What is HNSW?

Algorithms that find vectors close to a query without exhaustive comparison, trading exactness for speed.

A database optimized for storing and querying high-dimensional embedding vectors.

A graph structure of entities and relationships used for reasoning or retrieval.

A model specialized for converting data into vectors used for semantic search, clustering, and retrieval.

A retrieval approach that combines keyword (lexical) search with vector (semantic) search for better recall and precision.

A shift in real-world input data over time that can degrade model performance.