Glossary term

Vector database

A database built to store embeddings and quickly find the most similar ones.

How it works

A vector database stores embeddings and answers the question 'which stored vectors are closest to this one?' quickly, even among millions. It uses approximate nearest-neighbor indexes to avoid comparing against every item.

Many also store the original text and metadata alongside the vectors.

Using a vector database

Step 1Embed documents
Step 2Store vectors with text
Step 3Embed the query
Step 4Return nearest matches

In code

Store and query with Chroma

import chromadb

client = chromadb.Client()
docs = client.create_collection("docs")
docs.add(ids=["1", "2"], documents=["Cats nap a lot", "Stocks fell today"])
print(docs.query(query_texts=["sleepy kitten"], n_results=1))

Why it matters

It is the standard storage layer for semantic search and RAG applications.

Related terms

Vector search Embedding RAG