Update model_api.py

model_api.py

@@ -1,28 +1,21 @@
 from huggingface_hub import InferenceClient
 import os
-from dotenv import load_dotenv
-
-load_dotenv()
 
 def query_model(prompt):
     try:
         HF_TOKEN = os.getenv("HF_TOKEN")
-
-        client = InferenceClient(
+        # You can also set provider at the client level
+        client = InferenceClient(api_key=HF_TOKEN, provider="auto")
+        
+        response = client.chat.completions.create(
             model="Qwen/Qwen2.5-7B-Instruct",
-            token=HF_TOKEN
-        )
-
-        response = client.chat_completion(
             messages=[
                 {"role": "system", "content": "You are a professional fitness trainer."},
                 {"role": "user", "content": prompt}
             ],
-            max_tokens=1200,
+            max_tokens=1500,
             temperature=0.7
         )
-
         return response.choices[0].message.content
-
     except Exception as e:
-        return f"Model Error: {str(e)}"
+        return f"Error: {str(e)}"