Update app.py

app.py

@@ -529,7 +529,7 @@ def get_response_from_llama(query, model, selected_docs, file_type, num_calls=1,
     for _ in range(num_calls):
         try:
             # Generate content with streaming enabled
-            for response in client.text_generation(
+            for response in client.chat_completion(
                 prompt=prompt,
                 max_new_tokens=1000,  # Reduced to ensure we stay within token limits
                 temperature=temperature,