Show HN: Postgres extension for BM25 relevance-ranked full-text search
Not a pilot. Tiger Data just shipped a Postgres extension that outperforms ParadeDB by 4.7x—using Claude AI to cut development time from 12 months to 6.
Why it matters
Open-source tooling is collapsing development timelines for AI infrastructure. Tiger Data's pg_textsearch demonstrates how AI-assisted coding (Claude) enabled a solo engineer to build production-grade database search in half the estimated time, disrupting the competitive moat of established vendors like ParadeDB.
The key facts
7 to know4.7x query throughput advantage over ParadeDB/Tantivy at scale
Development timeline: estimated 6-12 months reduced to ~6 months actual (2 quarters) with AI-boosted development
pg_textsearch released open-source under Postgres license
Built by Tiger Data, a Postgres cloud vendor specializing in timeseries data
BM25 relevance-ranked full-text search for hybrid search stacks
Benchmarked on MS-MARCO dataset with publicly available methodology
Addresses Postgres native gap: no built-in ranked keyword search; alternative (ParadeDB) uses restrictive AGPL license
Go to the source
Hacker Newsgithub.com
Publisher excerpt: Last summer we faced a conundrum at my company, Tiger Data, a Postgres cloud vendor whose main business is in timeseries data. We were trying to grow our business towards emerging AI-centric workloads and wanted to provide a state-of-the-art hybrid search stack in Postgres. We'd already built…
