Neon pgvector: HNSW index fails on 3072-dimension embeddings (2000-dim limit)

TL;DR

Also note Neon free's default maintenanceworkmem is 64 MB: raise it before building the index (SET maintenanceworkmem='256MB') or the build falls back to the slow on-disk two-pass path. Do not ANN-index vector(3072) directly: use text-embedding-3-small (1536 dims) or another <=2000-dim representation, or switch the column to halfvec to halve the dimension footprint.

The error

HNSW index fails on 3072-dimension embeddings (2000-dim limit)

Fix

1. Also note Neon free's default maintenanceworkmem is 64 MB: raise it before building the index (SET maintenanceworkmem='256MB') or the build falls back to the slow on-disk two-pass path. Expected: You get the expected result; the problem is gone.

2. Re-run the original operation and confirm the error is gone. Expected: no error, normal output.

When to use

• You hit this exact error with Neon pgvector.
• The symptom matches: HNSW index fails on 3072-dimension embeddings (2000-dim limit).

When NOT to use

• A different error message from Neon pgvector; the cause here is specific to this error.
• Unrelated Neon pgvector issues (different feature, different failure).
• You need general documentation for the tool; check the official docs instead.

Compatibility

Reported against Neon pgvector. Source: https://github.com/aurahq-ai/aura/blob/HEAD/content/blog/why-neon-postgres.mdx.

Variant phrasings

HNSW index fails on 3072-dimension embeddings (2000-dim limit)

Why it happens

Creating an HNSW index on a vector(3072) column fails. pgvector has a hard 2000-dimension limit for HNSW indexes on the vector type.

Edge cases

• If your error message differs even slightly, this is probably a different issue; search the exact text.
• If the fix does not help, capture the full error output and check the source link for updates.

Source

https://github.com/aurahq-ai/aura/blob/HEAD/content/blog/why-neon-postgres.mdx

Source: Creating an HNSW index on a vector(3072) column fails. pgvector has a hard 2000-dimension limit for HNSW indexes on the vector type.

Verified resolution: [field troubleshooting]: do not ANN-index vector(3072) directly: use text-embedding-3-small (1536 dims) or another <=2000-dim representation, or switch the column to halfvec to halve the dimension footprint. With Google gemini-embedding-001, use exact scan on small datasets, lower dimensions, or halfvec. Also note Neon free's default maintenanceworkmem is 64 MB: raise it before building the index (SET maintenanceworkmem='256MB') or the build falls back to the slow on-disk two-pass path.

Source URL: https://github.com/aurahq-ai/aura/blob/HEAD/content/blog/why-neon-postgres.mdx