Cosine Similarity
Cosine compares vector directions. Normalization changes distance rankings, coordinate scaling changes meaning, and retrieval thresholds need evaluation.
-
-
Embedding Similarity
The dot product ties two candidates at 10.0000 that cosine separates at 1.0000 and 0.9806. The metric is not a formatting choice.
-
Approximate Nearest Neighbor Search
Approximate nearest-neighbor search trades exact top-k guarantees for less work. An exact scan supplies the baseline for measuring what an approximate vector index misses.
-
Retrieval-Augmented Generation and Agents
A model’s weights are a lossy, frozen snapshot of the world. Retrieval is how you stop relying on them.
-
Filtered Vector Search
A vector index returns the nearest neighbors, and a metadata filter such as an access rule decides which of them may be shown. Where the filter runs changes how many results come back and what can leak.
-
Preserving Access Controls in Retrieval Data
A retrieval index is a copy of documents, and copies do not inherit permissions. This post follows permissions from source ACLs through identity, filtering, revocation, and leakage tests.