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/config.py

@@ -32,11 +32,19 @@ class ChunkingConfig:
     overlap_tokens: int = 50
 
 
+@dataclass
+class LLMConfig:
+    model: str = "gpt-4o"
+    base_url: str | None = None
+    api_key_env: str | None = None
+
+
 @dataclass
 class RAGConfig:
     embedding: EmbeddingConfig
     qdrant: QdrantConfig
     chunking: ChunkingConfig
+    llm: LLMConfig = field(default_factory=LLMConfig)
     tone_file: str = "config/tone.txt"
     knowledge_base_path: str = "config/knowledge_base"
     user_info_path: str = "config/user_info"
@@ -82,10 +90,18 @@ def load_rag_config(config_path: str | Path | None = None) -> RAGConfig:
         overlap_tokens=ch.get("overlap_tokens", 50),
     )
 
+    llm_data = data.get("llm", {})
+    llm = LLMConfig(
+        model=llm_data.get("model", "gpt-4o"),
+        base_url=llm_data.get("base_url"),
+        api_key_env=llm_data.get("api_key_env"),
+    )
+
     return RAGConfig(
         embedding=embedding,
         qdrant=qdrant,
         chunking=chunking,
+        llm=llm,
         tone_file=data.get("tone_file", "config/tone.txt"),
         knowledge_base_path=data.get("knowledge_base_path", "config/knowledge_base"),
         user_info_path=data.get("user_info_path", "config/user_info"),