Upload app.py

app.py

@@ -83,7 +83,7 @@ def respond(
         keyword_dir = "keyword"  # Updated keyword directory
         load_and_process_dataset(data_update_path, keyword_dir, db_path)
 
-    # Load the model with the maximum context length and control the maximum number of tokens in the response
+    # Load the model with the maximum context length and control the maximum tokens in the response
     llm = Llama(
         model_path=model_path,
         n_ctx=500,  # Set the maximum context length
@@ -99,7 +99,7 @@ def respond(
         context = f"{system_prompt}\nUser: {message}\nAssistant: "
         truncated_context = truncate_context(context, max_context_tokens)
 
-        response = agent.process_query(user_id, message, context=truncated_context)
+        response = agent.process_query(user_id, message, truncated_context)
     except ValueError as e:
         logging.error(f"Error during processing: {e}")
         response = "Désolé, il y a eu une erreur lors du traitement de votre requête. Veuillez essayer à nouveau."