search

BerriAI / reliableGPT

Get 100% uptime, reliability from OpenAI. Handle Rate Limit, Timeout, API, Keys Errors
MIT License
624 stars 33 forks source link

Allow users to define their own Vector DB as their cache #28

Open ishaan-jaff opened 1 year ago

ishaan-jaff commented 1 year ago

Allow users to define their own Vector DB for the Cache. For compliance reasons users want the ability to define their own vector DB as cache

cc @grski

grski commented 1 year ago

@hkorzeniewski for tomorrow fyi

grski commented 1 year ago

For now we do not need vectorDB as we r doing simply an exact match with the cache - this is implemented here:https://github.com/BerriAI/reliableGPT/pull/33 In the future next steps will include proper vector store/db and semantic similarity matches.