Fix: Make LLM base_url optional to prevent startup hang

- Changed llm_base_url in config.py to be optional (defaulting to None).
- Updated 11y_agent.py to only pass ase_url to the OpenAI client if it is explicitly provided.

This prevents potential network hangs during OpenAI client initialization on platforms like Hugging Face Spaces, making the default setup more robust.

agent/a11y_agent.py

@@ -182,8 +182,12 @@ def create_agent(language: Optional[str] = None) -> A11yExpertAgent:
     vector_store.connect()
     
     api_key = settings.openai_api_key
-    base_url = settings.llm_base_url
-    llm_client = OpenAI(api_key=api_key, base_url=base_url)
+    
+    client_args = {"api_key": api_key}
+    if settings.llm_base_url:
+        client_args["base_url"] = settings.llm_base_url
+        
+    llm_client = OpenAI(**client_args)
     
     agent = A11yExpertAgent(
         vector_store=vector_store,

config.py

@@ -48,9 +48,9 @@ class Settings(BaseSettings):
         default="gpt-4o",
         description="Language model for chat completions"
     )
-    llm_base_url: str = Field(
-        default="https://api.openai.com/v1",
-        description="Base URL for OpenAI-compatible API"
+    llm_base_url: Optional[str] = Field(
+        default=None,
+        description="Base URL for OpenAI-compatible API (optional)"
     )
     
     # Embeddings Configuration