search

codefuse-ai / ModelCache

A LLM semantic caching system aiming to enhance user experience by reducing response time via cached query-result pairs.
Other
780 stars 40 forks source link

Is the project still being maintained, or are there any new plans for updates? #45

Open wongyan-data opened 2 months ago

wongyan-data commented 2 months ago

Is the project still being maintained, or are there any new plans for updates?

peng3307165 commented 1 week ago

Thank you for your attention, this project will continue to be maintained and updated. Due to some urgent reasons, updates have been slow over the past months, but there will be a series of updates coming next, including: --Add ModelCache Adapter --Add fastapi service --Add Docker file --Better embedding model support --Ranker logic

Regarding multimodal caching: --Supports multimodal cacheing. --comprehensive multimodal caching document.

If you're interested in this project, we welcome you to join our open-source efforts. Best wishes!