AI engineering glossary · RAG vector search
What is re-embedding?
Re-embedding: Recomputing all stored vectors with a new or updated embedding model and rebuilding the index. It is required when changing models, since vectors from different models are not comparable, and can be costly for large collections.
Re-embedding: an example
Moving to a new model means re-embedding all 8 million chunks and building a fresh index.
Related terms
More RAG vector search terms
- Recall-latency trade-off
- Reciprocal rank fusion
- Recursive character splitting
- Reranker
- Reranking
- Rescoring
- Retrieval evaluation
- Retrieval-augmented generation
Where you learn it
Re-embedding is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.