mle-agent 0.2.1

MLE-agent: An agent to automate your MLE processes

A Pair Coding Agent for AI Engineer and Data Scientist

:love_letter: Fathers' love for Kaia :love_letter:

Overview

MLE-Agent is designed as a pairing LLM agent for machine learning engineers and researchers. It is featured by:

• 🤖 Autonomous agent for building an ML/AI baseline
• :coffee: Interactive chat interface in the CLI to improve existing projects
• 📂 File system integration to build a well-organized project structure
• 🔍 Integration with Arxiv and Papers with Code for best practice and SOTA methods
• 🐛 Automatic debugger-coder interaction for high-quality code generation
• 🧰 AI/ML functions and MLOps tools integration

Get started

Installation

pip install mle-agent

Usage

mle new <project name>

And a project directory will be created under the current path, you need to start the project under the project directory.

cd <project name>
mle start

You can also start an interactive chat in the terminal under the project directory:

mle chat

Examples

Here are some example user requirements you can try:

I want to train an image classification model using CIFAR-10 dataset

I want to implement a SOTA continue learning algorithm for my sentiment analysis task

I want to build a text feature extraction model on my dataset located in /home/desktop/data/text.csv

And more...

Milestones

• :rocket: 11 July 2024: Release the 0.2.0 with multiple agents interaction (v0.2.0)
• :rocket: June 1st, 2024: Release the first rule-based version of MLE agent (v0.1.0)

Roadmap

The following is a list of the tasks we plan to do, welcome to propose something new!

:hammer: General Features

• Understand users' requirements to create an end-to-end AI project
• Suggest the SOTA data science solutions by using the web search
• Plan the ML engineering tasks with human interaction
• Execute the code on the local machine/cloud, debug and fix the errors
• Leverage the built-in functions to complete ML engineering tasks
• Interactive chat: A human-in-the-loop mode to help improve the existing ML projects
• Kaggle mode: to finish a Kaggle task without humans
• Summary and reflect the whole ML/AI pipeline
• Integration with Cloud data and testing and debugging platforms
• Local RAG support to make personal ML/AI coding assistant
• Function zoo: generate AI/ML functions and save them for future usage

:star: More LLMs and Serving Tools

• Ollama LLama3
• OpenAI GPTs
• Anthropic Claude 3.5 Sonnet

:sparkling_heart: Better user experience

• CLI Application
• Web UI
• Discord

:jigsaw: Functions and Integrations

• Local file system
• Local code exectutor
• Arxiv.org search
• Papers with Code search
• General keyword search
• Hugging Face
• SkyPilot cloud deployment
• Snowflake data
• AWS S3 data
• Databricks data catalog
• Wandb experiment monitoring
• MLflow management
• DBT data transform

Contributing

We welcome contributions from the community. We are looking for contributors to help us with the following tasks:

• Benchmark and Evaluate the agent
• Add more features to the agent
• Improve the documentation
• Write tests

If you are interested in contributing, please check the CONTRIBUTING.md file.

Support and Community

• Discord community. If you have any questions, please feel free to ask in the Discord community.
• Twitter. Follow us on Twitter to get the latest updates.

License

Check LICENSE file for more information.