AutoRAG documentation

RAG AutoML tool for automatically finds an optimal RAG pipeline for your data.

🤷‍♂️ Why AutoRAG?

There are numerous RAG pipelines and modules out there, but you don’t know what pipeline is great for “your own data” and “your own use-case.” Making and evaluating all RAG modules is very time-consuming and hard to do. But without it, you will never know which RAG pipeline is the best for your own use-case.

That’s where AutoRAG comes in.

🤸‍♂️ How can AutoRAG helps?

AutoRAG is a tool for finding optimal RAG pipeline for “your data.” You can evaluate various RAG modules automatically with your own evaluation data, and find the best RAG pipeline for your own use-case.

AutoRAG supports

  • Data Creation: Create RAG evaluation data with your own raw documents.

  • Optimization: Automatically run experiments to find the best RAG pipeline for your own data.

  • Deployment: Deploy the best RAG pipeline with single yaml file. Supports Flask server as well.

🏃‍♂️ Getting Started

pip install AutoRAG

In our documentation, we will guide you through the process of installation and tutorial for AutoRAG starter. After you find your first RAG pipeline with AutoRAG, you can learn how to read result files at here.

And do you want to get the ultimate performance RAG pipeline? Learn how make great evaluation dataset with your own raw documents at here.

Also, you can learn how to set various experiment configurations at optimization guide.

Of course, you can use your own local LLM or embedding model with AutoRAG. Go to here to learn how to use your own model with AutoRAG.

If you face any trouble? Check out our troubleshooting guide. Also, feel free to ask your question at our github issue or Discord channel.

👨‍👩‍👧‍👦 Ecosystem