Update app.py

app.py

@@ -296,11 +296,11 @@ model_name = "meta-llama/Meta-Llama-3.1-8B-Instruct"
 # Initialize Inference Client with model and token
 inference_client = InferenceClient()
 
-def chat_completion(prompt):
+def chat_completion(message, history):
     # Pass user input through Hugging Face model
     response = inference_client.chat(
         model=model_name,
-        messages=[{"role": "user", "content": prompt}],
+        messages=[{"role": "user", "content": message}],
         max_tokens=500,
         stream=False
     )
@@ -308,6 +308,7 @@ def chat_completion(prompt):
     # Extract content from the response
     response_text = response['choices'][0]['delta']['content']
     
+    # Return response and updated history
     return response_text
 
 # Create Gradio chat interface