Add LLM configuration and update URL routing

- Introduced LLM configuration in rag_config.yaml and corresponding LLMConfig class in config.py.
- Updated load_rag_config function to parse LLM settings from the configuration file.
- Added new API route for RAG in urls.py to facilitate access to the chat model.
- Modified QdrantVectorStore to use query_points method for improved functionality.

rag/vector_store.py

@@ -98,20 +98,24 @@ class QdrantVectorStore:
     ) -> list[dict]:
         """
         جستجوی شباهت بر اساس query vector.
+        از query_points استفاده می‌کند (qdrant-client >= 2.0).
         """
-        results = self.client.search(
+        response = self.client.query_points(
             collection_name=self.qdrant.collection_name,
-            query_vector=query_vector,
+            query=query_vector,
             limit=limit,
             score_threshold=score_threshold,
         )
+        points = getattr(response, "points", []) or []
 
         return [
             {
                 "id": str(r.id),
-                "score": r.score,
-                "text": r.payload.get("text", ""),
-                "metadata": {k: v for k, v in r.payload.items() if k != "text"},
+                "score": float(r.score) if r.score is not None else 0.0,
+                "text": (r.payload or {}).get("text", ""),
+                "metadata": {
+                    k: v for k, v in (r.payload or {}).items() if k != "text"
+                },
             }
-            for r in results
+            for r in points
         ]