top | item 40219731

Show HN: A key value store based on semantic similarity rather lexical equality

8 points| enesakar | 1 year ago |github.com

2 comments

order

esafak|1 year ago

A semantic cache is just an encoder in front of a regular cache. It is not hard to connect the two, so where do you see the value? If you DIY, you can choose your own cache.

JimmyRuska|1 year ago

Isn't this how most vector search backends work, cosine similarity sorting against whatever the vector embeddings returned? How is this different?