cancel
Showing results for 
Search instead for 
Did you mean: 
Generative AI
Explore discussions on generative artificial intelligence techniques and applications within the Databricks Community. Share ideas, challenges, and breakthroughs in this cutting-edge field.
cancel
Showing results for 
Search instead for 
Did you mean: 

Issue with Multi agent supervisor based agentic framework

SandipCoder
New Contributor II

I  have three agents in my multi agent framework (code attached)

 
Supervisor : This is the main controller
    "Genie":           #this is a genai agent
    "Coder":          #this is a re-act agent created on the fly
    "Weather":      #this is an existing model in UC based on single agent
 
The problem I am facing is :
 
1. For my agent they are not stopping after one iteration they are always reaching to max iteration count and then they find the END node.
 
2. For coder agent I am getting an error like : 
validation error for ChatAgentMessage Value error, Either 'content' or 'tool_calls' must be provided. [type=value_error, input_value={'role': 'assistant', 'co...4f5d-b5b9-248fc6785f9b'}, input_type=dict]
 
3. For Weather agent also I was getting error :
         'PyFuncModel' object has no attribute 'invoke' .
So I added the below function for existing model and called that while creating node for weather .But since then started getting another error :  AttributeError: 'list' object has no attribute 'get'
def agent_node_existing_model(state, agent, name😞
    result = agent.predict(state)
    return {
        "messages": [
            {
                "role": "assistant",
                "content": result["messages"][-1].content,
                "name": name,
            }
        ]
    }
 
weather_node = functools.partial(agent_node_existing_model, agent=weather_agent, name="Weather")
Sandip Bhowmick
0 REPLIES 0

Join Us as a Local Community Builder!

Passionate about hosting events and connecting people? Help us grow a vibrant local community—sign up today to get started!

Sign Up Now