changed to uvicorn setup for HF v14

main/api.py

@@ -51,8 +51,6 @@ class InferenceApi(LitAPI):
             stream: bool = False
     ) -> Any:
         """Make an authenticated request to the LLM Server."""
-        access_token = os.environ.get("InfAPITokenWrite")
-        headers = {"Authorization": f"Bearer {access_token}"} if access_token else {}
         base_url = self.llm_config.get('base_url', 'http://localhost:8002')
         full_endpoint = f"{base_url.rstrip('/')}/{self._get_endpoint(endpoint).lstrip('/')}"
 
@@ -64,16 +62,14 @@ class InferenceApi(LitAPI):
                         method,
                         self._get_endpoint(endpoint),
                         params=params,
-                        json=json,
-                        headers=headers
+                        json=json
                     )
                 else:
                     response = await client.request(
                         method,
                         self._get_endpoint(endpoint),
                         params=params,
-                        json=json,
-                        headers=headers
+                        json=json
                     )
                     response.raise_for_status()
                     return response