AI engineering glossary · RAG vector search
What is score fusion?
Score fusion: Combining relevance scores from different retrievers into one score, often after normalising them to a common range and using a weighted sum. The weight controls how much keyword or semantic evidence counts.
Score fusion: an example
final = 0.6 * normalised_vector_score + 0.4 * normalised_bm25_score.
Related terms
More RAG vector search terms
- Self-RAG
- Semantic cache
- Semantic chunking
- Sentence window retrieval
- Similarity threshold
- Small-to-big retrieval
- Sparse retrieval
- Structure-aware chunking
Where you learn it
Score fusion is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.