Glossary: Embeddings and Vector Search
metadata
Plain facts stored beside each vector, such as source, category, price and date. Hard conditions like "under $20" belong in metadata, checked exactly, because models don't do arithmetic.
Glossary: Embeddings and Vector Search
Plain facts stored beside each vector, such as source, category, price and date. Hard conditions like "under $20" belong in metadata, checked exactly, because models don't do arithmetic.