Vector Database
A database designed to store and efficiently query high-dimensional vector embeddings for similarity search.
In Depth
A vector database is a specialized database designed to store, index, and query high-dimensional vectors (embeddings). Unlike traditional databases that match on exact values, vector databases perform similarity searches—finding the vectors most similar to a given query vector using distance metrics like cosine similarity, Euclidean distance, or dot product. This enables semantic search, recommendation engines, and AI-powered retrieval. Popular vector databases include Pinecone, Weaviate, Milvus, Qdrant, and Chroma. PostgreSQL also supports vector operations through the pgvector extension, combining traditional relational capabilities with vector similarity search.
How AI for Database Helps
AI for Database leverages vector search internally to match your questions with relevant schema elements and past query patterns.
Related Terms
Embedding
A numerical vector representation of text, data, or objects that captures semantic meaning for AI processing.
Semantic Search
Search that understands the meaning and intent behind queries rather than just matching keywords.
RAG
Retrieval-Augmented Generation—an AI technique that enhances LLM responses by retrieving relevant context from external data sources.
Ready to try AI for Database?
Query your database in plain English. No SQL required. Start free today.