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/views.py

@@ -0,0 +1,43 @@
+"""
+ویوهای RAG — چت با استریم
+"""
+from django.http import StreamingHttpResponse
+from rest_framework import status
+from rest_framework.request import Request
+from rest_framework.response import Response
+from rest_framework.views import APIView
+
+from .chat import chat_rag_stream
+
+
+class ChatView(APIView):
+    """
+    چت RAG با استریم.
+    POST با {"message": "متن سوال"} یا query param message
+    """
+
+    def post(self, request: Request):
+        message = request.data.get("message") or request.query_params.get("message")
+        if not message or not isinstance(message, str):
+            return Response(
+                {"code": 400, "msg": "پارامتر message الزامی است."},
+                status=status.HTTP_400_BAD_REQUEST,
+            )
+        message = str(message).strip()
+        if not message:
+            return Response(
+                {"code": 400, "msg": "پیام نباید خالی باشد."},
+                status=status.HTTP_400_BAD_REQUEST,
+            )
+
+        def generate():
+            try:
+                for chunk in chat_rag_stream(message):
+                    yield chunk
+            except Exception as e:
+                yield f"\n[خطا: {e}]"
+
+        return StreamingHttpResponse(
+            generate(),
+            content_type="text/plain; charset=utf-8",
+        )