AI engineering glossary · RAG vector search
What is alpha weighting?
Alpha weighting: A single parameter in hybrid search, usually between 0 and 1, that sets the balance between vector and keyword scores. An alpha of 1 uses only vector scores, 0 only keyword scores, and tuning it on real queries improves results.
Alpha weighting: an example
With alpha = 0.7, the score is 0.7 times the semantic score plus 0.3 times the keyword score.
Related terms
More RAG vector search terms
- ANN recall
- Answer correctness
- Answer relevance
- Approximate nearest neighbour search
- Asymmetric search
- Attribution
- Binary quantisation
- Chunk
Where you learn it
Alpha weighting is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.