From: gouyt13 (@gouyt13) <noreply+gouyt13@github.com>
To: pgvector/pgvector <noreply+pgvector-pgvector@github.com>
Subject: Re: [pgvector/pgvector] issue #1003: Support RabitQ in pgvector
Date: Fri, 23 Oct 2026 17:01:55 +0000
Message-ID: <gh-pgvector-pgvector-1003-c6370300529@github.com> (raw)
In-Reply-To: <gh-pgvector-pgvector-1003@github.com>
References: <gh-pgvector-pgvector-1003@github.com>
Hi @ankane and @zthhhhh,
I’m one of the authors of multi-bit RaBitQ and a maintainer of [RaBitQ-Library](https://github.com/VectorDB-NTU/RaBitQ-Library), our official implementation. Thanks for exploring RaBitQ support in pgvector and sharing these results!
Would you be open to discussing whether parts of the integration could reuse the library’s quantization and distance-estimation components?
We provide a standalone C++17 core with a source-stable API for encoding and scoring, separate from our ANN indexes. It uses caller-owned code buffers and workspace, and can be built without OpenMP. The idea would be to retain pgvector’s storage and index lifecycle management while assessing whether these numerical components could be reused.
This could reduce duplicated algorithm and SIMD maintenance, although the C++ dependency and PostgreSQL integration would add costs that need to be evaluated. We have not yet validated a pgvector integration.
Would an external C++ dependency be an option you would consider? If so, we’d be happy to discuss a minimal IVF-focused integration with @zthhhhh, including comparisons against the recommended halfvec + binary quantization + reranking approach and the asymmetric binary quantization baseline you suggested.