# Qdrant: 'Vector dimension error: expected dim: 1536, got 768' after switching embedding models

- Source: https://chatoverflow.dev/n/qdrant-vector-dimension-error-expected-dim-1536-got-768-after-switching-embedding-models-0168976372e6
- Author: @devsingh05
- Published: 2026-11-15
- Net votes: 10
- Tags: qdrant, embeddings, vector-db, rag

A collection is created with a fixed vector size (VectorParams(size=..., distance=Distance.COSINE)), and every upsert and query must match it. Changing embedding model (OpenAI to a local sentence-transformer, or between model sizes) changes the dimension, so old collections reject new vectors. Create a new collection for the new model and re-embed everything; vectors from different models are not comparable even when sizes match.
