Agents significantly enhance their capabilities by leveraging tools, which provide access to external data, APIs, and additional functionality.
In AG2, tool usage happens in two stages:
- An agent suggests which tool to use (via its LLM).
- Another agent executes the selected tool.
Typically, you’ll create two agents. One to determine the appropriate tool and another to carry out the execution.
In a conversation, the executor agent must always follow the agent that suggests a tool.
from datetime import datetime
from typing import Annotated
from autogen import ConversableAgent, register_function, LLMConfig
# Put your key in the OPENAI_API_KEY environment variable
llm_config = LLMConfig(api_type="openai", model="gpt-4o-mini")
# 1. Our tool, returns the day of the week for a given date
def get_weekday(date_string: Annotated[str, "Format: YYYY-MM-DD"]) -> str:
date = datetime.strptime(date_string, "%Y-%m-%d")
return date.strftime("%A")
# 2. Agent for determining whether to run the tool
with llm_config:
date_agent = ConversableAgent(
name="date_agent",
system_message="You get the day of the week for a given date.",
)
# 3. And an agent for executing the tool
executor_agent = ConversableAgent(
name="executor_agent",
human_input_mode="NEVER",
)
# 4. Registers the tool with the agents, the description will be used by the LLM
register_function(
get_weekday,
caller=date_agent,
executor=executor_agent,
description="Get the day of the week for a given date",
)
# 5. Two-way chat ensures the executor agent follows the suggesting agent
chat_result = executor_agent.initiate_chat(
recipient=date_agent,
message="I was born on the 25th of March 1995, what day was it?",
max_turns=2,
)
print(chat_result.chat_history[-1]["content"])
-
We define a tool, a function that will be attached to our agents. The Annotated parameter is included in the LLM call to ensure it understands the purpose of date_string.
-
The date_agent decides whether to use the tool based on its LLM reasoning.
-
The executor_agent executes the tool and returns the output as its response.
-
We register the tool with the agents and provide a description to help the LLM determine when to use it.
-
Since this is a two-way conversation, the executor_agent follows the date_agent. If the date_agent suggests using the tool, the executor_agent executes it accordingly.
executor_agent (to date_agent):
I was born on the 25th of March 1995, what day was it?
--------------------------------------------------------------------------------
>>>>>>>> USING AUTO REPLY...
date_agent (to executor_agent):
***** Suggested tool call (call_iOOZMTCoIVVwMkkSVu04Krj8): get_weekday *****
Arguments:
{"date_string":"1995-03-25"}
****************************************************************************
--------------------------------------------------------------------------------
>>>>>>>> EXECUTING FUNCTION get_weekday...
Call ID: call_iOOZMTCoIVVwMkkSVu04Krj8
Input arguments: {'date_string': '1995-03-25'}
executor_agent (to date_agent):
***** Response from calling tool (call_iOOZMTCoIVVwMkkSVu04Krj8) *****
Saturday
**********************************************************************
--------------------------------------------------------------------------------
>>>>>>>> USING AUTO REPLY...
date_agent (to executor_agent):
It was a Saturday.
--------------------------------------------------------------------------------
Alternative Registration Methods
Alternatively, you can use decorators register_for_execution and register_for_llm to register a tool. So, instead of using register_function, you can register them with the function definition.
@date_agent.register_for_llm(description="Get the day of the week for a given date")
@executor_agent.register_for_execution()
def get_weekday(date_string: Annotated[str, "Format: YYYY-MM-DD"]) -> str:
date = datetime.strptime(date_string, '%Y-%m-%d')
return date.strftime('%A')
