Pg_textsearch – BM25 Ranking for Postgres
I built pg_textsearch, a Postgres extension that brings proper BM25 ranking to full-text search. It's designed for AI/RAG workloads where search quality directly impacts LLM output. Postgres native ts_rank lacks corpus-aware signals (no IDF, no TF saturation, no length normalization). This causes mediocre documents to rank above excellent matches, which matters when your LLM depends on retrieval quality. Quick example: CREATE EXTENSION pg_textsearch; CREATE INDEX articles_idx ON articles USING bm25(content); SELECT title, content to_bm25query('database performance', 'articles_idx') AS…
In plain words
pg_textsearch is a Postgres extension that implements BM25 ranking for full-text search. It addresses limitations in Postgres's native ts_rank function by adding corpus-aware signals like inverse document frequency, term frequency saturation, and length normalization. Built for AI and retrieval-augmented generation workloads where search result quality directly affects language model outputs, it integrates with pgvector for hybrid search and operates fully transactionally without sync jobs. The preview release uses an in-memory architecture with disk-based segments planned.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
I built pg_textsearch, a Postgres extension that brings proper BM25 ranking to full-text search. It's designed for AI/RAG workloads where search quality directly impacts LLM output. Postgres native ts_rank lacks corpus-aware signals (no IDF, no TF saturation, no length normalization). This causes mediocre documents to rank above excellent matches, which matters when your LLM depends on retrieval quality. Quick example: CREATE EXTENSION pg_textsearch; CREATE INDEX articles_idx ON articles USING bm25(content); SELECT title, content <@> to_bm25query('database performance', 'articles_idx') AS score FROM articles ORDER BY score LIMIT 10; Works seamlessly with pgvector or pgvectorscale for hybrid search. Fully transactional (no sync jobs). Preview release uses in-memory architecture (64MB default per index); disk-based segments coming soon. I love ParadeDB's pg_search but wanted something available on our managed Postgres. You can try pg_textsearch free on Tiger Cloud: https://console.cloud.timescale.com Blog: https://www.tigerdata.com/blog/introducing-pg_textsearch-tru... Docs: https://docs.tigerdata.com/use-timescale/latest/extensions/p... Feedback welcome, especially from folks building RAG systems or hybrid search applications.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, October 2025
the whole month →
- SA
I went down the rabbit hole on a side project and ended up building this: Strange Attractors(https://blog.shashanktomar.com/posts/strange-attractors). It’s built with three.js. Working on it reminded me of the little "maths for fun" exercises I used to do while learning programming in early days. Just trying things out, getting fascinated and geeky, and being surprised by the results. I spent way too much time on this, but it was extreme fun. My favorite part: someone pointed me to the Simone Attractor on Threads. It is a 2D attractor and I asked GPT to extrapolate it to…
AI · Oct 2025 · blog.shashanktomar.com
- ASAutism Simulator▲779
Hey all, I built this. It’s not trying to capture every autistic experience (that’d be impossible). It’s based on my own lived experience as well as that of friends on the spectrum. I'm trying to give people a feel for what masking, decision fatigue, and burnout can look like day-to-day. That’s hard to explain in words, but easier to show through choices and stats. I'm not trying to "define autism". I’ve gotten good feedback here about resilience, meds, and difficulty tuning. I’ll keep tweaking it. If even a few people walk away thinking, "ah, maybe that’s why my coworker struggles in those…
Life & fun · Oct 2025 · autism-simulator.vercel.app
