← Back to Glossary
Cosine Similarity
A mathematical formula measuring the angle between two vector arrows to determine how close their meanings are.
Why it exists
Measures semantic closeness regardless of vector magnitude. Scores range from -1.0 (opposite) to +1.0 (identical meaning).
How it works
Calculated as (A · B) / (||A|| * ||B||). Scores near 1.0 indicate high semantic relevance between query and chunk.
Related terms
Where you'll use this
roadmap