Fix LLM Access Error on App.

app.py

@@ -35,7 +35,11 @@ def create_client() -> Optional[InferenceClient]:
     if not HF_TOKEN:
         return None
     try:
-        return InferenceClient(model=MODEL_ID, token=HF_TOKEN)
+        # Use provider parameter for Inference Providers API
+        return InferenceClient(
+            provider="hf-inference",
+            api_key=HF_TOKEN,
+        )
     except Exception as e:
         print(f"Error creating client: {e}")
         return None
@@ -94,6 +98,7 @@ def generate_response(
     try:
         response_text = ""
         stream = client.chat_completion(
+            model=MODEL_ID,
             messages=messages,
             max_tokens=MAX_NEW_TOKENS,
             temperature=TEMPERATURE,
@@ -109,10 +114,13 @@ def generate_response(
                 
     except Exception as e:
         error_msg = str(e)
+        print(f"[DEBUG] Full error: {error_msg}")  # Log full error for debugging
         if "401" in error_msg or "unauthorized" in error_msg.lower():
-            yield "⚠️ **Authentication Error**: Invalid HuggingFace token. Please check your API token."
+            yield f"⚠️ **Authentication Error**: The model API returned 401. This could mean:\n\n1. The model `{MODEL_ID}` may require accepting terms at the model page\n2. The model may have been gated or moved\n3. Token permissions issue\n\n**Debug info**: {error_msg[:200]}"
         elif "429" in error_msg or "rate" in error_msg.lower():
             yield "⚠️ **Rate Limit**: Too many requests. Please wait a moment and try again."
+        elif "503" in error_msg or "loading" in error_msg.lower():
+            yield "⚠️ **Model Loading**: The model is currently loading. Please try again in a few seconds."
         else:
             yield f"⚠️ **Error**: {error_msg}"