Update multi_agent.py

multi_agent.py

@@ -43,10 +43,10 @@ def today_tool(text: str) -> str:
        Any date mathematics should occur outside this function."""
     return (str(date.today()) + "\n\nIf you have completed all tasks, respond with FINAL ANSWER.")
     
-def create_graph(model, max_tokens, temperature, topic):
+def create_graph(model, topic):
     tavily_tool = TavilySearchResults(max_results=10)
     
-    members = ["Content Planner", "Content Writer"]
+    members = ["Researcher"]
     options = ["FINISH"] + members
    
     system_prompt = (
@@ -87,7 +87,7 @@ def create_graph(model, max_tokens, temperature, topic):
         ]
     ).partial(options=str(options), members=", ".join(members))
     
-    llm = ChatOpenAI(model=model, max_tokens=max_tokens, temperature=temperature)
+    llm = ChatOpenAI(model=model)
     
     supervisor_chain = (
         prompt
@@ -95,38 +95,18 @@ def create_graph(model, max_tokens, temperature, topic):
         | JsonOutputFunctionsParser()
     )
 
-    content_planner_agent = create_agent(llm, [tavily_tool], system_prompt=
-                                    "You are a Content Planner working on planning a blog article "
-              "about the topic: " + topic + "."
-              "You collect information that helps the "
-              "audience learn something "
-              "and make informed decisions. "
-              "Your work is the basis for "
-              "the Content Writer to write an article on this topic.")
-    content_planner_node = functools.partial(agent_node, agent=content_planner_agent, name="Content Planner")
+    researcher_agent = create_agent(llm, [tavily_tool, today_tool], system_prompt=
+                                    "1. Research content on topic: " + topic + ". "
+                                    "2. Based on your research, write an in-depth article on the topic. " 
+                                    "3. The output must be in markdown format (omit the triple backticks). "
+                                    "4. At the beginning of the article, add current date and author: Multi-Agent AI System. "
+                                    "5. Also at the beginning of the article, add a references section with links to relevant content.")
+    researcher_node = functools.partial(agent_node, agent=researcher_agent, name="Researcher")
 
-    content_writer_agent = create_agent(llm, [today_tool], system_prompt=
-                                    "You are a Content Writer working on writing "
-              "a new opinion piece about the topic: " + topic + ". "
-              "You base your writing on the work of "
-              "the Content Planner, who provides an outline "
-              "and relevant context about the topic. "
-              "You follow the main objectives and "
-              "direction of the outline, "
-              "as provide by the Content Planner. "
-              "You also provide objective and impartial insights "
-              "and back them up with information "
-              "provide by the Content Planner. "
-              "You acknowledge in your opinion piece "
-              "when your statements are opinions "
-              "as opposed to objective statements.")
-    content_writer_node = functools.partial(agent_node, agent=content_writer_agent, name="Content Writer")
-    
     workflow = StateGraph(AgentState)
 
     workflow.add_node("Manager", supervisor_chain)
-    workflow.add_node("Content Planner", content_planner_node)
-    workflow.add_node("Content Writer", content_writer_node)
+    workflow.add_node("Researcher", researcher_node)
 
     for member in members:
         workflow.add_edge(member, "Manager")
@@ -139,8 +119,8 @@ def create_graph(model, max_tokens, temperature, topic):
     
     return workflow.compile()
 
-def run_multi_agent(llm, max_tokens, temperature, topic):
-    graph = create_graph(llm, max_tokens, temperature, topic)
+def run_multi_agent(llm, topic):
+    graph = create_graph(llm, topic)
     
     result = graph.invoke({
         "messages": [