FG
💻 Software🤖 AI & LLMs

Increase max vectors dimension limit for index

Freshabout 1 year ago
Mar 14, 20260 views
Confidence Score79%
79%

Problem

Hello ! I'm wondering what are the reasons for the maximal dimension limit for indexes HNSW and IVFFlat. Checking _really quickly_ the code, I see those `HNSW_MAX_DIM` and `IVFFLAT_MAX_DIM` constants set to 2000 which seem arbitrary to me, as a non-educated user. - Why do we have these limits ? - How would performance scale if the limited were, say, doubled ? - Is there a plan to increase the limits, considering other vector database products offer up to 32768 dimensions (or even more) for indexed vector ? Thank you !

Unverified for your environment

Select your OS to check compatibility.

1 Fix

Canonical Fix
High Confidence Fix
78% confidence100% success rate6 verificationsLast verified Mar 14, 2026

Solution: Increase max vectors dimension limit for index

Low Risk

It would be very interesting to be able to increase this limit beyond 2000. The new mistral-derivative embedding models (4096 dims) and OpenAI’s new text-embedding-3-large model (3072 dims) offer very good performances, but are not yet compatible with pgvector. We're likely to see more and more good models with an increasing number of dimensions.

78

Trust Score

6 verifications

100% success
  1. 1

    It would be very interesting to be able to increase this limit beyond 2000. The

    It would be very interesting to be able to increase this limit beyond 2000. The new mistral-derivative embedding models (4096 dims) and OpenAI’s new text-embedding-3-large model (3072 dims) offer very good performances, but are not yet compatible with pgvector. We're likely to see more and more good models with an increasing number of dimensions.

Validation

Resolved in pgvector/pgvector GitHub issue #461. Community reactions: 19 upvotes.

Verification Summary

Worked: 6
Partial: 1
Last verified Mar 14, 2026

Sign in to verify this fix

Environment

Submitted by

AC

Alex Chen

2450 rep

Tags

pgvectorembeddingsvector-search