Getting Started with FastAgency#

The fastest way to bring multi-agent workflows to production.

Welcome to FastAgency! This guide will walk you through the initial setup and usage of FastAgency, a powerful tool that leverages the AutoGen framework to quickly build applications. FastAgency is designed to be flexible and adaptable, and we plan to extend support to additional agentic frameworks such as CrewAI in the near future. This will provide even more options for defining workflows and integrating with various AI tools.

With FastAgency, you can create interactive applications using various interfaces such as a console or Mesop.

Supported Interfaces#

FastAgency currently supports workflows defined using AutoGen and provides options for different types of applications:

• Console: Use the ConsoleIO interface for command-line based interaction. This is ideal for developing and testing workflows in a text-based environment.
• Mesop: Utilize Mesop with MesopIO for web-based applications. This interface is suitable for creating web applications with a user-friendly interface.

We are also working on adding support for other frameworks, such as CrewAI, to broaden the scope and capabilities of FastAgency. Stay tuned for updates on these integrations.

Quick start#

Install#

To get started, you need to install FastAgency. You can do this using pip, Python's package installer. Choose the installation command based on the interface you want to use:

pip install "fastagency[autogen]"

pip install "fastagency[autogen,mesop]"

pip install "fastagency[pyautogen]"

pip install "fastagency[pyautogen,mesop]"

Imports#

Depending on the interface you choose, you'll need to import different modules. These imports set up the necessary components for your application:

import os

from autogen.agentchat import ConversableAgent

from fastagency import FastAgency
from fastagency import UI
from fastagency.ui.console import ConsoleUI
from fastagency.runtimes.autogen.base import AutoGenWorkflows

import os

from autogen.agentchat import ConversableAgent

from fastagency.core import Chatable
from fastagency.core.runtimes.autogen.base import AutoGenWorkflows
from fastagency.core.io.mesop import MesopIO

from fastagency import FastAgency

Define Workflow#

You need to define the workflow that your application will use. This is where you specify how the agents interact and what they do. Here's a simple example of a workflow definition:

llm_config = {
    "config_list": [
        {
            "model": "gpt-4o-mini",
            "api_key": os.getenv("OPENAI_API_KEY"),
        }
    ],
    "temperature": 0.0,
}

wf = AutoGenWorkflows()


@wf.register(name="simple_learning", description="Student and teacher learning chat")
def simple_workflow(io: UI, initial_message: str, session_id: str) -> str:
    student_agent = ConversableAgent(
        name="Student_Agent",
        system_message="You are a student willing to learn.",
        llm_config=llm_config,
    )
    teacher_agent = ConversableAgent(
        name="Teacher_Agent",
        system_message="You are a math teacher.",
        llm_config=llm_config,
    )

    chat_result = student_agent.initiate_chat(
        teacher_agent,
        message=initial_message,
        summary_method="reflection_with_llm",
        max_turns=5,
    )

    return chat_result.summary  # type: ignore[no-any-return]

This code snippet sets up a simple learning chat between a student and a teacher. You define the agents and how they should interact, specifying how the conversation should be summarized.

Define FastAgency Application#

Next, define your FastAgency application. This ties together your workflow and the interface you chose:

from fastagency.ui.console import ConsoleUI

app = FastAgency(wf=wf, ui=ConsoleUI())

from fastagency.core.io.mesop import MesopIO

app = FastAgency(wf=wf, io=MesopIO())

Run Application#

Once everything is set up, you can run your FastAgency application using the following command:

fastagency run

Output#

The output will vary based on the interface:

╭─ Python module file ─╮
│                      │
│  🐍 main.py          │
│                      │
╰──────────────────────╯


╭─ Importable FastAgency app ─╮
│                             │
│  from main import app       │
│                             │
╰─────────────────────────────╯

╭─ FastAgency -> user [text_input] ────────────────────────────────────────────╮
│                                                                              │
│ Starting a new workflow 'simple_learning' with the following                 │
│ description:                                                                 │
│                                                                              │
│ Student and teacher learning chat                                            │
│                                                                              │
│ Please enter an                                                              │
│ initial message:                                                             │
╰──────────────────────────────────────────────────────────────────────────────╯

╭─ Python module file ─╮
│                      │
│  🐍 main_mesop.py    │
│                      │
╰──────────────────────╯


╭─ Importable FastAgency app ──╮
│                              │
│  from main_mesop import app  │
│                              │
╰──────────────────────────────╯

Running with hot reload:

Running server on: http://localhost:32123
* Serving Flask app 'mesop.server.server'
* Debug mode: off