Vector database
A database that stores data as high-dimensional vectors (embeddings) and retrieves by semantic similarity rather than exact keywords.
A vector database stores text (or other data) as embeddings — numeric vectors that capture meaning — and finds the most similar items to a query vector. This enables semantic search: retrieving by meaning, not exact words.
For audio knowledge bases, transcripts are chunked, embedded and stored in a vector database (ChromaDB, Qdrant, Weaviate, Pinecone or Postgres with pgvector). It is the “memory” layer that RAG and AI agents search at query time.