Weโ€™re not just coding here; weโ€™re crafting the future of RAG and LLM optimization! ๐Ÿš€ Hereโ€™s a sneak peek at whatโ€™s cooking:

Currently in the Works

We get it; lifeโ€™s too short for manual hyperparameter tuning. Thatโ€™s why weโ€™re ramping up to support even more search types.

๐ŸŒˆ Diverse Chains Support

LLMChain and custom chains are in our pipeline. Because, hey, variety is the spice of life!

๐Ÿ›  Eval Tools and Metrics

Weโ€™re on it! Expect robust evaluation tools to quantify your success.

๐ŸŒŒ See Your Data Differently

Weโ€™re spicing up our visualization tools to give you an X-ray vision into your embedding spaces.

Future Plans

๐ŸŒ€ Async Experiments

Because your time is precious. Run Experiments() in parallel and get your results, like, yesterday.

๐Ÿ’ป Going Beyond Python

Heads up, JS and TS enthusiasts! Weโ€™re extending our magic to other languages.

๐Ÿ” Perfecting the Recall

Improving embedding quality via fine-tuning and human feedback. Because good enough is just not in our vocabulary.

๐Ÿ“ฆ Share, Donโ€™t Hoard

Easier data sharingโ€™s on the horizon with new serialization formats for embedding collections.

๐Ÿ“š Community Corner

Got an awesome feature idea? Or want to contribute? Our Discord community is the place to be!

Stay tuned, more awesomeness coming your way! ๐ŸŒŸ