What architectural decisions enabled pg_textsearch to outperform Tantivy/ParadeDB by 4.7×, especially given Tantivy’s reputation for speed?
vibes
Show HN: Postgres extension for BM25 relevance-ranked full-text search
61–70 of 75 posts
Re: Show HN: Postgres extension for BM25 relevance-ranked full-text search
#62I like that we get far with just the Postgres. For an Elixir world, it's a job processing queue via Oban[1] and a search engine via Torus[2] now.
[1] https://oban.pro/ [2] https://www.dimamik.com/posts/bm25_search/
Re: Show HN: Postgres extension for BM25 relevance-ranked full-text search
#63Please oh please let GCP add this to the supported managed Postgres extensions...
And Azure Flexible server please
Re: Show HN: Postgres extension for BM25 relevance-ranked full-text search
#64On a tangent note it’s amazing how hard it is to have a good case-insensitive search in Postgres. In SQL Server you just use case-insensitive collation (which is a default) and add an index (it’s the only one non-clustered) and call it a day. In postgres you need to go above and beyond just for that. It’s like postgres guys were “nah dog, everybody just uses lowercase; you don’t need to worry of people writing john d…
citext doesn't solve your problem of case-insensitive search?
It’s good for ids where you would like complete match (username, localeId, etc.) but not really for stuff like lastname where you would like to support at least most common prefix search as well
Re: Show HN: Postgres extension for BM25 relevance-ranked full-text search
#65On a tangent note it’s amazing how hard it is to have a good case-insensitive search in Postgres. In SQL Server you just use case-insensitive collation (which is a default) and add an index (it’s the only one non-clustered) and call it a day. In postgres you need to go above and beyond just for that. It’s like postgres guys were “nah dog, everybody just uses lowercase; you don’t need to worry of people writing john d…
> And don’t get me started with storing datetime with timezone (e.g “4/2/2007 7:23:57 PM -07:00“). In sql server you have datetimeoffset; in Postgres you fuck off :-) `TIMESTAMPTZ` / `TIMESTAMP WITH TIME ZONE` exists?
I don’t know who was the genius who invented that but timestamp *with time zone* doesn’t store the time zone.
Timestamp with time zone actually means gmt time created from a time zone which is then discarded because fuck you that’s why.
Re: Show HN: Postgres extension for BM25 relevance-ranked full-text search
#66[flagged]
Re: Show HN: Postgres extension for BM25 relevance-ranked full-text search
#67Re: Show HN: Postgres extension for BM25 relevance-ranked full-text search
#68[flagged]
Re: Show HN: Postgres extension for BM25 relevance-ranked full-text search
#69[flagged]
Re: Show HN: Postgres extension for BM25 relevance-ranked full-text search
#70[flagged]