vearch / vearch

Distributed vector search for AI-native applications

Home Page:https://vearch.github.io

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

hybrid search combining vector search with full-text search

bladehliu opened this issue · comments

redesign the core storage engine, just say 'vear' = an LSM doc store + a vector ANN index + a full-text index (optional)

one possible implementation is to extend Gamma to wrap Tantivy