Work in progress: 181,232 of 181,233 sites checked so far, more every week · updated 2 Nov 2026Missing a blog? Tell us

Top all-time · #16018

V

VectorChord

Company blog · blog.vectorchord.aidataprogramming

VectorChord is the company blog at blog.vectorchord.ai, writing about data and programming. Since 2025, 4 different Hacker News readers have linked it 24 times, most often “3B Vectors in PostgreSQL to Protect the Earth”. It is still writing: the last post was on 2026-02-14, and you can follow it by feed.

Visit the blog
24mentions?
4HN people?
2025–2025first – last linked?

Too few sampled comments (3) to say how often HN recommends it.?

Why HN links it

Commenters link these posts as benchmark and case-study material for VectorChord, a Postgres vector search extension, comparing its IVF and quantization indexing with pgvector's HNSW.

Summarised by Claude from a sample of 3 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.

Scalable, Low-latency and Hybrid-enabled Vector Search in Postgres. successor of pgvecto.rs

Most-linked posts?

  1. 3B Vectors in PostgreSQL to Protect the Earth
    3 people · 5 mentions · first linked 2025-04-08
  2. Vector Search over PostgreSQL: Analysis of Different Solutions
    2 people · 3 mentions · first linked 2025-04-16

What Hacker News says?

  1. We do have some benchmark number at https://blog.vectorchord.ai/vector-search-over-postgresql-a-... . It varies on different dataset, but most cases it's 2x or more QPS comparing to pgvector's hnsw at same recall.

    Comment linking /vector-search-over-postgresql-a-comparative-analysis-of-memory-and-disk-solutions

    on “The Case Against PGVector”
  2. Submitted PostgreSQL Full-Text Search: Fast When Done Right (Debunking the Slow Myth) as a story · 427 points

    HN discussion
  3. And we do have user hosting 3 Billion vectors with Postgres + VectorChord with sharding. And they're using vectors to save the earth! Check https://blog.vectorchord.ai/3-billion-vectors-in-postgresql-...

    Comment linking /3-billion-vectors-in-postgresql-to-protect-the-earth

    on “The Case Against PGVector”
  4. Submitted BM25 in PostgreSQL as a story · 139 points

    HN discussion
  5. We at https://github.com/tensorchord/VectorChord solved most of the pgvector issues mentioned in this blog: - We're IVF + quantization, can support 15x more updates per second comparing to pgvector's HNSW. Insert or delete an element in a posting list is a super light operation comparing to modify a graph (HNSW) - Our main branch can now index 100M 768-dim vector in 20min with 16vcpu and 32G memory. This enables use…

    Comment linking /vectorchord-04-faster-postgresql-vector-search-with-advanced-io-and-prefiltering

    on “The Case Against PGVector”
  6. Submitted Indexing 100M vectors in 20 minutes on PostgreSQL with 12GB RAM as a story · 92 points

    HN discussion
  7. Submitted Supercharge vector search with ColBERT rerank in PostgreSQL as a story · 72 points

    HN discussion
  8. Submitted Vector Search at 10k QPS in PostgreSQL as a story · 10 points

    HN discussion
  9. Submitted VectorChord 1.0: Vector Search on Postgres, 100x Faster Indexing than pgvector as a story · 6 points

    HN discussion
  10. Submitted VectorChord-BM25: PostgreSQL Search with BM25 – 3x Faster Than Elasticsearch as a story · 5 points

    HN discussion
  11. Submitted 3B Vectors in PostgreSQL to Protect the Earth as a story · 4 points

    HN discussion
  12. Submitted Vector Search over PostgreSQL: Analysis of Different Solutions as a story · 3 points

    HN discussion
  13. Submitted VectorChord 0.3: Multi-Vector Contextual Late Interaction in PostgreSQL as a story · 3 points

    HN discussion
  14. Submitted 3B Vectors in PostgreSQL to Protect the Earth as a story · 3 points

    HN discussion
  15. Submitted Vector Search over PostgreSQL: Analysis of Different Solutions as a story · 2 points

    HN discussion
  16. Submitted Protect the Earth with 3B Vector Search as a story · 2 points

    HN discussion
  17. Submitted Vector Search at 10k QPS in PostgreSQL as a story · 2 points

    HN discussion
  18. Submitted Hybrid Search with Postgres Native BM25 and VectorChord as a story · 2 points

    HN discussion
  19. Submitted Vector Search at 10k QPS in PostgreSQL as a story · 2 points

    HN discussion
  20. Submitted ARM and VectorChord: Affordable, Fast Vector Search as a story · 2 points

    HN discussion
  21. Submitted Earth Observability with the Help of Vectors as a story · 1 points

    HN discussion
  22. Submitted Vector Search at 10k QPS in PostgreSQL as a story · 1 points

    HN discussion
  23. Submitted VectorChord-BM25: Postgres BM25 Search – 3x Faster Than Elasticsearch as a story · 1 points

    HN discussion
  24. Submitted VectorChord 0.2: 60K-Dimensional Vectors, 50% Faster Indexing with ARM as a story · 1 points

    HN discussion

Search all of HN for blog.vectorchord.ai