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.

config/rag_config.yaml

@@ -18,6 +18,12 @@ chunking:
   max_chunk_tokens: 500
   overlap_tokens: 50
 
+# تنظیمات مدل چت (LLM) — Avalai
+llm:
+  model: "gpt-4o"
+  base_url: "https://api.avalai.ir/v1"
+  api_key_env: "AVALAI_API_KEY"
+
 tone_file: "config/tone.txt"
 knowledge_base_path: "config/knowledge_base"
 user_info_path: "config/user_info"