Hacker News new | past | comments | ask | show | jobs | submit login

looping back here. The langchain community just released a version of Hybrid Search which using postgres full text search. It's clever, and IMO probably a better approach than just sparse/dense vectors:

https://js.langchain.com/docs/modules/indexes/retrievers/sup...




Will check this out - it seems like its doing two separate searches where you specify two separate top K values. Curious what the trade offs are between this approach and weighting sparse/dense vectors




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: