[HN Gopher] Benchmarking Postgres Vector Search Approaches: Pgve...
___________________________________________________________________
Benchmarking Postgres Vector Search Approaches: Pgvector vs.
Lantern
Author : samaysharma
Score : 46 points
Date : 2024-01-17 18:41 UTC (4 hours ago)
(HTM) web link (tembo.io)
(TXT) w3m dump (tembo.io)
| systems wrote:
| in summary it seems pgvector is faster where it counts
| binidxaba wrote:
| Lantern argues that being able to create indexes quickly is
| useful for tuning the hnsw paramters.
| chuckhend wrote:
| Really great to see how the different config parameters (m,
| ef_construction, ef_search) impact latency and recall.
| darrenBaldwin03 wrote:
| Interesting blog! Makes me wonder what a comparison between
| Pinecone + ChromaDB + Pgvector would look like..
| nikita wrote:
| Does pgvector use parallel index build in this benchmark ?
| binidxaba wrote:
| It does not! Would be interesting to try that!
| dmezzetti wrote:
| If you'd like an alternate approach, txtai can store content in
| Postgres. This approach stores metadata/fields in the database
| and builds a Faiss/HNSW index alongside. The idea is to lean on
| two mature projects vs having to rewrite a full vector index
| implementation.
|
| https://neuml.hashnode.dev/external-database-integration
|
| https://github.com/neuml/txtai
|
| Disclaimer: I'm the primary author of txtai
___________________________________________________________________
(page generated 2024-01-17 23:00 UTC)