When it comes to running your agency, you have 3 options:
  1. Gradio Interface: The most convenient way to get started.
  2. Get Completion: For backend or custom integrations.
  3. Terminal Version: Best for quick debugging and testing.

​
Gradio Interface

To open a convenient Gradio interface in your browser, use the demo_gradio method: 
agency.demo_gradio(height=700)
Simply follow the localhost link from the terminal to start using your agency.

​
Get Completion

To get a response from your agency directly in code, use the get_completion method: 
response = agency.get_completion("I want you to build me a website",
                                 additional_instructions="This is an additional instruction for the task.",
                                 tool_choice={"type": "function", "function": {"name": "SendMessage"}},
                                 attachments=[],
                                 recipient_agent=dev,
                                 )
print(response)
Parameters:
  • message: The message to send to the agency.
  • additional_instructions (optional): Additional instructions that will be appended at the end of instructions for the recipient agent.
  • tool_choice (optional): Force the recipient agent to use a specific tool.
  • attachments (optional): A list of attachments to be sent with the message, following OpenAI format.
  • recipient_agent (optional): The agent to which the message should be sent.

​
Image attachments

When using the get_completion method, you can also pass an array of message objects to use vision capabilities (if your llm model supports it): 
message_objects = [
    {
        "type": "text",
        "text": "What is presented on these pictures?"
    },
    {
        "type": "image_file",
        "image_file": {"file_id": file_id}
    },
    {
        "type": "image_url",
        "image_url": {"url": "https://example.com/image.png"}
    }
]

response = agency.get_completion(message=message_objects)
print(response)

​
Terminal Version

To run the agency directly from your terminal, use the run_demo method: 
agency.run_demo()
When using the terminal to run the agency, you can send messages directly to any top-level agent by using the “mentions” feature. To do this, start your message with the agent’s name preceded by an @ symbol (for example, @Developer I want you to build me a website). This directs your message to the specified agent instead of the CEO. You can also press the tab key to autocomplete the agent’s name.

​
Deleting Agency

If you would like to delete the agency and all associated files, vector stores, and assistants on OpenAI, you can use the delete method: 
agency.delete()