BTC
ETH
SOL
XRP
BNB
TON
DOT
LTC
POL
HBAR
NEAR
ARB
UNI
A database built to store embeddings and quickly find the ones closest in meaning to a question.
AI Drafted with AI help · Reviewed by Keshav Aggarwal · Updated
In simple words
Imagine a library where books are shelved by what they are about, not by title. Ask about “sleeping animals” and you are led straight to the shelf on hibernation.
A vector database is that kind of library.
The technical side
Vector databases index embeddings so a nearest-neighbour search over millions of vectors returns in milliseconds, usually with approximate algorithms such as HNSW. Dedicated products include Pinecone, Weaviate and Qdrant; Postgres (pgvector) and many search engines also support vectors.
In a RAG app, the question is embedded, the closest document chunks are fetched from the vector database, and they are given to the model to answer from.
Vector Database kya hai?
Vector database aisi library hai jo matlab ke hisaab se cheezein dhoondhti hai, sirf shabd mila ke nahi. RAG isi pe chalta hai.
Related terms
- EmbeddingAIA list of numbers that captures the meaning of a piece of text or an image, so a computer can find things that mean similar things.
- RAG (Retrieval-Augmented Generation)AIA way to make an AI answer from trusted documents: it first looks up the relevant pages, then writes its answer from them.