MLSysOps / MLE-agent
- Π²ΡΠΎΡΠ½ΠΈΠΊ, 3 ΡΠ΅Π½ΡΡΠ±ΡΡ 2024β―Π³. Π² 00:00:03
https://github.com/MLSysOps/MLE-agent
π€ MLE-Agent: Your intelligent companion for seamless AI engineering and research. π Integrate with arxiv and paper with code to provide better code/research plans π§° OpenAI, Ollama, etc supported. π Code RAG
π Fathers' love for Kaia π
MLE-Agent is designed as a pairing LLM agent for machine learning engineers and researchers. It is featured by:
- π€ Autonomous Baseline Creation: Automatically builds ML/AI baselines.
- π Arxiv and Papers with Code Integration: Access best practices and state-of-the-art methods.
- π Smart Debugging: Ensures high-quality code through automatic debugger-coder interactions.
- π File System Integration: Organizes your project structure efficiently.
- π§° Comprehensive Tools Integration: Includes AI/ML functions and MLOps tools for a seamless workflow.
- β Interactive CLI Chat: Enhances your projects with an easy-to-use chat interface.
mle_v030.mp4
- π 07/25/2024: Release the
0.3.0with huge refactoring, many integrations, etc (v0.3.0) - π 07/11/2024: Release the
0.2.0with multiple agents interaction (v0.2.0) - π¨βπΌ 07/03/2024: Kaia is born
- π 06/01/2024: Release the first rule-based version of MLE agent (v0.1.0)
pip install mle-agent -U
# or from source
git clone git@github.com:MLSysOps/MLE-agent.git
pip install -e .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 startYou can also start an interactive chat in the terminal under the project directory:
mle chatThe following is a list of the tasks we plan to do, welcome to propose something new!
π¨ 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
β More LLMs and Serving Tools
- Ollama LLama3
- OpenAI GPTs
- Anthropic Claude 3.5 Sonnet
π Better user experience
- CLI Application
- Web UI
- Discord
𧩠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
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
Please check the CONTRIBUTING.md file if you want to contribute.
- Discord community. If you have any questions, please ask in the Discord community.
Check MIT License file for more information.