Skip to main content

Documentation Index

Fetch the complete documentation index at: https://wavefront.rootflo.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Get started with Flo AI in three steps

Build your first AI agent and understand the core concepts of Flo AI.

​
Step 1: Installation

Install Flo AI using pip or poetry:
pip install flo-ai
poetry add flo-ai
uv add flo-ai
Flo AI requires Python 3.10 or higher.
Configure your LLM provider API keys:
export OPENAI_API_KEY="your-openai-key"
export ANTHROPIC_API_KEY="your-anthropic-key"
export GOOGLE_API_KEY="your-google-key"

​
Step 2: Your First Agent

Create your first conversational agent:
import asyncio
from flo_ai.agent import AgentBuilder
from flo_ai.llm import OpenAI

async def main():
    # Create a simple conversational agent
    agent = (
        AgentBuilder()
        .with_name('Math Tutor')
        .with_prompt('You are a helpful math tutor.')
        .with_llm(OpenAI(model='gpt-4o-mini'))
        .build()
    )

    response = await agent.run('What is the formula for the area of a circle?')
    print(f'Response: {response[-1].content}')

asyncio.run(main())
Make sure you have set your OpenAI API key before running this example.

​
Step 3: Add Tools and Structure

Build an agent that can use tools:
import asyncio
from flo_ai.agent import AgentBuilder
from flo_ai.tool import flo_tool
from flo_ai.llm import Anthropic

@flo_tool(description="Perform mathematical calculations")
async def calculate(operation: str, x: float, y: float) -> float:
    """Calculate mathematical operations between two numbers."""
    operations = {
        'add': lambda: x + y,
        'subtract': lambda: x - y,
        'multiply': lambda: x * y,
        'divide': lambda: x / y if y != 0 else 0,
    }
    return operations.get(operation, lambda: 0)()

async def main():
    agent = (
        AgentBuilder()
        .with_name('Calculator Assistant')
        .with_prompt('You are a math assistant that can perform calculations.')
        .with_llm(Anthropic(model='claude-3-5-sonnet-20240620'))
        .with_tools([calculate.tool])
        .build()
    )

    response = await agent.run('Calculate 5 plus 3')
    print(f'Response: {response[-1].content}')

asyncio.run(main())

​
Next Steps

Now that you have your first agent running, explore these key features:

Multi-Agent Workflows

Learn how to create complex multi-agent workflows with Arium.

YAML Configuration

Define entire agent architectures in YAML for easy management.

Visual Studio

Design AI workflows visually with our React-based studio.

Production Deployment

Learn about production-ready features and best practices.
Need help? Check out our examples or join our community.