Autogen

Prerequisite

To start using the Autogen SDK with Orq, you need an API Key ready within your Orq.ai account.

📘
To setup your API key, see API keys & Endpoints.

💡
To use libraries with private models, see Onboarding Private Models.

Using Orq.ai as Proxy

Using the Autogen SDK, set the Base URL to the Orq.ai Proxy to feed calls through our API without changing any other part of your code.

Using the Orq.ai Proxy, you benefit from the Platform Traces, Cost and Usage Monitoring, keeping full compatibility and a unified API with all models while using the Autogen SDK.

base_url: https://api.orq.ai/v2/proxy

api_key: Your Orq API key

from autogen import AssistantAgent, UserProxyAgent, config_list_from_json
import os

config_list = [
    {
        "api_key": os.getenv("ORQ_API_KEY"),
        "model": "openai/gpt-3.5-turbo", # Format the model `supplier/model`
        "base_url": "https://api.orq.ai/v2/proxy",
        "api_type": "openai",
    }
]

assistant = AssistantAgent("assistant", llm_config={"config_list": config_list})
user_proxy = UserProxyAgent("user_proxy", code_execution_config={"work_dir": "coding", "use_docker": False})
user_proxy.initiate_chat(assistant, message="You are a helpful assistant")