update HuggingFaceInferenceAPI comment for clarity; change huggingface_hub version to minimum required

app/models/huggingface_inference_api.py

@@ -85,7 +85,7 @@ class HuggingFaceInferenceAPI(BaseLLM):
         print(f"[{self.name}] Calling Inference API with {len(messages)} messages", flush=True)
 
         try:
-            # Use chat completion endpoint
+            # Use chat_completion method (huggingface_hub InferenceClient)
             response = await asyncio.to_thread(
                 self.client.chat_completion,
                 messages=messages,

requirements.txt

@@ -2,7 +2,7 @@ fastapi==0.104.1
 uvicorn[standard]==0.24.0
 transformers==4.36.2
 accelerate==0.25.0
-huggingface_hub==0.19.4
+huggingface_hub>=0.26.0
 pydantic==2.5.0
 importlib-metadata
 --extra-index-url https://download.pytorch.org/whl/cpu