Merge pull request 'ci: harden the qdrant integration job (5s client timeout + cold storage)' (#60) from ci/harden-qdrant-integration into main

Reviewed-on: #60

src/server.py

@@ -37,6 +37,10 @@ COLLECTION_NAME = os.environ.get("COLLECTION_NAME", "")
 EMBEDDING_MODEL_NAME = os.environ.get("EMBEDDING_MODEL_NAME", "BAAI/bge-small-en-v1.5")
 DEFAULT_LIMIT = int(os.environ.get("SEARCH_LIMIT", "50"))
 
+# Per-request timeout (seconds) for Qdrant. The client default is 5s, which is
+# tight for a cold collection or a busy host: unset means keep that default.
+QDRANT_TIMEOUT = int(os.environ["QDRANT_TIMEOUT"]) if os.environ.get("QDRANT_TIMEOUT") else None
+
 if not QDRANT_URL:
     raise ValueError("QDRANT_URL environment variable is required.")
 if not COLLECTION_NAME:
@@ -61,8 +65,8 @@ def get_qdrant_client() -> QdrantClient:
     """Returns a singleton Qdrant client."""
     global _qdrant_client
     if _qdrant_client is None:
-        logger.info(f"Connecting to Qdrant at {QDRANT_URL}")
-        _qdrant_client = QdrantClient(url=QDRANT_URL)
+        logger.info(f"Connecting to Qdrant at {QDRANT_URL} (timeout={QDRANT_TIMEOUT})")
+        _qdrant_client = QdrantClient(url=QDRANT_URL, timeout=QDRANT_TIMEOUT)
     return _qdrant_client