Merge branch 'master' into core/inject-partial-to-partial-variables

.github/CODEOWNERS

@@ -0,0 +1,2 @@
+/.github/   @efriis @baskaryan @ccurme
+/libs/packages.yml   @efriis

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,7 +1,7 @@
 Thank you for contributing to LangChain!
 
 - [ ] **PR title**: "package: description"
-  - Where "package" is whichever of langchain, community, core, etc. is being modified. Use "docs: ..." for purely docs changes, "templates: ..." for template changes, "infra: ..." for CI changes.
+  - Where "package" is whichever of langchain, community, core, etc. is being modified. Use "docs: ..." for purely docs changes, "infra: ..." for CI changes.
   - Example: "community: add foobar LLM"
 
 

.github/scripts/check_diff.py

@@ -307,7 +307,7 @@ def _get_configs_for_multi_dirs(
                 f"Unknown lib: {file}. check_diff.py likely needs "
                 "an update for this new library!"
             )
-        elif any(file.startswith(p) for p in ["docs/", "templates/", "cookbook/"]):
+        elif any(file.startswith(p) for p in ["docs/", "cookbook/"]):
             if file.startswith("docs/"):
                 docs_edited = True
             dirs_to_run["lint"].add(".")

.github/scripts/get_min_versions.py

@@ -7,12 +7,17 @@
     # for python 3.10 and below, which doesnt have stdlib tomllib
     import tomli as tomllib
 
-from packaging.version import parse as parse_version
 from packaging.specifiers import SpecifierSet
 from packaging.version import Version
 
+
+import requests
+from packaging.version import parse
+from typing import List
+
 import re
 
+
 MIN_VERSION_LIBS = [
     "langchain-core",
     "langchain-community",
@@ -31,29 +36,61 @@
 ]
 
 
-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)
-    if _match:
-        return _match.group(1)
+def get_pypi_versions(package_name: str) -> List[str]:
+    """
+    Fetch all available versions for a package from PyPI.
+
+    Args:
+        package_name (str): Name of the package
+
+    Returns:
+        List[str]: List of all available versions
 
-    # case >=x.x.x,<y.y.y
-    _match = re.match(f"^>=({vstring}),<({vstring})$", version)
-    if _match:
-        _min = _match.group(1)
-        _max = _match.group(2)
-        assert parse_version(_min) < parse_version(_max)
-        return _min
+    Raises:
+        requests.exceptions.RequestException: If PyPI API request fails
+        KeyError: If package not found or response format unexpected
+    """
+    pypi_url = f"https://pypi.org/pypi/{package_name}/json"
+    response = requests.get(pypi_url)
+    response.raise_for_status()
+    return list(response.json()["releases"].keys())
 
-    # case x.x.x
-    _match = re.match(f"^({vstring})$", version)
-    if _match:
-        return _match.group(1)
 
-    raise ValueError(f"Unrecognized version format: {version}")
+def get_minimum_version(package_name: str, spec_string: str) -> Optional[str]:
+    """
+    Find the minimum published version that satisfies the given constraints.
+
+    Args:
+        package_name (str): Name of the package
+        spec_string (str): Version specification string (e.g., ">=0.2.43,<0.4.0,!=0.3.0")
+
+    Returns:
+        Optional[str]: Minimum compatible version or None if no compatible version found
+    """
+    # rewrite occurrences of ^0.0.z to 0.0.z (can be anywhere in constraint string)
+    spec_string = re.sub(r"\^0\.0\.(\d+)", r"0.0.\1", spec_string)
+    # rewrite occurrences of ^0.y.z to >=0.y.z,<0.y+1 (can be anywhere in constraint string)
+    for y in range(1, 10):
+        spec_string = re.sub(rf"\^0\.{y}\.(\d+)", rf">=0.{y}.\1,<0.{y+1}", spec_string)
+    # rewrite occurrences of ^x.y.z to >=x.y.z,<x+1.0.0 (can be anywhere in constraint string)
+    for x in range(1, 10):
+        spec_string = re.sub(
+            rf"\^{x}\.(\d+)\.(\d+)", rf">={x}.\1.\2,<{x+1}", spec_string
+        )
+
+    spec_set = SpecifierSet(spec_string)
+    all_versions = get_pypi_versions(package_name)
+
+    valid_versions = []
+    for version_str in all_versions:
+        try:
+            version = parse(version_str)
+            if spec_set.contains(version):
+                valid_versions.append(version)
+        except ValueError:
+            continue
+
+    return str(min(valid_versions)) if valid_versions else None
 
 
 def get_min_version_from_toml(
@@ -96,7 +133,7 @@ def get_min_version_from_toml(
                 ][0]["version"]
 
             # Use parse_version to get the minimum supported version from version_string
-            min_version = get_min_version(version_string)
+            min_version = get_minimum_version(lib, version_string)
 
             # Store the minimum version in the min_versions dictionary
             min_versions[lib] = min_version
@@ -112,6 +149,20 @@ def check_python_version(version_string, constraint_string):
     :param constraint_string: A string representing the package's Python version constraints (e.g. ">=3.6, <4.0").
     :return: True if the version matches the constraints, False otherwise.
     """
+
+    # rewrite occurrences of ^0.0.z to 0.0.z (can be anywhere in constraint string)
+    constraint_string = re.sub(r"\^0\.0\.(\d+)", r"0.0.\1", constraint_string)
+    # rewrite occurrences of ^0.y.z to >=0.y.z,<0.y+1.0 (can be anywhere in constraint string)
+    for y in range(1, 10):
+        constraint_string = re.sub(
+            rf"\^0\.{y}\.(\d+)", rf">=0.{y}.\1,<0.{y+1}.0", constraint_string
+        )
+    # rewrite occurrences of ^x.y.z to >=x.y.z,<x+1.0.0 (can be anywhere in constraint string)
+    for x in range(1, 10):
+        constraint_string = re.sub(
+            rf"\^{x}\.0\.(\d+)", rf">={x}.0.\1,<{x+1}.0.0", constraint_string
+        )
+
     try:
         version = Version(version_string)
         constraints = SpecifierSet(constraint_string)

.github/workflows/_integration_test.yml

@@ -41,12 +41,6 @@ jobs:
         shell: bash
         run: poetry run pip install "boto3<2" "google-cloud-aiplatform<2"
 
-      - name: 'Authenticate to Google Cloud'
-        id: 'auth'
-        uses: google-github-actions/auth@v2
-        with:
-          credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
-
       - name: Run integration tests
         shell: bash
         env:

.github/workflows/_release.yml

@@ -95,9 +95,30 @@ jobs:
           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 $REGEX || true | head -1)
+          PREV_TAG="$PKG_NAME==${VERSION%.*}.$(( ${VERSION##*.} - 1 ))"; [[ "${VERSION##*.}" -eq 0 ]] && PREV_TAG=""
+
+          # backup case if releasing e.g. 0.3.0, looks up last release
+          # note if last release (chronologically) was e.g. 0.1.47 it will get 
+          # that instead of the last 0.2 release
+          if [ -z "$PREV_TAG" ]; then
+            REGEX="^$PKG_NAME==\\d+\\.\\d+\\.\\d+\$"
+            echo $REGEX
+            PREV_TAG=$(git tag --sort=-creatordate | (grep -P $REGEX || true) | head -1)
+          fi
+
+          # if PREV_TAG is empty, let it be empty
+          if [ -z "$PREV_TAG" ]; then
+            echo "No previous tag found - first release"
+          else
+            # confirm prev-tag actually exists in git repo with git tag
+            GIT_TAG_RESULT=$(git tag -l "$PREV_TAG")
+            if [ -z "$GIT_TAG_RESULT" ]; then
+              echo "Previous tag $PREV_TAG not found in git repo"
+              exit 1
+            fi
+          fi
+
+
           TAG="${PKG_NAME}==${VERSION}"
           if [ "$TAG" == "$PREV_TAG" ]; then
             echo "No new version to release"
@@ -231,7 +252,7 @@ jobs:
         working-directory: ${{ inputs.working-directory }}
         id: min-version
         run: |
-          poetry run pip install packaging
+          poetry run pip install packaging requests
           python_version="$(poetry run python --version | awk '{print $2}')"
           min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml release $python_version)"
           echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
@@ -246,12 +267,6 @@ jobs:
           make tests
         working-directory: ${{ inputs.working-directory }}
 
-      - name: 'Authenticate to Google Cloud'
-        id: 'auth'
-        uses: google-github-actions/auth@v2
-        with:
-          credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
-
       - name: Import integration test dependencies
         run: poetry install --with test,test_integration
         working-directory: ${{ inputs.working-directory }}

.github/workflows/_test.yml

@@ -47,7 +47,7 @@ jobs:
         id: min-version
         shell: bash
         run: |
-          poetry run pip install packaging tomli
+          poetry run pip install packaging tomli requests
           python_version="$(poetry run python --version | awk '{print $2}')"
           min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml pull_request $python_version)"
           echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"

.github/workflows/check_diffs.yml

@@ -31,7 +31,7 @@ jobs:
         uses: Ana06/get-changed-files@v2.2.0
       - id: set-matrix
         run: |
-          python -m pip install packaging
+          python -m pip install packaging requests
           python .github/scripts/check_diff.py ${{ steps.files.outputs.all }} >> $GITHUB_OUTPUT
     outputs:
       lint: ${{ steps.set-matrix.outputs.lint }}

Makefile

@@ -66,12 +66,12 @@ spell_fix:
 
 ## lint: Run linting on the project.
 lint lint_package lint_tests:
-	poetry run ruff check docs templates cookbook
-	poetry run ruff format docs templates cookbook --diff
-	poetry run ruff check --select I docs templates cookbook
-	git grep 'from langchain import' docs/docs templates cookbook | grep -vE 'from langchain import (hub)' && exit 1 || exit 0
+	poetry run ruff check docs cookbook
+	poetry run ruff format docs cookbook cookbook --diff
+	poetry run ruff check --select I docs cookbook
+	git grep 'from langchain import' docs/docs 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 format docs cookbook
+	poetry run ruff check --select I --fix docs cookbook

README.md

@@ -59,7 +59,8 @@ For these applications, LangChain simplifies the entire application lifecycle:
 
 - **[LangGraph Cloud](https://langchain-ai.github.io/langgraph/cloud/)**: Turn your LangGraph applications into production-ready APIs and Assistants.
 
-![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](docs/static/svg/langchain_stack_062024.svg "LangChain Architecture Overview")
+![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](docs/static/svg/langchain_stack_112024.svg#gh-light-mode-only "LangChain Architecture Overview")
+![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](docs/static/svg/langchain_stack_112024_dark.svg#gh-dark-mode-only "LangChain Architecture Overview")
 
 ## 🧱 What can you build with LangChain?
 

cookbook/README.md

@@ -62,4 +62,5 @@ Notebook | Description
 [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.
 [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.
+[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.