Skip to content

Releases: tensorchord/VectorChord

0.5.2

15 Sep 07:17
@usamoi usamoi
0.5.2
91f672e
Compare
Choose a tag to compare
0.5.2 Latest
Latest

VectorChord 0.5.2 Release Notes

  • Add built-in query simpling, for recall evaluation with online queries, see also Query sampling. (#321, #334, #337, #338)
  • Fix MVCC violation if either build.rerank_in_table or vchordrq.prefilter is enabled. (#336)
  • Fix incorrect order of vchordrq.probes. (#342)

The vchord-postgres image includes pgvector 0.8.1 now. You could update the extension schema by running the following SQL:

ALTER EXTENSION pgvector UPDATE;
ALTER EXTENSION vchord UPDATE;
Assets 22

0.5.1

02 Sep 07:48
@usamoi usamoi
0.5.1
862c4c3
Compare
Choose a tag to compare
0.5.1

VectorChord 0.5.1 Release Notes

  • A little performance improvement. (#314)
  • Fix compilation on x86_64 nix with gcc.arch set. (#316)
  • Fix compilation and tests, and add initial simd support, on s390x and powerpc64le, see also s390x. (#318, #323, #324, #326, #325, #327, #328, #329, #330)

Full Changelog: 0.5.0...0.5.1

Loading

0.5.0

15 Aug 07:11
@VoVAllen VoVAllen
0.5.0
bb2961f
Compare
Choose a tag to compare
0.5.0

VectorChord v0.5.0

Two big upgrades, focused and pragmatic.

1) Experimental DiskANN (with RaBitQ) — vchordg (preview)

A new disk-backed graph index that keeps memory low while giving you a DiskANN-style option inside VectorChord.

  • When it shines: can be faster than IVF+RaBitQ (vchordrq) on some embeddings (e.g., OpenAI/Cohere) — but not always.
  • Caveats: slow build, and insert/delete are weaker than IVF. Dataset-dependent: benchmark before switching.
  • Try it: 
    CREATE INDEX ON items USING vchordg (embedding vector_l2_ops)
WITH (options = $$
  m = 64
  ef_construction = 128
$$);

SET vchordg.ef_search = 128;
  • Memory knob: bits = 1 halves index memory vs default bits = 2 (better recall/QPS).

We’re shipping this to give you a one-stop vector search toolbox at VectorChord. Feel free to share any thoughts and questions about it!

2) Recall measurement for IVF+RaBitQ — vchordrq_evaluate_query_recall

Approximate ≠ exact. Now you can quantify how close your results are with vchordrq_evaluate_query_recall. It accepts a query that returns row identifiers (e.g., ctid) and returns a recall score.

SET vchordrq.probes = '100';
SET vchordrq.epsilon = 1.0;

SELECT vchordrq_evaluate_query_recall(query => $$
  SELECT ctid FROM items
  ORDER BY embedding <-> '[3,1,2]'
  LIMIT 10
$$);  -- add ", exact_search => true" for table-scan ground truth

Note: recall evaluation targets vchordrq in 0.5 (not vchordg yet).

Other fixes

We fixed some performance regression problems in this release. User can enjoy better performances with it!

Talk to us

Thanks for building with us. If you have any question or thoughts, open an issue, join our discord or start a Discussion. Your notes guide what we fix first. If VectorChord helped you, drop us a ⭐ on GitHub and hit Watch → Releases.

Loading

0.4.3

20 Jun 04:51
@usamoi usamoi
0.4.3
65a1a05
Compare
Choose a tag to compare
0.4.3

VectorChord 0.4.3 Release Notes

  • use mimalloc on aarch64-linux
  • fix compilation with gcc on x86_64
  • fix compilation with clang on Windows
  • prompt the user to rebuild the index after the upgrade

Full Changelog: 0.4.2...0.4.3

Loading

0.4.2

29 May 23:46
@usamoi usamoi
0.4.2
695d052
Compare
Choose a tag to compare
0.4.2

VectorChord 0.4.2 Release Notes

  • fix compilation on aarch64 macos
  • add support for pgxnclient: you can install VectorChord with pgxnclient install vchord==0.4.2 now

Full Changelog: 0.4.1...0.4.2

Loading

0.4.1

24 May 09:54
@usamoi usamoi
0.4.1
24ddfa0
Compare
Choose a tag to compare
0.4.1

VectorChord 0.4.1 Release Notes

  • Fix potential precision issue if the dimension of vectors is 1, 2, 4, 8, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096, 8192, 16384, 32768.

Full Changelog: 0.4.0...0.4.1

Loading

0.4.0

23 May 18:18
@usamoi usamoi
0.4.0
5c3b5bc
Compare
Choose a tag to compare
0.4.0

VectorChord 0.4 Release Notes

Major Improvements

  • Streaming I/O & Page Prefetch

    • Complete rewrite of page layout to enable pipelined computation with streaming I/O.
    • On PostgreSQL 17, uses fadvise to prefetch buffers into the OS page cache, eliminating per-buffer read waits and fully leveraging disk throughput.
    • In upcoming PostgreSQL 18, direct support for io_uring will further streamline asynchronous I/O.
    • Benchmarks: 2–3× lower latency on cold queries (no buffer or page cache), translating to significantly improved tail latency in production.

  • Prefilter Acceleration

    • Introduces true prefilter support for vector + filter queries.
    • Previous postfilter approach ranked full result sets and then applied filters—inefficient when selectivity is low (e.g., 1% filter rate).
    • Applies SQL filters before full precision vector distance computations, avoiding unnecessary work.
    • Benchmarks: Up to 3× faster end-to-end search on highly selective filters without any additional tuning.

Other Improvements

  • Optimized Residual Quantization

    • Collaboration with RaBitQ author Jianyang: refactored distance term $|⟨o, q–c⟩|$ into $⟨o, q⟩ – ⟨o, c⟩$, so the query vector is quantized only once.
    • Result: ~20% QPS improvement over 0.3.
    • Recommendation: Enable residual quantization for L2 workloads.

  • Fast Walsh-Hadamard Transform for Rotation

    • Collaboration with RaBitQ author Jianyang: replaced manual vchordrq.prewarm_dim GUC with an on-the-fly Fast Walsh-Hadamard Transform.
    • Removes the need to configure a prewarmed dimension list and yields marginal speed gains during setup.

Thank you for using VectorChord! As always, we welcome feedback and contributions on GitHub.

Full Changelog: 0.3.0...0.4.0

Loading

0.3.0

11 Apr 08:11
@VoVAllen VoVAllen
0.3.0
bc886b2
Compare
Choose a tag to compare
0.3.0

Features

Native support for the maxsim operator and efficient indexing inspired by XTR-WARP project. This makes it possible to build ColBERT- or ColPaLI-style multi-vector retrieval applications seamlessly within PostgreSQL.

Improvements

  • More KMeans parameters can be configured
  • Better progress report for internal KMeans build

What's Changed

Full Changelog: 0.2.2...0.3.0

Contributors

cutecutecat, xieydd, and usamoi
Loading

0.2.2

18 Mar 12:31
@usamoi usamoi
0.2.2
63e2549
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
0.2.2

What's Changed

Full Changelog: 0.2.1...0.2.2

Contributors

cutecutecat, xieydd, and usamoi
Loading

0.2.1

19 Feb 13:05
@VoVAllen VoVAllen
0.2.1
0849b18
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
0.2.1

Major Improvement

We optimize the external centroid index building speed, about 30%. Now it takes about 30h to build index for 100M vectors with only 4 vcpu on i4i.xlarge.

What's Changed

  • refactor: move algorithm to a crate by @usamoi in #172
  • feat: pinning index in memory when building, second try by @usamoi in #181
  • fix: use linked list of vectors to skip realloc by @usamoi in #182
  • feat: use select algorithm to replace heap, if k in top-k is expected to be small by @usamoi in #183
  • ci: install pg13 in docker image by @usamoi in #186
  • ci: use less docker by @usamoi in #187
  • feat: rerank by fetching vectors in heap table by @usamoi in #189
  • ci: enable CI for pg13 by @usamoi in #185
  • chore: update dependencies by @usamoi in #190
  • refactor: remove meaningless target feature requirements by @usamoi in #192
  • fix: test simd operations in emulator by @usamoi in #193
  • feat: neon impl of u8::reduce_sum_of_x by @usamoi in #194
  • chore: update 0.2.1 schema (upgrade) script by @usamoi in #195

Full Changelog: 0.2.0...0.2.1

Contributors

usamoi
Loading