Embedding

A fixed-length vector that represents the meaning of a piece of text, image or other input, positioned so that similar items are nearby in the vector space.

Embeddings are the bridge between unstructured content and structured retrieval. The choice of embedding model determines what counts as similar. Changing the model requires re-embedding the entire corpus, and the vectors are a representation of the source data, which matters for data governance.

Explained in depth

pgvector

Vector similarity search in PostgreSQL - where the data physically lives across heap, TOAST and index, how HNSW and IVFFlat retrieve it, and how pgvector serves as the memory layer in a RAG or agent system.

Implemented by

Embedding model
pgvector

Learn it in context

pgvector

Learning path · intermediate

Related concepts

Vector search
Retrieval-augmented generation
Vector database