Applied AI·Embeddings and retrieval
you swapped embedding models and the old vectors are no longer comparable to the new ones, so the whole corpus has to be re-embedded.
Embedding model versioning
Draft summary, pending review
Vectors are only comparable within one model and version, so swapping embedding models means re-embedding the entire corpus and reindexing. Record the model name and version next to every vector; treat a model swap as a data migration, because it is one.