Vector Dimension Mismatch (1536 vs 3072 / DimensionMismatchError)

Upgrading from text-embedding-ada-002 (1536d) to text-embedding-3-large (default 3072d) without passing dimensions: 1536 breaks existing pgvector / Pinecone / Qdrant indexes.

1. Immediate Code & SKU Fix

Replace With SKU: text-embedding-3-small (1536d native) or text-embedding-3-large with dimensions: 1536

Install Command: npm install openai@latest

Required Env Vars: OPENAI_API_KEY

const emb = await openai.embeddings.create({ model: "text-embedding-3-large", input: text, dimensions: 1536 });

2. Verified Hot-Swap Fallback Route

JTBD: embeddings

Primary: openai → Fallback: voyage

liveHealth: operational · autoActOk: true

retrieval-quality bake-off winner is Voyage

GET /api/rescue JSON (<2 KB)Falsify Pick (/api/falsify)

Matched Error String Signatures (4)

DimensionMismatchErrorVector dimension 3072 does not match the dimension of the index 1536dimension mismatchexpected 1536 dimensions, not 3072

curl -s "https://getagentdepot.com/api/rescue?q=DimensionMismatchError"

Browse All 28 Agent Runtime Rescue Cards