Get the latest tech news

PGVector's Missing Features


PGVector offers infrastructure simplicity at the cost of missing some key features desireable in search solutions. We explain what those are in this blog.

Dense vector search is not perfect and will fail on queries like emails where Rob praises the team and does not mention productivity. Or, vice versa, you could narrow down your result set by requiring a term like emails where Rob praises the team "productivity". You can try it yourself on our hacker news search engine and see that on large datasets (up to billions of documents), Trieve’s handling of segments and scale guarantees that filters and order by’s are 0 cost.

Get the Android app

Or read this on Hacker News

Read more on:

Photo of missing features

missing features

Photo of pgvector

pgvector

Related news:

News photo

Understanding Pgvector's HNSW Index Storage in Postgres

News photo

Show HN: PGlite – in-browser WASM Postgres with pgvector and live sync

News photo

Smart rings will stay niche until they add these missing features