=sr_1_1?crid=1GMOMH0G7GLR&keywords=generative+ai+with+langchain&qid=1703247181&sprefix=%2Caps%2C298&sr=8-1) by [Ben Auffrath](https://www.amazon.com/stores/Ben-Auffarth/author/B08JQKSZ7D?ref=ap_rdr&store_ref=ap_rdr&isDramIntegrated=true&shoppingPortalEnabled=true), ©️ 2023 Packt Publishing
+- [LangChain AI Handbook](https://www.pinecone.io/learn/langchain/) By **James Briggs** and **Francisco Ingham**
+- [LangChain Cheatsheet](https://pub.towardsai.net/langchain-cheatsheet-all-secrets-on-a-single-page-8be26b721cde) by **Ivan Reznikov**
+
 
 ##  Tutorials
 
-### [LangChain v 0.1 by LangChain.ai](https://www.youtube.com/playlist?list=PLfaIDFEXuae0gBSJ9T0w7cu7iJZbH3T31)
-### [Build with Langchain - Advanced by LangChain.ai](https://www.youtube.com/playlist?list=PLfaIDFEXuae06tclDATrMYY0idsTdLg9v)
-### [LangGraph by LangChain.ai](https://www.youtube.com/playlist?list=PLfaIDFEXuae16n2TWUkKq5PgJ0w6Pkwtg)
 ### [by Greg Kamradt](https://www.youtube.com/playlist?list=PLqZXAkvF1bPNQER9mLmDbntNfSpzdDIU5)
 ### [by Sam Witteveen](https://www.youtube.com/playlist?list=PL8motc6AQftk1Bs42EW45kwYbyJ4jOdiZ)
 ### [by James Briggs](https://www.youtube.com/playlist?list=PLIUOU7oqGTLieV9uTIFMm6_4PXg-hlN6F)
@@ -12,6 +16,7 @@
 ### [by Mayo Oshin](https://www.youtube.com/@chatwithdata/search?query=langchain)
 ### [by 1 little Coder](https://www.youtube.com/playlist?list=PLpdmBGJ6ELUK-v0MK-t4wZmVEbxM5xk6L)
 
+
 ## Courses
 
 ### Featured courses on Deeplearning.AI
@@ -24,14 +29,12 @@
 ### Online courses
 
 - [Udemy](https://www.udemy.com/courses/search/?q=langchain)
-- [DataCamp](https://www.datacamp.com/courses/developing-llm-applications-with-langchain)
 - [Pluralsight](https://www.pluralsight.com/search?q=langchain)
 - [Coursera](https://www.coursera.org/search?query=langchain)
 - [Maven](https://maven.com/courses?query=langchain)
 - [Udacity](https://www.udacity.com/catalog/all/any-price/any-school/any-skill/any-difficulty/any-duration/any-type/relevance/page-1?searchValue=langchain)
 - [LinkedIn Learning](https://www.linkedin.com/search/results/learning/?keywords=langchain)
 - [edX](https://www.edx.org/search?q=langchain)
-- [freeCodeCamp](https://www.youtube.com/@freecodecamp/search?query=langchain)
 
 ## Short Tutorials
 
@@ -40,11 +43,7 @@
 - [by Rabbitmetrics](https://youtu.be/aywZrzNaKjs)
 - [by Ivan Reznikov](https://medium.com/@ivanreznikov/langchain-101-course-updated-668f7b41d6cb)
 
-## Books and Handbooks
-
-- [Generative AI with LangChain](https://www.amazon.com/Generative-AI-LangChain-language-ChatGPT/dp/1835083463/ref=sr_1_1?crid=1GMOMH0G7GLR&keywords=generative+ai+with+langchain&qid=1703247181&sprefix=%2Caps%2C298&sr=8-1) by [Ben Auffrath](https://www.amazon.com/stores/Ben-Auffarth/author/B08JQKSZ7D?ref=ap_rdr&store_ref=ap_rdr&isDramIntegrated=true&shoppingPortalEnabled=true), ©️ 2023 Packt Publishing
-- [LangChain AI Handbook](https://www.pinecone.io/learn/langchain/) By **James Briggs** and **Francisco Ingham**
-- [LangChain Cheatsheet](https://pub.towardsai.net/langchain-cheatsheet-all-secrets-on-a-single-page-8be26b721cde) by **Ivan Reznikov**
+## [Documentation: Use cases](/docs/use_cases)
 
 ---------------------
 

docs/docs/additional_resources/youtube.mdx

@@ -1,63 +1,137 @@
 # YouTube videos
 
-[Updated 2024-05-16]
+⛓ icon marks a new addition [last update 2023-09-21]
 
 ### [Official LangChain YouTube channel](https://www.youtube.com/@LangChain)
 
-### [Tutorials on YouTube](/docs/additional_resources/tutorials/#tutorials)
+### Introduction to LangChain with Harrison Chase, creator of LangChain
+- [Building the Future with LLMs, `LangChain`, & `Pinecone`](https://youtu.be/nMniwlGyX-c) by [Pinecone](https://www.youtube.com/@pinecone-io)
+- [LangChain and Weaviate with Harrison Chase and Bob van Luijt - Weaviate Podcast #36](https://youtu.be/lhby7Ql7hbk) by [Weaviate • Vector Database](https://www.youtube.com/@Weaviate)
+- [LangChain Demo + Q&A with Harrison Chase](https://youtu.be/zaYTXQFR0_s?t=788) by [Full Stack Deep Learning](https://www.youtube.com/@The_Full_Stack)
+- [LangChain Agents: Build Personal Assistants For Your Data (Q&A with Harrison Chase and Mayo Oshin)](https://youtu.be/gVkF8cwfBLI) by [Chat with data](https://www.youtube.com/@chatwithdata)
 
 ## Videos (sorted by views)
 
-Only videos with 40K+ views:
+- [Using `ChatGPT` with YOUR OWN Data. This is magical. (LangChain OpenAI API)](https://youtu.be/9AXP7tCI9PI) by [TechLead](https://www.youtube.com/@TechLead)
+- [First look - `ChatGPT` + `WolframAlpha` (`GPT-3.5` and Wolfram|Alpha via LangChain by James Weaver)](https://youtu.be/wYGbY811oMo) by [Dr Alan D. Thompson](https://www.youtube.com/@DrAlanDThompson) 
+- [LangChain explained - The hottest new Python framework](https://youtu.be/RoR4XJw8wIc) by [AssemblyAI](https://www.youtube.com/@AssemblyAI)
+- [Chatbot with INFINITE MEMORY using `OpenAI` & `Pinecone` - `GPT-3`, `Embeddings`, `ADA`, `Vector DB`, `Semantic`](https://youtu.be/2xNzB7xq8nk) by [David Shapiro ~ AI](https://www.youtube.com/@DaveShap)
+- [LangChain for LLMs is... basically just an Ansible playbook](https://youtu.be/X51N9C-OhlE) by [David Shapiro ~ AI](https://www.youtube.com/@DaveShap)
+- [Build your own LLM Apps with LangChain & `GPT-Index`](https://youtu.be/-75p09zFUJY) by [1littlecoder](https://www.youtube.com/@1littlecoder)
+- [`BabyAGI` - New System of Autonomous AI Agents with LangChain](https://youtu.be/lg3kJvf1kXo) by [1littlecoder](https://www.youtube.com/@1littlecoder)
+- [Run `BabyAGI` with Langchain Agents (with Python Code)](https://youtu.be/WosPGHPObx8) by [1littlecoder](https://www.youtube.com/@1littlecoder)
+- [How to Use Langchain With `Zapier` | Write and Send Email with GPT-3 | OpenAI API Tutorial](https://youtu.be/p9v2-xEa9A0) by [StarMorph AI](https://www.youtube.com/@starmorph)
+- [Use Your Locally Stored Files To Get Response From GPT - `OpenAI` | Langchain | Python](https://youtu.be/NC1Ni9KS-rk) by [Shweta Lodha](https://www.youtube.com/@shweta-lodha)
+- [`Langchain JS` | How to Use GPT-3, GPT-4 to Reference your own Data | `OpenAI Embeddings` Intro](https://youtu.be/veV2I-NEjaM) by [StarMorph AI](https://www.youtube.com/@starmorph)
+- [The easiest way to work with large language models | Learn LangChain in 10min](https://youtu.be/kmbS6FDQh7c) by [Sophia Yang](https://www.youtube.com/@SophiaYangDS)
+- [4 Autonomous AI Agents: “Westworld” simulation `BabyAGI`, `AutoGPT`, `Camel`, `LangChain`](https://youtu.be/yWbnH6inT_U) by [Sophia Yang](https://www.youtube.com/@SophiaYangDS)
+- [AI CAN SEARCH THE INTERNET? Langchain Agents + OpenAI ChatGPT](https://youtu.be/J-GL0htqda8) by [tylerwhatsgood](https://www.youtube.com/@tylerwhatsgood)
+- [Query Your Data with GPT-4 | Embeddings, Vector Databases | Langchain JS Knowledgebase](https://youtu.be/jRnUPUTkZmU) by [StarMorph AI](https://www.youtube.com/@starmorph)
+- [`Weaviate` + LangChain for LLM apps presented by Erika Cardenas](https://youtu.be/7AGj4Td5Lgw) by [`Weaviate` • Vector Database](https://www.youtube.com/@Weaviate)
+- [Langchain Overview — How to Use Langchain & `ChatGPT`](https://youtu.be/oYVYIq0lOtI) by [Python In Office](https://www.youtube.com/@pythoninoffice6568)
+- [Langchain Overview - How to Use Langchain & `ChatGPT`](https://youtu.be/oYVYIq0lOtI) by [Python In Office](https://www.youtube.com/@pythoninoffice6568)
+- [LangChain Tutorials](https://www.youtube.com/watch?v=FuqdVNB_8c0&list=PL9V0lbeJ69brU-ojMpU1Y7Ic58Tap0Cw6) by [Edrick](https://www.youtube.com/@edrickdch):
+  - [LangChain, Chroma DB, OpenAI Beginner Guide | ChatGPT with your PDF](https://youtu.be/FuqdVNB_8c0)
+  - [LangChain 101: The Complete Beginner's Guide](https://youtu.be/P3MAbZ2eMUI)
+- [Custom langchain Agent & Tools with memory. Turn any `Python function` into langchain tool with Gpt 3](https://youtu.be/NIG8lXk0ULg) by [echohive](https://www.youtube.com/@echohive)
+- [Building AI LLM Apps with LangChain (and more?) - LIVE STREAM](https://www.youtube.com/live/M-2Cj_2fzWI?feature=share) by [Nicholas Renotte](https://www.youtube.com/@NicholasRenotte)
+- [`ChatGPT` with any `YouTube` video using langchain and `chromadb`](https://youtu.be/TQZfB2bzVwU) by [echohive](https://www.youtube.com/@echohive)
+- [How to Talk to a `PDF` using LangChain and `ChatGPT`](https://youtu.be/v2i1YDtrIwk) by [Automata Learning Lab](https://www.youtube.com/@automatalearninglab)
+- [Langchain Document Loaders Part 1: Unstructured Files](https://youtu.be/O5C0wfsen98) by [Merk](https://www.youtube.com/@heymichaeldaigler) 
+- [LangChain - Prompt Templates (what all the best prompt engineers use)](https://youtu.be/1aRu8b0XNOQ) by [Nick Daigler](https://www.youtube.com/@nickdaigler)
+- [LangChain. Crear aplicaciones Python impulsadas por GPT](https://youtu.be/DkW_rDndts8) by [Jesús Conde](https://www.youtube.com/@0utKast)
+- [Easiest Way to Use GPT In Your Products | LangChain Basics Tutorial](https://youtu.be/fLy0VenZyGc) by [Rachel Woods](https://www.youtube.com/@therachelwoods)
+- [`BabyAGI` + `GPT-4` Langchain Agent with Internet Access](https://youtu.be/wx1z_hs5P6E) by [tylerwhatsgood](https://www.youtube.com/@tylerwhatsgood)
+- [Learning LLM Agents. How does it actually work? LangChain, AutoGPT & OpenAI](https://youtu.be/mb_YAABSplk) by [Arnoldas Kemeklis](https://www.youtube.com/@processusAI)
+- [Get Started with LangChain in `Node.js`](https://youtu.be/Wxx1KUWJFv4) by [Developers Digest](https://www.youtube.com/@DevelopersDigest)
+- [LangChain + `OpenAI` tutorial: Building a Q&A system w/ own text data](https://youtu.be/DYOU_Z0hAwo) by [Samuel Chan](https://www.youtube.com/@SamuelChan)
+- [Langchain + `Zapier` Agent](https://youtu.be/yribLAb-pxA) by [Merk](https://www.youtube.com/@heymichaeldaigler)
+- [Connecting the Internet with `ChatGPT` (LLMs) using Langchain And Answers Your Questions](https://youtu.be/9Y0TBC63yZg) by [Kamalraj M M](https://www.youtube.com/@insightbuilder)
+- [Build More Powerful LLM Applications for Business’s with LangChain (Beginners Guide)](https://youtu.be/sp3-WLKEcBg) by[ No Code Blackbox](https://www.youtube.com/@nocodeblackbox)
+- [LangFlow LLM Agent Demo for 🦜🔗LangChain](https://youtu.be/zJxDHaWt-6o) by [Cobus Greyling](https://www.youtube.com/@CobusGreylingZA)
+- [Chatbot Factory: Streamline Python Chatbot Creation with LLMs and Langchain](https://youtu.be/eYer3uzrcuM) by [Finxter](https://www.youtube.com/@CobusGreylingZA)
+- [LangChain Tutorial - ChatGPT mit eigenen Daten](https://youtu.be/0XDLyY90E2c) by [Coding Crashkurse](https://www.youtube.com/@codingcrashkurse6429)
+- [Chat with a `CSV` | LangChain Agents Tutorial (Beginners)](https://youtu.be/tjeti5vXWOU) by [GoDataProf](https://www.youtube.com/@godataprof)
+- [Introdução ao Langchain - #Cortes - Live DataHackers](https://youtu.be/fw8y5VRei5Y) by [Prof. João Gabriel Lima](https://www.youtube.com/@profjoaogabriellima)
+- [LangChain: Level up `ChatGPT` !? | LangChain Tutorial Part 1](https://youtu.be/vxUGx8aZpDE) by [Code Affinity](https://www.youtube.com/@codeaffinitydev)
+- [KI schreibt krasses Youtube Skript 😲😳 | LangChain Tutorial Deutsch](https://youtu.be/QpTiXyK1jus) by [SimpleKI](https://www.youtube.com/@simpleki)
+- [Chat with Audio: Langchain, `Chroma DB`, OpenAI, and `Assembly AI`](https://youtu.be/Kjy7cx1r75g) by [AI Anytime](https://www.youtube.com/@AIAnytime)
+- [QA over documents with Auto vector index selection with Langchain router chains](https://youtu.be/9G05qybShv8) by [echohive](https://www.youtube.com/@echohive)
+- [Build your own custom LLM application with `Bubble.io` & Langchain (No Code & Beginner friendly)](https://youtu.be/O7NhQGu1m6c) by [No Code Blackbox](https://www.youtube.com/@nocodeblackbox)
+- [Simple App to Question Your Docs: Leveraging `Streamlit`, `Hugging Face Spaces`, LangChain, and `Claude`!](https://youtu.be/X4YbNECRr7o) by [Chris Alexiuk](https://www.youtube.com/@chrisalexiuk)
+- [LANGCHAIN AI- `ConstitutionalChainAI` + Databutton AI ASSISTANT Web App](https://youtu.be/5zIU6_rdJCU) by [Avra](https://www.youtube.com/@Avra_b)
+- [LANGCHAIN AI AUTONOMOUS AGENT WEB APP - 👶 `BABY AGI` 🤖 with EMAIL AUTOMATION using `DATABUTTON`](https://youtu.be/cvAwOGfeHgw) by [Avra](https://www.youtube.com/@Avra_b)
+- [The Future of Data Analysis: Using A.I. Models in Data Analysis (LangChain)](https://youtu.be/v_LIcVyg5dk) by [Absent Data](https://www.youtube.com/@absentdata)
+- [Memory in LangChain | Deep dive (python)](https://youtu.be/70lqvTFh_Yg) by [Eden Marco](https://www.youtube.com/@EdenMarco)
+- [9 LangChain UseCases | Beginner's Guide | 2023](https://youtu.be/zS8_qosHNMw) by [Data Science Basics](https://www.youtube.com/@datasciencebasics)
+- [Use Large Language Models in Jupyter Notebook | LangChain | Agents & Indexes](https://youtu.be/JSe11L1a_QQ) by [Abhinaw Tiwari](https://www.youtube.com/@AbhinawTiwariAT)
+- [How to Talk to Your Langchain Agent | `11 Labs` + `Whisper`](https://youtu.be/N4k459Zw2PU) by [VRSEN](https://www.youtube.com/@vrsen)
+- [LangChain Deep Dive: 5 FUN AI App Ideas To Build Quickly and Easily](https://youtu.be/mPYEPzLkeks) by [James NoCode](https://www.youtube.com/@jamesnocode)
+- [LangChain 101: Models](https://youtu.be/T6c_XsyaNSQ) by [Mckay Wrigley](https://www.youtube.com/@realmckaywrigley)
+- [LangChain with JavaScript Tutorial #1 | Setup & Using LLMs](https://youtu.be/W3AoeMrg27o) by [Leon van Zyl](https://www.youtube.com/@leonvanzyl)
+- [LangChain Overview & Tutorial for Beginners: Build Powerful AI Apps Quickly & Easily (ZERO CODE)](https://youtu.be/iI84yym473Q) by [James NoCode](https://www.youtube.com/@jamesnocode)
+- [LangChain In Action: Real-World Use Case With Step-by-Step Tutorial](https://youtu.be/UO699Szp82M) by [Rabbitmetrics](https://www.youtube.com/@rabbitmetrics)
+- [Summarizing and Querying Multiple Papers with LangChain](https://youtu.be/p_MQRWH5Y6k) by [Automata Learning Lab](https://www.youtube.com/@automatalearninglab)
+- [Using Langchain (and `Replit`) through `Tana`, ask `Google`/`Wikipedia`/`Wolfram Alpha` to fill out a table](https://youtu.be/Webau9lEzoI) by [Stian Håklev](https://www.youtube.com/@StianHaklev)
+- [Langchain PDF App (GUI) | Create a ChatGPT For Your `PDF` in Python](https://youtu.be/wUAUdEw5oxM) by [Alejandro AO - Software & Ai](https://www.youtube.com/@alejandro_ao)
+- [Auto-GPT with LangChain 🔥 | Create Your Own Personal AI Assistant](https://youtu.be/imDfPmMKEjM) by [Data Science Basics](https://www.youtube.com/@datasciencebasics)
+- [Create Your OWN Slack AI Assistant with Python & LangChain](https://youtu.be/3jFXRNn2Bu8) by [Dave Ebbelaar](https://www.youtube.com/@daveebbelaar)
+- [How to Create LOCAL Chatbots with GPT4All and LangChain [Full Guide]](https://youtu.be/4p1Fojur8Zw) by [Liam Ottley](https://www.youtube.com/@LiamOttley)
+- [Build a `Multilingual PDF` Search App with LangChain, `Cohere` and `Bubble`](https://youtu.be/hOrtuumOrv8) by [Menlo Park Lab](https://www.youtube.com/@menloparklab)
+- [Building a LangChain Agent (code-free!) Using `Bubble` and `Flowise`](https://youtu.be/jDJIIVWTZDE) by [Menlo Park Lab](https://www.youtube.com/@menloparklab)
+- [Build a LangChain-based Semantic PDF Search App with No-Code Tools Bubble and Flowise](https://youtu.be/s33v5cIeqA4) by [Menlo Park Lab](https://www.youtube.com/@menloparklab)
+- [LangChain Memory Tutorial | Building a ChatGPT Clone in Python](https://youtu.be/Cwq91cj2Pnc) by [Alejandro AO - Software & Ai](https://www.youtube.com/@alejandro_ao)
+- [ChatGPT For Your DATA | Chat with Multiple Documents Using LangChain](https://youtu.be/TeDgIDqQmzs) by [Data Science Basics](https://www.youtube.com/@datasciencebasics)
+- [`Llama Index`: Chat with Documentation using URL Loader](https://youtu.be/XJRoDEctAwA) by [Merk](https://www.youtube.com/@heymichaeldaigler)
+- [Using OpenAI, LangChain, and `Gradio` to Build Custom GenAI Applications](https://youtu.be/1MsmqMg3yUc) by [David Hundley](https://www.youtube.com/@dkhundley)
+- [LangChain, Chroma DB, OpenAI Beginner Guide | ChatGPT with your PDF](https://youtu.be/FuqdVNB_8c0)
+- [Build AI chatbot with custom knowledge base using OpenAI API and GPT Index](https://youtu.be/vDZAZuaXf48) by [Irina Nik](https://www.youtube.com/@irina_nik)
+- [Build Your Own Auto-GPT Apps with LangChain (Python Tutorial)](https://youtu.be/NYSWn1ipbgg) by [Dave Ebbelaar](https://www.youtube.com/@daveebbelaar)
+- [Chat with Multiple `PDFs` | LangChain App Tutorial in Python (Free LLMs and Embeddings)](https://youtu.be/dXxQ0LR-3Hg) by [Alejandro AO - Software & Ai](https://www.youtube.com/@alejandro_ao)
+- [Chat with a `CSV` | `LangChain Agents` Tutorial (Beginners)](https://youtu.be/tjeti5vXWOU) by [Alejandro AO - Software & Ai](https://www.youtube.com/@alejandro_ao)
+- [Create Your Own ChatGPT with `PDF` Data in 5 Minutes (LangChain Tutorial)](https://youtu.be/au2WVVGUvc8) by [Liam Ottley](https://www.youtube.com/@LiamOttley)
+- [Build a Custom Chatbot with OpenAI: `GPT-Index` & LangChain | Step-by-Step Tutorial](https://youtu.be/FIDv6nc4CgU) by [Fabrikod](https://www.youtube.com/@fabrikod)
+- [`Flowise` is an open-source no-code UI visual tool to build 🦜🔗LangChain applications](https://youtu.be/CovAPtQPU0k) by [Cobus Greyling](https://www.youtube.com/@CobusGreylingZA)
+- [LangChain & GPT 4 For Data Analysis: The `Pandas` Dataframe Agent](https://youtu.be/rFQ5Kmkd4jc) by [Rabbitmetrics](https://www.youtube.com/@rabbitmetrics)
+- [`GirlfriendGPT` - AI girlfriend with LangChain](https://youtu.be/LiN3D1QZGQw) by [Girlfriend GPT](https://www.youtube.com/@girlfriendGPT)
+- [How to build with Langchain 10x easier | ⛓️ LangFlow & `Flowise`](https://youtu.be/Ya1oGL7ZTvU) by [AI Jason](https://www.youtube.com/@AIJasonZ)
+- [Getting Started With LangChain In 20 Minutes- Build Celebrity Search Application](https://youtu.be/_FpT1cwcSLg) by [Krish Naik](https://www.youtube.com/@krishnaik06)
+- ⛓ [Vector Embeddings Tutorial – Code Your Own AI Assistant with `GPT-4 API` + LangChain + NLP](https://youtu.be/yfHHvmaMkcA?si=5uJhxoh2tvdnOXok) by [FreeCodeCamp.org](https://www.youtube.com/@freecodecamp)
+- ⛓ [Fully LOCAL `Llama 2` Q&A with LangChain](https://youtu.be/wgYctKFnQ74?si=UX1F3W-B3MqF4-K-) by [1littlecoder](https://www.youtube.com/@1littlecoder)
+- ⛓ [Fully LOCAL `Llama 2` Langchain on CPU](https://youtu.be/yhECvKMu8kM?si=IvjxwlA1c09VwHZ4) by [1littlecoder](https://www.youtube.com/@1littlecoder)
+- ⛓ [Build LangChain Audio Apps with Python in 5 Minutes](https://youtu.be/7w7ysaDz2W4?si=BvdMiyHhormr2-vr) by [AssemblyAI](https://www.youtube.com/@AssemblyAI)
+- ⛓ [`Voiceflow` & `Flowise`: Want to Beat Competition? New Tutorial with Real AI Chatbot](https://youtu.be/EZKkmeFwag0?si=-4dETYDHEstiK_bb) by [AI SIMP](https://www.youtube.com/@aisimp)
+- ⛓ [THIS Is How You Build Production-Ready AI Apps (`LangSmith` Tutorial)](https://youtu.be/tFXm5ijih98?si=lfiqpyaivxHFyI94) by [Dave Ebbelaar](https://www.youtube.com/@daveebbelaar)
+- ⛓ [Build POWERFUL LLM Bots EASILY with Your Own Data - `Embedchain` - Langchain 2.0? (Tutorial)](https://youtu.be/jE24Y_GasE8?si=0yEDZt3BK5Q-LIuF) by [WorldofAI](https://www.youtube.com/@intheworldofai)
+- ⛓ [`Code Llama` powered Gradio App for Coding: Runs on CPU](https://youtu.be/AJOhV6Ryy5o?si=ouuQT6IghYlc1NEJ) by [AI Anytime](https://www.youtube.com/@AIAnytime)
+- ⛓ [LangChain Complete Course in One Video | Develop LangChain (AI) Based Solutions for Your Business](https://youtu.be/j9mQd-MyIg8?si=_wlNT3nP2LpDKztZ) by [UBprogrammer](https://www.youtube.com/@UBprogrammer)
+- ⛓ [How to Run `LLaMA` Locally on CPU or GPU | Python & Langchain & CTransformers Guide](https://youtu.be/SvjWDX2NqiM?si=DxFml8XeGhiLTzLV) by [Code With Prince](https://www.youtube.com/@CodeWithPrince)
+- ⛓ [PyData Heidelberg #11 - TimeSeries Forecasting & LLM Langchain](https://www.youtube.com/live/Glbwb5Hxu18?si=PIEY8Raq_C9PCHuW) by [PyData](https://www.youtube.com/@PyDataTV)
+- ⛓ [Prompt Engineering in Web Development | Using LangChain and Templates with OpenAI](https://youtu.be/pK6WzlTOlYw?si=fkcDQsBG2h-DM8uQ) by [Akamai Developer
+](https://www.youtube.com/@AkamaiDeveloper)
+- ⛓ [Retrieval-Augmented Generation (RAG) using LangChain and `Pinecone` - The RAG Special Episode](https://youtu.be/J_tCD_J6w3s?si=60Mnr5VD9UED9bGG) by [Generative AI and Data Science On AWS](https://www.youtube.com/@GenerativeAIOnAWS)
+- ⛓ [`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)
+- ⛓ [Build Chat PDF app in Python with LangChain, OpenAI, Streamlit | Full project | Learn Coding](https://www.youtube.com/watch?v=WYzFzZg4YZI) by [Jutsupoint](https://www.youtube.com/@JutsuPoint)
+- ⛓ [Build Eminem Bot App with LangChain, Streamlit, OpenAI | Full Python Project | Tutorial | AI ChatBot](https://www.youtube.com/watch?v=a2shHB4MRZ4) by [Jutsupoint](https://www.youtube.com/@JutsuPoint)
+
+
+### [Prompt Engineering and LangChain](https://www.youtube.com/watch?v=muXbPpG_ys4&list=PLEJK-H61Xlwzm5FYLDdKt_6yibO33zoMW) by [Venelin Valkov](https://www.youtube.com/@venelin_valkov)
+- [Getting Started with LangChain: Load Custom Data, Run OpenAI Models, Embeddings and `ChatGPT`](https://www.youtube.com/watch?v=muXbPpG_ys4)
+- [Loaders, Indexes & Vectorstores in LangChain: Question Answering on `PDF` files with `ChatGPT`](https://www.youtube.com/watch?v=FQnvfR8Dmr0)
+- [LangChain Models: `ChatGPT`, `Flan Alpaca`, `OpenAI Embeddings`, Prompt Templates & Streaming](https://www.youtube.com/watch?v=zy6LiK5F5-s)
+- [LangChain Chains: Use `ChatGPT` to Build Conversational Agents, Summaries and Q&A on Text With LLMs](https://www.youtube.com/watch?v=h1tJZQPcimM)
+- [Analyze Custom CSV Data with `GPT-4` using Langchain](https://www.youtube.com/watch?v=Ew3sGdX8at4)
+- [Build ChatGPT Chatbots with LangChain Memory: Understanding and Implementing Memory in Conversations](https://youtu.be/CyuUlf54wTs)
 
-- [Using `ChatGPT` with YOUR OWN Data. This is magical. (LangChain `OpenAI API`)](https://youtu.be/9AXP7tCI9PI)
-- [Chat with Multiple `PDFs` | LangChain App Tutorial in Python (Free LLMs and Embeddings)](https://youtu.be/dXxQ0LR-3Hg?si=pjXKhsHRzn10vOqX)
-- [`Hugging Face` + Langchain in 5 mins | Access 200k+ FREE AI models for your AI apps](https://youtu.be/_j7JEDWuqLE?si=psimQscN3qo2dOa9)
-- [LangChain Crash Course For Beginners | LangChain Tutorial](https://youtu.be/nAmC7SoVLd8?si=qJdvyG5-rnjqfdj1)
-- [Vector Embeddings Tutorial – Code Your Own AI Assistant with GPT-4 API + LangChain + NLP](https://youtu.be/yfHHvmaMkcA?si=UBP3yw50cLm3a2nj)
-- [Development with Large Language Models Tutorial – `OpenAI`, Langchain, Agents, `Chroma`](https://youtu.be/xZDB1naRUlk?si=v8J1q6oFHRyTkf7Y)
-- [Langchain: `PDF` Chat App (GUI) | ChatGPT for Your PDF FILES | Step-by-Step Tutorial](https://youtu.be/RIWbalZ7sTo?si=LbKsCcuyv0BtnrTY)
-- [Vector Search `RAG` Tutorial – Combine Your Data with LLMs with Advanced Search](https://youtu.be/JEBDfGqrAUA?si=pD7oxpfwWeJCxfBt)
-- [LangChain Crash Course for Beginners](https://youtu.be/lG7Uxts9SXs?si=Yte4S5afN7KNCw0F)
-- [Learn `RAG` From Scratch – Python AI Tutorial from a LangChain Engineer](https://youtu.be/sVcwVQRHIc8?si=_LN4g0vOgSdtlB3S)
-- [`Llama 2` in LangChain — FIRST Open Source Conversational Agent!](https://youtu.be/6iHVJyX2e50?si=rtq1maPrzWKHbwVV)
-- [LangChain Tutorial for Beginners | Generative AI Series](https://youtu.be/cQUUkZnyoD0?si=KYz-bvcocdqGh9f_)
-- [Chatbots with `RAG`: LangChain Full Walkthrough](https://youtu.be/LhnCsygAvzY?si=yS7T98VLfcWdkDek)
-- [LangChain Explained In 15 Minutes - A MUST Learn For Python Programmers](https://youtu.be/mrjq3lFz23s?si=wkQGcSKUJjuiiEPf)
-- [LLM Project | End to End LLM Project Using Langchain, `OpenAI` in Finance Domain](https://youtu.be/MoqgmWV1fm8?si=oVl-5kJVgd3a07Y_)
-- [What is LangChain?](https://youtu.be/1bUy-1hGZpI?si=NZ0D51VM5y-DhjGe)
-- [`RAG` + Langchain Python Project: Easy AI/Chat For Your Doc](https://youtu.be/tcqEUSNCn8I?si=RLcWPBVLIErRqdmU)
-- [Getting Started With LangChain In 20 Minutes- Build Celebrity Search Application](https://youtu.be/_FpT1cwcSLg?si=X9qVazlXYucN_JBP)
-- [LangChain GEN AI Tutorial – 6 End-to-End Projects using OpenAI, Google `Gemini Pro`, `LLAMA2`](https://youtu.be/x0AnCE9SE4A?si=_92gJYm7kb-V2bi0)
-- [Complete Langchain GEN AI Crash Course With 6 End To End LLM Projects With OPENAI, `LLAMA2`, `Gemini Pro`](https://youtu.be/aWKrL4z5H6w?si=NVLi7Yiq0ccE7xXE)
-- [AI Leader Reveals The Future of AI AGENTS (LangChain CEO)](https://youtu.be/9ZhbA0FHZYc?si=1r4P6kRvKVvEhRgE)
-- [Learn How To Query Pdf using Langchain Open AI in 5 min](https://youtu.be/5Ghv-F1wF_0?si=ZZRjrWfeiFOVrcvu)
-- [Reliable, fully local RAG agents with `LLaMA3`](https://youtu.be/-ROS6gfYIts?si=75CXA8W_BbnkIxcV)
-- [Learn `LangChain.js` - Build LLM apps with JavaScript and `OpenAI`](https://youtu.be/HSZ_uaif57o?si=Icj-RAhwMT-vHaYA)
-- [LLM Project | End to End LLM Project Using LangChain, Google Palm In Ed-Tech Industry](https://youtu.be/AjQPRomyd-k?si=eC3NT6kn02Lhpz-_)
-- [Chatbot Answering from Your Own Knowledge Base: Langchain, `ChatGPT`, `Pinecone`, and `Streamlit`: | Code](https://youtu.be/nAKhxQ3hcMA?si=9Zd_Nd_jiYhtml5w)
-- [LangChain is AMAZING | Quick Python Tutorial](https://youtu.be/I4mFqyqFkxg?si=aJ66qh558OfNAczD)
-- [`GirlfriendGPT` - AI girlfriend with LangChain](https://youtu.be/LiN3D1QZGQw?si=kZR-lnJwixeVrjmh)
-- [Using NEW `MPT-7B` in `Hugging Face` and LangChain](https://youtu.be/DXpk9K7DgMo?si=99JDpV_ueimwJhMi)
-- [LangChain - COMPLETE TUTORIAL - Basics to advanced concept!](https://youtu.be/a89vqgK-Qcs?si=0aVO2EOqsw7GE5e3)
-- [LangChain Agents: Simply Explained!](https://youtu.be/Xi9Ui-9qcPw?si=DCuG7nGx8dxcfhkx)
-- [Chat With Multiple `PDF` Documents With Langchain And Google `Gemini Pro`](https://youtu.be/uus5eLz6smA?si=YUwvHtaZsGeIl0WD)
-- [LLM Project | End to end LLM project Using Langchain, `Google Palm` in Retail Industry](https://youtu.be/4wtrl4hnPT8?si=_eOKPpdLfWu5UXMQ)
-- [Tutorial | Chat with any Website using Python and Langchain](https://youtu.be/bupx08ZgSFg?si=KRrjYZFnuLsstGwW)
-- [Prompt Engineering And LLM's With LangChain In One Shot-Generative AI](https://youtu.be/t2bSApmPzU4?si=87vPQQtYEWTyu2Kx)
-- [Build a Custom Chatbot with `OpenAI`: `GPT-Index` & LangChain | Step-by-Step Tutorial](https://youtu.be/FIDv6nc4CgU?si=gR1u3DUG9lvzBIKK)
-- [Search Your `PDF` App using Langchain, `ChromaDB`, and Open Source LLM: No OpenAI API (Runs on CPU)](https://youtu.be/rIV1EseKwU4?si=UxZEoXSiPai8fXgl)
-- [Building a `RAG` application from scratch using Python, LangChain, and the `OpenAI API`](https://youtu.be/BrsocJb-fAo?si=hvkh9iTGzJ-LnsX-)
-- [Function Calling via `ChatGPT API` - First Look With LangChain](https://youtu.be/0-zlUy7VUjg?si=Vc6LFseckEc6qvuk)
-- [Private GPT, free deployment! Langchain-Chachat helps you easily play with major mainstream AI models! | Zero Degree Commentary](https://youtu.be/3LLUyaHP-3I?si=AZumEeFXsvqaLl0f)
-- [Create a ChatGPT clone using `Streamlit` and LangChain](https://youtu.be/IaTiyQ2oYUQ?si=WbgsYmqPDnMidSUK)
-- [What's next for AI agents ft. LangChain's Harrison Chase](https://youtu.be/pBBe1pk8hf4?si=H4vdBF9nmkNZxiHt)
-- [`LangFlow`: Build Chatbots without Writing Code - LangChain](https://youtu.be/KJ-ux3hre4s?si=TJuDu4bAlva1myNL)
-- [Building a LangChain Custom Medical Agent with Memory](https://youtu.be/6UFtRwWnHws?si=wymYad26VgigRkHy)
-- [`Ollama` meets LangChain](https://youtu.be/k_1pOF1mj8k?si=RlBiCrmaR3s7SnMK)
-- [End To End LLM Langchain Project using `Pinecone` Vector Database](https://youtu.be/erUfLIi9OFM?si=aHpuHXdIEmAfS4eF)
-- [`LLaMA2` with LangChain - Basics | LangChain TUTORIAL](https://youtu.be/cIRzwSXB4Rc?si=FUs0OLVJpzKhut0h)
-- [Understanding `ReACT` with LangChain](https://youtu.be/Eug2clsLtFs?si=imgj534ggxlypS0d)
 
 ---------------------
-[Updated 2024-05-16]
+⛓ icon marks a new addition [last update 2024-02-04]

docs/docs/changelog/core.mdx

@@ -1,10 +1,27 @@
 # langchain-core
 
-## 0.1.x
+## 0.1.7 (Jan 5, 2024)
+
+#### Deleted
+
+No deletions.
 
 #### Deprecated
 
 - `BaseChatModel` methods `__call__`, `call_as_llm`, `predict`, `predict_messages`. Will be removed in 0.2.0. Use `BaseChatModel.invoke` instead.
 - `BaseChatModel` methods `apredict`, `apredict_messages`. Will be removed in 0.2.0. Use `BaseChatModel.ainvoke` instead.
 - `BaseLLM` methods `__call__, `predict`, `predict_messages`. Will be removed in 0.2.0. Use `BaseLLM.invoke` instead.
-- `BaseLLM` methods `apredict`, `apredict_messages`. Will be removed in 0.2.0. Use `BaseLLM.ainvoke` instead.
+- `BaseLLM` methods `apredict`, `apredict_messages`. Will be removed in 0.2.0. Use `BaseLLM.ainvoke` instead.
+
+#### Fixed
+
+- Restrict recursive URL scraping: [#15559](https://github.com/langchain-ai/langchain/pull/15559)
+
+#### Added
+
+No additions.
+
+#### Beta
+
+- Marked `langchain_core.load.load` and `langchain_core.load.loads` as beta.
+- Marked `langchain_core.beta.runnables.context.ContextGet` and `langchain_core.beta.runnables.context.ContextSet` as beta.

docs/docs/changelog/langchain.mdx

@@ -1,73 +1,16 @@
 # langchain
 
-## 0.2.0
-
-### Deleted
-
-As of release 0.2.0, `langchain` is required to be integration-agnostic. This means that code in `langchain`  should not by default instantiate any specific chat models, llms, embedding models, vectorstores etc; instead, the user will be required to specify those explicitly.
-
-The following functions and classes require an explicit LLM to be passed as an argument:
-
-- `langchain.agents.agent_toolkits.vectorstore.toolkit.VectorStoreToolkit`
-- `langchain.agents.agent_toolkits.vectorstore.toolkit.VectorStoreRouterToolkit`
-- `langchain.chains.openai_functions.get_openapi_chain`
-- `langchain.chains.router.MultiRetrievalQAChain.from_retrievers`
-- `langchain.indexes.VectorStoreIndexWrapper.query`
-- `langchain.indexes.VectorStoreIndexWrapper.query_with_sources`
-- `langchain.indexes.VectorStoreIndexWrapper.aquery_with_sources`
-- `langchain.chains.flare.FlareChain`
-
-The following classes now require passing an explicit Embedding model as an argument:
-
-- `langchain.indexes.VectostoreIndexCreator`
-
-The following code has been removed:
-
-- `langchain.natbot.NatBotChain.from_default` removed in favor of the `from_llm` class method.
-
-### Deprecated
-
-We have two main types of deprecations:
-
-1. Code that was moved from `langchain` into another package (e.g, `langchain-community`)
-
-If you try to import it from `langchain`, the import will keep on working, but will raise a deprecation warning. The warning will provide a replacement import statement.
-
-```python
-python -c "from langchain.document_loaders.markdown import UnstructuredMarkdownLoader"
-
-```
-
-```python
-LangChainDeprecationWarning: Importing UnstructuredMarkdownLoader from langchain.document_loaders is deprecated. Please replace deprecated imports:
-
->> from langchain.document_loaders import UnstructuredMarkdownLoader
-
-with new imports of:
-
->> from langchain_community.document_loaders import UnstructuredMarkdownLoader
-```
-
-We will continue supporting the imports in `langchain` until release 0.4 as long as the relevant package where the code lives is installed. (e.g., as long as `langchain_community` is installed.)
-
-However, we advise for users to not rely on these imports and instead migrate to the new imports. To help with this process, we’re releasing a migration script via the LangChain CLI. See further instructions in migration guide.
-
-1. Code that has better alternatives available and will eventually be removed, so there’s only a single way to do things. (e.g., `predict_messages` method in ChatModels has been deprecated in favor of `invoke`).
-
-Many of these were marked for removal in 0.2. We have bumped the removal to 0.3.
-
-
 ## 0.1.0 (Jan 5, 2024)
 
-### Deleted
+#### Deleted
 
 No deletions.
 
-### Deprecated
+#### Deprecated
 
 Deprecated classes and methods will be removed in 0.2.0
 
-| Deprecated                      | Alternative                       | Reason                                         |
+| Deprecated                | Alternative                       | Reason                                         |
 |---------------------------------|-----------------------------------|------------------------------------------------|
 | ChatVectorDBChain               | ConversationalRetrievalChain      | More general to all retrievers                 |
 | create_ernie_fn_chain           | create_ernie_fn_runnable          | Use LCEL under the hood                        |

docs/docs/concepts.mdx

@@ -1,907 +0,0 @@
-# Conceptual guide
-
-import ThemedImage from '@theme/ThemedImage';
-import useBaseUrl from '@docusaurus/useBaseUrl';
-
-This section contains introductions to key parts of LangChain.
-
-## Architecture
-
-LangChain as a framework consists of a number of packages.
-
-### `langchain-core`
-This package contains base abstractions of different components and ways to compose them together.
-The interfaces for core components like LLMs, vectorstores, retrievers and more are defined here.
-No third party integrations are defined here.
-The dependencies are kept purposefully very lightweight.
-
-### Partner packages
-
-While the long tail of integrations are in `langchain-community`, we split popular integrations into their own packages (e.g. `langchain-openai`, `langchain-anthropic`, etc).
-This was done in order to improve support for these important integrations.
-
-### `langchain`
-
-The main `langchain` package contains chains, agents, and retrieval strategies that make up an application's cognitive architecture.
-These are NOT third party integrations.
-All chains, agents, and retrieval strategies here are NOT specific to any one integration, but rather generic across all integrations.
-
-### `langchain-community`
-
-This package contains third party integrations that are maintained by the LangChain community.
-Key partner packages are separated out (see below).
-This contains all integrations for various components (LLMs, vectorstores, retrievers).
-All dependencies in this package are optional to keep the package as lightweight as possible.
-
-### [`langgraph`](https://langchain-ai.github.io/langgraph)
-
-`langgraph` is an extension of `langchain` aimed at
-building robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph.
-
-LangGraph exposes high level interfaces for creating common types of agents, as well as a low-level API for composing custom flows.
-
-### [`langserve`](/docs/langserve)
-
-A package to deploy LangChain chains as REST APIs. Makes it easy to get a production ready API up and running.
-
-### [LangSmith](https://docs.smith.langchain.com)
-
-A developer platform that lets you debug, test, evaluate, and monitor LLM applications.
-
-<ThemedImage
-  alt="Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers."
-  sources={{
-    light: useBaseUrl('/svg/langchain_stack.svg'),
-    dark: useBaseUrl('/svg/langchain_stack_dark.svg'),
-  }}
-  title="LangChain Framework Overview"
-/>
-
-## LangChain Expression Language (LCEL)
-<span data-heading-keywords="lcel"></span>
-
-LangChain Expression Language, or LCEL, is a declarative way to chain LangChain components.
-LCEL was designed from day 1 to **support putting prototypes in production, with no code changes**, from the simplest “prompt + LLM” chain to the most complex chains (we’ve seen folks successfully run LCEL chains with 100s of steps in production). To highlight a few of the reasons you might want to use LCEL:
-
-**First-class streaming support**
-When you build your chains with LCEL you get the best possible time-to-first-token (time elapsed until the first chunk of output comes out). For some chains this means eg. we stream tokens straight from an LLM to a streaming output parser, and you get back parsed, incremental chunks of output at the same rate as the LLM provider outputs the raw tokens.
-
-**Async support**
-Any chain built with LCEL can be called both with the synchronous API (eg. in your Jupyter notebook while prototyping) as well as with the asynchronous API (eg. in a [LangServe](/docs/langserve/) server). This enables using the same code for prototypes and in production, with great performance, and the ability to handle many concurrent requests in the same server.
-
-**Optimized parallel execution**
-Whenever your LCEL chains have steps that can be executed in parallel (eg if you fetch documents from multiple retrievers) we automatically do it, both in the sync and the async interfaces, for the smallest possible latency.
-
-**Retries and fallbacks**
-Configure retries and fallbacks for any part of your LCEL chain. This is a great way to make your chains more reliable at scale. We’re currently working on adding streaming support for retries/fallbacks, so you can get the added reliability without any latency cost.
-
-**Access intermediate results**
-For more complex chains it’s often very useful to access the results of intermediate steps even before the final output is produced. This can be used to let end-users know something is happening, or even just to debug your chain. You can stream intermediate results, and it’s available on every [LangServe](/docs/langserve) server.
-
-**Input and output schemas**
-Input and output schemas give every LCEL chain Pydantic and JSONSchema schemas inferred from the structure of your chain. This can be used for validation of inputs and outputs, and is an integral part of LangServe.
-
-[**Seamless LangSmith tracing**](https://docs.smith.langchain.com)
-As your chains get more and more complex, it becomes increasingly important to understand what exactly is happening at every step.
-With LCEL, **all** steps are automatically logged to [LangSmith](https://docs.smith.langchain.com/) for maximum observability and debuggability.
-
-[**Seamless LangServe deployment**](/docs/langserve)
-Any chain created with LCEL can be easily deployed using [LangServe](/docs/langserve).
-
-### Runnable interface
-<span data-heading-keywords="invoke"></span>
-
-To make it as easy as possible to create custom chains, we've implemented a ["Runnable"](https://api.python.langchain.com/en/stable/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable) protocol. Many LangChain components implement the `Runnable` protocol, including chat models, LLMs, output parsers, retrievers, prompt templates, and more. There are also several useful primitives for working with runnables, which you can read about below.
-
-This is a standard interface, which makes it easy to define custom chains as well as invoke them in a standard way.
-The standard interface includes:
-
-- `stream`: stream back chunks of the response
-- `invoke`: call the chain on an input
-- `batch`: call the chain on a list of inputs
-
-These also have corresponding async methods that should be used with [asyncio](https://docs.python.org/3/library/asyncio.html) `await` syntax for concurrency:
-
-- `astream`: stream back chunks of the response async
-- `ainvoke`: call the chain on an input async
-- `abatch`: call the chain on a list of inputs async
-- `astream_log`: stream back intermediate steps as they happen, in addition to the final response
-- `astream_events`: **beta** stream events as they happen in the chain (introduced in `langchain-core` 0.1.14)
-
-The **input type** and **output type** varies by component:
-
-| Component | Input Type | Output Type |
-| --- | --- | --- |
-| Prompt | Dictionary | PromptValue |
-| ChatModel | Single string, list of chat messages or a PromptValue | ChatMessage |
-| LLM | Single string, list of chat messages or a PromptValue | String |
-| OutputParser | The output of an LLM or ChatModel | Depends on the parser |
-| Retriever | Single string | List of Documents |
-| Tool | Single string or dictionary, depending on the tool | Depends on the tool |
-
-
-All runnables expose input and output **schemas** to inspect the inputs and outputs:
-- `input_schema`: an input Pydantic model auto-generated from the structure of the Runnable
-- `output_schema`: an output Pydantic model auto-generated from the structure of the Runnable
-
-## Components
-
-LangChain provides standard, extendable interfaces and external integrations for various components useful for building with LLMs.
-Some components LangChain implements, some components we rely on third-party integrations for, and others are a mix.
-
-### Chat models
-<span data-heading-keywords="chat model,chat models"></span>
-
-Language models that use a sequence of messages as inputs and return chat messages as outputs (as opposed to using plain text).
-These are traditionally newer models (older models are generally `LLMs`, see below).
-Chat models support the assignment of distinct roles to conversation messages, helping to distinguish messages from the AI, users, and instructions such as system messages.
-
-Although the underlying models are messages in, message out, the LangChain wrappers also allow these models to take a string as input. This means you can easily use chat models in place of LLMs.
-
-When a string is passed in as input, it is converted to a `HumanMessage` and then passed to the underlying model.
-
-LangChain does not host any Chat Models, rather we rely on third party integrations.
-
-We have some standardized parameters when constructing ChatModels:
-- `model`: the name of the model
-
-ChatModels also accept other parameters that are specific to that integration.
-
-:::important
-**Tool Calling** Some chat models have been fine-tuned for tool calling and provide a dedicated API for tool calling.
-Generally, such models are better at tool calling than non-fine-tuned models, and are recommended for use cases that require tool calling.
-Please see the [tool calling section](/docs/concepts/#functiontool-calling) for more information.
-:::
-
-For specifics on how to use chat models, see the [relevant how-to guides here](/docs/how_to/#chat-models).
-
-#### Multimodality
-
-Some chat models are multimodal, accepting images, audio and even video as inputs. These are still less common, meaning model providers haven't standardized on the "best" way to define the API. Multimodal **outputs** are even less common. As such, we've kept our multimodal abstractions fairly light weight and plan to further solidify the multimodal APIs and interaction patterns as the field matures.
-
-In LangChain, most chat models that support multimodal inputs also accept those values in OpenAI's content blocks format. So far this is restricted to image inputs. For models like Gemini which support video and other bytes input, the APIs also support the native, model-specific representations.
-
-For specifics on how to use multimodal models, see the [relevant how-to guides here](/docs/how_to/#multimodal).
-
-For a full list of LangChain model providers with multimodal models, [check out this table](/docs/integrations/chat/#advanced-features).
-
-### LLMs
-<span data-heading-keywords="llm,llms"></span>
-
-Language models that takes a string as input and returns a string.
-These are traditionally older models (newer models generally are [Chat Models](/docs/concepts/#chat-models), see below).
-
-Although the underlying models are string in, string out, the LangChain wrappers also allow these models to take messages as input.
-This gives them the same interface as [Chat Models](/docs/concepts/#chat-models).
-When messages are passed in as input, they will be formatted into a string under the hood before being passed to the underlying model.
-
-LangChain does not host any LLMs, rather we rely on third party integrations.
-
-For specifics on how to use LLMs, see the [relevant how-to guides here](/docs/how_to/#llms).
-
-### Messages
-
-Some language models take a list of messages as input and return a message.
-There are a few different types of messages.
-All messages have a `role`, `content`, and `response_metadata` property.
-
-The `role` describes WHO is saying the message.
-LangChain has different message classes for different roles.
-
-The `content` property describes the content of the message.
-This can be a few different things:
-
-- A string (most models deal this type of content)
-- A List of dictionaries (this is used for multimodal input, where the dictionary contains information about that input type and that input location)
-
-#### HumanMessage
-
-This represents a message from the user.
-
-#### AIMessage
-
-This represents a message from the model. In addition to the `content` property, these messages also have:
-
-**`response_metadata`**
-
-The `response_metadata` property contains additional metadata about the response. The data here is often specific to each model provider.
-This is where information like log-probs and token usage may be stored.
-
-**`tool_calls`**
-
-These represent a decision from an language model to call a tool. They are included as part of an `AIMessage` output.
-They can be accessed from there with the `.tool_calls` property.
-
-This property returns a list of dictionaries. Each dictionary has the following keys:
-
-- `name`: The name of the tool that should be called.
-- `args`: The arguments to that tool.
-- `id`: The id of that tool call.
-
-#### SystemMessage
-
-This represents a system message, which tells the model how to behave. Not every model provider supports this.
-
-#### FunctionMessage
-
-This represents the result of a function call. In addition to `role` and `content`, this message has a `name` parameter which conveys the name of the function that was called to produce this result.
-
-#### ToolMessage
-
-This represents the result of a tool call. This is distinct from a FunctionMessage in order to match OpenAI's `function` and `tool` message types. In addition to `role` and `content`, this message has a `tool_call_id` parameter which conveys the id of the call to the tool that was called to produce this result.
-
-
-### Prompt templates
-<span data-heading-keywords="prompt,prompttemplate,chatprompttemplate"></span>
-
-Prompt templates help to translate user input and parameters into instructions for a language model.
-This can be used to guide a model's response, helping it understand the context and generate relevant and coherent language-based output.
-
-Prompt Templates take as input a dictionary, where each key represents a variable in the prompt template to fill in.
-
-Prompt Templates output a PromptValue. This PromptValue can be passed to an LLM or a ChatModel, and can also be cast to a string or a list of messages.
-The reason this PromptValue exists is to make it easy to switch between strings and messages.
-
-There are a few different types of prompt templates:
-
-#### String PromptTemplates
-
-These prompt templates are used to format a single string, and generally are used for simpler inputs.
-For example, a common way to construct and use a PromptTemplate is as follows:
-
-```python
-from langchain_core.prompts import PromptTemplate
-
-prompt_template = PromptTemplate.from_template("Tell me a joke about {topic}")
-
-prompt_template.invoke({"topic": "cats"})
-```
-
-#### ChatPromptTemplates
-
-These prompt templates are used to format a list of messages. These "templates" consist of a list of templates themselves.
-For example, a common way to construct and use a ChatPromptTemplate is as follows:
-
-```python
-from langchain_core.prompts import ChatPromptTemplate
-
-prompt_template = ChatPromptTemplate.from_messages([
-    ("system", "You are a helpful assistant"),
-    ("user", "Tell me a joke about {topic}")
-])
-
-prompt_template.invoke({"topic": "cats"})
-```
-
-In the above example, this ChatPromptTemplate will construct two messages when called.
-The first is a system message, that has no variables to format.
-The second is a HumanMessage, and will be formatted by the `topic` variable the user passes in.
-
-#### MessagesPlaceholder
-<span data-heading-keywords="messagesplaceholder"></span>
-
-This prompt template is responsible for adding a list of messages in a particular place.
-In the above ChatPromptTemplate, we saw how we could format two messages, each one a string.
-But what if we wanted the user to pass in a list of messages that we would slot into a particular spot?
-This is how you use MessagesPlaceholder.
-
-```python
-from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
-from langchain_core.messages import HumanMessage
-
-prompt_template = ChatPromptTemplate.from_messages([
-    ("system", "You are a helpful assistant"),
-    MessagesPlaceholder("msgs")
-])
-
-prompt_template.invoke({"msgs": [HumanMessage(content="hi!")]})
-```
-
-This will produce a list of two messages, the first one being a system message, and the second one being the HumanMessage we passed in.
-If we had passed in 5 messages, then it would have produced 6 messages in total (the system message plus the 5 passed in).
-This is useful for letting a list of messages be slotted into a particular spot.
-
-An alternative way to accomplish the same thing without using the `MessagesPlaceholder` class explicitly is:
-
-```python
-prompt_template = ChatPromptTemplate.from_messages([
-    ("system", "You are a helpful assistant"),
-    ("placeholder", "{msgs}") # <-- This is the changed part
-])
-```
-
-For specifics on how to use prompt templates, see the [relevant how-to guides here](/docs/how_to/#prompt-templates).
-
-### Example selectors
-One common prompting technique for achieving better performance is to include examples as part of the prompt.
-This gives the language model concrete examples of how it should behave.
-Sometimes these examples are hardcoded into the prompt, but for more advanced situations it may be nice to dynamically select them.
-Example Selectors are classes responsible for selecting and then formatting examples into prompts.
-
-For specifics on how to use example selectors, see the [relevant how-to guides here](/docs/how_to/#example-selectors).
-
-### Output parsers
-<span data-heading-keywords="output parser"></span>
-
-:::note
-
-The information here refers to parsers that take a text output from a model try to parse it into a more structured representation.
-More and more models are supporting function (or tool) calling, which handles this automatically.
-It is recommended to use function/tool calling rather than output parsing.
-See documentation for that [here](/docs/concepts/#function-tool-calling).
-
-:::
-
-Responsible for taking the output of a model and transforming it to a more suitable format for downstream tasks.
-Useful when you are using LLMs to generate structured data, or to normalize output from chat models and LLMs.
-
-LangChain has lots of different types of output parsers. This is a list of output parsers LangChain supports. The table below has various pieces of information:
-
-**Name**: The name of the output parser
-
-**Supports Streaming**: Whether the output parser supports streaming.
-
-**Has Format Instructions**: Whether the output parser has format instructions. This is generally available except when (a) the desired schema is not specified in the prompt but rather in other parameters (like OpenAI function calling), or (b) when the OutputParser wraps another OutputParser.
-
-**Calls LLM**: Whether this output parser itself calls an LLM. This is usually only done by output parsers that attempt to correct misformatted output.
-
-**Input Type**: Expected input type. Most output parsers work on both strings and messages, but some (like OpenAI Functions) need a message with specific kwargs.
-
-**Output Type**: The output type of the object returned by the parser.
-
-**Description**: Our commentary on this output parser and when to use it.
-
-| Name            | Supports Streaming | Has Format Instructions       | Calls LLM | Input Type                       | Output Type          | Description                                                                                                                                                                                                                                              |
-|-----------------|--------------------|-------------------------------|-----------|----------------------------------|----------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| [JSON](https://api.python.langchain.com/en/latest/output_parsers/langchain_core.output_parsers.json.JsonOutputParser.html#langchain_core.output_parsers.json.JsonOutputParser)            | ✅                  | ✅                             |           | `str` \| `Message`               | JSON object          | Returns a JSON object as specified. You can specify a Pydantic model and it will return JSON for that model. Probably the most reliable output parser for getting structured data that does NOT use function calling.                                    |
-| [XML](https://api.python.langchain.com/en/latest/output_parsers/langchain_core.output_parsers.xml.XMLOutputParser.html#langchain_core.output_parsers.xml.XMLOutputParser)            | ✅                  | ✅                             |           | `str` \| `Message`                 | `dict`               | Returns a dictionary of tags. Use when XML output is needed. Use with models that are good at writing XML (like Anthropic's).                                                                                                                            |
-| [CSV](https://api.python.langchain.com/en/latest/output_parsers/langchain_core.output_parsers.list.CommaSeparatedListOutputParser.html#langchain_core.output_parsers.list.CommaSeparatedListOutputParser)           | ✅                  | ✅                             |           | `str` \| `Message`                 | `List[str]`          | Returns a list of comma separated values.                                                                                                                                                                                                                |
-| [OutputFixing](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.fix.OutputFixingParser.html#langchain.output_parsers.fix.OutputFixingParser)    |                    |                               | ✅         | `str` \| `Message`                 |                      | Wraps another output parser. If that output parser errors, then this will pass the error message and the bad output to an LLM and ask it to fix the output.                                                                                              |
-| [RetryWithError](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.retry.RetryWithErrorOutputParser.html#langchain.output_parsers.retry.RetryWithErrorOutputParser)  |                    |                               | ✅         | `str` \| `Message`                 |                      | Wraps another output parser. If that output parser errors, then this will pass the original inputs, the bad output, and the error message to an LLM and ask it to fix it. Compared to OutputFixingParser, this one also sends the original instructions. |
-| [Pydantic](https://api.python.langchain.com/en/latest/output_parsers/langchain_core.output_parsers.pydantic.PydanticOutputParser.html#langchain_core.output_parsers.pydantic.PydanticOutputParser)        |                    | ✅                             |           | `str` \| `Message`                 | `pydantic.BaseModel` | Takes a user defined Pydantic model and returns data in that format.                                                                                                                                                                                     |
-| [YAML](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.yaml.YamlOutputParser.html#langchain.output_parsers.yaml.YamlOutputParser)        |                    | ✅                             |           | `str` \| `Message`                 | `pydantic.BaseModel` | Takes a user defined Pydantic model and returns data in that format. Uses YAML to encode it.                                                                                                                                                                                    |
-| [PandasDataFrame](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.pandas_dataframe.PandasDataFrameOutputParser.html#langchain.output_parsers.pandas_dataframe.PandasDataFrameOutputParser) |                    | ✅                             |           | `str` \| `Message`                 | `dict`               | Useful for doing operations with pandas DataFrames.                                                                                                                                                                                                      |
-| [Enum](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.enum.EnumOutputParser.html#langchain.output_parsers.enum.EnumOutputParser)            |                    | ✅                             |           | `str` \| `Message`                 | `Enum`               | Parses response into one of the provided enum values.                                                                                                                                                                                                    |
-| [Datetime](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.datetime.DatetimeOutputParser.html#langchain.output_parsers.datetime.DatetimeOutputParser)        |                    | ✅                             |           | `str` \| `Message`                 | `datetime.datetime`  | Parses response into a datetime string.                                                                                                                                                                                                                  |
-| [Structured](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.structured.StructuredOutputParser.html#langchain.output_parsers.structured.StructuredOutputParser)      |                    | ✅                             |           | `str` \| `Message`                 | `Dict[str, str]`     | An output parser that returns structured information. It is less powerful than other output parsers since it only allows for fields to be strings. This can be useful when you are working with smaller LLMs.                                            |
-
-For specifics on how to use output parsers, see the [relevant how-to guides here](/docs/how_to/#output-parsers).
-
-### Chat history
-Most LLM applications have a conversational interface.
-An essential component of a conversation is being able to refer to information introduced earlier in the conversation.
-At bare minimum, a conversational system should be able to access some window of past messages directly.
-
-The concept of `ChatHistory` refers to a class in LangChain which can be used to wrap an arbitrary chain.
-This `ChatHistory` will keep track of inputs and outputs of the underlying chain, and append them as messages to a message database.
-Future interactions will then load those messages and pass them into the chain as part of the input.
-
-### Documents
-<span data-heading-keywords="document,documents"></span>
-
-A Document object in LangChain contains information about some data. It has two attributes:
-
-- `page_content: str`: The content of this document. Currently is only a string.
-- `metadata: dict`: Arbitrary metadata associated with this document. Can track the document id, file name, etc.
-
-### Document loaders
-<span data-heading-keywords="document loader,document loaders"></span>
-
-These classes load Document objects. LangChain has hundreds of integrations with various data sources to load data from: Slack, Notion, Google Drive, etc.
-
-Each DocumentLoader has its own specific parameters, but they can all be invoked in the same way with the `.load` method.
-An example use case is as follows:
-
-```python
-from langchain_community.document_loaders.csv_loader import CSVLoader
-
-loader = CSVLoader(
-    ...  # <-- Integration specific parameters here
-)
-data = loader.load()
-```
-
-For specifics on how to use document loaders, see the [relevant how-to guides here](/docs/how_to/#document-loaders).
-
-### Text splitters
-
-Once you've loaded documents, you'll often want to transform them to better suit your application. The simplest example is you may want to split a long document into smaller chunks that can fit into your model's context window. LangChain has a number of built-in document transformers that make it easy to split, combine, filter, and otherwise manipulate documents.
-
-When you want to deal with long pieces of text, it is necessary to split up that text into chunks. As simple as this sounds, there is a lot of potential complexity here. Ideally, you want to keep the semantically related pieces of text together. What "semantically related" means could depend on the type of text. This notebook showcases several ways to do that.
-
-At a high level, text splitters work as following:
-
-1. Split the text up into small, semantically meaningful chunks (often sentences).
-2. Start combining these small chunks into a larger chunk until you reach a certain size (as measured by some function).
-3. Once you reach that size, make that chunk its own piece of text and then start creating a new chunk of text with some overlap (to keep context between chunks).
-
-That means there are two different axes along which you can customize your text splitter:
-
-1. How the text is split
-2. How the chunk size is measured
-
-For specifics on how to use text splitters, see the [relevant how-to guides here](/docs/how_to/#text-splitters).
-
-### Embedding models
-<span data-heading-keywords="embedding,embeddings"></span>
-
-The Embeddings class is a class designed for interfacing with text embedding models. There are lots of embedding model providers (OpenAI, Cohere, Hugging Face, etc) - this class is designed to provide a standard interface for all of them.
-
-Embeddings create a vector representation of a piece of text. This is useful because it means we can think about text in the vector space, and do things like semantic search where we look for pieces of text that are most similar in the vector space.
-
-The base Embeddings class in LangChain provides two methods: one for embedding documents and one for embedding a query. The former takes as input multiple texts, while the latter takes a single text. The reason for having these as two separate methods is that some embedding providers have different embedding methods for documents (to be searched over) vs queries (the search query itself).
-
-For specifics on how to use embedding models, see the [relevant how-to guides here](/docs/how_to/#embedding-models).
-
-### Vector stores
-<span data-heading-keywords="vector,vectorstore,vectorstores,vector store,vector stores"></span>
-
-One of the most common ways to store and search over unstructured data is to embed it and store the resulting embedding vectors,
-and then at query time to embed the unstructured query and retrieve the embedding vectors that are 'most similar' to the embedded query.
-A vector store takes care of storing embedded data and performing vector search for you.
-
-Vector stores can be converted to the retriever interface by doing:
-
-```python
-vectorstore = MyVectorStore()
-retriever = vectorstore.as_retriever()
-```
-
-For specifics on how to use vector stores, see the [relevant how-to guides here](/docs/how_to/#vector-stores).
-
-### Retrievers
-<span data-heading-keywords="retriever,retrievers"></span>
-
-A retriever is an interface that returns documents given an unstructured query.
-It is more general than a vector store.
-A retriever does not need to be able to store documents, only to return (or retrieve) them.
-Retrievers can be created from vectorstores, but are also broad enough to include [Wikipedia search](/docs/integrations/retrievers/wikipedia/) and [Amazon Kendra](/docs/integrations/retrievers/amazon_kendra_retriever/).
-
-Retrievers accept a string query as input and return a list of Document's as output.
-
-For specifics on how to use retrievers, see the [relevant how-to guides here](/docs/how_to/#retrievers).
-
-### Tools
-<span data-heading-keywords="tool,tools"></span>
-
-Tools are interfaces that an agent, a chain, or a chat model / LLM can use to interact with the world.
-
-A tool consists of the following components:
-
-1. The name of the tool
-2. A description of what the tool does
-3. JSON schema of what the inputs to the tool are
-4. The function to call
-5. Whether the result of a tool should be returned directly to the user (only relevant for agents)
-
-The name, description and JSON schema are provided as context
-to the LLM, allowing the LLM to determine how to use the tool
-appropriately.
-
-Given a list of available tools and a prompt, an LLM can request
-that one or more tools be invoked with appropriate arguments.
-
-Generally, when designing tools to be used by a chat model or LLM, it is important to keep in mind the following:
-
-- Chat models that have been fine-tuned for tool calling will be better at tool calling than non-fine-tuned models.
-- Non fine-tuned models may not be able to use tools at all, especially if the tools are complex or require multiple tool calls.
-- Models will perform better if the tools have well-chosen names, descriptions, and JSON schemas.
-- Simpler tools are generally easier for models to use than more complex tools.
-
-For specifics on how to use tools, see the [relevant how-to guides here](/docs/how_to/#tools).
-
-### Toolkits
-
-Toolkits are collections of tools that are designed to be used together for specific tasks. They have convenient loading methods.
-
-All Toolkits expose a `get_tools` method which returns a list of tools.
-You can therefore do:
-
-```python
-# Initialize a toolkit
-toolkit = ExampleTookit(...)
-
-# Get list of tools
-tools = toolkit.get_tools()
-```
-
-### Agents
-
-By themselves, language models can't take actions - they just output text.
-A big use case for LangChain is creating **agents**.
-Agents are systems that use an LLM as a reasoning engine to determine which actions to take and what the inputs to those actions should be.
-The results of those actions can then be fed back into the agent and it determine whether more actions are needed, or whether it is okay to finish.
-
-[LangGraph](https://github.com/langchain-ai/langgraph) is an extension of LangChain specifically aimed at creating highly controllable and customizable agents.
-Please check out that documentation for a more in depth overview of agent concepts.
-
-There is a legacy agent concept in LangChain that we are moving towards deprecating: `AgentExecutor`.
-AgentExecutor was essentially a runtime for agents.
-It was a great place to get started, however, it was not flexible enough as you started to have more customized agents.
-In order to solve that we built LangGraph to be this flexible, highly-controllable runtime.
-
-If you are still using AgentExecutor, do not fear: we still have a guide on [how to use AgentExecutor](/docs/how_to/agent_executor).
-It is recommended, however, that you start to transition to LangGraph.
-In order to assist in this we have put together a [transition guide on how to do so](/docs/how_to/migrate_agent).
-
-### Callbacks
-
-LangChain provides a callbacks system that allows you to hook into the various stages of your LLM application. This is useful for logging, monitoring, streaming, and other tasks.
-
-You can subscribe to these events by using the `callbacks` argument available throughout the API. This argument is list of handler objects, which are expected to implement one or more of the methods described below in more detail.
-
-#### Callback Events
-
-| Event            | Event Trigger                               | Associated Method     |
-|------------------|---------------------------------------------|-----------------------|
-| Chat model start | When a chat model starts                    | `on_chat_model_start` |
-| LLM start        | When a llm starts                           | `on_llm_start`        |
-| LLM new token    | When an llm OR chat model emits a new token | `on_llm_new_token`    |
-| LLM ends         | When an llm OR chat model ends              | `on_llm_end`          |
-| LLM errors       | When an llm OR chat model errors            | `on_llm_error`        |
-| Chain start      | When a chain starts running                 | `on_chain_start`      |
-| Chain end        | When a chain ends                           | `on_chain_end`        |
-| Chain error      | When a chain errors                         | `on_chain_error`      |
-| Tool start       | When a tool starts running                  | `on_tool_start`       |
-| Tool end         | When a tool ends                            | `on_tool_end`         |
-| Tool error       | When a tool errors                          | `on_tool_error`       |
-| Agent action     | When an agent takes an action               | `on_agent_action`     |
-| Agent finish     | When an agent ends                          | `on_agent_finish`     |
-| Retriever start  | When a retriever starts                     | `on_retriever_start`  |
-| Retriever end    | When a retriever ends                       | `on_retriever_end`    |
-| Retriever error  | When a retriever errors                     | `on_retriever_error`  |
-| Text             | When arbitrary text is run                  | `on_text`             |
-| Retry            | When a retry event is run                   | `on_retry`            |
-
-#### Callback handlers
-
-Callback handlers can either be `sync` or `async`:
-
-* Sync callback handlers implement the [BaseCallbackHandler](https://api.python.langchain.com/en/latest/callbacks/langchain_core.callbacks.base.BaseCallbackHandler.html) interface.
-* Async callback handlers implement the [AsyncCallbackHandler](https://api.python.langchain.com/en/latest/callbacks/langchain_core.callbacks.base.AsyncCallbackHandler.html) interface.
-
-During run-time LangChain configures an appropriate callback manager (e.g., [CallbackManager](https://api.python.langchain.com/en/latest/callbacks/langchain_core.callbacks.manager.CallbackManager.html) or [AsyncCallbackManager](https://api.python.langchain.com/en/latest/callbacks/langchain_core.callbacks.manager.AsyncCallbackManager.html) which will be responsible for calling the appropriate method on each "registered" callback handler when the event is triggered.
-
-#### Passing callbacks
-
-The `callbacks` property is available on most objects throughout the API (Models, Tools, Agents, etc.) in two different places:
-
-The callbacks are available on most objects throughout the API (Models, Tools, Agents, etc.) in two different places:
-
-- **Request time callbacks**: Passed at the time of the request in addition to the input data.
-    Available on all standard `Runnable` objects. These callbacks are INHERITED by all children
-    of the object they are defined on. For example, `chain.invoke({"number": 25}, {"callbacks": [handler]})`.
-- **Constructor callbacks**: `chain = TheNameOfSomeChain(callbacks=[handler])`. These callbacks
-    are passed as arguments to the constructor of the object. The callbacks are scoped
-    only to the object they are defined on, and are **not** inherited by any children of the object.
-
-:::warning
-Constructor callbacks are scoped only to the object they are defined on. They are **not** inherited by children
-of the object.
-:::
-
-If you're creating a custom chain or runnable, you need to remember to propagate request time
-callbacks to any child objects.
-
-:::important Async in Python<=3.10
-
-Any `RunnableLambda`, a `RunnableGenerator`, or `Tool` that invokes other runnables
-and is running async in python<=3.10, will have to propagate callbacks to child
-objects manually. This is because LangChain cannot automatically propagate
-callbacks to child objects in this case.
-
-This is a common reason why you may fail to see events being emitted from custom
-runnables or tools.
-:::
-
-For specifics on how to use callbacks, see the [relevant how-to guides here](/docs/how_to/#callbacks).
-
-## Techniques
-
-### Streaming
-
-Individual LLM calls often run for much longer than traditional resource requests.
-This compounds when you build more complex chains or agents that require multiple reasoning steps.
-
-Fortunately, LLMs generate output iteratively, which means it's possible to show sensible intermediate results
-before the final response is ready. Consuming output as soon as it becomes available has therefore become a vital part of the UX
-around building apps with LLMs to help alleviate latency issues, and LangChain aims to have first-class support for streaming.
-
-Below, we'll discuss some concepts and considerations around streaming in LangChain.
-
-#### Tokens
-
-The unit that most model providers use to measure input and output is via a unit called a **token**.
-Tokens are the basic units that language models read and generate when processing or producing text.
-The exact definition of a token can vary depending on the specific way the model was trained -
-for instance, in English, a token could be a single word like "apple", or a part of a word like "app".
-
-When you send a model a prompt, the words and characters in the prompt are encoded into tokens using a **tokenizer**.
-The model then streams back generated output tokens, which the tokenizer decodes into human-readable text.
-The below example shows how OpenAI models tokenize `LangChain is cool!`:
-
-![](/img/tokenization.png)
-
-You can see that it gets split into 5 different tokens, and that the boundaries between tokens are not exactly the same as word boundaries.
-
-The reason language models use tokens rather than something more immediately intuitive like "characters"
-has to do with how they process and understand text. At a high-level, language models iteratively predict their next generated output based on
-the initial input and their previous generations. Training the model using tokens language models to handle linguistic
-units (like words or subwords) that carry meaning, rather than individual characters, which makes it easier for the model
-to learn and understand the structure of the language, including grammar and context.
-Furthermore, using tokens can also improve efficiency, since the model processes fewer units of text compared to character-level processing.
-
-#### Callbacks
-
-The lowest level way to stream outputs from LLMs in LangChain is via the [callbacks](/docs/concepts/#callbacks) system. You can pass a
-callback handler that handles the [`on_llm_new_token`](https://api.python.langchain.com/en/latest/callbacks/langchain.callbacks.streaming_aiter.AsyncIteratorCallbackHandler.html#langchain.callbacks.streaming_aiter.AsyncIteratorCallbackHandler.on_llm_new_token) event into LangChain components. When that component is invoked, any
-[LLM](/docs/concepts/#llms) or [chat model](/docs/concepts/#chat-models) contained in the component calls
-the callback with the generated token. Within the callback, you could pipe the tokens into some other destination, e.g. a HTTP response.
-You can also handle the [`on_llm_end`](https://api.python.langchain.com/en/latest/callbacks/langchain.callbacks.streaming_aiter.AsyncIteratorCallbackHandler.html#langchain.callbacks.streaming_aiter.AsyncIteratorCallbackHandler.on_llm_end) event to perform any necessary cleanup.
-
-You can see [this how-to section](/docs/how_to/#callbacks) for more specifics on using callbacks.
-
-Callbacks were the first technique for streaming introduced in LangChain. While powerful and generalizable,
-they can be unwieldy for developers. For example:
-
-- You need to explicitly initialize and manage some aggregator or other stream to collect results.
-- The execution order isn't explicitly guaranteed, and you could theoretically have a callback run after the `.invoke()` method finishes.
-- Providers would often make you pass an additional parameter to stream outputs instead of returning them all at once.
-- You would often ignore the result of the actual model call in favor of callback results.
-
-#### `.stream()` and `.astream()`
-
-LangChain also includes the `.stream()` method (and the equivalent `.astream()` method for [async](https://docs.python.org/3/library/asyncio.html) environments) as a more ergonomic streaming interface.
-`.stream()` returns an iterator, which you can consume with a simple `for` loop. Here's an example with a chat model:
-
-```python
-from langchain_anthropic import ChatAnthropic
-
-model = ChatAnthropic(model="claude-3-sonnet-20240229")
-
-for chunk in model.stream("what color is the sky?"):
-    print(chunk.content, end="|", flush=True)
-```
-
-For models (or other components) that don't support streaming natively, this iterator would just yield a single chunk, but
-you could still use the same general pattern. Using `.stream()` will also automatically call the model in streaming mode
-without the need to provide additional config.
-
-The type of each outputted chunk depends on the type of component - for example, chat models yield [`AIMessageChunks`](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessageChunk.html).
-Because this method is part of [LangChain Expression Language](/docs/concepts/#langchain-expression-language-lcel),
-you can handle formatting differences from different outputs using an [output parser](/docs/concepts/#output-parsers) to transform
-each yielded chunk.
-
-You can check out [this guide](/docs/how_to/streaming/#using-stream) for more detail on how to use `.stream()`.
-
-#### `.astream_events()`
-
-While the `.stream()` method is easier to use than callbacks, it only returns one type of value. This is fine for single LLM calls,
-but as you build more complex chains of several LLM calls together, you may want to use the intermediate values of
-the chain alongside the final output - for example, returning sources alongside the final generation when building a chat
-over documents app.
-
-There are ways to do this using the aforementioned callbacks, or by constructing your chain in such a way that it passes intermediate
-values to the end with something like [`.assign()`](/docs/how_to/passthrough/), but LangChain also includes an
-`.astream_events()` method that combines the flexibility of callbacks with the ergonomics of `.stream()`. When called, it returns an iterator
-which yields [various types of events](/docs/how_to/streaming/#event-reference) that you can filter and process according
-to the needs of your project.
-
-Here's one small example that prints just events containing streamed chat model output:
-
-```python
-from langchain_core.output_parsers import StrOutputParser
-from langchain_core.prompts import ChatPromptTemplate
-from langchain_anthropic import ChatAnthropic
-
-model = ChatAnthropic(model="claude-3-sonnet-20240229")
-
-prompt = ChatPromptTemplate.from_template("tell me a joke about {topic}")
-parser = StrOutputParser()
-chain = prompt | model | parser
-
-async for event in chain.astream_events({"topic": "parrot"}, version="v2"):
-    kind = event["event"]
-    if kind == "on_chat_model_stream":
-        print(event, end="|", flush=True)
-```
-
-You can roughly think of it as an iterator over callback events (though the format differs) - and you can use it on almost all LangChain components!
-
-See [this guide](/docs/how_to/streaming/#using-stream-events) for more detailed information on how to use `.astream_events()`.
-
-### Structured output
-
-LLMs are capable of generating arbitrary text. This enables the model to respond appropriately to a wide
-range of inputs, but for some use-cases, it can be useful to constrain the LLM's output
-to a specific format or structure. This is referred to as **structured output**.
-
-For example, if the output is to be stored in a relational database,
-it is much easier if the model generates output that adheres to a defined schema or format.
-[Extracting specific information](/docs/tutorials/extraction/) from unstructured text is another
-case where this is particularly useful. Most commonly, the output format will be JSON,
-though other formats such as [YAML](/docs/how_to/output_parser_yaml/) can be useful too. Below, we'll discuss
-a few ways to get structured output from models in LangChain.
-
-#### `.with_structured_output()`
-
-For convenience, some LangChain chat models support a `.with_structured_output()` method.
-This method only requires a schema as input, and returns a dict or Pydantic object.
-Generally, this method is only present on models that support one of the more advanced methods described below,
-and will use one of them under the hood. It takes care of importing a suitable output parser and
-formatting the schema in the right format for the model.
-
-For more information, check out this [how-to guide](/docs/how_to/structured_output/#the-with_structured_output-method).
-
-#### Raw prompting
-
-The most intuitive way to get a model to structure output is to ask nicely.
-In addition to your query, you can give instructions describing what kind of output you'd like, then
-parse the output using an [output parser](/docs/concepts/#output-parsers) to convert the raw
-model message or string output into something more easily manipulated.
-
-The biggest benefit to raw prompting is its flexibility:
-
-- Raw prompting does not require any special model features, only sufficient reasoning capability to understand
-the passed schema.
-- You can prompt for any format you'd like, not just JSON. This can be useful if the model you
-are using is more heavily trained on a certain type of data, such as XML or YAML.
-
-However, there are some drawbacks too:
-
-- LLMs are non-deterministic, and prompting a LLM to consistently output data in the exactly correct format
-for smooth parsing can be surprisingly difficult and model-specific.
-- Individual models have quirks depending on the data they were trained on, and optimizing prompts can be quite difficult.
-Some may be better at interpreting [JSON schema](https://json-schema.org/), others may be best with TypeScript definitions,
-and still others may prefer XML.
-
-While we'll next go over some ways that you can take advantage of features offered by
-model providers to increase reliability, prompting techniques remain important for tuning your
-results no matter what method you choose.
-
-#### JSON mode
-<span data-heading-keywords="json mode"></span>
-
-Some models, such as [Mistral](/docs/integrations/chat/mistralai/), [OpenAI](/docs/integrations/chat/openai/),
-[Together AI](/docs/integrations/chat/together/) and [Ollama](/docs/integrations/chat/ollama/),
-support a feature called **JSON mode**, usually enabled via config.
-
-When enabled, JSON mode will constrain the model's output to always be some sort of valid JSON.
-Often they require some custom prompting, but it's usually much less burdensome and along the lines of,
-`"you must always return JSON"`, and the [output is easier to parse](/docs/how_to/output_parser_json/).
-
-It's also generally simpler and more commonly available than tool calling.
-
-Here's an example:
-
-```python
-from langchain_core.prompts import ChatPromptTemplate
-from langchain_openai import ChatOpenAI
-from langchain.output_parsers.json import SimpleJsonOutputParser
-
-model = ChatOpenAI(
-    model="gpt-4o",
-    model_kwargs={ "response_format": { "type": "json_object" } },
-)
-
-prompt = ChatPromptTemplate.from_template(
-    "Answer the user's question to the best of your ability."
-    'You must always output a JSON object with an "answer" key and a "followup_question" key.'
-    "{question}"
-)
-
-chain = prompt | model | SimpleJsonOutputParser()
-
-chain.invoke({ "question": "What is the powerhouse of the cell?" })
-```
-
-```
-{'answer': 'The powerhouse of the cell is the mitochondrion. It is responsible for producing energy in the form of ATP through cellular respiration.',
- 'followup_question': 'Would you like to know more about how mitochondria produce energy?'}
-```
-
-For a full list of model providers that support JSON mode, see [this table](/docs/integrations/chat/#advanced-features).
-
-#### Function/tool calling
-
-:::info
-We use the term tool calling interchangeably with function calling. Although
-function calling is sometimes meant to refer to invocations of a single function,
-we treat all models as though they can return multiple tool or function calls in
-each message.
-:::
-
-Tool calling allows a model to respond to a given prompt by generating output that
-matches a user-defined schema. While the name implies that the model is performing
-some action, this is actually not the case! The model is coming up with the
-arguments to a tool, and actually running the tool (or not) is up to the user -
-for example, if you want to [extract output matching some schema](/docs/tutorials/extraction)
-from unstructured text, you could give the model an "extraction" tool that takes
-parameters matching the desired schema, then treat the generated output as your final
-result.
-
-For models that support it, tool calling can be very convenient. It removes the
-guesswork around how best to prompt schemas in favor of a built-in model feature. It can also
-more naturally support agentic flows, since you can just pass multiple tool schemas instead
-of fiddling with enums or unions.
-
-Many LLM providers, including [Anthropic](https://www.anthropic.com/),
-[Cohere](https://cohere.com/), [Google](https://cloud.google.com/vertex-ai),
-[Mistral](https://mistral.ai/), [OpenAI](https://openai.com/), and others,
-support variants of a tool calling feature. These features typically allow requests
-to the LLM to include available tools and their schemas, and for responses to include
-calls to these tools. For instance, given a search engine tool, an LLM might handle a
-query by first issuing a call to the search engine. The system calling the LLM can
-receive the tool call, execute it, and return the output to the LLM to inform its
-response. LangChain includes a suite of [built-in tools](/docs/integrations/tools/)
-and supports several methods for defining your own [custom tools](/docs/how_to/custom_tools).
-
-LangChain provides a standardized interface for tool calling that is consistent across different models.
-
-The standard interface consists of:
-
-* `ChatModel.bind_tools()`: a method for specifying which tools are available for a model to call. This method accepts [LangChain tools](/docs/concepts/#tools) here.
-* `AIMessage.tool_calls`: an attribute on the `AIMessage` returned from the model for accessing the tool calls requested by the model.
-
-The following how-to guides are good practical resources for using function/tool calling:
-
-- [How to return structured data from an LLM](/docs/how_to/structured_output/)
-- [How to use a model to call tools](/docs/how_to/tool_calling/)
-
-For a full list of model providers that support tool calling, [see this table](/docs/integrations/chat/#advanced-features).
-
-### Retrieval
-
-LangChain provides several advanced retrieval types. A full list is below, along with the following information:
-
-**Name**: Name of the retrieval algorithm.
-
-**Index Type**: Which index type (if any) this relies on.
-
-**Uses an LLM**: Whether this retrieval method uses an LLM.
-
-**When to Use**: Our commentary on when you should considering using this retrieval method.
-
-**Description**: Description of what this retrieval algorithm is doing.
-
-| Name                      | Index Type                   | Uses an LLM               | When to Use                                                                                                                                   | Description                                                                                                                                                                                                                                                                                      |
-|---------------------------|------------------------------|---------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| [Vectorstore](/docs/how_to/vectorstore_retriever/)               | Vectorstore                  | No                        | If you are just getting started and looking for something quick and easy.                                                                     | This is the simplest method and the one that is easiest to get started with. It involves creating embeddings for each piece of text.                                                                                                                                                             |
-| [ParentDocument](/docs/how_to/parent_document_retriever/)            | Vectorstore + Document Store | No                        | If your pages have lots of smaller pieces of distinct information that are best indexed by themselves, but best retrieved all together.       | This involves indexing multiple chunks for each document. Then you find the chunks that are most similar in embedding space, but you retrieve the whole parent document and return that (rather than individual chunks).                                                                         |
-| [Multi Vector](/docs/how_to/multi_vector/)              | Vectorstore + Document Store | Sometimes during indexing | If you are able to extract information from documents that you think is more relevant to index than the text itself.                          | This involves creating multiple vectors for each document. Each vector could be created in a myriad of ways - examples include summaries of the text and hypothetical questions.                                                                                                                 |
-| [Self Query](/docs/how_to/self_query/)               | Vectorstore                  | Yes                       | If users are asking questions that are better answered by fetching documents based on metadata rather than similarity with the text.          | This uses an LLM to transform user input into two things: (1) a string to look up semantically, (2) a metadata filer to go along with it. This is useful because oftentimes questions are about the METADATA of documents (not the content itself).                                              |
-| [Contextual Compression](/docs/how_to/contextual_compression/)    | Any                          | Sometimes                 | If you are finding that your retrieved documents contain too much irrelevant information and are distracting the LLM.                         | This puts a post-processing step on top of another retriever and extracts only the most relevant information from retrieved documents. This can be done with embeddings or an LLM.                                                                                                               |
-| [Time-Weighted Vectorstore](/docs/how_to/time_weighted_vectorstore/) | Vectorstore                  | No                        | If you have timestamps associated with your documents, and you want to retrieve the most recent ones                                          | This fetches documents based on a combination of semantic similarity (as in normal vector retrieval) and recency (looking at timestamps of indexed documents)                                                                                                                                    |
-| [Multi-Query Retriever](/docs/how_to/MultiQueryRetriever/)     | Any                          | Yes                       | If users are asking questions that are complex and require multiple pieces of distinct information to respond                                 | This uses an LLM to generate multiple queries from the original one. This is useful when the original query needs pieces of information about multiple topics to be properly answered. By generating multiple queries, we can then fetch documents for each of them.                             |
-| [Ensemble](/docs/how_to/ensemble_retriever/)                  | Any                          | No                        | If you have multiple retrieval methods and want to try combining them.                                                                        | This fetches documents from multiple retrievers and then combines them.                                                                                                                                                                                                                          |
-
-For a high-level guide on retrieval, see this [tutorial on RAG](/docs/tutorials/rag/).
-
-### Text splitting
-
-LangChain offers many different types of `text splitters`.
-These all live in the `langchain-text-splitters` package.
-
-Table columns:
-
-- **Name**: Name of the text splitter
-- **Classes**: Classes that implement this text splitter
-- **Splits On**: How this text splitter splits text
-- **Adds Metadata**: Whether or not this text splitter adds metadata about where each chunk came from.
-- **Description**: Description of the splitter, including recommendation on when to use it.
-
-
-| Name     | Classes                                                                                                                                                                                                             | Splits On                                                   | Adds Metadata | Description                                                                                                                                                                                                                                                                  |
-|----------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------|---------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| Recursive | [RecursiveCharacterTextSplitter](/docs/how_to/recursive_text_splitter/), [RecursiveJsonSplitter](/docs/how_to/recursive_json_splitter/) | A list of user defined characters     |               | Recursively splits text. This splitting is trying to keep related pieces of text next to each other. This is the `recommended way` to start splitting text.                                                                                                                    |
-| HTML      | [HTMLHeaderTextSplitter](/docs/how_to/HTML_header_metadata_splitter/), [HTMLSectionSplitter](/docs/how_to/HTML_section_aware_splitter/)          | HTML specific characters                                                                                                 | ✅             | Splits text based on HTML-specific characters. Notably, this adds in relevant information about where that chunk came from (based on the HTML)                                                                                                                               |
-| Markdown  | [MarkdownHeaderTextSplitter](/docs/how_to/markdown_header_metadata_splitter/),                                                                                                           | Markdown specific characters                                                                                    | ✅             | Splits text based on Markdown-specific characters. Notably, this adds in relevant information about where that chunk came from (based on the Markdown)                                                                                                                       |
-| Code      | [many languages](/docs/how_to/code_splitter/)                                                                                                                                 | Code (Python, JS) specific characters                                                                           |               | Splits text based on characters specific to coding languages. 15 different languages are available to choose from.                                                                                                                                                           |
-| Token    | [many classes](/docs/how_to/split_by_token/)                                                                                                                                  | Tokens                                                                                                          |               | Splits text on tokens. There exist a few different ways to measure tokens.                                                                                                                                                                                                   |
-| Character  | [CharacterTextSplitter](/docs/how_to/character_text_splitter/)                                                                                                                | A user defined character                                                                                        |               | Splits text based on a user defined character. One of the simpler methods.                                                                                                                                                                                                   |
-| Semantic Chunker (Experimental) | [SemanticChunker](/docs/how_to/semantic-chunker/)                                                                                                                             | Sentences                                                                                                       |               | First splits on sentences. Then combines ones next to each other if they are semantically similar enough. Taken from [Greg Kamradt](https://github.com/FullStackRetrieval-com/RetrievalTutorials/blob/main/tutorials/LevelsOfTextSplitting/5_Levels_Of_Text_Splitting.ipynb) |
-| Integration: AI21 Semantic | [AI21SemanticTextSplitter](/docs/integrations/document_transformers/ai21_semantic_text_splitter/)                                                                                                                    |    ✅           | Identifies distinct topics that form coherent pieces of text and splits along those.                                                                                                                                                                                         |
-
-
-
-

docs/docs/contributing/code.mdx

@@ -206,7 +206,9 @@ ignore-words-list = 'momento,collison,ned,foor,reworkd,parth,whats,aapply,mysogy
 
 `langchain-core` and partner packages **do not use** optional dependencies in this way.
 
-You'll notice that `pyproject.toml` and `poetry.lock` are **not** touched when you add optional dependencies below.
+You only need to add a new dependency if a **unit test** relies on the package.
+If your package is only required for **integration tests**, then you can skip these
+steps and leave all pyproject.toml and poetry.lock files alone.
 
 If you're adding a new dependency to Langchain, assume that it will be an optional dependency, and
 that most users won't have it installed.
@@ -214,12 +216,20 @@ that most users won't have it installed.
 Users who do not have the dependency installed should be able to **import** your code without
 any side effects (no warnings, no errors, no exceptions).
 
-To introduce the dependency to a library, please do the following:
+To introduce the dependency to the pyproject.toml file correctly, please do the following:
 
-1. Open extended_testing_deps.txt and add the dependency
-2. Add a unit test that the very least attempts to import the new code. Ideally, the unit
+1. Add the dependency to the main group as an optional dependency
+  ```bash
+  poetry add --optional [package_name]
+  ```
+2. Open pyproject.toml and add the dependency to the `extended_testing` extra
+3. Relock the poetry file to update the extra.
+  ```bash
+  poetry lock --no-update
+  ```
+4. Add a unit test that the very least attempts to import the new code. Ideally, the unit
 test makes use of lightweight fixtures to test the logic of the code.
-3. Please use the `@pytest.mark.requires(package_name)` decorator for any unit tests that require the dependency.
+5. Please use the `@pytest.mark.requires(package_name)` decorator for any tests that require the dependency.
 
 ## Adding a Jupyter Notebook
 

docs/docs/contributing/documentation/style_guide.mdx

@@ -16,15 +16,15 @@ LangChain's documentation aspires to follow the [Diataxis framework](https://dia
 Under this framework, all documentation falls under one of four categories:
 
 - **Tutorials**: Lessons that take the reader by the hand through a series of conceptual steps to complete a project.
-  - An example of this is our [LCEL streaming guide](/docs/how_to/streaming).
-  - Our guides on [custom components](/docs/how_to/custom_chat_model) is another one.
+  - An example of this is our [LCEL streaming guide](/docs/expression_language/streaming).
+  - Our guides on [custom components](/docs/modules/model_io/chat/custom_chat_model) is another one.
 - **How-to guides**: Guides that take the reader through the steps required to solve a real-world problem.
-  - The clearest examples of this are our [Use case](/docs/how_to#use-cases) quickstart pages.
+  - The clearest examples of this are our [Use case](/docs/use_cases/) quickstart pages.
 - **Reference**: Technical descriptions of the machinery and how to operate it.
-  - Our [Runnable interface](/docs/concepts#interface) page is an example of this.
+  - Our [Runnable interface](/docs/expression_language/interface) page is an example of this.
   - The [API reference pages](https://api.python.langchain.com/) are another.
 - **Explanation**: Explanations that clarify and illuminate a particular topic.
-  - The [LCEL primitives pages](/docs/how_to/sequence) are an example of this.
+  - The [LCEL primitives pages](/docs/expression_language/primitives/sequence) are an example of this.
 
 Each category serves a distinct purpose and requires a specific approach to writing and structuring the content.
 
@@ -35,14 +35,14 @@ when contributing new documentation:
 
 ### Getting started
 
-The [getting started section](/docs/introduction) includes a high-level introduction to LangChain, a quickstart that
+The [getting started section](/docs/get_started/introduction) includes a high-level introduction to LangChain, a quickstart that
 tours LangChain's various features, and logistical instructions around installation and project setup.
 
 It contains elements of **How-to guides** and **Explanations**.
 
 ### Use cases
 
-[Use cases](/docs/how_to#use-cases) are guides that are meant to show how to use LangChain to accomplish a specific task (RAG, information extraction, etc.).
+[Use cases](/docs/use_cases/) are guides that are meant to show how to use LangChain to accomplish a specific task (RAG, information extraction, etc.).
 The quickstarts should be good entrypoints for first-time LangChain developers who prefer to learn by getting something practical prototyped,
 then taking the pieces apart retrospectively. These should mirror what LangChain is good at.
 
@@ -55,7 +55,7 @@ The below sections are listed roughly in order of increasing level of abstractio
 
 ### Expression Language
 
-[LangChain Expression Language (LCEL)](/docs/concepts#langchain-expression-language-lcel) is the fundamental way that most LangChain components fit together, and this section is designed to teach
+[LangChain Expression Language (LCEL)](/docs/expression_language/) is the fundamental way that most LangChain components fit together, and this section is designed to teach
 developers how to use it to build with LangChain's primitives effectively.
 
 This section should contains **Tutorials** that teach how to stream and use LCEL primitives for more abstract tasks, **Explanations** of specific behaviors,
@@ -63,7 +63,7 @@ and some **References** for how to use different methods in the Runnable interfa
 
 ### Components
 
-The [components section](/docs/concepts) covers concepts one level of abstraction higher than LCEL.
+The [components section](/docs/modules) covers concepts one level of abstraction higher than LCEL.
 Abstract base classes like `BaseChatModel` and `BaseRetriever` should be covered here, as well as core implementations of these base classes,
 such as `ChatPromptTemplate` and `RecursiveCharacterTextSplitter`. Customization guides belong here too.
 
@@ -88,7 +88,7 @@ Concepts covered in `Integrations` should generally exist in `langchain_communit
 
 ### Guides and Ecosystem
 
-The [Guides](/docs/tutorials) and [Ecosystem](https://docs.smith.langchain.com/) sections should contain guides that address higher-level problems than the sections above.
+The [Guides](/docs/guides) and [Ecosystem](/docs/langsmith/) sections should contain guides that address higher-level problems than the sections above.
 This includes, but is not limited to, considerations around productionization and development workflows.
 
 These should contain mostly **How-to guides**, **Explanations**, and **Tutorials**.
@@ -102,7 +102,7 @@ LangChain's API references. Should act as **References** (as the name implies) w
 We have set up our docs to assist a new developer to LangChain. Let's walk through the intended path:
 
 - The developer lands on https://python.langchain.com, and reads through the introduction and the diagram.
-- If they are just curious, they may be drawn to the [Quickstart](/docs/tutorials/llm_chain) to get a high-level tour of what LangChain contains.
+- If they are just curious, they may be drawn to the [Quickstart](/docs/get_started/quickstart) to get a high-level tour of what LangChain contains.
 - If they have a specific task in mind that they want to accomplish, they will be drawn to the Use-Case section. The use-case should provide a good, concrete hook that shows the value LangChain can provide them and be a good entrypoint to the framework.
 - They can then move to learn more about the fundamentals of LangChain through the Expression Language sections.
 - Next, they can learn about LangChain's various components and integrations.

docs/docs/contributing/documentation/technical_logistics.mdx

@@ -71,8 +71,6 @@ make docs_clean
 make api_docs_clean
 ```
 
-
-
 Next, you can build the documentation as outlined below:
 
 ```bash
@@ -80,18 +78,6 @@ make docs_build
 make api_docs_build
 ```
 
-:::tip
-
-The `make api_docs_build` command takes a long time. If you're making cosmetic changes to the API docs and want to see how they look, use:
-
-```bash
-make api_docs_quick_preview
-```
-
-which will just build a small subset of the API reference.
-
-:::
-
 Finally, run the link checker to ensure all links are valid:
 
 ```bash

docs/docs/contributing/index.mdx

@@ -48,7 +48,7 @@ In a similar vein, we do enforce certain linting, formatting, and documentation
 If you are finding these difficult (or even just annoying) to work with, feel free to contact a maintainer for help -
 we do not want these to get in the way of getting good code into the codebase.
 
-### 🌟 Recognition
+# 🌟 Recognition
 
 If your contribution has made its way into a release, we will want to give you credit on Twitter (only if you want though)!
-If you have a Twitter account you would like us to mention, please let us know in the PR or through another means.
+If you have a Twitter account you would like us to mention, please let us know in the PR or through another means.

docs/docs/contributing/integrations.mdx

@@ -190,9 +190,12 @@ Maintainer steps (Contributors should **not** do these):
 
 ## Partner package in external repo
 
-Partner packages in external repos must be coordinated between the LangChain team and
-the partner organization to ensure that they are maintained and updated.
+If you are creating a partner package in an external repo, you should follow the same steps as above, 
+but you will need to set up your own CI/CD and package management.
 
-If you're interested in creating a partner package in an external repo, please start
-with one in the LangChain repo, and then reach out to the LangChain team to discuss
-how to move it to an external repo.
+Name your package as `langchain-{partner}-{integration}`.
+
+Still, you have to create the `libs/partners/{partner}-{integration}` folder in the `LangChain` monorepo
+and add a `README.md` file with a link to the external repo. 
+See this [example](https://github.com/langchain-ai/langchain/tree/master/libs/partners/google-genai).
+This allows keeping track of all the partner packages in the `LangChain` documentation.

docs/docs/contributing/repo_structure.mdx

@@ -6,7 +6,7 @@ sidebar_position: 0.5
 If you plan on contributing to LangChain code or documentation, it can be useful
 to understand the high level structure of the repository.
 
-LangChain is organized as a [monorepo](https://en.wikipedia.org/wiki/Monorepo) that contains multiple packages.
+LangChain is organized as a [monorep](https://en.wikipedia.org/wiki/Monorepo) that contains multiple packages.
 
 Here's the structure visualized as a tree:
 
@@ -15,22 +15,12 @@ Here's the structure visualized as a tree:
 ├── cookbook # Tutorials and examples
 ├── docs # Contains content for the documentation here: https://python.langchain.com/
 ├── libs
-│   ├── langchain
-│   │   ├── langchain
+│   ├── langchain # Main package
 │   │   ├── tests/unit_tests # Unit tests (present in each package not shown for brevity)
 │   │   ├── tests/integration_tests # Integration tests (present in each package not shown for brevity)
-│   ├── community # Third-party integrations
-│   │   ├── langchain-community
-│   ├── core # Base interfaces for key abstractions
-│   │   ├── langchain-core
-│   ├── experimental # Experimental components and chains
-│   │   ├── langchain-experimental
-|   ├── cli # Command line interface
-│   │   ├── langchain-cli
-│   ├── text-splitters
-│   │   ├── langchain-text-splitters
-│   ├── standard-tests
-│   │   ├── langchain-standard-tests
+│   ├── langchain-community # Third-party integrations
+│   ├── langchain-core # Base interfaces for key abstractions
+│   ├── langchain-experimental # Experimental components and chains
 │   ├── partners
 │       ├── langchain-partner-1
 │       ├── langchain-partner-2

docs/docs/expression_language/cookbook/code_writing.ipynb

@@ -0,0 +1,139 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "1e997ab7",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_class_name: hidden\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f09fd305",
+   "metadata": {},
+   "source": [
+    "# Code writing\n",
+    "\n",
+    "Example of how to use LCEL to write Python code."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0653c7c7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet  langchain-core langchain-experimental langchain-openai"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "bd7c259a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import (\n",
+    "    ChatPromptTemplate,\n",
+    ")\n",
+    "from langchain_experimental.utilities import PythonREPL\n",
+    "from langchain_openai import ChatOpenAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "73795d2d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "template = \"\"\"Write some python code to solve the user's problem. \n",
+    "\n",
+    "Return only python code in Markdown format, e.g.:\n",
+    "\n",
+    "```python\n",
+    "....\n",
+    "```\"\"\"\n",
+    "prompt = ChatPromptTemplate.from_messages([(\"system\", template), (\"human\", \"{input}\")])\n",
+    "\n",
+    "model = ChatOpenAI()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "42859e8a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def _sanitize_output(text: str):\n",
+    "    _, after = text.split(\"```python\")\n",
+    "    return after.split(\"```\")[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "5ded1a86",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = prompt | model | StrOutputParser() | _sanitize_output | PythonREPL().run"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "208c2b75",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Python REPL can execute arbitrary code. Use with caution.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'4\\n'"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"input\": \"whats 2 plus 2\"})"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/expression_language/cookbook/multiple_chains.ipynb

@@ -0,0 +1,267 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "877102d1-02ea-4fa3-8ec7-a08e242b95b3",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_position: 2\n",
+    "title: Multiple chains\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0f2bf8d3",
+   "metadata": {},
+   "source": [
+    "Runnables can easily be used to string together multiple Chains"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "id": "0f316b5c",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet  langchain langchain-openai"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "d65d4e9e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'El país donde se encuentra la ciudad de Honolulu, donde nació Barack Obama, el 44º Presidente de los Estados Unidos, es Estados Unidos. Honolulu se encuentra en la isla de Oahu, en el estado de Hawái.'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from operator import itemgetter\n",
+    "\n",
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "prompt1 = ChatPromptTemplate.from_template(\"what is the city {person} is from?\")\n",
+    "prompt2 = ChatPromptTemplate.from_template(\n",
+    "    \"what country is the city {city} in? respond in {language}\"\n",
+    ")\n",
+    "\n",
+    "model = ChatOpenAI()\n",
+    "\n",
+    "chain1 = prompt1 | model | StrOutputParser()\n",
+    "\n",
+    "chain2 = (\n",
+    "    {\"city\": chain1, \"language\": itemgetter(\"language\")}\n",
+    "    | prompt2\n",
+    "    | model\n",
+    "    | StrOutputParser()\n",
+    ")\n",
+    "\n",
+    "chain2.invoke({\"person\": \"obama\", \"language\": \"spanish\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "878f8176",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "\n",
+    "prompt1 = ChatPromptTemplate.from_template(\n",
+    "    \"generate a {attribute} color. Return the name of the color and nothing else:\"\n",
+    ")\n",
+    "prompt2 = ChatPromptTemplate.from_template(\n",
+    "    \"what is a fruit of color: {color}. Return the name of the fruit and nothing else:\"\n",
+    ")\n",
+    "prompt3 = ChatPromptTemplate.from_template(\n",
+    "    \"what is a country with a flag that has the color: {color}. Return the name of the country and nothing else:\"\n",
+    ")\n",
+    "prompt4 = ChatPromptTemplate.from_template(\n",
+    "    \"What is the color of {fruit} and the flag of {country}?\"\n",
+    ")\n",
+    "\n",
+    "model_parser = model | StrOutputParser()\n",
+    "\n",
+    "color_generator = (\n",
+    "    {\"attribute\": RunnablePassthrough()} | prompt1 | {\"color\": model_parser}\n",
+    ")\n",
+    "color_to_fruit = prompt2 | model_parser\n",
+    "color_to_country = prompt3 | model_parser\n",
+    "question_generator = (\n",
+    "    color_generator | {\"fruit\": color_to_fruit, \"country\": color_to_country} | prompt4\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "d621a870",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "ChatPromptValue(messages=[HumanMessage(content='What is the color of strawberry and the flag of China?', additional_kwargs={}, example=False)])"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "question_generator.invoke(\"warm\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "b4a9812b-bead-4fd9-ae27-0b8be57e5dc1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='The color of an apple is typically red or green. The flag of China is predominantly red with a large yellow star in the upper left corner and four smaller yellow stars surrounding it.', additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "prompt = question_generator.invoke(\"warm\")\n",
+    "model.invoke(prompt)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6d75a313-f1c8-4e94-9a17-24e0bf4a2bdc",
+   "metadata": {},
+   "source": [
+    "### Branching and Merging\n",
+    "\n",
+    "You may want the output of one component to be processed by 2 or more other components. [RunnableParallels](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.RunnableParallel.html#langchain_core.runnables.base.RunnableParallel) let you split or fork the chain so multiple components can process the input in parallel. Later, other components can join or merge the results to synthesize a final response. This type of chain creates a computation graph that looks like the following:\n",
+    "\n",
+    "```text\n",
+    "     Input\n",
+    "      / \\\n",
+    "     /   \\\n",
+    " Branch1 Branch2\n",
+    "     \\   /\n",
+    "      \\ /\n",
+    "      Combine\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "247fa0bd-4596-4063-8cb3-1d7fc119d982",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "planner = (\n",
+    "    ChatPromptTemplate.from_template(\"Generate an argument about: {input}\")\n",
+    "    | ChatOpenAI()\n",
+    "    | StrOutputParser()\n",
+    "    | {\"base_response\": RunnablePassthrough()}\n",
+    ")\n",
+    "\n",
+    "arguments_for = (\n",
+    "    ChatPromptTemplate.from_template(\n",
+    "        \"List the pros or positive aspects of {base_response}\"\n",
+    "    )\n",
+    "    | ChatOpenAI()\n",
+    "    | StrOutputParser()\n",
+    ")\n",
+    "arguments_against = (\n",
+    "    ChatPromptTemplate.from_template(\n",
+    "        \"List the cons or negative aspects of {base_response}\"\n",
+    "    )\n",
+    "    | ChatOpenAI()\n",
+    "    | StrOutputParser()\n",
+    ")\n",
+    "\n",
+    "final_responder = (\n",
+    "    ChatPromptTemplate.from_messages(\n",
+    "        [\n",
+    "            (\"ai\", \"{original_response}\"),\n",
+    "            (\"human\", \"Pros:\\n{results_1}\\n\\nCons:\\n{results_2}\"),\n",
+    "            (\"system\", \"Generate a final response given the critique\"),\n",
+    "        ]\n",
+    "    )\n",
+    "    | ChatOpenAI()\n",
+    "    | StrOutputParser()\n",
+    ")\n",
+    "\n",
+    "chain = (\n",
+    "    planner\n",
+    "    | {\n",
+    "        \"results_1\": arguments_for,\n",
+    "        \"results_2\": arguments_against,\n",
+    "        \"original_response\": itemgetter(\"base_response\"),\n",
+    "    }\n",
+    "    | final_responder\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "2564f310-0674-4bb1-9c4e-d7848ca73511",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'While Scrum has its potential cons and challenges, many organizations have successfully embraced and implemented this project management framework to great effect. The cons mentioned above can be mitigated or overcome with proper training, support, and a commitment to continuous improvement. It is also important to note that not all cons may be applicable to every organization or project.\\n\\nFor example, while Scrum may be complex initially, with proper training and guidance, teams can quickly grasp the concepts and practices. The lack of predictability can be mitigated by implementing techniques such as velocity tracking and release planning. The limited documentation can be addressed by maintaining a balance between lightweight documentation and clear communication among team members. The dependency on team collaboration can be improved through effective communication channels and regular team-building activities.\\n\\nScrum can be scaled and adapted to larger projects by using frameworks like Scrum of Scrums or LeSS (Large Scale Scrum). Concerns about speed versus quality can be addressed by incorporating quality assurance practices, such as continuous integration and automated testing, into the Scrum process. Scope creep can be managed by having a well-defined and prioritized product backlog, and a strong product owner can be developed through training and mentorship.\\n\\nResistance to change can be overcome by providing proper education and communication to stakeholders and involving them in the decision-making process. Ultimately, the cons of Scrum can be seen as opportunities for growth and improvement, and with the right mindset and support, they can be effectively managed.\\n\\nIn conclusion, while Scrum may have its challenges and potential cons, the benefits and advantages it offers in terms of collaboration, flexibility, adaptability, transparency, and customer satisfaction make it a widely adopted and successful project management framework. With proper implementation and continuous improvement, organizations can leverage Scrum to drive innovation, efficiency, and project success.'"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"input\": \"scrum\"})"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "poetry-venv",
+   "language": "python",
+   "name": "poetry-venv"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/expression_language/cookbook/prompt_llm_parser.ipynb

@@ -0,0 +1,436 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "abf7263d-3a62-4016-b5d5-b157f92f2070",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_position: 0\n",
+    "title: Prompt + LLM\n",
+    "---\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9a434f2b-9405-468c-9dfd-254d456b57a6",
+   "metadata": {},
+   "source": [
+    "The most common and valuable composition is taking:\n",
+    "\n",
+    "``PromptTemplate`` / ``ChatPromptTemplate`` -> ``LLM`` / ``ChatModel`` -> ``OutputParser``\n",
+    "\n",
+    "Almost any other chains you build will use this building block."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "93aa2c87",
+   "metadata": {},
+   "source": [
+    "## PromptTemplate + LLM\n",
+    "\n",
+    "The simplest composition is just combining a prompt and model to create a chain that takes user input, adds it to a prompt, passes it to a model, and returns the raw model output.\n",
+    "\n",
+    "Note, you can mix and match PromptTemplate/ChatPromptTemplates and LLMs/ChatModels as you like here."
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "id": "ef79a54b",
+   "metadata": {},
+   "source": [
+    "%pip install --upgrade --quiet  langchain langchain-openai"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "466b65b3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_template(\"tell me a joke about {foo}\")\n",
+    "model = ChatOpenAI()\n",
+    "chain = prompt | model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "e3d0a6cd",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"Why don't bears wear shoes?\\n\\nBecause they have bear feet!\", additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"foo\": \"bears\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7eb9ef50",
+   "metadata": {},
+   "source": [
+    "Often times we want to attach kwargs that'll be passed to each model call. Here are a few examples of that:"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0b1d8f88",
+   "metadata": {},
+   "source": [
+    "### Attaching Stop Sequences"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "562a06bf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = prompt | model.bind(stop=[\"\\n\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "43f5d04c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Why did the bear never wear shoes?', additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"foo\": \"bears\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f3eaf88a",
+   "metadata": {},
+   "source": [
+    "### Attaching Function Call information"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "f94b71b2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "functions = [\n",
+    "    {\n",
+    "        \"name\": \"joke\",\n",
+    "        \"description\": \"A joke\",\n",
+    "        \"parameters\": {\n",
+    "            \"type\": \"object\",\n",
+    "            \"properties\": {\n",
+    "                \"setup\": {\"type\": \"string\", \"description\": \"The setup for the joke\"},\n",
+    "                \"punchline\": {\n",
+    "                    \"type\": \"string\",\n",
+    "                    \"description\": \"The punchline for the joke\",\n",
+    "                },\n",
+    "            },\n",
+    "            \"required\": [\"setup\", \"punchline\"],\n",
+    "        },\n",
+    "    }\n",
+    "]\n",
+    "chain = prompt | model.bind(function_call={\"name\": \"joke\"}, functions=functions)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "decf7710",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='', additional_kwargs={'function_call': {'name': 'joke', 'arguments': '{\\n  \"setup\": \"Why don\\'t bears wear shoes?\",\\n  \"punchline\": \"Because they have bear feet!\"\\n}'}}, example=False)"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"foo\": \"bears\"}, config={})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9098c5ed",
+   "metadata": {},
+   "source": [
+    "## PromptTemplate + LLM + OutputParser\n",
+    "\n",
+    "We can also add in an output parser to easily transform the raw LLM/ChatModel output into a more workable format"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "cc194c78",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "\n",
+    "chain = prompt | model | StrOutputParser()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "77acf448",
+   "metadata": {},
+   "source": [
+    "Notice that this now returns a string - a much more workable format for downstream tasks"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "e3d69a18",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"Why don't bears wear shoes?\\n\\nBecause they have bear feet!\""
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"foo\": \"bears\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c01864e5",
+   "metadata": {},
+   "source": [
+    "### Functions Output Parser\n",
+    "\n",
+    "When you specify the function to return, you may just want to parse that directly"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "ad0dd88e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.output_parsers.openai_functions import JsonOutputFunctionsParser\n",
+    "\n",
+    "chain = (\n",
+    "    prompt\n",
+    "    | model.bind(function_call={\"name\": \"joke\"}, functions=functions)\n",
+    "    | JsonOutputFunctionsParser()\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "1e7aa8eb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'setup': \"Why don't bears like fast food?\",\n",
+       " 'punchline': \"Because they can't catch it!\"}"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"foo\": \"bears\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "d4aa1a01",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.output_parsers.openai_functions import JsonKeyOutputFunctionsParser\n",
+    "\n",
+    "chain = (\n",
+    "    prompt\n",
+    "    | model.bind(function_call={\"name\": \"joke\"}, functions=functions)\n",
+    "    | JsonKeyOutputFunctionsParser(key_name=\"setup\")\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "8b6df9ba",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"Why don't bears wear shoes?\""
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"foo\": \"bears\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "023fbccb-ef7d-489e-a9ba-f98e17283d51",
+   "metadata": {},
+   "source": [
+    "## Simplifying input\n",
+    "\n",
+    "To make invocation even simpler, we can add a `RunnableParallel` to take care of creating the prompt input dict for us:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "9601c0f0-71f9-4bd4-a672-7bd04084b018",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.runnables import RunnableParallel, RunnablePassthrough\n",
+    "\n",
+    "map_ = RunnableParallel(foo=RunnablePassthrough())\n",
+    "chain = (\n",
+    "    map_\n",
+    "    | prompt\n",
+    "    | model.bind(function_call={\"name\": \"joke\"}, functions=functions)\n",
+    "    | JsonKeyOutputFunctionsParser(key_name=\"setup\")\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "7ec4f154-fda5-4847-9220-41aa902fdc33",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"Why don't bears wear shoes?\""
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke(\"bears\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "def00bfe-0f83-4805-8c8f-8a53f99fa8ea",
+   "metadata": {},
+   "source": [
+    "Since we're composing our map with another Runnable, we can even use some syntactic sugar and just use a dict:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "7bf3846a-02ee-41a3-ba1b-a708827d4f3a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = (\n",
+    "    {\"foo\": RunnablePassthrough()}\n",
+    "    | prompt\n",
+    "    | model.bind(function_call={\"name\": \"joke\"}, functions=functions)\n",
+    "    | JsonKeyOutputFunctionsParser(key_name=\"setup\")\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "e566d6a1-538d-4cb5-a210-a63e082e4c74",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"Why don't bears like fast food?\""
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke(\"bears\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/expression_language/get_started.ipynb

@@ -0,0 +1,537 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "366a0e68-fd67-4fe5-a292-5c33733339ea",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_position: 0\n",
+    "title: Get started\n",
+    "keywords: [chain.invoke]\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "befa7fd1",
+   "metadata": {},
+   "source": [
+    "LCEL makes it easy to build complex chains from basic components, and supports out of the box functionality such as streaming, parallelism, and logging."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9a9acd2e",
+   "metadata": {},
+   "source": [
+    "## Basic example: prompt + model + output parser\n",
+    "\n",
+    "The most basic and common use case is chaining a prompt template and a model together. To see how this works, let's create a chain that takes a topic and generates a joke:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "278b0027",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet  langchain-core langchain-community langchain-openai"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c3d54f72",
+   "metadata": {},
+   "source": [
+    "```{=mdx}\n",
+    "import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
+    "\n",
+    "<ChatModelTabs openaiParams={`model=\"gpt-4\"`} />\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f9eed8e8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# | output: false\n",
+    "# | echo: false\n",
+    "\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "model = ChatOpenAI(model=\"gpt-4\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "466b65b3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"Why don't ice creams ever get invited to parties?\\n\\nBecause they always drip when things heat up!\""
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_template(\"tell me a short joke about {topic}\")\n",
+    "output_parser = StrOutputParser()\n",
+    "\n",
+    "chain = prompt | model | output_parser\n",
+    "\n",
+    "chain.invoke({\"topic\": \"ice cream\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "81c502c5-85ee-4f36-aaf4-d6e350b7792f",
+   "metadata": {},
+   "source": [
+    "Notice this line of the code, where we piece together these different components into a single chain using LCEL:\n",
+    "\n",
+    "```\n",
+    "chain = prompt | model | output_parser\n",
+    "```\n",
+    "\n",
+    "The `|` symbol is similar to a [unix pipe operator](https://en.wikipedia.org/wiki/Pipeline_(Unix)), which chains together the different components, feeding the output from one component as input into the next component. \n",
+    "\n",
+    "In this chain the user input is passed to the prompt template, then the prompt template output is passed to the model, then the model output is passed to the output parser. Let's take a look at each component individually to really understand what's going on."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "aa1b77fa",
+   "metadata": {},
+   "source": [
+    "### 1. Prompt\n",
+    "\n",
+    "`prompt` is a `BasePromptTemplate`, which means it takes in a dictionary of template variables and produces a `PromptValue`. A `PromptValue` is a wrapper around a completed prompt that can be passed to either an `LLM` (which takes a string as input) or `ChatModel` (which takes a sequence of messages as input). It can work with either language model type because it defines logic both for producing `BaseMessage`s and for producing a string."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "b8656990",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "ChatPromptValue(messages=[HumanMessage(content='tell me a short joke about ice cream')])"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "prompt_value = prompt.invoke({\"topic\": \"ice cream\"})\n",
+    "prompt_value"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "e6034488",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[HumanMessage(content='tell me a short joke about ice cream')]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "prompt_value.to_messages()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "60565463",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Human: tell me a short joke about ice cream'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "prompt_value.to_string()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "577f0f76",
+   "metadata": {},
+   "source": [
+    "### 2. Model\n",
+    "\n",
+    "The `PromptValue` is then passed to `model`. In this case our `model` is a `ChatModel`, meaning it will output a `BaseMessage`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "33cf5f72",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"Why don't ice creams ever get invited to parties?\\n\\nBecause they always bring a melt down!\")"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "message = model.invoke(prompt_value)\n",
+    "message"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "327e7db8",
+   "metadata": {},
+   "source": [
+    "If our `model` was an `LLM`, it would output a string."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "8feb05da",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'\\n\\nRobot: Why did the ice cream truck break down? Because it had a meltdown!'"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_openai import OpenAI\n",
+    "\n",
+    "llm = OpenAI(model=\"gpt-3.5-turbo-instruct\")\n",
+    "llm.invoke(prompt_value)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "91847478",
+   "metadata": {},
+   "source": [
+    "### 3. Output parser\n",
+    "\n",
+    "And lastly we pass our `model` output to the `output_parser`, which is a `BaseOutputParser` meaning it takes either a string or a \n",
+    "`BaseMessage` as input. The specific `StrOutputParser` simply converts any input into a string."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "533e59a8",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"Why did the ice cream go to therapy? \\n\\nBecause it had too many toppings and couldn't find its cone-fidence!\""
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "output_parser.invoke(message)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9851e842",
+   "metadata": {},
+   "source": [
+    "### 4. Entire Pipeline\n",
+    "\n",
+    "To follow the steps along:\n",
+    "\n",
+    "1. We pass in user input on the desired topic as `{\"topic\": \"ice cream\"}`\n",
+    "2. The `prompt` component takes the user input, which is then used to construct a PromptValue after using the `topic` to construct the prompt. \n",
+    "3. The `model` component takes the generated prompt, and passes into the OpenAI LLM model for evaluation. The generated output from the model is a `ChatMessage` object. \n",
+    "4. Finally, the `output_parser` component takes in a `ChatMessage`, and transforms this into a Python string, which is returned from the invoke method. \n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c4873109",
+   "metadata": {},
+   "source": [
+    "```mermaid\n",
+    "graph LR\n",
+    "    A(Input: topic=ice cream) --> |Dict| B(PromptTemplate)\n",
+    "    B -->|PromptValue| C(ChatModel)    \n",
+    "    C -->|ChatMessage| D(StrOutputParser)\n",
+    "    D --> |String| F(Result)\n",
+    "```\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fe63534d",
+   "metadata": {},
+   "source": [
+    ":::info\n",
+    "\n",
+    "Note that if you’re curious about the output of any components, you can always test out a smaller version of the chain such as `prompt` or `prompt | model` to see the intermediate results:\n",
+    "\n",
+    ":::"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "11089b6f-23f8-474f-97ec-8cae8d0ca6d4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "input = {\"topic\": \"ice cream\"}\n",
+    "\n",
+    "prompt.invoke(input)\n",
+    "# > ChatPromptValue(messages=[HumanMessage(content='tell me a short joke about ice cream')])\n",
+    "\n",
+    "(prompt | model).invoke(input)\n",
+    "# > AIMessage(content=\"Why did the ice cream go to therapy?\\nBecause it had too many toppings and couldn't cone-trol itself!\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cc7d3b9d-e400-4c9b-9188-f29dac73e6bb",
+   "metadata": {},
+   "source": [
+    "## RAG Search Example\n",
+    "\n",
+    "For our next example, we want to run a retrieval-augmented generation chain to add some context when responding to questions."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b8fe8eb4",
+   "metadata": {},
+   "source": [
+    "```{=mdx}\n",
+    "<ChatModelTabs />\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "662426e8-4316-41dc-8312-9b58edc7e0c9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Requires:\n",
+    "# pip install langchain docarray tiktoken\n",
+    "\n",
+    "from langchain_community.vectorstores import DocArrayInMemorySearch\n",
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.runnables import RunnableParallel, RunnablePassthrough\n",
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "\n",
+    "vectorstore = DocArrayInMemorySearch.from_texts(\n",
+    "    [\"harrison worked at kensho\", \"bears like to eat honey\"],\n",
+    "    embedding=OpenAIEmbeddings(),\n",
+    ")\n",
+    "retriever = vectorstore.as_retriever()\n",
+    "\n",
+    "template = \"\"\"Answer the question based only on the following context:\n",
+    "{context}\n",
+    "\n",
+    "Question: {question}\n",
+    "\"\"\"\n",
+    "prompt = ChatPromptTemplate.from_template(template)\n",
+    "output_parser = StrOutputParser()\n",
+    "\n",
+    "setup_and_retrieval = RunnableParallel(\n",
+    "    {\"context\": retriever, \"question\": RunnablePassthrough()}\n",
+    ")\n",
+    "chain = setup_and_retrieval | prompt | model | output_parser\n",
+    "\n",
+    "chain.invoke(\"where did harrison work?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f0999140-6001-423b-970b-adf1dfdb4dec",
+   "metadata": {},
+   "source": [
+    "In this case, the composed chain is: "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5b88e9bb-f04a-4a56-87ec-19a0e6350763",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = setup_and_retrieval | prompt | model | output_parser"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6e929e15-40a5-4569-8969-384f636cab87",
+   "metadata": {},
+   "source": [
+    "To explain this, we first can see that the prompt template above takes in `context` and `question` as values to be substituted in the prompt. Before building the prompt template, we want to retrieve relevant documents to the search and include them as part of the context. \n",
+    "\n",
+    "As a preliminary step, we’ve setup the retriever using an in memory store, which can retrieve documents based on a query. This is a runnable component as well that can be chained together with other components, but you can also try to run it separately:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a7319ef6-613b-4638-ad7d-4a2183702c1d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "retriever.invoke(\"where did harrison work?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e6833844-f1c4-444c-a3d2-31b3c6b31d46",
+   "metadata": {},
+   "source": [
+    "We then use the `RunnableParallel` to prepare the expected inputs into the prompt by using the entries for the retrieved documents as well as the original user question, using the retriever for document search, and RunnablePassthrough to pass the user’s question:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "dcbca26b-d6b9-4c24-806c-1ec8fdaab4ed",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "setup_and_retrieval = RunnableParallel(\n",
+    "    {\"context\": retriever, \"question\": RunnablePassthrough()}\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "68c721c1-048b-4a64-9d78-df54fe465992",
+   "metadata": {},
+   "source": [
+    "To review, the complete chain is:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1d5115a7-7b8e-458b-b936-26cc87ee81c4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "setup_and_retrieval = RunnableParallel(\n",
+    "    {\"context\": retriever, \"question\": RunnablePassthrough()}\n",
+    ")\n",
+    "chain = setup_and_retrieval | prompt | model | output_parser"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5c6f5f74-b387-48a0-bedd-1fae202cd10a",
+   "metadata": {},
+   "source": [
+    "With the flow being:\n",
+    "\n",
+    "1. The first steps create a `RunnableParallel` object with two entries.  The first entry, `context` will include the document results fetched by the retriever. The second entry, `question` will contain the user’s original question. To pass on the question, we use `RunnablePassthrough` to copy this entry. \n",
+    "2. Feed the dictionary from the step above to the `prompt` component. It then takes the user input which is `question` as well as the retrieved document which is `context` to construct a prompt and output a PromptValue. \n",
+    "3. The `model` component takes the generated prompt, and passes into the OpenAI LLM model for evaluation. The generated output from the model is a `ChatMessage` object. \n",
+    "4. Finally, the `output_parser` component takes in a `ChatMessage`, and transforms this into a Python string, which is returned from the invoke method.\n",
+    "\n",
+    "```mermaid\n",
+    "graph LR\n",
+    "    A(Question) --> B(RunnableParallel)\n",
+    "    B -->|Question| C(Retriever)\n",
+    "    B -->|Question| D(RunnablePassThrough)\n",
+    "    C -->|context=retrieved docs| E(PromptTemplate)\n",
+    "    D -->|question=Question| E\n",
+    "    E -->|PromptValue| F(ChatModel)    \n",
+    "    F -->|ChatMessage| G(StrOutputParser)\n",
+    "    G --> |String| H(Result)\n",
+    "```\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8c2438df-164e-4bbe-b5f4-461695e45b0f",
+   "metadata": {},
+   "source": [
+    "## Next steps\n",
+    "\n",
+    "We recommend reading our [Advantages of LCEL](/docs/expression_language/why) section next to see a side-by-side comparison of the code needed to produce common functionality with and without LCEL."
+   ]
+  }
+ ],
+ "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": "3.11.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/expression_language/how_to/decorator.ipynb

@@ -0,0 +1,136 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "b45110ef",
+   "metadata": {},
+   "source": [
+    "# Create a runnable with the @chain decorator\n",
+    "\n",
+    "You can also turn an arbitrary function into a chain by adding a `@chain` decorator. This is functionaly equivalent to wrapping in a [`RunnableLambda`](/docs/expression_language/primitives/functions).\n",
+    "\n",
+    "This will have the benefit of improved observability by tracing your chain correctly. Any calls to runnables inside this function will be traced as nested childen.\n",
+    "\n",
+    "It will also allow you to use this as any other runnable, compose it in chain, etc.\n",
+    "\n",
+    "Let's take a look at this in action!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "23b2b564",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet  langchain langchain-openai"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "d9370420",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.runnables import chain\n",
+    "from langchain_openai import ChatOpenAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "b7f74f7e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompt1 = ChatPromptTemplate.from_template(\"Tell me a joke about {topic}\")\n",
+    "prompt2 = ChatPromptTemplate.from_template(\"What is the subject of this joke: {joke}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "2b0365c4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "@chain\n",
+    "def custom_chain(text):\n",
+    "    prompt_val1 = prompt1.invoke({\"topic\": text})\n",
+    "    output1 = ChatOpenAI().invoke(prompt_val1)\n",
+    "    parsed_output1 = StrOutputParser().invoke(output1)\n",
+    "    chain2 = prompt2 | ChatOpenAI() | StrOutputParser()\n",
+    "    return chain2.invoke({\"joke\": parsed_output1})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "904d6872",
+   "metadata": {},
+   "source": [
+    "`custom_chain` is now a runnable, meaning you will need to use `invoke`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "6448bdd3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'The subject of this joke is bears.'"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "custom_chain.invoke(\"bears\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "aa767ea9",
+   "metadata": {},
+   "source": [
+    "If you check out your LangSmith traces, you should see a `custom_chain` trace in there, with the calls to OpenAI nested underneath"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f1245bdc",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/expression_language/how_to/inspect.ipynb

@@ -5,21 +5,11 @@
    "id": "8c5eb99a",
    "metadata": {},
    "source": [
-    "# How to inspect runnables\n",
+    "# Inspect your runnables\n",
     "\n",
-    ":::info Prerequisites\n",
+    "Once you create a runnable with LCEL, you may often want to inspect it to get a better sense for what is going on. This notebook covers some methods for doing so.\n",
     "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "- [LangChain Expression Language (LCEL)](/docs/concepts/#langchain-expression-language)\n",
-    "- [Chaining runnables](/docs/how_to/sequence/)\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "Once you create a runnable with [LangChain Expression Language](/docs/concepts/#langchain-expression-language), you may often want to inspect it to get a better sense for what is going on. This notebook covers some methods for doing so.\n",
-    "\n",
-    "This guide shows some ways you can programmatically introspect the internal steps of chains. If you are instead interested in debugging issues in your chain, see [this section](/docs/how_to/debugging) instead.\n",
-    "\n",
-    "First, let's create an example chain. We will create one that does retrieval:"
+    "First, let's create an example LCEL. We will create one that does retrieval"
    ]
   },
   {
@@ -29,7 +19,21 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install -qU langchain langchain-openai faiss-cpu tiktoken"
+    "%pip install --upgrade --quiet  langchain langchain-openai faiss-cpu tiktoken"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "a88f4b24",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.prompts import ChatPromptTemplate\n",
+    "from langchain_community.vectorstores import FAISS\n",
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "from langchain_openai import ChatOpenAI, OpenAIEmbeddings"
    ]
   },
   {
@@ -39,12 +43,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.vectorstores import FAISS\n",
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_core.runnables import RunnablePassthrough\n",
-    "from langchain_openai import ChatOpenAI, OpenAIEmbeddings\n",
-    "\n",
     "vectorstore = FAISS.from_texts(\n",
     "    [\"harrison worked at kensho\"], embedding=OpenAIEmbeddings()\n",
     ")\n",
@@ -57,8 +55,16 @@
     "\"\"\"\n",
     "prompt = ChatPromptTemplate.from_template(template)\n",
     "\n",
-    "model = ChatOpenAI()\n",
-    "\n",
+    "model = ChatOpenAI()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "70e3fe93",
+   "metadata": {},
+   "outputs": [],
+   "source": [
     "chain = (\n",
     "    {\"context\": retriever, \"question\": RunnablePassthrough()}\n",
     "    | prompt\n",
@@ -74,7 +80,7 @@
    "source": [
     "## Get a graph\n",
     "\n",
-    "You can use the `get_graph()` method to get a graph representation of the runnable:"
+    "You can get a graph of the runnable"
    ]
   },
   {
@@ -94,7 +100,7 @@
    "source": [
     "## Print a graph\n",
     "\n",
-    "While that is not super legible, you can use the `print_ascii()` method to show that graph in a way that's easier to understand:"
+    "While that is not super legible, you can print it to get a display that's easier to understand"
    ]
   },
   {
@@ -160,7 +166,7 @@
    "source": [
     "## Get the prompts\n",
     "\n",
-    "You may want to see just the prompts that are used in a chain with the `get_prompts()` method:"
+    "An important part of every chain is the prompts that are used. You can get the prompts present in the chain:"
    ]
   },
   {
@@ -184,18 +190,6 @@
     "chain.get_prompts()"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "c5a74bd5",
-   "metadata": {},
-   "source": [
-    "## Next steps\n",
-    "\n",
-    "You've now learned how to introspect your composed LCEL chains.\n",
-    "\n",
-    "Next, check out the other how-to guides on runnables in this section, or the related how-to guide on [debugging your chains](/docs/how_to/debugging)."
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -221,7 +215,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.1"
   }
  },
  "nbformat": 4,

docs/docs/expression_language/how_to/message_history.ipynb

@@ -0,0 +1,592 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "6a4becbd-238e-4c1d-a02d-08e61fbc3763",
+   "metadata": {},
+   "source": [
+    "# Add message history (memory)\n",
+    "\n",
+    "The `RunnableWithMessageHistory` lets us add message history to certain types of chains. It wraps another Runnable and manages the chat message history for it.\n",
+    "\n",
+    "Specifically, it can be used for any Runnable that takes as input one of\n",
+    "\n",
+    "* a sequence of `BaseMessage`\n",
+    "* a dict with a key that takes a sequence of `BaseMessage`\n",
+    "* a dict with a key that takes the latest message(s) as a string or sequence of `BaseMessage`, and a separate key that takes historical messages\n",
+    "\n",
+    "And returns as output one of\n",
+    "\n",
+    "* a string that can be treated as the contents of an `AIMessage`\n",
+    "* a sequence of `BaseMessage`\n",
+    "* a dict with a key that contains a sequence of `BaseMessage`\n",
+    "\n",
+    "Let's take a look at some examples to see how it works. First we construct a runnable (which here accepts a dict as input and returns a message as output):"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "2ed413b4-33a1-48ee-89b0-2d4917ec101a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
+    "from langchain_openai.chat_models import ChatOpenAI\n",
+    "\n",
+    "model = ChatOpenAI()\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"You're an assistant who's good at {ability}. Respond in 20 words or fewer\",\n",
+    "        ),\n",
+    "        MessagesPlaceholder(variable_name=\"history\"),\n",
+    "        (\"human\", \"{input}\"),\n",
+    "    ]\n",
+    ")\n",
+    "runnable = prompt | model"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9fd175e1-c7b8-4929-a57e-3331865fe7aa",
+   "metadata": {},
+   "source": [
+    "To manage the message history, we will need:\n",
+    "1. This runnable;\n",
+    "2. A callable that returns an instance of `BaseChatMessageHistory`.\n",
+    "\n",
+    "Check out the [memory integrations](https://integrations.langchain.com/memory) page for implementations of chat message histories using Redis and other providers. Here we demonstrate using an in-memory `ChatMessageHistory` as well as more persistent storage using `RedisChatMessageHistory`."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3d83adad-9672-496d-9f25-5747e7b8c8bb",
+   "metadata": {},
+   "source": [
+    "## In-memory\n",
+    "\n",
+    "Below we show a simple example in which the chat history lives in memory, in this case via a global Python dict.\n",
+    "\n",
+    "We construct a callable `get_session_history` that references this dict to return an instance of `ChatMessageHistory`. The arguments to the callable can be specified by passing a configuration to the `RunnableWithMessageHistory` at runtime. By default, the configuration parameter is expected to be a single string `session_id`. This can be adjusted via the `history_factory_config` kwarg.\n",
+    "\n",
+    "Using the single-parameter default:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "54348d02-d8ee-440c-bbf9-41bc0fbbc46c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.chat_message_histories import ChatMessageHistory\n",
+    "from langchain_core.chat_history import BaseChatMessageHistory\n",
+    "from langchain_core.runnables.history import RunnableWithMessageHistory\n",
+    "\n",
+    "store = {}\n",
+    "\n",
+    "\n",
+    "def get_session_history(session_id: str) -> BaseChatMessageHistory:\n",
+    "    if session_id not in store:\n",
+    "        store[session_id] = ChatMessageHistory()\n",
+    "    return store[session_id]\n",
+    "\n",
+    "\n",
+    "with_message_history = RunnableWithMessageHistory(\n",
+    "    runnable,\n",
+    "    get_session_history,\n",
+    "    input_messages_key=\"input\",\n",
+    "    history_messages_key=\"history\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "01acb505-3fd3-4ab4-9f04-5ea07e81542e",
+   "metadata": {},
+   "source": [
+    "Note that we've specified `input_messages_key` (the key to be treated as the latest input message) and `history_messages_key` (the key to add historical messages to).\n",
+    "\n",
+    "When invoking this new runnable, we specify the corresponding chat history via a configuration parameter:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "01384412-f08e-4634-9edb-3f46f475b582",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Cosine is a trigonometric function that calculates the ratio of the adjacent side to the hypotenuse of a right triangle.')"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "with_message_history.invoke(\n",
+    "    {\"ability\": \"math\", \"input\": \"What does cosine mean?\"},\n",
+    "    config={\"configurable\": {\"session_id\": \"abc123\"}},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "954688a2-9a3f-47ee-a9e8-fa0c83e69477",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Cosine is a mathematical function used to calculate the length of a side in a right triangle.')"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Remembers\n",
+    "with_message_history.invoke(\n",
+    "    {\"ability\": \"math\", \"input\": \"What?\"},\n",
+    "    config={\"configurable\": {\"session_id\": \"abc123\"}},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "39350d7c-2641-4744-bc2a-fd6a57c4ea90",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='I can help with math problems. What do you need assistance with?')"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# New session_id --> does not remember.\n",
+    "with_message_history.invoke(\n",
+    "    {\"ability\": \"math\", \"input\": \"What?\"},\n",
+    "    config={\"configurable\": {\"session_id\": \"def234\"}},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d29497be-3366-408d-bbb9-d4a8bf4ef37c",
+   "metadata": {},
+   "source": [
+    "The configuration parameters by which we track message histories can be customized by passing in a list of ``ConfigurableFieldSpec`` objects to the ``history_factory_config`` parameter. Below, we use two parameters: a `user_id` and `conversation_id`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "1c89daee-deff-4fdf-86a3-178f7d8ef536",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.runnables import ConfigurableFieldSpec\n",
+    "\n",
+    "store = {}\n",
+    "\n",
+    "\n",
+    "def get_session_history(user_id: str, conversation_id: str) -> BaseChatMessageHistory:\n",
+    "    if (user_id, conversation_id) not in store:\n",
+    "        store[(user_id, conversation_id)] = ChatMessageHistory()\n",
+    "    return store[(user_id, conversation_id)]\n",
+    "\n",
+    "\n",
+    "with_message_history = RunnableWithMessageHistory(\n",
+    "    runnable,\n",
+    "    get_session_history,\n",
+    "    input_messages_key=\"input\",\n",
+    "    history_messages_key=\"history\",\n",
+    "    history_factory_config=[\n",
+    "        ConfigurableFieldSpec(\n",
+    "            id=\"user_id\",\n",
+    "            annotation=str,\n",
+    "            name=\"User ID\",\n",
+    "            description=\"Unique identifier for the user.\",\n",
+    "            default=\"\",\n",
+    "            is_shared=True,\n",
+    "        ),\n",
+    "        ConfigurableFieldSpec(\n",
+    "            id=\"conversation_id\",\n",
+    "            annotation=str,\n",
+    "            name=\"Conversation ID\",\n",
+    "            description=\"Unique identifier for the conversation.\",\n",
+    "            default=\"\",\n",
+    "            is_shared=True,\n",
+    "        ),\n",
+    "    ],\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "65c5622e-09b8-4f2f-8c8a-2dab0fd040fa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with_message_history.invoke(\n",
+    "    {\"ability\": \"math\", \"input\": \"Hello\"},\n",
+    "    config={\"configurable\": {\"user_id\": \"123\", \"conversation_id\": \"1\"}},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "18f1a459-3f88-4ee6-8542-76a907070dd6",
+   "metadata": {},
+   "source": [
+    "### Examples with runnables of different signatures\n",
+    "\n",
+    "The above runnable takes a dict as input and returns a BaseMessage. Below we show some alternatives."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "48eae1bf-b59d-4a61-8e62-b6dbf667e866",
+   "metadata": {},
+   "source": [
+    "#### Messages input, dict output"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "17733d4f-3a32-4055-9d44-5d58b9446a26",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'output_message': AIMessage(content=\"Simone de Beauvoir believed in the existence of free will. She argued that individuals have the ability to make choices and determine their own actions, even in the face of social and cultural constraints. She rejected the idea that individuals are purely products of their environment or predetermined by biology or destiny. Instead, she emphasized the importance of personal responsibility and the need for individuals to actively engage in creating their own lives and defining their own existence. De Beauvoir believed that freedom and agency come from recognizing one's own freedom and actively exercising it in the pursuit of personal and collective liberation.\")}"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.messages import HumanMessage\n",
+    "from langchain_core.runnables import RunnableParallel\n",
+    "\n",
+    "chain = RunnableParallel({\"output_message\": ChatOpenAI()})\n",
+    "\n",
+    "\n",
+    "def get_session_history(session_id: str) -> BaseChatMessageHistory:\n",
+    "    if session_id not in store:\n",
+    "        store[session_id] = ChatMessageHistory()\n",
+    "    return store[session_id]\n",
+    "\n",
+    "\n",
+    "with_message_history = RunnableWithMessageHistory(\n",
+    "    chain,\n",
+    "    get_session_history,\n",
+    "    output_messages_key=\"output_message\",\n",
+    ")\n",
+    "\n",
+    "with_message_history.invoke(\n",
+    "    [HumanMessage(content=\"What did Simone de Beauvoir believe about free will\")],\n",
+    "    config={\"configurable\": {\"session_id\": \"baz\"}},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "efb57ef5-91f9-426b-84b9-b77f071a9dd7",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'output_message': AIMessage(content='Simone de Beauvoir\\'s views on free will were closely aligned with those of her contemporary and partner Jean-Paul Sartre. Both de Beauvoir and Sartre were existentialist philosophers who emphasized the importance of individual freedom and the rejection of determinism. They believed that human beings have the capacity to transcend their circumstances and create their own meaning and values.\\n\\nSartre, in his famous work \"Being and Nothingness,\" argued that human beings are condemned to be free, meaning that we are burdened with the responsibility of making choices and defining ourselves in a world that lacks inherent meaning. Like de Beauvoir, Sartre believed that individuals have the ability to exercise their freedom and make choices in the face of external and internal constraints.\\n\\nWhile there may be some nuanced differences in their philosophical writings, overall, de Beauvoir and Sartre shared a similar belief in the existence of free will and the importance of individual agency in shaping one\\'s own life.')}"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "with_message_history.invoke(\n",
+    "    [HumanMessage(content=\"How did this compare to Sartre\")],\n",
+    "    config={\"configurable\": {\"session_id\": \"baz\"}},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a39eac5f-a9d8-4729-be06-5e7faf0c424d",
+   "metadata": {},
+   "source": [
+    "#### Messages input, messages output"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e45bcd95-e31f-4a9a-967a-78f96e8da881",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "RunnableWithMessageHistory(\n",
+    "    ChatOpenAI(),\n",
+    "    get_session_history,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "04daa921-a2d1-40f9-8cd1-ae4e9a4163a7",
+   "metadata": {},
+   "source": [
+    "#### Dict with single key for all messages input, messages output"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "27157f15-9fb0-4167-9870-f4d7f234b3cb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from operator import itemgetter\n",
+    "\n",
+    "RunnableWithMessageHistory(\n",
+    "    itemgetter(\"input_messages\") | ChatOpenAI(),\n",
+    "    get_session_history,\n",
+    "    input_messages_key=\"input_messages\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "418ca7af-9ed9-478c-8bca-cba0de2ca61e",
+   "metadata": {},
+   "source": [
+    "## Persistent storage"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "76799a13-d99a-4c4f-91f2-db699e40b8df",
+   "metadata": {},
+   "source": [
+    "In many cases it is preferable to persist conversation histories. `RunnableWithMessageHistory` is agnostic as to how the `get_session_history` callable retrieves its chat message histories. See [here](https://github.com/langchain-ai/langserve/blob/main/examples/chat_with_persistence_and_user/server.py) for an example using a local filesystem. Below we demonstrate how one could use Redis. Check out the [memory integrations](https://integrations.langchain.com/memory) page for implementations of chat message histories using other providers."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6bca45e5-35d9-4603-9ca9-6ac0ce0e35cd",
+   "metadata": {},
+   "source": [
+    "### Setup\n",
+    "\n",
+    "We'll need to install Redis if it's not installed already:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "477d04b3-c2b6-4ba5-962f-492c0d625cd5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet redis"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6a0ec9e0-7b1c-4c6f-b570-e61d520b47c6",
+   "metadata": {},
+   "source": [
+    "Start a local Redis Stack server if we don't have an existing Redis deployment to connect to:\n",
+    "```bash\n",
+    "docker run -d -p 6379:6379 -p 8001:8001 redis/redis-stack:latest\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "cd6a250e-17fe-4368-a39d-1fe6b2cbde68",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "REDIS_URL = \"redis://localhost:6379/0\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "36f43b87-655c-4f64-aa7b-bd8c1955d8e5",
+   "metadata": {},
+   "source": [
+    "### [LangSmith](/docs/langsmith)\n",
+    "\n",
+    "LangSmith is especially useful for something like message history injection, where it can be hard to otherwise understand what the inputs are to various parts of the chain.\n",
+    "\n",
+    "Note that LangSmith is not needed, but it is helpful.\n",
+    "If you do want to use LangSmith, after you sign up at the link above, make sure to uncoment the below and set your environment variables to start logging traces:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "2afc1556-8da1-4499-ba11-983b66c58b18",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
+    "# os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f9d81796-ce61-484c-89e2-6c567d5e54ef",
+   "metadata": {},
+   "source": [
+    "Updating the message history implementation just requires us to define a new callable, this time returning an instance of `RedisChatMessageHistory`:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "ca7c64d8-e138-4ef8-9734-f82076c47d80",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.chat_message_histories import RedisChatMessageHistory\n",
+    "\n",
+    "\n",
+    "def get_message_history(session_id: str) -> RedisChatMessageHistory:\n",
+    "    return RedisChatMessageHistory(session_id, url=REDIS_URL)\n",
+    "\n",
+    "\n",
+    "with_message_history = RunnableWithMessageHistory(\n",
+    "    runnable,\n",
+    "    get_message_history,\n",
+    "    input_messages_key=\"input\",\n",
+    "    history_messages_key=\"history\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "37eefdec-9901-4650-b64c-d3c097ed5f4d",
+   "metadata": {},
+   "source": [
+    "We can invoke as before:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "a85bcc22-ca4c-4ad5-9440-f94be7318f3e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Cosine is a trigonometric function that represents the ratio of the adjacent side to the hypotenuse in a right triangle.')"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "with_message_history.invoke(\n",
+    "    {\"ability\": \"math\", \"input\": \"What does cosine mean?\"},\n",
+    "    config={\"configurable\": {\"session_id\": \"foobar\"}},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "ab29abd3-751f-41ce-a1b0-53f6b565e79d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='The inverse of cosine is the arccosine function, denoted as acos or cos^-1, which gives the angle corresponding to a given cosine value.')"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "with_message_history.invoke(\n",
+    "    {\"ability\": \"math\", \"input\": \"What's its inverse\"},\n",
+    "    config={\"configurable\": {\"session_id\": \"foobar\"}},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "da3d1feb-b4bb-4624-961c-7db2e1180df7",
+   "metadata": {},
+   "source": [
+    ":::{.callout-tip}\n",
+    "\n",
+    "[Langsmith trace](https://smith.langchain.com/public/bd73e122-6ec1-48b2-82df-e6483dc9cb63/r)\n",
+    "\n",
+    ":::"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "61d5115e-64a1-4ad5-b676-8afd4ef6093e",
+   "metadata": {},
+   "source": [
+    "Looking at the Langsmith trace for the second call, we can see that when constructing the prompt, a \"history\" variable has been injected which is a list of two messages (our first input and first output)."
+   ]
+  }
+ ],
+ "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": "3.10.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/expression_language/how_to/routing.ipynb

@@ -7,6 +7,7 @@
    "source": [
     "---\n",
     "sidebar_position: 3\n",
+    "title: \"Route logic based on input\"\n",
     "keywords: [RunnableBranch, LCEL]\n",
     "---"
    ]
@@ -16,25 +17,16 @@
    "id": "4b47436a",
    "metadata": {},
    "source": [
-    "# How to route between sub-chains\n",
+    "# Dynamically route logic based on input\n",
     "\n",
-    ":::info Prerequisites\n",
+    "This notebook covers how to do routing in the LangChain Expression Language.\n",
     "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "- [LangChain Expression Language (LCEL)](/docs/concepts/#langchain-expression-language)\n",
-    "- [Chaining runnables](/docs/how_to/sequence/)\n",
-    "- [Configuring chain parameters at runtime](/docs/how_to/configure)\n",
-    "- [Prompt templates](/docs/concepts/#prompt-templates)\n",
-    "- [Chat Messages](/docs/concepts/#message-types)\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "Routing allows you to create non-deterministic chains where the output of a previous step defines the next step. Routing can help provide structure and consistency around interactions with models by allowing you to define states and use information related to those states as context to model calls.\n",
+    "Routing allows you to create non-deterministic chains where the output of a previous step defines the next step. Routing helps provide structure and consistency around interactions with LLMs.\n",
     "\n",
     "There are two ways to perform routing:\n",
     "\n",
-    "1. Conditionally return runnables from a [`RunnableLambda`](/docs/how_to/functions) (recommended)\n",
-    "2. Using a `RunnableBranch` (legacy)\n",
+    "1. Conditionally return runnables from a [`RunnableLambda`](/docs/expression_language/primitives/functions) (recommended)\n",
+    "2. Using a `RunnableBranch`.\n",
     "\n",
     "We'll illustrate both methods using a two step sequence where the first step classifies an input question as being about `LangChain`, `Anthropic`, or `Other`, then routes to a corresponding prompt chain."
    ]
@@ -335,7 +327,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.utils.math import cosine_similarity\n",
+    "from langchain.utils.math import cosine_similarity\n",
     "from langchain_core.output_parsers import StrOutputParser\n",
     "from langchain_core.prompts import PromptTemplate\n",
     "from langchain_core.runnables import RunnableLambda, RunnablePassthrough\n",
@@ -438,18 +430,6 @@
     "print(chain.invoke(\"What's a path integral\"))"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "ff40bcb3",
-   "metadata": {},
-   "source": [
-    "## Next steps\n",
-    "\n",
-    "You've now learned how to add routing to your composed LCEL chains.\n",
-    "\n",
-    "Next, check out the other how-to guides on runnables in this section."
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "927b7498",
@@ -473,7 +453,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/expression_language/index.mdx

@@ -0,0 +1,33 @@
+---
+sidebar_class_name: hidden
+---
+
+# LangChain Expression Language (LCEL)
+
+LangChain Expression Language, or LCEL, is a declarative way to easily compose chains together.
+LCEL was designed from day 1 to **support putting prototypes in production, with no code changes**, from the simplest “prompt + LLM” chain to the most complex chains (we’ve seen folks successfully run LCEL chains with 100s of steps in production). To highlight a few of the reasons you might want to use LCEL:
+
+[**First-class streaming support**](/docs/expression_language/streaming)
+When you build your chains with LCEL you get the best possible time-to-first-token (time elapsed until the first chunk of output comes out). For some chains this means eg. we stream tokens straight from an LLM to a streaming output parser, and you get back parsed, incremental chunks of output at the same rate as the LLM provider outputs the raw tokens.
+
+[**Async support**](/docs/expression_language/interface)
+Any chain built with LCEL can be called both with the synchronous API (eg. in your Jupyter notebook while prototyping) as well as with the asynchronous API (eg. in a [LangServe](/docs/langsmith) server). This enables using the same code for prototypes and in production, with great performance, and the ability to handle many concurrent requests in the same server.
+
+[**Optimized parallel execution**](/docs/expression_language/primitives/parallel)
+Whenever your LCEL chains have steps that can be executed in parallel (eg if you fetch documents from multiple retrievers) we automatically do it, both in the sync and the async interfaces, for the smallest possible latency.
+
+[**Retries and fallbacks**](/docs/guides/productionization/fallbacks)
+Configure retries and fallbacks for any part of your LCEL chain. This is a great way to make your chains more reliable at scale. We’re currently working on adding streaming support for retries/fallbacks, so you can get the added reliability without any latency cost.
+
+[**Access intermediate results**](/docs/expression_language/interface#async-stream-events-beta)
+For more complex chains it’s often very useful to access the results of intermediate steps even before the final output is produced. This can be used to let end-users know something is happening, or even just to debug your chain. You can stream intermediate results, and it’s available on every [LangServe](/docs/langserve) server.
+
+[**Input and output schemas**](/docs/expression_language/interface#input-schema)
+Input and output schemas give every LCEL chain Pydantic and JSONSchema schemas inferred from the structure of your chain. This can be used for validation of inputs and outputs, and is an integral part of LangServe.
+
+[**Seamless LangSmith tracing**](/docs/langsmith)
+As your chains get more and more complex, it becomes increasingly important to understand what exactly is happening at every step.
+With LCEL, **all** steps are automatically logged to [LangSmith](/docs/langsmith/) for maximum observability and debuggability.
+
+[**Seamless LangServe deployment**](/docs/langserve)
+Any chain created with LCEL can be easily deployed using [LangServe](/docs/langserve).

docs/docs/expression_language/primitives/assign.ipynb

@@ -6,6 +6,7 @@
    "source": [
     "---\n",
     "sidebar_position: 6\n",
+    "title: \"Assign: Add values to state\"\n",
     "keywords: [RunnablePassthrough, assign, LCEL]\n",
     "---"
    ]
@@ -14,38 +15,32 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# How to add values to a chain's state\n",
+    "# Adding values to chain state\n",
     "\n",
-    ":::info Prerequisites\n",
+    "The `RunnablePassthrough.assign(...)` static method takes an input value and adds the extra arguments passed to the assign function.\n",
     "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "- [LangChain Expression Language (LCEL)](/docs/concepts/#langchain-expression-language)\n",
-    "- [Chaining runnables](/docs/how_to/sequence/)\n",
-    "- [Calling runnables in parallel](/docs/how_to/parallel/)\n",
-    "- [Custom functions](/docs/how_to/functions/)\n",
-    "- [Passing data through](/docs/how_to/passthrough)\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "An alternate way of [passing data through](/docs/how_to/passthrough) steps of a chain is to leave the current values of the chain state unchanged while assigning a new value under a given key. The [`RunnablePassthrough.assign()`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.passthrough.RunnablePassthrough.html#langchain_core.runnables.passthrough.RunnablePassthrough.assign) static method takes an input value and adds the extra arguments passed to the assign function.\n",
-    "\n",
-    "This is useful in the common [LangChain Expression Language](/docs/concepts/#langchain-expression-language) pattern of additively creating a dictionary to use as input to a later step.\n",
+    "This is useful when additively creating a dictionary to use as input to a later step, which is a common LCEL pattern.\n",
     "\n",
     "Here's an example:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[33mWARNING: You are using pip version 22.0.4; however, version 24.0 is available.\n",
+      "You should consider upgrading via the '/Users/jacoblee/.pyenv/versions/3.10.5/bin/python -m pip install --upgrade pip' command.\u001b[0m\u001b[33m\n",
+      "\u001b[0mNote: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
    "source": [
-    "%pip install --upgrade --quiet langchain langchain-openai\n",
-    "\n",
-    "import os\n",
-    "from getpass import getpass\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass()"
+    "%pip install --upgrade --quiet langchain langchain-openai"
    ]
   },
   {
@@ -90,12 +85,12 @@
     "\n",
     "## Streaming\n",
     "\n",
-    "One convenient feature of this method is that it allows values to pass through as soon as they are available. To show this off, we'll use `RunnablePassthrough.assign()` to immediately return source docs in a retrieval chain:"
+    "One nice feature of this method is that it allows values to pass through as soon as they are available. To show this off, we'll use `RunnablePassthrough.assign()` to immediately return source docs in a retrieval chain:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -152,13 +147,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "We can see that the first chunk contains the original `\"question\"` since that is immediately available. The second chunk contains `\"context\"` since the retriever finishes second. Finally, the output from the `generation_chain` streams in chunks as soon as it is available.\n",
-    "\n",
-    "## Next steps\n",
-    "\n",
-    "Now you've learned how to pass data through your chains to help to help format the data flowing through your chains.\n",
-    "\n",
-    "To learn more, see the other how-to guides on runnables in this section."
+    "We can see that the first chunk contains the original `\"question\"` since that is immediately available. The second chunk contains `\"context\"` since the retriever finishes second. Finally, the output from the `generation_chain` streams in chunks as soon as it is available."
    ]
   },
   {
@@ -169,7 +158,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3",
    "language": "python",
    "name": "python3"
   },
@@ -183,9 +172,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 4
+ "nbformat_minor": 2
 }

docs/docs/expression_language/primitives/binding.ipynb

@@ -7,6 +7,7 @@
    "source": [
     "---\n",
     "sidebar_position: 2\n",
+    "title: \"Binding: Attach runtime args\"\n",
     "keywords: [RunnableBinding, LCEL]\n",
     "---"
    ]
@@ -16,22 +17,11 @@
    "id": "711752cb-4f15-42a3-9838-a0c67f397771",
    "metadata": {},
    "source": [
-    "# How to add default invocation args to a Runnable\n",
+    "# Binding: Attach runtime args\n",
     "\n",
-    ":::info Prerequisites\n",
+    "Sometimes we want to invoke a Runnable within a Runnable sequence with constant arguments that are not part of the output of the preceding Runnable in the sequence, and which are not part of the user input. We can use `Runnable.bind()` to pass these arguments in.\n",
     "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "- [LangChain Expression Language (LCEL)](/docs/concepts/#langchain-expression-language)\n",
-    "- [Chaining runnables](/docs/how_to/sequence/)\n",
-    "- [Tool calling](/docs/how_to/tool_calling/)\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "Sometimes we want to invoke a [`Runnable`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html) within a [RunnableSequence](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.RunnableSequence.html) with constant arguments that are not part of the output of the preceding Runnable in the sequence, and which are not part of the user input. We can use the [`Runnable.bind()`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable.bind) method to set these arguments ahead of time.\n",
-    "\n",
-    "## Binding stop sequences\n",
-    "\n",
-    "Suppose we have a simple prompt + model chain:"
+    "Suppose we have a simple prompt + model sequence:"
    ]
   },
   {
@@ -41,20 +31,25 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# | output: false\n",
-    "# | echo: false\n",
-    "\n",
-    "%pip install -qU langchain langchain_openai\n",
-    "\n",
-    "import os\n",
-    "from getpass import getpass\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass()"
+    "%pip install --upgrade --quiet  langchain langchain-openai"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
+   "id": "950297ed-2d67-4091-8ea7-1d412d259d04",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "from langchain_openai import ChatOpenAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
    "id": "f3fdf86d-155f-4587-b7cd-52d363970c1d",
    "metadata": {},
    "outputs": [
@@ -64,21 +59,19 @@
      "text": [
       "EQUATION: x^3 + 7 = 12\n",
       "\n",
-      "SOLUTION: \n",
-      "Subtract 7 from both sides:\n",
+      "SOLUTION:\n",
+      "Subtracting 7 from both sides of the equation, we get:\n",
+      "x^3 = 12 - 7\n",
       "x^3 = 5\n",
       "\n",
-      "Take the cube root of both sides:\n",
-      "x = ∛5\n"
+      "Taking the cube root of both sides, we get:\n",
+      "x = ∛5\n",
+      "\n",
+      "Therefore, the solution to the equation x^3 + 7 = 12 is x = ∛5.\n"
      ]
     }
    ],
    "source": [
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_core.runnables import RunnablePassthrough\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
     "prompt = ChatPromptTemplate.from_messages(\n",
     "    [\n",
     "        (\n",
@@ -88,9 +81,7 @@
     "        (\"human\", \"{equation_statement}\"),\n",
     "    ]\n",
     ")\n",
-    "\n",
     "model = ChatOpenAI(temperature=0)\n",
-    "\n",
     "runnable = (\n",
     "    {\"equation_statement\": RunnablePassthrough()} | prompt | model | StrOutputParser()\n",
     ")\n",
@@ -103,12 +94,12 @@
    "id": "929c9aba-a4a0-462c-adac-2cfc2156e117",
    "metadata": {},
    "source": [
-    "and want to call the model with certain `stop` words so that we shorten the output as is useful in certain types of prompting techniques. While we can pass some arguments into the constructor, other runtime args use the `.bind()` method as follows:"
+    "and want to call the model with certain `stop` words:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 12,
    "id": "32e0484a-78c5-4570-a00b-20d597245a96",
    "metadata": {},
    "outputs": [
@@ -129,25 +120,92 @@
     "    | model.bind(stop=\"SOLUTION\")\n",
     "    | StrOutputParser()\n",
     ")\n",
-    "\n",
     "print(runnable.invoke(\"x raised to the third plus seven equals 12\"))"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "f4bd641f-6b58-4ca9-a544-f69095428f16",
+   "metadata": {},
+   "source": [
+    "## Attaching OpenAI functions\n",
+    "\n",
+    "One particularly useful application of binding is to attach OpenAI functions to a compatible OpenAI model:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "f66a0fe4-fde0-4706-8863-d60253f211c7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "function = {\n",
+    "    \"name\": \"solver\",\n",
+    "    \"description\": \"Formulates and solves an equation\",\n",
+    "    \"parameters\": {\n",
+    "        \"type\": \"object\",\n",
+    "        \"properties\": {\n",
+    "            \"equation\": {\n",
+    "                \"type\": \"string\",\n",
+    "                \"description\": \"The algebraic expression of the equation\",\n",
+    "            },\n",
+    "            \"solution\": {\n",
+    "                \"type\": \"string\",\n",
+    "                \"description\": \"The solution to the equation\",\n",
+    "            },\n",
+    "        },\n",
+    "        \"required\": [\"equation\", \"solution\"],\n",
+    "    },\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "f381f969-df8e-48a3-bf5c-d0397cfecde0",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='', additional_kwargs={'function_call': {'name': 'solver', 'arguments': '{\\n\"equation\": \"x^3 + 7 = 12\",\\n\"solution\": \"x = ∛5\"\\n}'}}, example=False)"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Need gpt-4 to solve this one correctly\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"Write out the following equation using algebraic symbols then solve it.\",\n",
+    "        ),\n",
+    "        (\"human\", \"{equation_statement}\"),\n",
+    "    ]\n",
+    ")\n",
+    "model = ChatOpenAI(model=\"gpt-4\", temperature=0).bind(\n",
+    "    function_call={\"name\": \"solver\"}, functions=[function]\n",
+    ")\n",
+    "runnable = {\"equation_statement\": RunnablePassthrough()} | prompt | model\n",
+    "runnable.invoke(\"x raised to the third plus seven equals 12\")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "f07d7528-9269-4d6f-b12e-3669592a9e03",
    "metadata": {},
    "source": [
-    "What you can bind to a Runnable will depend on the extra parameters you can pass when invoking it.\n",
-    "\n",
-    "## Attaching OpenAI tools\n",
-    "\n",
-    "Another common use-case is tool calling. While you should generally use the [`.bind_tools()`](/docs/how_to/tool_calling/) method for tool-calling models, you can also bind provider-specific args directly if you want lower level control:"
+    "## Attaching OpenAI tools"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "id": "2cdeeb4c-0c1f-43da-bd58-4f591d9e0671",
    "metadata": {},
    "outputs": [],
@@ -176,17 +234,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 9,
    "id": "2b65beab-48bb-46ff-a5a4-ef8ac95a513c",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_z0OU2CytqENVrRTI6T8DkI3u', 'function': {'arguments': '{\"location\": \"San Francisco, CA\", \"unit\": \"celsius\"}', 'name': 'get_current_weather'}, 'type': 'function'}, {'id': 'call_ft96IJBh0cMKkQWrZjNg4bsw', 'function': {'arguments': '{\"location\": \"New York, NY\", \"unit\": \"celsius\"}', 'name': 'get_current_weather'}, 'type': 'function'}, {'id': 'call_tfbtGgCLmuBuWgZLvpPwvUMH', 'function': {'arguments': '{\"location\": \"Los Angeles, CA\", \"unit\": \"celsius\"}', 'name': 'get_current_weather'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 84, 'prompt_tokens': 85, 'total_tokens': 169}, 'model_name': 'gpt-3.5-turbo-1106', 'system_fingerprint': 'fp_77a673219d', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-d57ad5fa-b52a-4822-bc3e-74f838697e18-0', tool_calls=[{'name': 'get_current_weather', 'args': {'location': 'San Francisco, CA', 'unit': 'celsius'}, 'id': 'call_z0OU2CytqENVrRTI6T8DkI3u'}, {'name': 'get_current_weather', 'args': {'location': 'New York, NY', 'unit': 'celsius'}, 'id': 'call_ft96IJBh0cMKkQWrZjNg4bsw'}, {'name': 'get_current_weather', 'args': {'location': 'Los Angeles, CA', 'unit': 'celsius'}, 'id': 'call_tfbtGgCLmuBuWgZLvpPwvUMH'}])"
+       "AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_zHN0ZHwrxM7nZDdqTp6dkPko', 'function': {'arguments': '{\"location\": \"San Francisco, CA\", \"unit\": \"celsius\"}', 'name': 'get_current_weather'}, 'type': 'function'}, {'id': 'call_aqdMm9HBSlFW9c9rqxTa7eQv', 'function': {'arguments': '{\"location\": \"New York, NY\", \"unit\": \"celsius\"}', 'name': 'get_current_weather'}, 'type': 'function'}, {'id': 'call_cx8E567zcLzYV2WSWVgO63f1', 'function': {'arguments': '{\"location\": \"Los Angeles, CA\", \"unit\": \"celsius\"}', 'name': 'get_current_weather'}, 'type': 'function'}]})"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -195,27 +253,13 @@
     "model = ChatOpenAI(model=\"gpt-3.5-turbo-1106\").bind(tools=tools)\n",
     "model.invoke(\"What's the weather in SF, NYC and LA?\")"
    ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "095001f7",
-   "metadata": {},
-   "source": [
-    "## Next steps\n",
-    "\n",
-    "You now know how to bind runtime arguments to a Runnable.\n",
-    "\n",
-    "To learn more, see the other how-to guides on runnables in this section, including:\n",
-    "\n",
-    "- [Using configurable fields and alternatives](/docs/how_to/configure) to change parameters of a step in a chain, or even swap out entire steps, at runtime"
-   ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "poetry-venv",
    "language": "python",
-   "name": "python3"
+   "name": "poetry-venv"
   },
   "language_info": {
    "codemirror_mode": {

docs/docs/expression_language/primitives/configure.ipynb

@@ -7,6 +7,7 @@
    "source": [
     "---\n",
     "sidebar_position: 7\n",
+    "title: \"Configure runtime chain internals\"\n",
     "keywords: [ConfigurableField, configurable_fields, ConfigurableAlternatives, configurable_alternatives, LCEL]\n",
     "---"
    ]
@@ -16,24 +17,16 @@
    "id": "39eaf61b",
    "metadata": {},
    "source": [
-    "# How to configure runtime chain internals\n",
+    "# Configure chain internals at runtime\n",
     "\n",
-    ":::info Prerequisites\n",
-    "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "- [LangChain Expression Language (LCEL)](/docs/concepts/#langchain-expression-language)\n",
-    "- [Chaining runnables](/docs/how_to/sequence/)\n",
-    "- [Binding runtime arguments](/docs/how_to/binding/)\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "Sometimes you may want to experiment with, or even expose to the end user, multiple different ways of doing things within your chains.\n",
-    "This can include tweaking parameters such as temperature or even swapping out one model for another.\n",
+    "Oftentimes you may want to experiment with, or even expose to the end user, multiple different ways of doing things.\n",
     "In order to make this experience as easy as possible, we have defined two methods.\n",
     "\n",
-    "- A `configurable_fields` method. This lets you configure particular fields of a runnable.\n",
-    "  - This is related to the [`.bind`](/docs/how_to/binding) method on runnables, but allows you to specify parameters for a given step in a chain at runtime rather than specifying them beforehand.\n",
-    "- A `configurable_alternatives` method. With this method, you can list out alternatives for any particular runnable that can be set during runtime, and swap them for those specified alternatives."
+    "First, a `configurable_fields` method. \n",
+    "This lets you configure particular fields of a runnable.\n",
+    "\n",
+    "Second, a `configurable_alternatives` method.\n",
+    "With this method, you can list out alternatives for any particular runnable that can be set during runtime."
    ]
   },
   {
@@ -41,55 +34,36 @@
    "id": "f2347a11",
    "metadata": {},
    "source": [
-    "## Configurable Fields\n",
-    "\n",
-    "Let's walk through an example that configures chat model fields like temperature at runtime:"
+    "## Configuration Fields"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a06f6e2d",
+   "metadata": {},
+   "source": [
+    "### With LLMs\n",
+    "With LLMs we can configure things like temperature"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "40ed76a2",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[33mWARNING: You are using pip version 22.0.4; however, version 24.0 is available.\n",
-      "You should consider upgrading via the '/Users/jacoblee/.pyenv/versions/3.10.5/bin/python -m pip install --upgrade pip' command.\u001b[0m\u001b[33m\n",
-      "\u001b[0mNote: you may need to restart the kernel to use updated packages.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet langchain langchain-openai\n",
-    "\n",
-    "import os\n",
-    "from getpass import getpass\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass()"
+    "%pip install --upgrade --quiet  langchain langchain-openai"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 35,
    "id": "7ba735f4",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='17', response_metadata={'token_usage': {'completion_tokens': 1, 'prompt_tokens': 11, 'total_tokens': 12}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-ba26a0da-0a69-4533-ab7f-21178a73d303-0')"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
-    "from langchain_core.prompts import PromptTemplate\n",
+    "from langchain.prompts import PromptTemplate\n",
     "from langchain_core.runnables import ConfigurableField\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
@@ -99,32 +73,43 @@
     "        name=\"LLM Temperature\",\n",
     "        description=\"The temperature of the LLM\",\n",
     "    )\n",
-    ")\n",
-    "\n",
-    "model.invoke(\"pick a random number\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "b0f74589",
-   "metadata": {},
-   "source": [
-    "Above, we defined `temperature` as a [`ConfigurableField`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.utils.ConfigurableField.html#langchain_core.runnables.utils.ConfigurableField) that we can set at runtime. To do so, we use the [`with_config`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable.with_config) method like this:"
+    ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 38,
+   "id": "63a71165",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='7')"
+      ]
+     },
+     "execution_count": 38,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model.invoke(\"pick a random number\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
    "id": "4f83245c",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='12', response_metadata={'token_usage': {'completion_tokens': 1, 'prompt_tokens': 11, 'total_tokens': 12}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-ba8422ad-be77-4cb1-ac45-ad0aae74e3d9-0')"
+       "AIMessage(content='34')"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 39,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -138,48 +123,54 @@
    "id": "9da1fcd2",
    "metadata": {},
    "source": [
-    "Note that the passed `llm_temperature` entry in the dict has the same key as the `id` of the `ConfigurableField`.\n",
-    "\n",
-    "We can also do this to affect just one step that's part of a chain:"
+    "We can also do this when its used as part of a chain"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 40,
    "id": "e75ae678",
    "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompt = PromptTemplate.from_template(\"Pick a random number above {x}\")\n",
+    "chain = prompt | model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "id": "44886071",
+   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='27', response_metadata={'token_usage': {'completion_tokens': 1, 'prompt_tokens': 14, 'total_tokens': 15}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-ecd4cadd-1b72-4f92-b9a0-15e08091f537-0')"
+       "AIMessage(content='57')"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 41,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "prompt = PromptTemplate.from_template(\"Pick a random number above {x}\")\n",
-    "chain = prompt | model\n",
-    "\n",
     "chain.invoke({\"x\": 0})"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 42,
    "id": "c09fac15",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='35', response_metadata={'token_usage': {'completion_tokens': 1, 'prompt_tokens': 14, 'total_tokens': 15}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-a916602b-3460-46d3-a4a8-7c926ec747c0-0')"
+       "AIMessage(content='6')"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 42,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -200,9 +191,35 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 43,
+   "id": "7d5836b2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.runnables.hub import HubRunnable"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
    "id": "9a9ea077",
    "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompt = HubRunnable(\"rlm/rag-prompt\").configurable_fields(\n",
+    "    owner_repo_commit=ConfigurableField(\n",
+    "        id=\"hub_commit\",\n",
+    "        name=\"Hub Commit\",\n",
+    "        description=\"The Hub commit to pull from\",\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "id": "c4a62cee",
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -210,28 +227,18 @@
        "ChatPromptValue(messages=[HumanMessage(content=\"You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question. If you don't know the answer, just say that you don't know. Use three sentences maximum and keep the answer concise.\\nQuestion: foo \\nContext: bar \\nAnswer:\")])"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 47,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "from langchain.runnables.hub import HubRunnable\n",
-    "\n",
-    "prompt = HubRunnable(\"rlm/rag-prompt\").configurable_fields(\n",
-    "    owner_repo_commit=ConfigurableField(\n",
-    "        id=\"hub_commit\",\n",
-    "        name=\"Hub Commit\",\n",
-    "        description=\"The Hub commit to pull from\",\n",
-    "    )\n",
-    ")\n",
-    "\n",
     "prompt.invoke({\"question\": \"foo\", \"context\": \"bar\"})"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 49,
    "id": "f33f3cf2",
    "metadata": {},
    "outputs": [
@@ -241,7 +248,7 @@
        "ChatPromptValue(messages=[HumanMessage(content=\"[INST]<<SYS>> You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question. If you don't know the answer, just say that you don't know. Use three sentences maximum and keep the answer concise.<</SYS>> \\nQuestion: foo \\nContext: bar \\nAnswer: [/INST]\")])"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 49,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -266,32 +273,22 @@
    "id": "ac733d35",
    "metadata": {},
    "source": [
-    "The `configurable_alternatives()` method allows us to swap out steps in a chain with an alternative. Below, we swap out one chat model for another:"
+    "### With LLMs\n",
+    "\n",
+    "Let's take a look at doing this with LLMs"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
-   "id": "3db59f45",
+   "execution_count": 4,
+   "id": "430ab8cc",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[33mWARNING: You are using pip version 22.0.4; however, version 24.0 is available.\n",
-      "You should consider upgrading via the '/Users/jacoblee/.pyenv/versions/3.10.5/bin/python -m pip install --upgrade pip' command.\u001b[0m\u001b[33m\n",
-      "\u001b[0mNote: you may need to restart the kernel to use updated packages.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet langchain-anthropic\n",
-    "\n",
-    "import os\n",
-    "from getpass import getpass\n",
-    "\n",
-    "os.environ[\"ANTHROPIC_API_KEY\"] = getpass()"
+    "from langchain.prompts import PromptTemplate\n",
+    "from langchain_community.chat_models import ChatAnthropic\n",
+    "from langchain_core.runnables import ConfigurableField\n",
+    "from langchain_openai import ChatOpenAI"
    ]
   },
   {
@@ -299,27 +296,9 @@
    "execution_count": 18,
    "id": "71248a9f",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"Here's a bear joke for you:\\n\\nWhy don't bears wear socks? \\nBecause they have bear feet!\\n\\nHow's that? I tried to come up with a simple, silly pun-based joke about bears. Puns and wordplay are a common way to create humorous bear jokes. Let me know if you'd like to hear another one!\", response_metadata={'id': 'msg_018edUHh5fUbWdiimhrC3dZD', 'model': 'claude-3-haiku-20240307', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 13, 'output_tokens': 80}}, id='run-775bc58c-28d7-4e6b-a268-48fa6661f02f-0')"
-      ]
-     },
-     "execution_count": 18,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
-    "from langchain_anthropic import ChatAnthropic\n",
-    "from langchain_core.prompts import PromptTemplate\n",
-    "from langchain_core.runnables import ConfigurableField\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "llm = ChatAnthropic(\n",
-    "    model=\"claude-3-haiku-20240307\", temperature=0\n",
-    ").configurable_alternatives(\n",
+    "llm = ChatAnthropic(temperature=0).configurable_alternatives(\n",
     "    # This gives this field an id\n",
     "    # When configuring the end runnable, we can then use this id to configure this field\n",
     "    ConfigurableField(id=\"llm\"),\n",
@@ -333,25 +312,44 @@
     "    # You can add more configuration options here\n",
     ")\n",
     "prompt = PromptTemplate.from_template(\"Tell me a joke about {topic}\")\n",
-    "chain = prompt | llm\n",
-    "\n",
+    "chain = prompt | llm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "e598b1f1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\" Here's a silly joke about bears:\\n\\nWhat do you call a bear with no teeth?\\nA gummy bear!\")"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
     "# By default it will call Anthropic\n",
     "chain.invoke({\"topic\": \"bears\"})"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 20,
    "id": "48b45337",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"Why don't bears like fast food?\\n\\nBecause they can't catch it!\", response_metadata={'token_usage': {'completion_tokens': 15, 'prompt_tokens': 13, 'total_tokens': 28}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-7bdaa992-19c9-4f0d-9a0c-1f326bc992d4-0')"
+       "AIMessage(content=\"Sure, here's a bear joke for you:\\n\\nWhy don't bears wear shoes?\\n\\nBecause they already have bear feet!\")"
       ]
      },
-     "execution_count": 19,
+     "execution_count": 20,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -363,17 +361,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 21,
    "id": "42647fb7",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"Here's a bear joke for you:\\n\\nWhy don't bears wear socks? \\nBecause they have bear feet!\\n\\nHow's that? I tried to come up with a simple, silly pun-based joke about bears. Puns and wordplay are a common way to create humorous bear jokes. Let me know if you'd like to hear another one!\", response_metadata={'id': 'msg_01BZvbmnEPGBtcxRWETCHkct', 'model': 'claude-3-haiku-20240307', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 13, 'output_tokens': 80}}, id='run-59b6ee44-a1cd-41b8-a026-28ee67cdd718-0')"
+       "AIMessage(content=\" Here's a silly joke about bears:\\n\\nWhat do you call a bear with no teeth?\\nA gummy bear!\")"
       ]
      },
-     "execution_count": 20,
+     "execution_count": 21,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -395,23 +393,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 25,
    "id": "9f6a7c6c",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"Here's a bear joke for you:\\n\\nWhy don't bears wear socks? \\nBecause they have bear feet!\", response_metadata={'id': 'msg_01DtM1cssjNFZYgeS3gMZ49H', 'model': 'claude-3-haiku-20240307', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 13, 'output_tokens': 28}}, id='run-8199af7d-ea31-443d-b064-483693f2e0a1-0')"
-      ]
-     },
-     "execution_count": 22,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
-    "llm = ChatAnthropic(model=\"claude-3-haiku-20240307\", temperature=0)\n",
+    "llm = ChatAnthropic(temperature=0)\n",
     "prompt = PromptTemplate.from_template(\n",
     "    \"Tell me a joke about {topic}\"\n",
     ").configurable_alternatives(\n",
@@ -425,25 +412,44 @@
     "    poem=PromptTemplate.from_template(\"Write a short poem about {topic}\"),\n",
     "    # You can add more configuration options here\n",
     ")\n",
-    "chain = prompt | llm\n",
-    "\n",
+    "chain = prompt | llm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "97eda915",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\" Here's a silly joke about bears:\\n\\nWhat do you call a bear with no teeth?\\nA gummy bear!\")"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
     "# By default it will write a joke\n",
     "chain.invoke({\"topic\": \"bears\"})"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 27,
    "id": "927297a1",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"Here is a short poem about bears:\\n\\nMajestic bears, strong and true,\\nRoaming the forests, wild and free.\\nPowerful paws, fur soft and brown,\\nCommanding respect, nature's crown.\\n\\nForaging for berries, fishing streams,\\nProtecting their young, fierce and keen.\\nMighty bears, a sight to behold,\\nGuardians of the wilderness, untold.\\n\\nIn the wild they reign supreme,\\nEmbodying nature's grand theme.\\nBears, a symbol of strength and grace,\\nCaptivating all who see their face.\", response_metadata={'id': 'msg_01Wck3qPxrjURtutvtodaJFn', 'model': 'claude-3-haiku-20240307', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 13, 'output_tokens': 134}}, id='run-69414a1e-51d7-4bec-a307-b34b7d61025e-0')"
+       "AIMessage(content=' Here is a short poem about bears:\\n\\nThe bears awaken from their sleep\\nAnd lumber out into the deep\\nForests filled with trees so tall\\nForaging for food before nightfall \\nTheir furry coats and claws so sharp\\nSniffing for berries and fish to nab\\nLumbering about without a care\\nThe mighty grizzly and black bear\\nProud creatures, wild and free\\nRuling their domain majestically\\nWandering the woods they call their own\\nBefore returning to their dens alone')"
       ]
      },
-     "execution_count": 23,
+     "execution_count": 27,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -466,25 +472,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 28,
    "id": "97538c23",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"In the forest deep and wide,\\nBears roam with grace and pride.\\nWith fur as dark as night,\\nThey rule the land with all their might.\\n\\nIn winter's chill, they hibernate,\\nIn spring they emerge, hungry and great.\\nWith claws sharp and eyes so keen,\\nThey hunt for food, fierce and lean.\\n\\nBut beneath their tough exterior,\\nLies a gentle heart, warm and superior.\\nThey love their cubs with all their might,\\nProtecting them through day and night.\\n\\nSo let us admire these majestic creatures,\\nIn awe of their strength and features.\\nFor in the wild, they reign supreme,\\nThe mighty bears, a timeless dream.\", response_metadata={'token_usage': {'completion_tokens': 133, 'prompt_tokens': 13, 'total_tokens': 146}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-5eec0b96-d580-49fd-ac4e-e32a0803b49b-0')"
-      ]
-     },
-     "execution_count": 25,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
-    "llm = ChatAnthropic(\n",
-    "    model=\"claude-3-haiku-20240307\", temperature=0\n",
-    ").configurable_alternatives(\n",
+    "llm = ChatAnthropic(temperature=0).configurable_alternatives(\n",
     "    # This gives this field an id\n",
     "    # When configuring the end runnable, we can then use this id to configure this field\n",
     "    ConfigurableField(id=\"llm\"),\n",
@@ -510,8 +503,27 @@
     "    poem=PromptTemplate.from_template(\"Write a short poem about {topic}\"),\n",
     "    # You can add more configuration options here\n",
     ")\n",
-    "chain = prompt | llm\n",
-    "\n",
+    "chain = prompt | llm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "1dcc7ccc",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"In the forest, where tall trees sway,\\nA creature roams, both fierce and gray.\\nWith mighty paws and piercing eyes,\\nThe bear, a symbol of strength, defies.\\n\\nThrough snow-kissed mountains, it does roam,\\nA guardian of its woodland home.\\nWith fur so thick, a shield of might,\\nIt braves the coldest winter night.\\n\\nA gentle giant, yet wild and free,\\nThe bear commands respect, you see.\\nWith every step, it leaves a trace,\\nOf untamed power and ancient grace.\\n\\nFrom honeyed feast to salmon's leap,\\nIt takes its place, in nature's keep.\\nA symbol of untamed delight,\\nThe bear, a wonder, day and night.\\n\\nSo let us honor this noble beast,\\nIn forests where its soul finds peace.\\nFor in its presence, we come to know,\\nThe untamed spirit that in us also flows.\")"
+      ]
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
     "# We can configure it write a poem with OpenAI\n",
     "chain.with_config(configurable={\"prompt\": \"poem\", \"llm\": \"openai\"}).invoke(\n",
     "    {\"topic\": \"bears\"}\n",
@@ -520,17 +532,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 30,
    "id": "e4ee9fbc",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"Why don't bears wear shoes?\\n\\nBecause they have bear feet!\", response_metadata={'token_usage': {'completion_tokens': 13, 'prompt_tokens': 13, 'total_tokens': 26}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-c1b14c9c-4988-49b8-9363-15bfd479973a-0')"
+       "AIMessage(content=\"Sure, here's a bear joke for you:\\n\\nWhy don't bears wear shoes?\\n\\nBecause they have bear feet!\")"
       ]
      },
-     "execution_count": 26,
+     "execution_count": 30,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -552,41 +564,35 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 31,
    "id": "5cf53202",
    "metadata": {},
+   "outputs": [],
+   "source": [
+    "openai_joke = chain.with_config(configurable={\"llm\": \"openai\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "id": "9486d701",
+   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"Why did the bear break up with his girlfriend? \\nBecause he couldn't bear the relationship anymore!\", response_metadata={'token_usage': {'completion_tokens': 20, 'prompt_tokens': 13, 'total_tokens': 33}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-391ebd55-9137-458b-9a11-97acaff6a892-0')"
+       "AIMessage(content=\"Why don't bears wear shoes?\\n\\nBecause they have bear feet!\")"
       ]
      },
-     "execution_count": 27,
+     "execution_count": 32,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "openai_joke = chain.with_config(configurable={\"llm\": \"openai\"})\n",
-    "\n",
     "openai_joke.invoke({\"topic\": \"bears\"})"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "76702b0e",
-   "metadata": {},
-   "source": [
-    "## Next steps\n",
-    "\n",
-    "You now know how to configure a chain's internal steps at runtime.\n",
-    "\n",
-    "To learn more, see the other how-to guides on runnables in this section, including:\n",
-    "\n",
-    "- Using [.bind()](/docs/how_to/binding) as a simpler way to set a runnable's runtime parameters"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -612,7 +618,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.11.5"
   }
  },
  "nbformat": 4,

docs/docs/expression_language/primitives/functions.ipynb

@@ -7,6 +7,7 @@
    "source": [
     "---\n",
     "sidebar_position: 3\n",
+    "title: \"Lambda: Run custom functions\"\n",
     "keywords: [RunnableLambda, LCEL]\n",
     "---"
    ]
@@ -16,64 +17,27 @@
    "id": "fbc4bf6e",
    "metadata": {},
    "source": [
-    "# How to run custom functions\n",
+    "# Run custom functions\n",
     "\n",
-    ":::info Prerequisites\n",
+    "You can use arbitrary functions in the pipeline.\n",
     "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "- [LangChain Expression Language (LCEL)](/docs/concepts/#langchain-expression-language)\n",
-    "- [Chaining runnables](/docs/how_to/sequence/)\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "You can use arbitrary functions as [Runnables](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable). This is useful for formatting or when you need functionality not provided by other LangChain components, and custom functions used as Runnables are called [`RunnableLambdas`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.RunnableLambda.html).\n",
-    "\n",
-    "Note that all inputs to these functions need to be a SINGLE argument. If you have a function that accepts multiple arguments, you should write a wrapper that accepts a single dict input and unpacks it into multiple argument.\n",
-    "\n",
-    "This guide will cover:\n",
-    "\n",
-    "- How to explicitly create a runnable from a custom function using the `RunnableLambda` constructor and the convenience `@chain` decorator\n",
-    "- Coercion of custom functions into runnables when used in chains\n",
-    "- How to accept and use run metadata in your custom function\n",
-    "- How to stream with custom functions by having them return generators\n",
-    "\n",
-    "## Using the constructor\n",
-    "\n",
-    "Below, we explicitly wrap our custom logic using the `RunnableLambda` constructor:"
+    "Note that all inputs to these functions need to be a SINGLE argument. If you have a function that accepts multiple arguments, you should write a wrapper that accepts a single input and unpacks it into multiple argument."
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "5c34d2af",
+   "cell_type": "raw",
+   "id": "9a5fe916",
    "metadata": {},
-   "outputs": [],
    "source": [
-    "%pip install -qU langchain langchain_openai\n",
-    "\n",
-    "import os\n",
-    "from getpass import getpass\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass()"
+    "%pip install --upgrade --quiet langchain langchain-openai"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "id": "6bb221b3",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='3 + 9 equals 12.', response_metadata={'token_usage': {'completion_tokens': 8, 'prompt_tokens': 14, 'total_tokens': 22}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-73728de3-e483-49e3-ad54-51bd9570e71a-0')"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "from operator import itemgetter\n",
     "\n",
@@ -94,9 +58,8 @@
     "    return _multiple_length_function(_dict[\"text1\"], _dict[\"text2\"])\n",
     "\n",
     "\n",
-    "model = ChatOpenAI()\n",
-    "\n",
     "prompt = ChatPromptTemplate.from_template(\"what is {a} + {b}\")\n",
+    "model = ChatOpenAI()\n",
     "\n",
     "chain1 = prompt | model\n",
     "\n",
@@ -108,56 +71,28 @@
     "    }\n",
     "    | prompt\n",
     "    | model\n",
-    ")\n",
-    "\n",
-    "chain.invoke({\"foo\": \"bar\", \"bar\": \"gah\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "b7926002",
-   "metadata": {},
-   "source": [
-    "## The convenience `@chain` decorator\n",
-    "\n",
-    "You can also turn an arbitrary function into a chain by adding a `@chain` decorator. This is functionaly equivalent to wrapping the function in a `RunnableLambda` constructor as shown above. Here's an example:"
+    ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
-   "id": "3142a516",
+   "execution_count": 2,
+   "id": "5488ec85",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "'The subject of the joke is the bear and his girlfriend.'"
+       "AIMessage(content='3 + 9 = 12', response_metadata={'token_usage': {'completion_tokens': 7, 'prompt_tokens': 14, 'total_tokens': 21}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_b28b39ffa8', 'finish_reason': 'stop', 'logprobs': None}, id='run-bd204541-81fd-429a-ad92-dd1913af9b1c-0')"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.runnables import chain\n",
-    "\n",
-    "prompt1 = ChatPromptTemplate.from_template(\"Tell me a joke about {topic}\")\n",
-    "prompt2 = ChatPromptTemplate.from_template(\"What is the subject of this joke: {joke}\")\n",
-    "\n",
-    "\n",
-    "@chain\n",
-    "def custom_chain(text):\n",
-    "    prompt_val1 = prompt1.invoke({\"topic\": text})\n",
-    "    output1 = ChatOpenAI().invoke(prompt_val1)\n",
-    "    parsed_output1 = StrOutputParser().invoke(output1)\n",
-    "    chain2 = prompt2 | ChatOpenAI() | StrOutputParser()\n",
-    "    return chain2.invoke({\"joke\": parsed_output1})\n",
-    "\n",
-    "\n",
-    "custom_chain.invoke(\"bears\")"
+    "chain.invoke({\"foo\": \"bar\", \"bar\": \"gah\"})"
    ]
   },
   {
@@ -165,78 +100,31 @@
    "id": "4728ddd9-914d-42ce-ae9b-72c9ce8ec940",
    "metadata": {},
    "source": [
-    "Above, the `@chain` decorator is used to convert `custom_chain` into a runnable, which we invoke with the `.invoke()` method.\n",
+    "## Accepting a Runnable Config\n",
     "\n",
-    "If you are using a tracing with [LangSmith](https://docs.smith.langchain.com/), you should see a `custom_chain` trace in there, with the calls to OpenAI nested underneath.\n",
-    "\n",
-    "## Automatic coercion in chains\n",
-    "\n",
-    "When using custom functions in chains with the pipe operator (`|`), you can omit the `RunnableLambda` or `@chain` constructor and rely on coercion. Here's a simple example with a function that takes the output from the model and returns the first five letters of it:"
+    "Runnable lambdas can optionally accept a [RunnableConfig](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.config.RunnableConfig.html#langchain_core.runnables.config.RunnableConfig), which they can use to pass callbacks, tags, and other configuration information to nested runs."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "80b3b5f6-5d58-44b9-807e-cce9a46bf49f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.runnables import RunnableConfig"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 4,
-   "id": "5ab39a87",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Once '"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "prompt = ChatPromptTemplate.from_template(\"tell me a story about {topic}\")\n",
-    "\n",
-    "model = ChatOpenAI()\n",
-    "\n",
-    "chain_with_coerced_function = prompt | model | (lambda x: x.content[:5])\n",
-    "\n",
-    "chain_with_coerced_function.invoke({\"topic\": \"bears\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "c9a481d1",
-   "metadata": {},
-   "source": [
-    "Note that we didn't need to wrap the custom function `(lambda x: x.content[:5])` in a `RunnableLambda` constructor because the `model` on the left of the pipe operator is already a Runnable. The custom function is **coerced** into a runnable. See [this section](/docs/how_to/sequence/#coercion) for more information.\n",
-    "\n",
-    "## Passing run metadata\n",
-    "\n",
-    "Runnable lambdas can optionally accept a [RunnableConfig](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.config.RunnableConfig.html#langchain_core.runnables.config.RunnableConfig) parameter, which they can use to pass callbacks, tags, and other configuration information to nested runs."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
    "id": "ff0daf0c-49dd-4d21-9772-e5fa133c5f36",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'foo': 'bar'}\n",
-      "Tokens Used: 62\n",
-      "\tPrompt Tokens: 56\n",
-      "\tCompletion Tokens: 6\n",
-      "Successful Requests: 1\n",
-      "Total Cost (USD): $9.6e-05\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "import json\n",
     "\n",
-    "from langchain_core.runnables import RunnableConfig\n",
-    "\n",
     "\n",
     "def parse_or_fix(text: str, config: RunnableConfig):\n",
     "    fixing_chain = (\n",
@@ -244,7 +132,7 @@
     "            \"Fix the following text:\\n\\n```text\\n{input}\\n```\\nError: {error}\"\n",
     "            \" Don't narrate, just respond with the fixed data.\"\n",
     "        )\n",
-    "        | model\n",
+    "        | ChatOpenAI()\n",
     "        | StrOutputParser()\n",
     "    )\n",
     "    for _ in range(3):\n",
@@ -252,22 +140,12 @@
     "            return json.loads(text)\n",
     "        except Exception as e:\n",
     "            text = fixing_chain.invoke({\"input\": text, \"error\": e}, config)\n",
-    "    return \"Failed to parse\"\n",
-    "\n",
-    "\n",
-    "from langchain_community.callbacks import get_openai_callback\n",
-    "\n",
-    "with get_openai_callback() as cb:\n",
-    "    output = RunnableLambda(parse_or_fix).invoke(\n",
-    "        \"{foo: bar}\", {\"tags\": [\"my-tag\"], \"callbacks\": [cb]}\n",
-    "    )\n",
-    "    print(output)\n",
-    "    print(cb)"
+    "    return \"Failed to parse\""
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "id": "1a5e709e-9d75-48c7-bb9c-503251990505",
    "metadata": {},
    "outputs": [
@@ -302,7 +180,7 @@
    "source": [
     "# Streaming\n",
     "\n",
-    "You can use generator functions (ie. functions that use the `yield` keyword, and behave like iterators) in a chain.\n",
+    "You can use generator functions (ie. functions that use the `yield` keyword, and behave like iterators) in a LCEL pipeline.\n",
     "\n",
     "The signature of these generators should be `Iterator[Input] -> Iterator[Output]`. Or for async generators: `AsyncIterator[Input] -> AsyncIterator[Output]`.\n",
     "\n",
@@ -310,13 +188,30 @@
     "- implementing a custom output parser\n",
     "- modifying the output of a previous step, while preserving streaming capabilities\n",
     "\n",
-    "Here's an example of a custom output parser for comma-separated lists. First, we create a chain that generates such a list as text:"
+    "Here's an example of a custom output parser for comma-separated lists:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "29f55c38",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import Iterator, List\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_template(\n",
+    "    \"Write a comma-separated list of 5 animals similar to: {animal}. Do not include numbers\"\n",
+    ")\n",
+    "model = ChatOpenAI(temperature=0.0)\n",
+    "\n",
+    "str_chain = prompt | model | StrOutputParser()"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 7,
-   "id": "29f55c38",
+   "id": "75aa946b",
    "metadata": {},
    "outputs": [
     {
@@ -328,44 +223,37 @@
     }
    ],
    "source": [
-    "from typing import Iterator, List\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_template(\n",
-    "    \"Write a comma-separated list of 5 animals similar to: {animal}. Do not include numbers\"\n",
-    ")\n",
-    "\n",
-    "str_chain = prompt | model | StrOutputParser()\n",
-    "\n",
     "for chunk in str_chain.stream({\"animal\": \"bear\"}):\n",
     "    print(chunk, end=\"\", flush=True)"
    ]
   },
   {
-   "cell_type": "markdown",
-   "id": "46345323",
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "d002a7fe",
    "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'lion, tiger, wolf, gorilla, panda'"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "Next, we define a custom function that will aggregate the currently streamed output and yield it when the model generates the next comma in the list:"
+    "str_chain.invoke({\"animal\": \"bear\"})"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "id": "f08b8a5b",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "['lion']\n",
-      "['tiger']\n",
-      "['wolf']\n",
-      "['gorilla']\n",
-      "['raccoon']\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# This is a custom parser that splits an iterator of llm tokens\n",
     "# into a list of strings separated by commas\n",
@@ -384,58 +272,23 @@
     "            # save the rest for the next iteration\n",
     "            buffer = buffer[comma_index + 1 :]\n",
     "    # yield the last chunk\n",
-    "    yield [buffer.strip()]\n",
-    "\n",
-    "\n",
-    "list_chain = str_chain | split_into_list\n",
-    "\n",
-    "for chunk in list_chain.stream({\"animal\": \"bear\"}):\n",
-    "    print(chunk, flush=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0a5adb69",
-   "metadata": {},
-   "source": [
-    "Invoking it gives a full array of values:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "9ea4ddc6",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "['lion', 'tiger', 'wolf', 'gorilla', 'raccoon']"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "list_chain.invoke({\"animal\": \"bear\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "96e320ed",
-   "metadata": {},
-   "source": [
-    "## Async version\n",
-    "\n",
-    "If you are working in an `async` environment, here is an `async` version of the above example:"
+    "    yield [buffer.strip()]"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 10,
-   "id": "569dbbef",
+   "id": "02e414aa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "list_chain = str_chain | split_into_list"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "7ed8799d",
    "metadata": {},
    "outputs": [
     {
@@ -450,6 +303,46 @@
      ]
     }
    ],
+   "source": [
+    "for chunk in list_chain.stream({\"animal\": \"bear\"}):\n",
+    "    print(chunk, flush=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "9ea4ddc6",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['lion', 'tiger', 'wolf', 'gorilla', 'elephant']"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "list_chain.invoke({\"animal\": \"bear\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "96e320ed",
+   "metadata": {},
+   "source": [
+    "## Async version"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "569dbbef",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "from typing import AsyncIterator\n",
     "\n",
@@ -469,15 +362,35 @@
     "    yield [buffer.strip()]\n",
     "\n",
     "\n",
-    "list_chain = str_chain | asplit_into_list\n",
-    "\n",
+    "list_chain = str_chain | asplit_into_list"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "7a76b713",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['lion']\n",
+      "['tiger']\n",
+      "['wolf']\n",
+      "['gorilla']\n",
+      "['panda']\n"
+     ]
+    }
+   ],
+   "source": [
     "async for chunk in list_chain.astream({\"animal\": \"bear\"}):\n",
     "    print(chunk, flush=True)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 15,
    "id": "3a650482",
    "metadata": {},
    "outputs": [
@@ -487,7 +400,7 @@
        "['lion', 'tiger', 'wolf', 'gorilla', 'panda']"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -495,18 +408,6 @@
    "source": [
     "await list_chain.ainvoke({\"animal\": \"bear\"})"
    ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "3306ac3b",
-   "metadata": {},
-   "source": [
-    "## Next steps\n",
-    "\n",
-    "Now you've learned a few different ways to use custom logic within your chains, and how to implement streaming.\n",
-    "\n",
-    "To learn more, see the other how-to guides on runnables in this section."
-   ]
   }
  ],
  "metadata": {
@@ -525,7 +426,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,