Skip to main content

Easily connect large language models into your application

Project description

llmio

Easily connect large language models into your application

pylint mypy ruff tests

llmio uses type hints to enable function execution with OpenAIs API.

Setup

pip install llmio

Example

import asyncio

import openai

from llmio import Assistant


assistant = Assistant(
    instruction="""
        You are a calculating assistant.
        Always use commands to calculate things.
        Never try to calculate things on your own.
        """,
    client=openai.AsyncOpenAI(api_key=os.environ["OPENAI_TOKEN"]),
    model="gpt-4o-mini",
)


@assistant.command()
async def add(num1: float, num2: float) -> float:
    """
    Add two numbers
    """
    print(f"Adding {num1} + {num2}")
    return num1 + num2


@assistant.command()
async def multiply(num1: float, num2: float) -> float:
    """
    Multiply two numbers
    """
    print(f"Multiplying {num1} * {num2}")
    return num1 * num2


async def main():
    history = []

    async for reply, history in assistant.speak(input(">>"), history):
        print(reply)


if __name__ == "__main__":
    asyncio.run(main())

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

llmio-0.3.0.tar.gz (4.8 kB view hashes)

Uploaded Source

Built Distribution

llmio-0.3.0-py3-none-any.whl (5.5 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page