cfunklabs-rag-react-docs 0.1.2__tar.gz → 0.1.3__tar.gz

{cfunklabs_rag_react_docs-0.1.2 → cfunklabs_rag_react_docs-0.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cfunklabs-rag-react-docs
-Version: 0.1.2
+Version: 0.1.3
 Summary: Retrieval-only MCP server over the indexed React documentation, with a prebuilt index downloaded on first run.
 Project-URL: Homepage, https://github.com/cfunklabs/rag-react-docs
 Project-URL: Repository, https://github.com/cfunklabs/rag-react-docs
@@ -13,6 +13,7 @@ Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python :: 3
 Classifier: Topic :: Software Development :: Documentation
 Requires-Python: >=3.14
+Requires-Dist: certifi>=2024.0.0
 Requires-Dist: chromadb>=1.5.9
 Requires-Dist: mcp>=1.28.1
 Requires-Dist: platformdirs>=4.0.0

{cfunklabs_rag_react_docs-0.1.2 → cfunklabs_rag_react_docs-0.1.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "cfunklabs-rag-react-docs"
-version = "0.1.2"
+version = "0.1.3"
 description = "Retrieval-only MCP server over the indexed React documentation, with a prebuilt index downloaded on first run."
 readme = "README.md"
 requires-python = ">=3.14"
@@ -17,6 +17,7 @@ classifiers = [
 # Runtime deps for the published wheel: retrieval + MCP server only. The generation/ingestion
 # stack (langchain, langgraph, anthropic, ...) is dev-only and lives in [dependency-groups].
 dependencies = [
+    "certifi>=2024.0.0",
     "chromadb>=1.5.9",
     "mcp>=1.28.1",
     "platformdirs>=4.0.0",

{cfunklabs_rag_react_docs-0.1.2 → cfunklabs_rag_react_docs-0.1.3}/src/rag_react_docs/__init__.py

@@ -5,4 +5,4 @@ ChromaDB index is downloaded from a GitHub Release on first run (see `datastore.
 users never run the ingestion pipeline themselves.
 """
 
-__version__ = "0.1.2"
+__version__ = "0.1.3"

{cfunklabs_rag_react_docs-0.1.2 → cfunklabs_rag_react_docs-0.1.3}/src/rag_react_docs/datastore.py

@@ -2,18 +2,21 @@
 
 The published package ships no vectors: the ~34 MB index lives as a GitHub Release asset and is
 fetched + cached the first time the server needs it. Subsequent runs read straight from the
-cache and work offline. Only the standard library is used for the download so the wheel stays
-dependency-light (no httpx/requests).
+cache and work offline. The download uses urllib with an explicit certifi CA bundle so TLS
+verification works even on interpreters that lack a configured system cert store (e.g. the
+python.org macOS framework build), rather than relying on the ambient default SSL context.
 """
 
 import hashlib
 import os
 import shutil
+import ssl
 import tarfile
 import tempfile
 import urllib.request
 from pathlib import Path
 
+import certifi
 import chromadb
 
 from .config import COLLECTION_NAME, INDEX_URL, datastore_dir
@@ -24,9 +27,14 @@ from .config import COLLECTION_NAME, INDEX_URL, datastore_dir
 # looks valid on the next run.
 _MARKER = "chroma.sqlite3"
 
+# Verify TLS against certifi's CA bundle instead of the interpreter default. Some Python builds
+# (notably python.org macOS framework installs) ship without usable root certificates, which
+# makes the default context fail with CERTIFICATE_VERIFY_FAILED on any HTTPS download.
+_SSL_CONTEXT = ssl.create_default_context(cafile=certifi.where())
+
 
 def _download(url: str, dest: Path) -> None:
-    with urllib.request.urlopen(url) as response, open(dest, "wb") as out:
+    with urllib.request.urlopen(url, context=_SSL_CONTEXT) as response, open(dest, "wb") as out:
         shutil.copyfileobj(response, out)
 
 
@@ -46,7 +54,7 @@ def _verify_checksum(archive: Path, url: str) -> None:
     tolerated (some releases may not publish one) but a present-and-mismatched one is fatal.
     """
     try:
-        with urllib.request.urlopen(url + ".sha256") as response:
+        with urllib.request.urlopen(url + ".sha256", context=_SSL_CONTEXT) as response:
             expected = response.read().decode().strip().split()[0]
     except Exception:
         return

{cfunklabs_rag_react_docs-0.1.2 → cfunklabs_rag_react_docs-0.1.3}/src/rag_react_docs/server.py

@@ -11,7 +11,7 @@ import sys
 
 from mcp.server.fastmcp import FastMCP
 
-from .config import DEFAULT_TOP_K
+from .config import DEFAULT_TOP_K, INDEX_URL
 from .datastore import get_rag_collection
 from .retrieval import retrieve_chunks
 
@@ -19,12 +19,23 @@ from .retrieval import retrieve_chunks
 mcp = FastMCP("rag-react-docs")
 
 
-def _collection_is_empty() -> bool:
+def _index_error() -> str | None:
+    """Return a human-readable reason the index is unavailable, or None if it's ready.
+
+    Distinguishes a real load/download failure (surfacing the underlying exception and the
+    URL it tried) from a genuinely empty collection, so callers report the actual cause rather
+    than a catch-all "index is empty" message.
+    """
     try:
-        return get_rag_collection().count() == 0
-    except Exception:
-        # Treat a missing/uninitialized/failed-download collection the same as an empty one.
-        return True
+        count = get_rag_collection().count()
+    except Exception as exc:
+        return (
+            f"Could not load the documentation index (downloaded from {INDEX_URL}): "
+            f"{type(exc).__name__}: {exc}"
+        )
+    if count == 0:
+        return "The documentation index loaded but contains no documents."
+    return None
 
 
 @mcp.tool()
@@ -40,17 +51,10 @@ def search_docs(question: str, k: int = DEFAULT_TOP_K) -> list[dict]:
         - content:  the raw chunk text to ground an answer on
         - distance: the retrieval distance (lower is more similar)
     """
-    if _collection_is_empty():
-        return [
-            {
-                "source": "rag-react-docs",
-                "content": (
-                    "The documentation index is empty or could not be loaded. "
-                    "Check network access on first run so the index can be downloaded."
-                ),
-                "distance": None,
-            }
-        ]
+    error = _index_error()
+    if error:
+        print(f"[rag-react-docs] {error}", file=sys.stderr)
+        return [{"source": "rag-react-docs", "content": error, "distance": None}]
 
     return retrieve_chunks(question, k)
 
@@ -61,16 +65,11 @@ def main() -> None:
     # JSON-RPC protocol, so anything printed there would corrupt the stream.
     print(f"[rag-react-docs] MCP server starting on stdio (top_k={DEFAULT_TOP_K}).", file=sys.stderr)
     print("[rag-react-docs] Ensuring documentation index is available...", file=sys.stderr)
-    try:
-        if _collection_is_empty():
-            print(
-                "[rag-react-docs] Warning: index empty or unavailable -- check network access.",
-                file=sys.stderr,
-            )
-        else:
-            print("[rag-react-docs] Index ready.", file=sys.stderr)
-    except Exception as exc:  # pragma: no cover - defensive; _collection_is_empty swallows most
-        print(f"[rag-react-docs] Warning: could not verify index: {exc}", file=sys.stderr)
+    error = _index_error()
+    if error:
+        print(f"[rag-react-docs] Warning: {error}", file=sys.stderr)
+    else:
+        print("[rag-react-docs] Index ready.", file=sys.stderr)
 
     print("[rag-react-docs] Ready. Press Ctrl+C to stop.", file=sys.stderr)
     try: