infra: lint new docs to match templates (#22786)

.github/workflows/check_new_docs.yml

@@ -0,0 +1,31 @@
+---
+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+# There's no point in testing an outdated version of the code.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 }}

docs/scripts/check_templates.py

@@ -0,0 +1,43 @@
+import re
+import sys
+from pathlib import Path
+from typing import Union
+
+CURR_DIR = Path(__file__).parent.absolute()
+
+CHAT_MODEL_HEADERS = (
+    "## Overview",
+    "### Integration details",
+    "### Model features",
+    "## Setup",
+    "## Instantiation",
+    "## Invocation",
+    "## Chaining",
+    "## API reference",
+)
+CHAT_MODEL_REGEX = r".*".join(CHAT_MODEL_HEADERS)
+
+
+def check_chat_model(path: Path) -> None:
+    with open(path, "r") as f:
+        doc = f.read()
+    if not re.search(CHAT_MODEL_REGEX, doc, re.DOTALL):
+        raise ValueError(
+            f"Document {path} does not match the ChatModel Integration page template. "
+            f"Please see https://github.com/langchain-ai/langchain/issues/22296 for "
+            f"instructions on how to correctly format a ChatModel Integration page."
+        )
+
+
+def main(*new_doc_paths: Union[str, Path]) -> None:
+    for path in new_doc_paths:
+        path = Path(path).resolve().absolute()
+        if CURR_DIR.parent / "docs" / "integrations" / "chat" in path.parents:
+            print(f"Checking chat model page {path}")
+            check_chat_model(path)
+        else:
+            continue
+
+
+if __name__ == "__main__":
+    main(*sys.argv[1:])