Key technologySimilarity index21 min
Approximate nearest-neighbour search over embeddings.Core featuresHNSW and IVF indexesMetadata filters inside the searchQuantisation to cut memoryNamespaces for tenantspgvector keeps it inside PostgresWhen to useRetrieval for LLM answers (RAG)Semantic search and "more like this"Candidate generation for recommendationsFinding documents by text, usually through an inverted index.Splitting data across machines so no single node holds it all.Keeping hot data in fast storage to skip slow lookups.
PremiumVector databases
Find the stored vectors nearest to a query vector, fast enough to sit in a request: the retrieval layer under RAG, semantic search and recommendations.
Premium
This technology page is on the Premium plan
Readers with Lifetime Access read it in full. Already bought it? Sign in from the top bar.
What’s inside
- At a glance
- Key concepts and capabilities
- Use cases
- How the indexes work
- Filtering: where correctness is decided
- Choosing a product
- Numbers to have ready
- When to reach for something else
- How interviewers probe