A vector database is a specialised database optimised for storing and similarity-searching high-dimensional vectors – usually embeddings. It uses algorithms such as HNSW or IVF to retrieve the most similar vectors to a query within milliseconds, even from billions of entries.
Well-known systems are Pinecone, Weaviate, Qdrant, Chroma and PostgreSQL with pgvector. Modern job platforms use vector databases to store candidate profiles, job postings, company descriptions and reviews and search them semantically.
More than raw search speed matters. Filters (for example by region, industry, weekly hours), hybrid search (combining keyword and vector search) and scalability are essential. GDPR compliance also matters – sensitive data must not flow unprotected into third-party cloud services.
Lunigi uses vector databases in the backend; users only see the curated results in their inbox.