Merge branch 'master' into snova-jorgep/bind_tools_sambastudio_chat_m…

…odels

.github/scripts/check_diff.py

@@ -32,18 +32,8 @@
     "huggingface",
 ]
 
-# Cap python version at 3.12 for some packages with dependencies that are not yet
-# compatible with python 3.13 (mostly hf tokenizers).
 PY_312_MAX_PACKAGES = [
-    f"libs/partners/{integration}"
-    for integration in [
-        "chroma",
-        "couchbase",
-        "huggingface",
-        "mistralai",
-        "nomic",
-        "qdrant",
-    ]
+    "libs/partners/huggingface",  # https://github.com/pytorch/pytorch/issues/130249
 ]
 
 
@@ -134,10 +124,11 @@ def _get_configs_for_single_dir(job: str, dir_: str) -> List[Dict[str, str]]:
     elif dir_ in PY_312_MAX_PACKAGES:
         py_versions = ["3.9", "3.12"]
 
-    elif dir_ in ["libs/community", "libs/langchain"] and job == "extended-tests":
-        # community extended test resolution in 3.12 is slow
-        # even in uv
-        py_versions = ["3.9", "3.11"]
+    elif dir_ == "libs/langchain" and job == "extended-tests":
+        py_versions = ["3.9", "3.13"]
+
+    elif dir_ == "libs/community" and job == "extended-tests":
+        py_versions = ["3.9", "3.12"]
 
     elif dir_ == "libs/community" and job == "compile-integration-tests":
         # community integration deps are slow in 3.12

.github/workflows/_compile_integration_test.yml

@@ -13,14 +13,15 @@ on:
         description: "Python version to use"
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "1.8.4"
 
 jobs:
   build:
     defaults:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
+    timeout-minutes: 20
     name: "poetry run pytest -m compile tests/integration_tests #${{ inputs.python-version }}"
     steps:
       - uses: actions/checkout@v4

.github/workflows/_integration_test.yml

@@ -12,7 +12,7 @@ on:
         description: "Python version to use"
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "1.8.4"
 
 jobs:
   build:

.github/workflows/_lint.yml

@@ -13,7 +13,7 @@ on:
         description: "Python version to use"
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "1.8.4"
   WORKDIR: ${{ inputs.working-directory == '' && '.' || inputs.working-directory }}
 
   # This env var allows us to get inline annotations when ruff has complaints.
@@ -23,6 +23,7 @@ jobs:
   build:
     name: "make lint #${{ inputs.python-version }}"
     runs-on: ubuntu-latest
+    timeout-minutes: 20
     steps:
       - uses: actions/checkout@v4
 

.github/workflows/_release.yml

@@ -21,7 +21,7 @@ on:
 
 env:
   PYTHON_VERSION: "3.11"
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "1.8.4"
 
 jobs:
   build:
@@ -167,6 +167,7 @@ jobs:
       - release-notes
       - test-pypi-publish
     runs-on: ubuntu-latest
+    timeout-minutes: 20
     steps:
       - uses: actions/checkout@v4
 
@@ -191,7 +192,12 @@ jobs:
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
 
-      - name: Import published package
+      - uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: ${{ inputs.working-directory }}/dist/
+
+      - name: Import dist package
         shell: bash
         working-directory: ${{ inputs.working-directory }}
         env:
@@ -207,15 +213,7 @@ jobs:
         # - attempt install again after 5 seconds if it fails because there is
         #   sometimes a delay in availability on test pypi
         run: |
-          poetry run pip install \
-            --extra-index-url https://test.pypi.org/simple/ \
-            "$PKG_NAME==$VERSION" || \
-          ( \
-            sleep 15 && \
-            poetry run pip install \
-              --extra-index-url https://test.pypi.org/simple/ \
-              "$PKG_NAME==$VERSION" \
-          )
+          poetry run pip install dist/*.whl
 
           # Replace all dashes in the package name with underscores,
           # since that's how Python imports packages with dashes in the name.
@@ -224,20 +222,18 @@ jobs:
           poetry run python -c "import $IMPORT_NAME; print(dir($IMPORT_NAME))"
 
       - name: Import test dependencies
-        run: poetry install --with test
+        run: poetry install --with test --no-root
         working-directory: ${{ inputs.working-directory }}
 
-      # Overwrite the local version of the package with the test PyPI version.
+      # Overwrite the local version of the package with the built version
       - name: Import published package (again)
         working-directory: ${{ inputs.working-directory }}
         shell: bash
         env:
           PKG_NAME: ${{ needs.build.outputs.pkg-name }}
           VERSION: ${{ needs.build.outputs.version }}
         run: |
-          poetry run pip install \
-            --extra-index-url https://test.pypi.org/simple/ \
-            "$PKG_NAME==$VERSION"
+          poetry run pip install dist/*.whl
 
       - name: Run unit tests
         run: make tests

.github/workflows/_test.yml

@@ -13,14 +13,15 @@ on:
         description: "Python version to use"
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "1.8.4"
 
 jobs:
   build:
     defaults:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
+    timeout-minutes: 20
     name: "make test #${{ inputs.python-version }}"
     steps:
       - uses: actions/checkout@v4

.github/workflows/_test_doc_imports.yml

@@ -9,11 +9,12 @@ on:
         description: "Python version to use"
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "1.8.4"
 
 jobs:
   build:
     runs-on: ubuntu-latest
+    timeout-minutes: 20
     name: "check doc imports #${{ inputs.python-version }}"
     steps:
       - uses: actions/checkout@v4

.github/workflows/_test_pydantic.yml

@@ -18,14 +18,15 @@ on:
         description: "Pydantic version to test."
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "1.8.4"
 
 jobs:
   build:
     defaults:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
+    timeout-minutes: 20
     name: "make test # pydantic: ~=${{ inputs.pydantic-version }}, python: ${{ inputs.python-version }}, "
     steps:
       - uses: actions/checkout@v4

.github/workflows/_test_release.yml

@@ -14,7 +14,7 @@ on:
         description: "Release from a non-master branch (danger!)"
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "1.8.4"
   PYTHON_VERSION: "3.10"
 
 jobs:

.github/workflows/api_doc_build.yml

@@ -5,7 +5,7 @@ on:
   schedule:
     - cron:  '0 13 * * *'
 env:
-  POETRY_VERSION: "1.8.1"
+  POETRY_VERSION: "1.8.4"
   PYTHON_VERSION: "3.11"
 
 jobs:
@@ -73,7 +73,7 @@ jobs:
         working-directory: langchain
         run: |
           python -m uv pip install $(ls ./libs/partners | xargs -I {} echo "./libs/partners/{}")
-          python -m uv pip install libs/core libs/langchain libs/text-splitters libs/community libs/experimental
+          python -m uv pip install libs/core libs/langchain libs/text-splitters libs/community libs/experimental libs/standard-tests
           python -m uv pip install -r docs/api_reference/requirements.txt
 
       - name: Set Git config

.github/workflows/check_diffs.yml

@@ -17,7 +17,7 @@ concurrency:
   cancel-in-progress: true
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "1.8.4"
 
 jobs:
   build:
@@ -119,6 +119,7 @@ jobs:
         job-configs: ${{ fromJson(needs.build.outputs.extended-tests) }}
       fail-fast: false
     runs-on: ubuntu-latest
+    timeout-minutes: 20
     defaults:
       run:
         working-directory: ${{ matrix.job-configs.working-directory }}

.github/workflows/run_notebooks.yml

@@ -15,7 +15,7 @@ on:
     - cron: '0 13 * * *'
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "1.8.4"
 
 jobs:
   build:

.github/workflows/scheduled_test.yml

@@ -2,32 +2,70 @@ name: Scheduled tests
 
 on:
   workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+    inputs:
+      working-directory-force:
+        type: string
+        description: "From which folder this pipeline executes - defaults to all in matrix - example value: libs/partners/anthropic"
+      python-version-force:
+        type: string
+        description: "Python version to use - defaults to 3.9 and 3.11 in matrix - example value: 3.9"
   schedule:
     - cron:  '0 13 * * *'
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "1.8.4"
+  DEFAULT_LIBS: >
+    [
+      "libs/partners/openai",
+      "libs/partners/anthropic",
+      "libs/partners/fireworks",
+      "libs/partners/groq",
+      "libs/partners/mistralai",
+      "libs/partners/google-vertexai",
+      "libs/partners/google-genai",
+      "libs/partners/aws"
+    ]
 
 jobs:
+  compute-matrix:
+    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
+    runs-on: ubuntu-latest
+    name: Compute matrix
+    outputs:
+      matrix: ${{ steps.set-matrix.outputs.matrix }}
+    steps:
+      - name: Set matrix
+        id: set-matrix
+        env:
+          DEFAULT_LIBS: ${{ env.DEFAULT_LIBS }}
+          WORKING_DIRECTORY_FORCE: ${{ github.event.inputs.working-directory-force || '' }}
+          PYTHON_VERSION_FORCE: ${{ github.event.inputs.python-version-force || '' }}
+        run: |
+          # echo "matrix=..." where matrix is a json formatted str with keys python-version and working-directory
+          # python-version should default to 3.9 and 3.11, but is overridden to [PYTHON_VERSION_FORCE] if set
+          # working-directory should default to DEFAULT_LIBS, but is overridden to [WORKING_DIRECTORY_FORCE] if set
+          python_version='["3.9", "3.11"]'
+          working_directory="$DEFAULT_LIBS"
+          if [ -n "$PYTHON_VERSION_FORCE" ]; then
+            python_version="[\"$PYTHON_VERSION_FORCE\"]"
+          fi
+          if [ -n "$WORKING_DIRECTORY_FORCE" ]; then
+            working_directory="[\"$WORKING_DIRECTORY_FORCE\"]"
+          fi
+          matrix="{\"python-version\": $python_version, \"working-directory\": $working_directory}"
+          echo $matrix
+          echo "matrix=$matrix" >> $GITHUB_OUTPUT
   build:
     if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
     name: Python ${{ matrix.python-version }} - ${{ matrix.working-directory }}
     runs-on: ubuntu-latest
+    needs: [compute-matrix]
+    timeout-minutes: 20
     strategy:
       fail-fast: false
       matrix:
-        python-version:
-          - "3.9"
-          - "3.11"
-        working-directory:
-          - "libs/partners/openai"
-          - "libs/partners/anthropic"
-          - "libs/partners/fireworks"
-          - "libs/partners/groq"
-          - "libs/partners/mistralai"
-          - "libs/partners/google-vertexai"
-          - "libs/partners/google-genai"
-          - "libs/partners/aws"
+        python-version: ${{ fromJSON(needs.compute-matrix.outputs.matrix).python-version }}
+        working-directory: ${{ fromJSON(needs.compute-matrix.outputs.matrix).working-directory }}
 
     steps:
       - uses: actions/checkout@v4

cookbook/README.md

@@ -63,4 +63,5 @@ Notebook | Description
 [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.
 [rag-locally-on-intel-cpu.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/rag-locally-on-intel-cpu.ipynb) | Perform Retrieval-Augmented-Generation (RAG) on locally downloaded open-source models using langchain and open source tools and execute it on Intel Xeon CPU. We showed an example of how to apply RAG on Llama 2 model and enable it to answer the queries related to Intel Q1 2024 earnings release.
 [visual_RAG_vdms.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/visual_RAG_vdms.ipynb) | Performs Visual Retrieval-Augmented-Generation (RAG) using videos and scene descriptions generated by open source models.
-[contextual_rag.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/contextual_rag.ipynb) | Performs contextual retrieval-augmented generation (RAG) prepending chunk-specific explanatory context to each chunk before embedding.
+[contextual_rag.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/contextual_rag.ipynb) | Performs contextual retrieval-augmented generation (RAG) prepending chunk-specific explanatory context to each chunk before embedding.
+[rag-agents-locally-on-intel-cpu.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/local_rag_agents_intel_cpu.ipynb) | Build a RAG agent locally with open source models that routes questions through one of two paths to find answers. The agent generates answers based on documents retrieved from either the vector database or retrieved from web search. If the vector database lacks relevant information, the agent opts for web search. Open-source models for LLM and embeddings are used locally on an Intel Xeon CPU to execute this pipeline.

docs/api_reference/create_api_rst.py

@@ -479,11 +479,11 @@ def _package_namespace(package_name: str) -> str:
     Returns:
         modified package_name: Can be either "langchain" or "langchain_{package_name}"
     """
-    return (
-        package_name
-        if package_name == "langchain"
-        else f"langchain_{package_name.replace('-', '_')}"
-    )
+    if package_name == "langchain":
+        return "langchain"
+    if package_name == "standard-tests":
+        return "langchain_tests"
+    return f"langchain_{package_name.replace('-', '_')}"
 
 
 def _package_dir(package_name: str = "langchain") -> Path:

docs/cassettes/extraction_0bb138d7-116e-4542-aa5f-bebf0c301ec6.msgpack.zlib

@@ -0,0 +1 @@
+eNqNVXlsFFUYXzQxlUTBqCjGY1xJFOls59qrTaN0l4Wlx5Zu1S4Vlrdv3u5OO5fzZpfdIh54H9WMZ/APr5ZdrLUKbTmqeMSooIgoRi0oGkMsoAGtGiXE1LfbrbSWROePmXnv+97vu37f99bl08jAkqbO6JVUExkAmmSBrXV5A92SQti8O6cgM6mJ3Y2hcHNXypCGr02apo4rKyqALjk0HalAckBNqUizFTAJzAryr8uoCNMd08Ts/hnCGruCMAYJhO2VVOsaO9SILdUkCztH3ZwSPTwib9ELKc5eTtkNTUYFWQojw762nJpyQJisATCWsAmI5N9q/8Ll/xPX+f9w+am4wnTcFWRH0UQkF7YSukkLGq1IqlTQVMkeS77YNBBQyCIOZIzIhokUnWTfTBkFJMbhXptPIiCS2hy0ze5Oati0+qbm+1UAISLoSIWaKKkJ65VEh6SXUyKKy8BEPcRnFRWrafW0I6TTQJbSKDd+ynoN6LosQVCQV7RhTe0txUibWR1NF/cUYqNJBVXTGggRJxYGKxqzhBgqxTqcnIN7LUOThEmqTApNy4D4k9OL8tcnC3QA2wkIXSKdlRs/3DdZR8PWhnoAQ+EpkMCASWsDMBSX0D9530ippqQgK+9rnG6uJDxljnewrMO9aQowzqrQ2lAsxNYph5FpZGmoEQzrBSYHNa1dQtbwaDQK49GYUu0J+ZeChpsYb21DXUuD5HClBNDWiPTQEtxe44oyuAkAQ0SexZxGs26e4xmB8bpo1sE4WAdL1zUGg0yNlI5E42wkwCtB5kYg3hDNYuaWTN1iRstCn+zLyvGkwMYy4dBNCRdW4i2iaEYXMfVRsd2h10eT4XA2Elwa09oY2SV5IpFlVRTxLpWWxOpAU8iR5Ey1vrmt4cZAQM1EXZyHa2xPuds6WAHURJcK2aQzzfNeYZJ7Tp6hmZKHLkbwMIWnb4IbMlITZtLq4hnPRgNhnbQ4uitHUmam8LpuwkO0e2e+1OovhmpPUXhOt59w0toRMKRyiuOoBi1NcQwnUKy3khcqnW5qcX1zr69kpvm0FNzUbAAVxwkNF01QPg+TKbUdiT2+05J9R4HspJIF90mP0iijaxjRJa+s3ha6aXzI0UF//3hn0ZqRAKrUUTRr7SiyfnVHZrUISb8n06sVxtsh8FIMpWB8oHREN7SCGeIQrWCrixW8fSXJBO96SKwMzZLUskMZmrQ5kiVFIvksvkuTFlvdTpLsbdMVTK0dkZmcF4rVYN6crGEghRC2YPsUjOD1et84vdIEFE9UvG5uaKoWRpO9YTkFb5uuUIJ4kcG9mQltWhKt4XlkEYVej8vr5FzOGAJczA2cHMexfAyQUoBYPO7eTkafBAlKoZi6Zpg0RpBcK2bWGi5XQKYwY6p51sm7SKRVlKRCOSWicCrm1wox4CpKN5CsAfFVX4D2AZhEdLjIPyvvjzQsrA/6trTQk4lEh/TxKy2valiV4vFcGBmkMFYPlLWUSIalgXIEq2lhxBrwIFfMCTkOIsHliYM4XUPG0ATaP7TrLkzaPJCJ72lo9Sf5anulIPD2KkoB1R4XKVPx4rszV4hVTbw3Y80VD5XZis+ZDz+2rPZd5oJ7vj25oObZ1iNDj+zZcYL6aaHfP/u8+RHjQGDfvHlbfXNPHn9sS+uChp83zBp5feS3rw9cbq/ZeIHpu0a7ePSLnkM/nAgeG7rvyVu3a1tOVu3+E36Bti9/8MBfT73/Dkgff/uXQ0Pf5wZnNl5SverYHVfe/fmiTbufkp5deVF1stN2oTz43jx3cMFg3Wbho8cHlsz58dNvLt71zr5zsp1lVx7ae50vRH/3uLrkkueemPNGwrn34+z9s48+PHMmOlj7aN1VnVfv7AzsXft7rK9qY+UnNe5v5juPfvDrQ0+89Apfdd1o/8ogvTZcuerg4dlHP23Zvw/6d7a+1fhH11WDewbm1ApXPO9b9eal3x823z/bEbj3rPXPZEf/rGmZb1vffFt61odztevr9hzJ9J7/2e7rhdYTq5+uHX53f9OXYw88ZxtZdZ5fuqxs1+3Hqjq9ZWNfReHI+X/c89LYaJkSCa64q7/h3Oi2zWh598srBh2ZpV3wt3NstrGxM23O3MqR42fYbH8DSCB5jw==