Skip to main content
BETAThis is a new design — give feedback

Vector Database

Also known as: Vector DB, Embedding Database, Vector Store

In one sentence

A specialized database designed to store and search embeddings—numerical representations of text, images, or other data. It finds similar items by comparing how close their vectors are in mathematical space.

Explain like I'm 12

Imagine a library where instead of organizing books alphabetically, you group them by what they're actually about. A vector database works like that—it stores the 'meaning' of things as numbers and can instantly find items with similar meanings.

In context

Vector databases power the search behind RAG (Retrieval-Augmented Generation) systems. When you ask a company's AI chatbot a question, it converts your question into a vector, searches the vector database for the most relevant company documents, and feeds those documents to the AI along with your question. Popular vector databases include Pinecone, Weaviate, Chroma, Qdrant, and Milvus. Many traditional databases like PostgreSQL (with pgvector) now support vector search too.

See also

EmbeddingRAG (Retrieval-Augmented Generation)Inference

Related Guides

Learn more about Vector Database in these guides:

Vector Database Examples: Real-World Use Cases and Code

Intermediate

Practical examples of vector databases in action: semantic search, chatbot memory, recommendation systems, and more with code snippets.

9 min read

Vector Databases 101: Storage, Indexing, and Search

Intermediate

Deep dive into vector databases. How they work, when to use them, and how to choose the right one for your needs.

11 min read

Vector Database Fundamentals

Intermediate

Vector databases store and search embeddings efficiently. Learn how they work, when to use them, and popular options.

7 min read