mwin 0.1.3

Track OpenAI, Claude, Gemini and OpenAI-compatible models then give solutions to improve your agent system.

mwin

mwin: Track OpenAI, Claude, Gemini and OpenAI-compatible models then give solutions to improve your agent system.
Our goal is to make llm application more valuable and effortlessly improve llm capabilities.

Quickstart

You can use pip install mwin

pip install mwin

OR pip install from source.

git clone https://github.com/yanghui1-arch/mwin.git
cd src
pip install -e .

Then you need to configure mwin through CLI.

mwin configure

Then you just follow the instructions to configure mwin.

> Which deployment type do you choose?
> 1 - mwin Cloud Platform (default)
> 2 - mwin Local Platform
> Please input the choice number.>2
> Please enter your API key:
> Congrats to configure aitrace.

It needs an AITrace API key. You can get the apikey after logging http://localhost:5173. Finally use @track to track your llm input and output

from mwin import track, LLMProvider
from openai import OpenAI

openai_apikey = 'YOUR API KEY'

@track(
    project_name="aitrace_demo",
    tags=['test', 'demo'],
    track_llm=LLMProvider.OPENAI,    
)
def llm_classification(film_comment: str):
    prompt = "Please classify the film comment into happy, sad or others. Just tell me result. Don't output anything."
    cli = OpenAI(base_url='https://api.deepseek.com', api_key=openai_apikey)
    cli.chat.completions.create(
        messages=[{"role": "user", "content": f"{prompt}\nfilm_comment: {film_comment}"}],
        model="deepseek-chat"
    ).choices[0].message.content
    llm_counts(film_comment=film_comment)
    return "return value"

@track(
    project_name="aitrace_demo",
    tags=['test', 'demo', 'second_demo'],
    track_llm=LLMProvider.OPENAI,
)
def llm_counts(film_comment: str):
    prompt = "Count the film comment words. just output word number. Don't output anything others."
    cli = OpenAI(base_url='https://api.deepseek.com', api_key=openai_apikey)
    return cli.chat.completions.create(
        messages=[{"role": "user", "content": f"{prompt}\nfilm_comment: {film_comment}"}],
        model="deepseek-chat"
    ).choices[0].message.content

llm_classification("Wow! It sucks.")

Development

minw project package manager is uv. If you are a beginner uver, please click uv link: uv official link

uv install
uv .venv/Script/activate

You can watch more detailed debug information by using --log-level=DEBUG or set AT_LOG_LEVEL=DEBUG for Windows or export AT_LOG_LEVEL=DEBUG for Linux and Mac.