AutoGen Studio ：Team creation failed: Model creation failed: model_info is required when model name is not a valid OpenAI mode

[wpcool]

I use another LLM as base model ,when I run in playground , it errors :"Team creation failed: Model creation failed: model_info is required when model name is not a valid OpenAI mode" . but I have write model_info in the "model_client"

[ScottWilliamAnderson]

I'm unsure if this is a bug perhaps?

[wantanej]

At first I used "o1" family it happen like the picture above.

After I added "mode_info" as below picture. It can solve the above issue, but faced new one on "The model does not support function calling."

Please suggest how to solve the issue.

[ScottWilliamAnderson]

After further research in the Docs, I found an example of how the model information shoult be formatted, in the documentation:
https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/faq.html#q-can-i-use-other-models-with-autogen-studio

E.g.:

"model_client": {
        "model": "bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF",
        "model_type": "OpenAIChatCompletionClient",
        "base_url": "http://localhost:1234/v1",
        "api_version": "1.0",
        "component_type": "model",
        "model_capabilities": {
          "vision": false,
          "function_calling": true,
          "json_output": false
        }
      },

@wpcool It would be helpful to see your full JSON, but my suspicion is your "model" field either didn't conform to the xxx/yyyy standard, or the order of the items in the dictionary is different from the above perhaps?

[web4zn]

did you solve this?

[victordibia]

Hi,

Based on the documentation here

---

Declarative Specification of Componenents

AutoGen Studio is built on the declarative specification behaviors of AutoGen AgentChat. This allows users to define teams, agents, models, tools, and termination conditions in python and then dump them into a JSON file for use in AutoGen Studio.

Here's an example of an agent team and how it is converted to a JSON file:

from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.teams import RoundRobinGroupChat
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_agentchat.conditions import  TextMentionTermination

agent = AssistantAgent(
        name="weather_agent",
        model_client=OpenAIChatCompletionClient(
            model="gpt-4o-mini",
        ),
    )

agent_team = RoundRobinGroupChat([agent], termination_condition=TextMentionTermination("TERMINATE"))
config = agent_team.dump_component()
print(config.model_dump_json())

{
  "provider": "autogen_agentchat.teams.RoundRobinGroupChat",
  "component_type": "team",
  "version": 1,
  "component_version": 1,
  "description": "A team that runs a group chat with participants taking turns in a round-robin fashion\n    to publish a message to all.",
  "label": "RoundRobinGroupChat",
  "config": {
    "participants": [
      {
        "provider": "autogen_agentchat.agents.AssistantAgent",
        "component_type": "agent",
        "version": 1,
        "component_version": 1,
        "description": "An agent that provides assistance with tool use.",
        "label": "AssistantAgent",
        "config": {
          "name": "weather_agent",
          "model_client": {
            "provider": "autogen_ext.models.openai.OpenAIChatCompletionClient",
            "component_type": "model",
            "version": 1,
            "component_version": 1,
            "description": "Chat completion client for OpenAI hosted models.",
            "label": "OpenAIChatCompletionClient",
            "config": { "model": "gpt-4o-mini" }
          },
          "tools": [],
          "handoffs": [],
          "model_context": {
            "provider": "autogen_core.model_context.UnboundedChatCompletionContext",
            "component_type": "chat_completion_context",
            "version": 1,
            "component_version": 1,
            "description": "An unbounded chat completion context that keeps a view of the all the messages.",
            "label": "UnboundedChatCompletionContext",
            "config": {}
          },
          "description": "An agent that provides assistance with ability to use tools.",
          "system_message": "You are a helpful AI assistant. Solve tasks using your tools. Reply with TERMINATE when the task has been completed.",
          "model_client_stream": false,
          "reflect_on_tool_use": false,
          "tool_call_summary_format": "{result}"
        }
      }
    ],
    "termination_condition": {
      "provider": "autogen_agentchat.conditions.TextMentionTermination",
      "component_type": "termination",
      "version": 1,
      "component_version": 1,
      "description": "Terminate the conversation if a specific text is mentioned.",
      "label": "TextMentionTermination",
      "config": { "text": "TERMINATE" }
    }
  }
}

This example shows a team with a single agent, using the RoundRobinGroupChat type and a TextMentionTermination condition.

[krupanss]

Model name should follow the names given in the file "_model_info.py"

File Path: .../site-packages/autogen_ext/models/openai/_model_info.py

I was trying to use Gemini Flash Lite and gave the model name as "gemini-2.0-flash-lite" as per the documentation in https://ai.google.dev/gemini-api/docs/models/gemini#gemini-2.0-flash-lite.

After changing it to the name given in the model_info file, the error is resolved.

Reference for _model_info.py: