All parameters inside the Agent class, follow the same structure as OpenAI’s Assistants API. However, there are a few advanced parameters that require more explanation.

​
Parallel Tool Calls

Whether to run tools in parallel or sequentially. By default, this parameter is set to True.

from agency_swarm import Agent

agent = Agent(name='MyAgent', parallel_tool_calls=False)

​
File Search Configuration

File search configuration for the agent, as described in the OpenAI documentation.

from agency_swarm import Agent

agent = Agent(
    name='MyAgent',
    file_search={
        'max_num_results': 25,
        'ranking_options': {
            "score_threshold": 0.5,
            "ranker": "auto"
        }
    }
)

Parameters:

  • max_num_results: The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive. Note that the file search tool may output fewer than max_num_results results.
  • ranking_options: The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0. See the file search tool documentation for more information.

​
Response Validator

This is a special function that allows you to validate the response before sending it to the user or another agent. This function should raise an error if the response is invalid. The agent will then see this error as the user message and try correct itself accordingly.


from agency_swarm import Agent

class MyAgent(Agent):
    def response_validator(self, message: str) -> str:
        """This function is used to validate the response before sending it to the user or another agent."""
        if "bad word" in message:
            raise ValueError("Please don't use bad words.")

        return message

​
Few-Shot Examples

Few-show examples help the agent to understand how to respond. The format for examples follows message object format on OpenAI:

from agency_swarm import Agent

examples=[
    {
        "role": "user",
        "content": "Hi!",
        "attachments": [],
        "metadata": {},
    },
    {
        "role": "assistant",
        "content": "Hi! I am the CEO. I am here to help you with your tasks. Please tell me what you need help with.",
        "attachments": [],
        "metadata": {},
    }
]

agent = Agent(
    name='MyAgent',
    examples=examples
)