{"name":"pg_vectorsearch","repo":"timescale/pg_vectorsearch","url":"https://midorreal.com/project/timescale-pg-vectorsearch","repository":"https://github.com/timescale/pg_vectorsearch","description":"High-performance vector search for PostgreSQL","facts":{"license":{"value":"PostgreSQL","source":"https://github.com/timescale/pg_vectorsearch","checked":"22 Nov 2026"},"language":{"value":"C","source":"https://github.com/timescale/pg_vectorsearch","checked":"22 Nov 2026"},"last_release":{"value":"v0.1.0, 13 Oct 2026","source":"https://github.com/timescale/pg_vectorsearch/releases","checked":"22 Nov 2026"},"releases":{"value":"3","source":"https://github.com/timescale/pg_vectorsearch/releases","checked":"19 Nov 2026"},"contributors":{"value":"8","source":"https://github.com/timescale/pg_vectorsearch/graphs/contributors","checked":"19 Nov 2026"},"archived":{"value":"no","source":"https://github.com/timescale/pg_vectorsearch","checked":"22 Nov 2026"}},"stars":451.0,"writeup":{"what_it_is":"pg_vectorsearch is a PostgreSQL extension for approximate nearest neighbor (ANN) vector search. It adds a PRISM index access method that uses RaBitQ quantization, a hierarchical centroid tree, and posting lists.","audience":"PostgreSQL users who need vector similarity search, especially those with existing pgvector tables","claims":[{"kind":"specific","claim":"Supports indexing existing pgvector vector and halfvec columns without changing the table","excerpt":"index existing `vector` and `halfvec` columns as-is","status":"not_checked"},{"kind":"specific","claim":"Supports vectors up to 8192 dimensions, with dimension constraints above 1968","excerpt":"Any dimension up to 1968 is supported.","status":"not_checked"},{"kind":"broad","claim":"Is faster than pgvector's IVFFlat and HNSW for querying and index building","excerpt":"an [index that is significantly faster][announcement] than","status":"too_broad"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-11-17"},"why_now":null,"owner_supplied":null,"score":{"verdict":"sleeper","hype":21,"reality":64,"gap":-43,"momentum":0.7,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T07:00:00+00:00","verdict_source":"rule"},"early_read":null,"changes":[{"date":"2026-10-13T13:12:31+00:00","text":"Latest release v0.1.0","source":"https://github.com/timescale/pg_vectorsearch/releases"},{"date":"2026-10-09T17:16:56+00:00","text":"First release","source":"https://github.com/timescale/pg_vectorsearch/releases"},{"date":"2026-01-30T15:34:57+00:00","text":"Repository created","source":"https://github.com/timescale/pg_vectorsearch"}],"cite":"pg_vectorsearch is a GitHub project at https://github.com/timescale/pg_vectorsearch written mainly in C, described there as \"High-performance vector search for PostgreSQL\".","attribution":"Data from Mid or Real, https://midorreal.com/project/timescale-pg-vectorsearch, checked 22 November 2026. Attribution with a link is required.","still_real":null}