Glossary · Definition
Vector database
A vector database stores embeddings and finds the most similar ones quickly, which is how RAG systems locate relevant passages among millions.
By Nythrex EngineeringUpdated 1 min read
In plain words
Searching millions of embeddings one by one would be slow. Vector databases (or vector indexes inside regular databases, like pgvector in PostgreSQL) use special indexes to find the nearest matches in milliseconds, usually combined with filters for permissions and metadata.
When it matters to you
- Your knowledge base is larger than what fits into a prompt
- You need fast semantic search
- You need to filter by user, tenant or document status
Common pitfalls
- Adding a new database when your existing one can do the job
- No hybrid (keyword + vector) search
- Filtering permissions after retrieval instead of in the query
Keep reading
ComparisonVector databases comparedVector stores for RAG: pgvector, Pinecone, Qdrant, Azure AI Search and OpenSearch compared on ops, hybrid search, filtering, scale and cost.GlossaryEmbeddingsEmbeddings are lists of numbers that represent the meaning of text, so a computer can find passages that mean similar things even when they use different words.GlossaryRAG (retrieval-augmented generation)RAG is a technique where an AI system first searches your documents or data for relevant passages and then lets a language model answer using them, with cita…
Want a second opinion on your project?
Tell us what you’re building and where you’re stuck. We’ll reply within one business day with the most practical next step — even if that step isn’t us.