Automatic hyperparameter optimization of your retrieval augmented generation pipeline.
Stop fiddling around manually with embeddings, rerankers, chunk size, top k and so on. Let the machine do the tuning of your RAG pipeline.
This is an early prototype and therefore slow as hell.
poetry install
Set you pararmeters and models in autorag/config.py
and run the following commands:
poetry shell
python autorag/main.py
Have fun! 💃🪩🕺
Help spread LLM apps @ ellamind.com
Teach AI to dance @ discoresearch.org (Discord)