CREA

CREA is designed to be a Collaborative Failure-aware REasoning Agent for Biomedical AutoML.

Quick Start

Setup environment

We recommend using uv to manage the environment and dependencies.

1. Install uv (if you haven't already):

pip install uv

or using the standalone installer:

curl -LsSf https://astral.sh/uv/install.sh | sh

2. Create a virtual environment with Python 3.11:

uv venv --python 3.11
source .venv/bin/activate  # On Windows use: .venv\Scripts\activate

3. Install dependencies:

uv pip install -r requirements.txt
uv pip install -e .

4. Set up API keys: Set up your private API key for OPENAI-compatible endpoints:

export OPENAI_BASE_URL="<your base url>" # (e.g. https://api.openai.com/v1)
export OPENAI_API_KEY="<your key>"

Setup knowledge base for RAG Tool

You can create the knowledge base with create_rag_db.sh. For MONAI-1.4.0, you can also download from Huggingface.

You could use this command to check whether the creation succeeds.

python -m crea.monai_rag.query_rag_db

Test with Example Dataset

You can download the example dataset from Huggingface. Download command:

hf download blueyo0/organmnist3d --local-dir dataset/organmnist3d --repo-type dataset

Then run the quick_start.sh to test:

bash quick_start.sh

🙏 Acknowledgement

• We thank all medical workers and dataset owners for making public datasets available to the community.
• Thanks to the open-source of the following projects, our code is developed based on their contributions:
  • aideml
  • monai
  • AutoGluon
  • AutoKeras
  • Auto-SKlearn
  • ML-Master