Quickstart¶

Welcome to our Quickstart Guide! This guide is designed to help you get up and running with the AI Refinery SDK as quickly and smoothly as possible. For a more detailed overview of our project creation guidelines, visit our Project Guidelines page. In this quickstart guide, we will create a simple example project that utilizes both a custom utility agent and a built-in utility agent.

Environment Variables¶

To facilitate seamless login to the AI Refinery service, begin by setting the ACCOUNT and API_KEY environment variables as shown below.

export ACCOUNT="your_account"  
export API_KEY="your_api_key"  

Creating a Custom Agent¶

A custom agent is a Python function designed to process a string query and return a single output. An example of a custom utility agent can be seen below:

import os
import asyncio
import random
import string

from openai import AsyncOpenAI

from air import login, DistillerClient
from air import utils

auth = login(
    account=str(os.getenv("ACCOUNT")),
    api_key=str(os.getenv("API_KEY")),
)

async def simple_agent(query: str, **kwargs):
    global auth

    prompt = f"""Your task is to generate some synthetic data so that it will be useful to answer the user question. Do not mention this is synthetic data in your answer.\n\n{query}"""
    # This is for local serving
    client = AsyncOpenAI(**auth.openai())

    # This is for production endpoint
    # client = AsyncOpenAI(**auth.openai())

    response = await client.chat.completions.create(
        messages=[{"role": "user", "content": prompt}],
        model="meta-llama/Llama-3.1-70B-Instruct",
    )

    return response.choices[0].message.content

In this example, the simple_agent generates synthetic data in response to a user's query using the OpenAI API. Depending on your requirements, you can customize the agent to be simpler (e.g., returning "hello" for every input query) or more complex (e.g., interacting with other agents or retrieving relevant information using RAG). You can achieve this by modifying the provided function accordingly.

Creating a Distiller Client¶

Next, use our DistillerClient API to create a distiller client. This client will interface with the AI Refinery service to run your project. Below is a function that sets up the distiller client. Here's what it does:

• Instantiates a DistillerClient.
• Creates a project named example using the configuration specified in the example.yaml file. Details of example.yaml are provided in the next section.
• Adds the previously defined simple_agent to the custom_agent_gallery under the name Data Scientist Agent.
• Runs the project in interactive mode.

def interactive():
    distiller_client = DistillerClient()

    # upload your config file to register a new distiller project
    distiller_client.create_project(config_path="example.yaml", project="example")

    # Define a mapping between your custom agent to Callable.
    # When the custom agent is summoned by the super agent / orchestrator,
    # distiller-sdk will run the custom agent and send its response back to the
    # multi-agent system.
    custom_agent_gallery = {
        "Data Scientist Agent": simple_agent,
    }

    distiller_client.interactive(
        project="example",
        uuid="test_user",
        custom_agent_gallery=custom_agent_gallery,
    )
if __name__ == "__main__":

    # Run Interactive Mode
    print("\nInteractive Mode")
    interactive()

Project Configuration¶

Next, you will need to configure your project by using YAML.

orchestrator:
  agent_list:
    - agent_name: "Data Scientist Agent"
    - agent_name: "Search Agent"

utility_agents:
  - agent_class: CustomAgent
    agent_name: "Data Scientist Agent"
    agent_description: "The data scientist can help you perform data analytics."
    config: {}

  - agent_class: SearchAgent
    agent_name: "Search Agent"

Project Setup & Execution¶

Now that you have all the necessary code needed for the project, let us set it up and execute it.

Structure¶

• Create a directory named example.
• Inside the example directory, create a Python file named example.py and place all the Python code mentioned above into this file.
• Also, within the example directory, create a YAML file named example.yaml and paste the provided YAML configuration into this file.

This gives us the following project structure:

example/  
│  
├── example.py  
├── example.yaml

Execution¶

To execute the example project, run the following commands on your terminal:

cd example/
python example.py

Running these commands will create the project on the AI Refinery server. You can now interact with the agents directly from your terminal.