Angles and Cosine Similarity
Compute angles and cosine similarity from vector coordinates, normalize embeddings responsibly, and handle zero vectors in retrieval code.
Tag
#embeddings
6articleswith this tag.
Vector Norms Measure Size, Not Meaning
Calculate L1, L2, and L-infinity vector norms, verify their defining rules, and see what an embedding magnitude can—and cannot—tell you.
Dimension Counts Independent Directions
Separate the number of embedding coordinates from the number of samples, and learn why a matrix shape alone cannot tell you how many independent directions its vectors span.
Vector Spaces: Test Whether AI Representations Stay Legal
Test zero, addition, and scalar closure, then use normalized embeddings as a counterexample that separates a useful representation set from a vector space.
Sentence Transformers v6 Makes Late Interaction Easier, Not Cheaper
Sentence Transformers v6 adds multi-vector retrieval, while its own results show a modest average quality gain beside a much larger storage bill.
From vectors to embeddings: the geometry behind similarity
Build an intuitive understanding of vectors, dot products, cosine similarity, and why embeddings turn meaning into geometry.