From 2ee3113417a0901138ec9fcd6f50a05d351bbd75 Mon Sep 17 00:00:00 2001 From: Andrew Kane Date: Wed, 22 Oct 2025 13:10:58 -0700 Subject: [PATCH] Updated readme [skip ci] --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index b8d0627..0f7ee7a 100644 --- a/README.md +++ b/README.md @@ -812,7 +812,7 @@ Yes, pgvector uses the write-ahead log (WAL), which allows for replication and p #### What if I want to index vectors with more than 2,000 dimensions? -You can use [half-precision indexing](#half-precision-indexing) to index up to 4,000 dimensions or [binary quantization](#binary-quantization) to index up to 64,000 dimensions. Another option is [dimensionality reduction](https://en.wikipedia.org/wiki/Dimensionality_reduction). +You can use [half-precision vectors](#half-precision-vectors) or [half-precision indexing](#half-precision-indexing) to index up to 4,000 dimensions or [binary quantization](#binary-quantization) to index up to 64,000 dimensions. Other options are [indexing subvectors](#indexing-subvectors) (for models that support it) or [dimensionality reduction](https://en.wikipedia.org/wiki/Dimensionality_reduction). #### Can I store vectors with different dimensions in the same column?