AI Glossaryinfrastructure

Vector Database

A specialized database optimized for storing and searching high-dimensional vector embeddings, enabling semantic similarity search.

How It Works

Vector databases store embeddings and find similar vectors efficiently using algorithms like HNSW or IVF. When you search "how to deploy a Next.js app," the query is converted to an embedding and the database returns documents with similar embeddings, regardless of exact keyword matches. Popular options: Pinecone (managed), Weaviate (open source), pgvector (PostgreSQL extension, works with Supabase), Chroma (local development).

Common Use Cases

  • 1RAG knowledge bases
  • 2Semantic search engines
  • 3Recommendation systems
  • 4Image similarity search

Related Terms

RAG (Retrieval-Augmented Generation)

A technique that enhances AI responses by retrieving relevant information from a knowledge base before generating an answer.

Embeddings

Numerical vector representations of text that capture semantic meaning, enabling similarity search and clustering.

Semantic Search

A search approach that finds results based on meaning rather than exact keyword matches, using embeddings to understand the intent behind queries.

Need help implementing Vector Database?

AI 4U Labs builds production AI apps in 2-4 weeks. We use Vector Database in real products every day.

Let's Talk