Update app.py

app.py

@@ -83,7 +83,7 @@ agent = ToolCallingAgent(tools=[retriever_tool], model=HfApiModel(model))
 def respond(message, history: list[tuple[str, str]], system_message, max_tokens, temperature, top_p, score,):
 
     print(datetime.now())
-    context = retriever_tool(question)
+    context = retriever_tool(message)
     
     prompt = f"""Given the question and supporting documents below, give a comprehensive answer to the question.
     Respond only to the question asked, response should be concise and relevant to the question and answer in the same language as the question.
@@ -96,15 +96,13 @@ def respond(message, history: list[tuple[str, str]], system_message, max_tokens,
     {context}
     """
     
-    messages = [{"role": "user", "content": prompt}]
-
     for val in history:
         if val[0]:
             messages.append({"role": "user", "content": val[0]})
         if val[1]:
             messages.append({"role": "assistant", "content": val[1]})
 
-    messages.append({"role": "user", "content": message})
+    messages.append({"role": "user", "content": prompt})
 
     response = ""
 
@@ -117,8 +115,6 @@ def respond(message, history: list[tuple[str, str]], system_message, max_tokens,
     ):
         token = message.choices[0].delta.content
         
-#        answer = client.chat_completion(messages, temperature=0.1).choices[0].message.content
-
         response += token
         yield response