Skip to main content
Bluecoders
← Tech glossary

Vector Database

TechTool

A vector database is a database specialised in storing and efficiently searching high-dimensional vectors (embeddings), via approximate nearest-neighbour (ANN) algorithms such as HNSW, IVF or DiskANN.

A vector [database](/ressources/glossaire-de-la-tech/bdd-base-de-donnees-database) is a database specialised in storing and efficiently searching high-dimensional vectors ([embeddings](/ressources/glossaire-de-la-tech/embeddings)), via approximate nearest-neighbour (ANN) algorithms such as HNSW, IVF or DiskANN.

They are the storage layer of RAG architectures: you index the embeddings of every chunk of a corpus and then retrieve, in milliseconds, the chunks semantically closest to a given question — even across millions of vectors.

Reference solutions include Pinecone, Qdrant, Weaviate, Milvus, Chroma (open source) and Turbopuffer — plus extensions of existing databases: pgvector for PostgreSQL, Atlas Vector Search for MongoDB, Elasticsearch and OpenSearch.

Related terms

Ready to find the missing piece of your team?

Let's talk about your hiring needs. A team member will get back to you quickly to qualify the brief and kick off the search.

Start a searchI'm a candidate