Merge remote-tracking branch 'upstream/master'

.github/CONTRIBUTING.md

@@ -23,7 +23,7 @@ It's essential that we maintain great documentation and testing. If you:
   - Update any affected example notebooks and documentation. These live in `docs`.
   - Update unit and integration tests when relevant.
 - Add a feature
-  - Add a demo notebook in `docs/modules`.
+  - Add a demo notebook in `docs/docs/`.
   - Add unit and integration tests.
 
 We are a small, progress-oriented team. If there's something you'd like to add or change, opening a pull request is the
@@ -72,9 +72,10 @@ tell Poetry to use the virtualenv python environment (`poetry config virtualenvs
 
 ### Core vs. Experimental
 
-This repository contains two separate projects:
+This repository contains three separate projects:
 - `langchain`: core langchain code, abstractions, and use cases.
-- `langchain.experimental`: see the [Experimental README](https://github.com/langchain-ai/langchain/tree/master/libs/experimental/README.md) for more information.
+- `langchain_core`: contain interfaces for key abstractions as well as logic for combining them in chains (LCEL).
+- `langchain_experimental`: see the [Experimental README](https://github.com/langchain-ai/langchain/tree/master/libs/experimental/README.md) for more information.
 
 Each of these has its own development environment. Docs are run from the top-level makefile, but development
 is split across separate test & release flows.
@@ -128,6 +129,24 @@ make docker_tests
 
 There are also [integration tests and code-coverage](https://github.com/langchain-ai/langchain/tree/master/libs/langchain/tests/README.md) available.
 
+### Only develop langchain_core or langchain_experimental
+
+If you are only developing `langchain_core` or `langchain_experimental`, you can simply install the dependencies for the respective projects and run tests:
+
+```bash
+cd libs/core
+poetry install --with test
+make test
+```
+
+Or:
+
+```bash
+cd libs/experimental
+poetry install --with test
+make test
+```
+
 ### Formatting and Linting
 
 Run these locally before submitting a PR; the CI system will check also.
@@ -214,6 +233,10 @@ ignore-words-list = 'momento,collison,ned,foor,reworkd,parth,whats,aapply,mysogy
 
 Langchain relies heavily on optional dependencies to keep the Langchain package lightweight.
 
+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.
 

.github/scripts/check_diff.py

@@ -0,0 +1,45 @@
+import json
+import sys
+
+ALL_DIRS = {
+    "libs/core",
+    "libs/langchain",
+    "libs/experimental",
+}
+
+if __name__ == "__main__":
+    files = sys.argv[1:]
+    dirs_to_run = set()
+
+    for file in files:
+        if any(
+            file.startswith(dir_)
+            for dir_ in (
+                ".github/workflows",
+                ".github/tools",
+                ".github/actions",
+                "libs/core",
+                ".github/scripts/check_diff.py",
+            )
+        ):
+            dirs_to_run = ALL_DIRS
+            break
+        elif "libs/community" in file:
+            dirs_to_run.update(
+                ("libs/community", "libs/langchain", "libs/experimental")
+            )
+        elif "libs/partners" in file:
+            partner_dir = file.split("/")[2]
+            dirs_to_run.update(
+                (f"libs/partners/{partner_dir}", "libs/langchain", "libs/experimental")
+            )
+        elif "libs/langchain" in file:
+            dirs_to_run.update(("libs/langchain", "libs/experimental"))
+        elif "libs/experimental" in file:
+            dirs_to_run.add("libs/experimental")
+        elif file.startswith("libs/"):
+            dirs_to_run = ALL_DIRS
+            break
+        else:
+            pass
+    print(json.dumps(list(dirs_to_run)))

.github/workflows/langchain_ci.yml → .github/workflows/_all_ci.yml

@@ -1,20 +1,24 @@
 ---
-name: libs/langchain CI
+name: langchain CI
 
 on:
-  push:
-    branches: [ master ]
-  pull_request:
-    paths:
-      - '.github/actions/poetry_setup/action.yml'
-      - '.github/tools/**'
-      - '.github/workflows/_lint.yml'
-      - '.github/workflows/_test.yml'
-      - '.github/workflows/_pydantic_compatibility.yml'
-      - '.github/workflows/langchain_ci.yml'
-      - 'libs/*'
-      - 'libs/langchain/**'
-  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+  workflow_call:
+    inputs:
+      working-directory:
+        required: true
+        type: string
+        description: "From which folder this pipeline executes"
+  workflow_dispatch:
+    inputs:
+      working-directory:
+        required: true
+        type: choice
+        default: 'libs/langchain'
+        options:
+        - libs/langchain
+        - libs/core
+        - libs/experimental
+
 
 # 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.
@@ -23,55 +27,52 @@ on:
 # 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 }}
+  group: ${{ github.workflow }}-${{ github.ref }}-${{ inputs.working-directory }}
   cancel-in-progress: true
 
 env:
   POETRY_VERSION: "1.6.1"
-  WORKDIR: "libs/langchain"
 
 jobs:
   lint:
-    uses:
-      ./.github/workflows/_lint.yml
+    uses: ./.github/workflows/_lint.yml
     with:
-      working-directory: libs/langchain
+      working-directory: ${{ inputs.working-directory }}
     secrets: inherit
 
   test:
-    uses:
-      ./.github/workflows/_test.yml
+    uses: ./.github/workflows/_test.yml
     with:
-      working-directory: libs/langchain
+      working-directory: ${{ inputs.working-directory }}
     secrets: inherit
 
   compile-integration-tests:
-    uses:
-      ./.github/workflows/_compile_integration_test.yml
+    uses: ./.github/workflows/_compile_integration_test.yml
+    if: ${{ inputs.working-directory != 'libs/core' }}
     with:
-      working-directory: libs/langchain
+      working-directory: ${{ inputs.working-directory }}
     secrets: inherit
 
   pydantic-compatibility:
-    uses:
-      ./.github/workflows/_pydantic_compatibility.yml
+    uses: ./.github/workflows/_pydantic_compatibility.yml
     with:
-      working-directory: libs/langchain
+      working-directory: ${{ inputs.working-directory }}
     secrets: inherit
 
   extended-tests:
     runs-on: ubuntu-latest
-    defaults:
-      run:
-        working-directory: ${{ env.WORKDIR }}
     strategy:
       matrix:
         python-version:
           - "3.8"
           - "3.9"
           - "3.10"
           - "3.11"
+    if: ${{ inputs.working-directory == 'libs/langchain' }}
     name: Python ${{ matrix.python-version }} extended tests
+    defaults:
+      run:
+        working-directory: ${{ inputs.working-directory }}
     steps:
       - uses: actions/checkout@v4
 
@@ -80,7 +81,7 @@ jobs:
         with:
           python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: libs/langchain
+          working-directory: ${{ inputs.working-directory }}
           cache-key: extended
 
       - name: Install dependencies
@@ -89,6 +90,11 @@ jobs:
           echo "Running extended tests, installing dependencies with poetry..."
           poetry install -E extended_testing
 
+      - name: Install langchain core editable
+        shell: bash
+        run: |
+          poetry run pip install -e ../core
+
       - name: Run extended tests
         run: make extended_tests
 

.github/workflows/_lint.yml

@@ -68,15 +68,15 @@ jobs:
         # It doesn't matter how you change it, any change will cause a cache-bust.
         working-directory: ${{ inputs.working-directory }}
         run: |
-          poetry install --with dev,lint,test,typing
+          poetry install --with lint,typing
 
       - name: Install langchain editable
         working-directory: ${{ inputs.working-directory }}
         if: ${{ inputs.langchain-location }}
         env:
           LANGCHAIN_LOCATION: ${{ inputs.langchain-location }}
         run: |
-          pip install -e "$LANGCHAIN_LOCATION"
+          poetry run pip install -e "$LANGCHAIN_LOCATION"
 
       - name: Get .mypy_cache to speed up mypy
         uses: actions/cache@v3

.github/workflows/_pydantic_compatibility.yml

@@ -7,6 +7,10 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
+      langchain-location:
+        required: false
+        type: string
+        description: "Relative path to the langchain library folder"
 
 env:
   POETRY_VERSION: "1.6.1"
@@ -40,6 +44,14 @@ jobs:
         shell: bash
         run: poetry install
 
+      - name: Install langchain editable
+        working-directory: ${{ inputs.working-directory }}
+        if: ${{ inputs.langchain-location }}
+        env:
+          LANGCHAIN_LOCATION: ${{ inputs.langchain-location }}
+        run: |
+          poetry run pip install -e "$LANGCHAIN_LOCATION"
+
       - name: Install the opposite major version of pydantic
         # If normal tests use pydantic v1, here we'll use v2, and vice versa.
         shell: bash

.github/workflows/_test.yml

@@ -7,6 +7,10 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
+      langchain-location:
+        required: false
+        type: string
+        description: "Relative path to the langchain library folder"
 
 env:
   POETRY_VERSION: "1.6.1"
@@ -38,11 +42,20 @@ jobs:
 
       - name: Install dependencies
         shell: bash
-        run: poetry install
+        run: poetry install --with test
+
+      - name: Install langchain editable
+        working-directory: ${{ inputs.working-directory }}
+        if: ${{ inputs.langchain-location }}
+        env:
+          LANGCHAIN_LOCATION: ${{ inputs.langchain-location }}
+        run: |
+          poetry run pip install -e "$LANGCHAIN_LOCATION"
 
       - name: Run core tests
         shell: bash
-        run: make test
+        run: |
+          make test
 
       - name: Ensure the tests did not create any additional files
         shell: bash

.github/workflows/check_diffs.yml

@@ -0,0 +1,47 @@
+---
+name: Check library diffs
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+    paths:
+      - ".github/actions/**"
+      - ".github/tools/**"
+      - ".github/workflows/**"
+      - "libs/**"
+
+# 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@v4
+        with:
+          python-version: '3.10'
+      - id: files
+        uses: Ana06/[email protected]
+      - id: set-matrix
+        run: echo "dirs-to-run=$(python .github/scripts/check_diff.py ${{ steps.files.outputs.all }})" >> $GITHUB_OUTPUT
+    outputs:
+      dirs-to-run: ${{ steps.set-matrix.outputs.dirs-to-run }}
+  ci:
+    needs: [ build ]
+    strategy:
+      matrix:
+        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-run) }}
+    uses: ./.github/workflows/_all_ci.yml
+    with:
+      working-directory: ${{ matrix.working-directory }}
+
+