rag-colls 0.2.0.18

rag-colls - Implement recent advanced RAG techniques

rag-colls

rag-colls a.k.a RAG Collections.

Simple and easy to use, production-ready advanced RAG techniques.

📑 Table of Contents

• 📖 Documentation
• 🔧 Installation
• 📚 Notebooks
• 🚀 Upcoming
• 🎉 Quickstart
• 💻 Develop Guidance
• ©️ License

📖 Documentation

Please visit documentation to get latest update.

🔧 Installation

• You can easily install it from pypi:

pip install -U rag-colls

• Docker - 🐳:

# Clone the repository
git clone https://github.com/hienhayho/rag-colls.git
cd rag-colls/

# Choose python version and setup OPENAI_API_KEY
export PYTHON_VERSION="3.11"
export OPENAI_API_KEY="your-openai-api-key-here"

# Docker build
DOCKER_BUILDKIT=1 docker build \
                -f docker/Dockerfile \
                --build-arg OPENAI_API_KEY="$OPENAI_API_KEY" \
                --build-arg PYTHON_VERSION="$PYTHON_VERSION" \
                -t rag-colls:$PYTHON_VERSION .

docker run -it --name rag_colls --shm-size=2G rag-colls:$PYTHON_VERSION

📚 Notebooks

We have provided some notebooks for example usage.

RAG Tech	Code	Guide	Tech Description
BasicRAG	BasicRAG	Colab	Integrate with Chromadb
ContextualRAG	ContextualRAG	Colab	Integrate with Chromadb and BM25s version
RAFT	RAFT	Colab	Boost RAG with SFT

🚀 Upcoming

We are currently working on these projects and will be updated soon.

RAG Tech	Link
Graph-RAG	Blog, Paper
RAG-RL	Paper

🎉 Quickstart

Please refer to example for more information.

💻 Develop Guidance

Please refer to DEVELOP.md for more information.

💎 Acknowledgement

This project is supported by UIT AIClub.

©️ LICENSE

rag-colls is under MIT LICENSE.