Skip to content

Vector Database

A database that stores embeddings and performs fast similarity search, the backbone of RAG systems.

It uses approximate nearest-neighbor (ANN) indexes to find the most similar vectors in milliseconds across millions of items. Popular options include Qdrant, Pinecone, and pgvector for Postgres.

Related resources

Qdrant Vector Database
Qdrant is a high-performance open-source vector database and similarity search engine designed for production use. Written in Rust, it powers RAG pipelines, recommendation systems, and semantic search with rich payload filtering, multi-tenancy support, and both self-hosted and managed cloud deployment options.
Pinecone
Pinecone is a fully managed vector database built for production RAG and semantic search, offering serverless scaling, hybrid search, and metadata filtering. It removes the operational burden of running vector infrastructure yourself, letting teams focus on application logic — with usage-based pricing and a free starter tier.
Chroma
Chroma is a developer-friendly open-source embedding database that gets RAG prototypes running in minutes with a simple Python or JavaScript API. It runs in-process for local development and scales through its hosted cloud offering, making it the easiest entry point into vector search for most developers.