Is there a way to deploy the system json script as a REST API

[ateeq666]

Hi,
So I wanted to know how we could use the json script that we can extract when creating a system on Autogen Studio UI.
Because I want to see whether I can make use of the UI in order to easily create agents to deploy for production.
But I am not well versed in json.
So if someone could provide some insight on how to do so. It would help alot.

`{
"provider": "autogen_agentchat.teams.RoundRobinGroupChat",
"component_type": "team",
"version": 1,
"component_version": 1,
"description": "A single AssistantAgent (with a calculator tool) in a RoundRobinGroupChat team. ",
"label": "RoundRobin Team_17531",
"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": "assistant_agent",
"model_client": {
"provider": "autogen_ext.models.openai.AzureOpenAIChatCompletionClient",
"component_type": "model",
"version": 1,
"component_version": 1,
"description": "GPT-4o Mini Azure OpenAI model client.",
"label": "AzureOpenAI GPT-4o-mini",
"config": {
"model": "gpt-4o",
"api_key": "2a926b69bbe44671a4ffd1fdea6c1ab6",
"azure_endpoint": "https://tcgai-OpenAI-01.openai.azure.com/",
"azure_deployment": "gpt-4o",
"api_version": "2024-06-01"
}
},
"workbench": {
"provider": "autogen_core.tools.StaticWorkbench",
"component_type": "workbench",
"version": 1,
"component_version": 1,
"description": "A workbench that provides a static set of tools that do not change after\n each tool execution.",
"label": "StaticWorkbench",
"config": {
"tools": [
{
"provider": "autogen_core.tools.FunctionTool",
"component_type": "tool",
"version": 1,
"component_version": 1,
"description": "Create custom tools by wrapping standard Python functions.",
"label": "FunctionTool",
"config": {
"source_code": "def calculator(a: float, b: float, operator: str) -> str:\n try:\n if operator == "+":\n return str(a + b)\n elif operator == "-":\n return str(a - b)\n elif operator == "*":\n return str(a * b)\n elif operator == "/":\n if b == 0:\n return "Error: Division by zero"\n return str(a / b)\n else:\n return "Error: Invalid operator. Please use +, -, *, or /"\n except Exception as e:\n return f"Error: {str(e)}"\n",
"name": "calculator",
"description": "A simple calculator that performs basic arithmetic operations",
"global_imports": [],
"has_cancellation_support": false
}
}
]
}
},
"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 assistant. Solve tasks carefully. When done, say TERMINATE.",
"model_client_stream": false,
"reflect_on_tool_use": false,
"tool_call_summary_format": "{result}",
"metadata": {}
}
}
],
"termination_condition": {
"provider": "autogen_agentchat.base.OrTerminationCondition",
"component_type": "termination",
"version": 1,
"component_version": 1,
"label": "OrTerminationCondition",
"config": {
"conditions": [
{
"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"
}
},
{
"provider": "autogen_agentchat.conditions.MaxMessageTermination",
"component_type": "termination",
"version": 1,
"component_version": 1,
"description": "Terminate the conversation after a maximum number of messages have been exchanged.",
"label": "MaxMessageTermination",
"config": {
"max_messages": 10,
"include_agent_event": false
}
}
]
}
},
"emit_team_events": false}

}`

above is the basic code for default round robin team.
So I want to know how to deploy this as a REST API. And posting question to the API URL that the system is linked to.

Thank you

[Sachin13p]

Hello, do you get the solution on this ask to create Rest API? I am looking for same. I do see doc in DEPLOY Section of Studio but I need more details. Please let me know on this.