infra: ci matrix (#14306)

.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/_all_ci.yml

@@ -1,21 +1,24 @@
 ---
-name: libs/langchain CI
+name: langchain CI
 
 on:
-  push:
+  workflow_call:
-    branches: [master]
+    inputs:
-  pull_request:
+      working-directory:
-    paths:
+        required: true
-      - ".github/actions/poetry_setup/action.yml"
+        type: string
-      - ".github/tools/**"
+        description: "From which folder this pipeline executes"
-      - ".github/workflows/_lint.yml"
+  workflow_dispatch:
-      - ".github/workflows/_test.yml"
+    inputs:
-      - ".github/workflows/_pydantic_compatibility.yml"
+      working-directory:
-      - ".github/workflows/langchain_ci.yml"
+        required: true
-      - "libs/*"
+        type: choice
-      - "libs/langchain/**"
+        default: 'libs/langchain'
-      - "libs/core/**"
+        options:
-  workflow_dispatch: # Allows to trigger the workflow manually in GitHub UI
+        - 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.
@@ -24,43 +27,40 @@ 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
     with:
-      working-directory: libs/langchain
+      working-directory: ${{ inputs.working-directory }}
     secrets: inherit
 
   test:
     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
+    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
     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:
@@ -68,7 +68,11 @@ jobs:
           - "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
 
@@ -77,7 +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

.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/get-changed-files@v2.2.0
+      - 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 }}
+
+

.github/workflows/langchain_cli_ci.yml

@@ -1,47 +0,0 @@
----
-name: libs/cli 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_cli_ci.yml'
-      - 'libs/cli/**'
-      - 'libs/*'
-  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
-
-# 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
-
-env:
-  POETRY_VERSION: "1.6.1"
-  WORKDIR: "libs/cli"
-
-jobs:
-  lint:
-    uses:
-      ./.github/workflows/_lint.yml
-    with:
-      working-directory: libs/cli
-      langchain-location: ../langchain
-    secrets: inherit
-
-  test:
-    uses:
-      ./.github/workflows/_test.yml
-    with:
-      working-directory: libs/cli
-    secrets: inherit

.github/workflows/langchain_core_ci.yml

@@ -1,52 +0,0 @@
----
-name: libs/langchain core 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_core_ci.yml'
-      - 'libs/core/**'
-  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
-
-# 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
-
-env:
-  POETRY_VERSION: "1.6.1"
-  WORKDIR: "libs/core"
-
-jobs:
-  lint:
-    uses:
-      ./.github/workflows/_lint.yml
-    with:
-      working-directory: libs/core
-    secrets: inherit
-
-  test:
-    uses:
-      ./.github/workflows/_test.yml
-    with:
-      working-directory: libs/core
-    secrets: inherit
-
-  pydantic-compatibility:
-    uses:
-      ./.github/workflows/_pydantic_compatibility.yml
-    with:
-      working-directory: libs/core
-    secrets: inherit

.github/workflows/langchain_experimental_ci.yml

@@ -1,136 +0,0 @@
----
-name: libs/experimental 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/langchain_experimental_ci.yml"
-      - "libs/*"
-      - "libs/experimental/**"
-      - "libs/langchain/**"
-      - "libs/core/**"
-  workflow_dispatch: # Allows to trigger the workflow manually in GitHub UI
-
-# 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
-
-env:
-  POETRY_VERSION: "1.6.1"
-  WORKDIR: "libs/experimental"
-
-jobs:
-  lint:
-    uses: ./.github/workflows/_lint.yml
-    with:
-      working-directory: libs/experimental
-    secrets: inherit
-
-  test:
-    uses: ./.github/workflows/_test.yml
-    with:
-      working-directory: libs/experimental
-    secrets: inherit
-
-  compile-integration-tests:
-    uses: ./.github/workflows/_compile_integration_test.yml
-    with:
-      working-directory: libs/experimental
-    secrets: inherit
-
-  # It's possible that langchain-experimental works fine with the latest *published* langchain,
-  # but is broken with the langchain on `master`.
-  #
-  # We want to catch situations like that *before* releasing a new langchain, hence this test.
-  test-with-latest-langchain:
-    runs-on: ubuntu-latest
-    defaults:
-      run:
-        working-directory: ${{ env.WORKDIR }}
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
-    name: test with unpublished langchain - Python ${{ matrix.python-version }}
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
-        uses: "./.github/actions/poetry_setup"
-        with:
-          python-version: ${{ matrix.python-version }}
-          poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ env.WORKDIR }}
-          cache-key: unpublished-langchain
-
-      - name: Install dependencies
-        shell: bash
-        run: |
-          echo "Running tests with unpublished langchain, installing dependencies with poetry..."
-          poetry install
-
-          echo "Editably installing langchain outside of poetry, to avoid messing up lockfile..."
-          poetry run pip install -e ../langchain
-          poetry run pip install -e ../core
-
-      - name: Run tests
-        run: make test
-  extended-tests:
-    runs-on: ubuntu-latest
-    defaults:
-      run:
-        working-directory: ${{ env.WORKDIR }}
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
-    name: Python ${{ matrix.python-version }} extended tests
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
-        uses: "./.github/actions/poetry_setup"
-        with:
-          python-version: ${{ matrix.python-version }}
-          poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: libs/experimental
-          cache-key: extended
-
-      - name: Install dependencies
-        shell: bash
-        run: |
-          echo "Running extended tests, installing dependencies with poetry..."
-          poetry install -E extended_testing
-
-      - name: Run extended tests
-        run: make extended_tests
-
-      - name: Ensure the tests did not create any additional files
-        shell: bash
-        run: |
-          set -eu
-
-          STATUS="$(git status)"
-          echo "$STATUS"
-
-          # grep will exit non-zero if the target message isn't found,
-          # and `set -e` above will cause the step to fail.
-          echo "$STATUS" | grep 'nothing to commit, working tree clean'