Results for "vector search"

Search algorithm for generation that keeps top-k partial sequences; can improve likelihood but reduce diversity.

A datastore optimized for similarity search over embeddings, enabling semantic retrieval at scale.

A continuous vector encoding of an item (word, image, user) such that semantic similarity corresponds to geometric closeness.

Architecture that retrieves relevant documents (e.g., from a vector DB) and conditions generation on them to reduce hallucinations.

Mechanisms for retaining context across turns/sessions: scratchpads, vector memories, structured stores.

Mathematical foundation for ML involving vector spaces, matrices, and linear transformations.

Vector whose direction remains unchanged under linear transformation.

Measure of vector magnitude; used in regularization and optimization.

Matrix of first-order derivatives for vector-valued functions.

Retrieval based on embedding similarity rather than keyword overlap, capturing paraphrases and related concepts.

Choosing step size along gradient direction.

Directly optimizing control policies.

Set of vectors closed under addition and scalar multiplication.