fix system prompt

agent.py

@@ -100,12 +100,17 @@ def web_search(query: str) -> str:
         ])
     return {"web_results": formatted_search_docs}
 
-
     
-
-system_prompt =  "You are a helpful assistant"
+system_prompt = """
+You are a helpful assistant tasked with answering questions using a set of tools. 
+Now, I will ask you a question. Report your thoughts, and finish your answer with the following template: 
+FINAL ANSWER: [YOUR FINAL ANSWER]. 
+YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.
+Your answer should only start with "FINAL ANSWER: ", then follows with the answer. 
+"""
 sys_msg = SystemMessage(content=system_prompt)
 
+
 tools = [
     wiki_search,
     web_search,
@@ -114,6 +119,7 @@ tools = [
     transcribe_audio
 ]
 
+
 llm = ChatGroq(model="qwen-qwq-32b", temperature=0.7)
 llm_with_tools = llm.bind_tools(tools)
 
@@ -121,24 +127,9 @@ def assistant(state: MessagesState):
     """Assistant node"""
     return {"messages": [llm_with_tools.invoke(state["messages"])]}
 
-def final_answer(question, answer):
-  sys_prompt = """
-  You are an assistant. You help to extract the final answer based given an answer
-  of a question.
-
-  Example:
-  **QUESTION:** what is 1+1?
-  **ANSWER:** the result is 2
-  **OUTPUT:** 2
-  """
-  conversation = f"Extract final answer from\QUESTION:{question}\ANSWER:{answer}\OUTPUT:"
-  print(f"conversation: {conversation}")
-  messages = [
-    {"role": "system", "content": sys_prompt},
-    {"role": "user", "content": conversation},
-  ]
-  response = llm.invoke(messages)
-  return response.content.replace("**OUTPUT:**","").replace("**ANSWER:**","")
+def final_answer(answer):
+  print(f"ANSWER: {answer}")
+  return answer.replace("FINAL ANSWER:","")
 
 builder = StateGraph(MessagesState)
 builder.add_node("assistant", assistant)
@@ -153,14 +144,15 @@ graph = builder.compile()
 
 
 def get_answer(query):
-  messages = [HumanMessage(content=query)]
+  messages = [sys_msg, HumanMessage(content=query)]
   results = graph.invoke({"messages": messages})
-  return final_answer(query, results["messages"][-1].content)
+  return final_answer(results["messages"][-1].content)
 
 if __name__ == "__main__":
     question = "In the video https://www.youtube.com/watch?v=L1vXCYZAYYM, what is the highest number of bird species to be on camera simultaneously?"
     question = "Hi, I was out sick from my classes on Friday, so I'm trying to figure out what I need to study for my Calculus mid-term next week. My friend from class sent me an audio recording of Professor Willowbrook giving out the recommended reading for the test, but my headphones are broken :(\n\nCould you please listen to the recording for me and tell me the page numbers I'm supposed to go over? I've attached a file called Homework.mp3 that has the recording. Please provide just the page numbers as a comma-delimited list. And please provide the list in ascending order."
     question = "What is the first name of the only Malko Competition recipient from the 20th Century (after 1977) whose nationality on record is a country that no longer exists?"
+    question = "Where were the Vietnamese specimens described by Kuznetzov in Nedoshivina's 2010 paper eventually deposited? Just give me the city name without abbreviations."
     # getmessages = [HumanMessage(content=question)]
     # messages = graph.invoke({"messages": messages})
     # for m in messages["messages"]: