Vector Database
Database specialized in storing and searching numerical vectors (embeddings) - essential for RAG, AI recommendations, semantic search.
What a vector database does
Different from classic databases (SQL searching by ID, MongoDB searching by keys), a vector database is optimized for semantic similarity search. It stores numerical vectors (embeddings) with hundreds or thousands of dimensions and quickly answers "find the 10 closest records to this vector" queries.
Why you need it
Embeddings are numerical representations of content (text, images, audio) that capture meaning. Two synonymous sentences have close vectors. That allows semantic search ("vacuum" finds "vacuum cleaner" and "robot vacuum") - impossible with classic SQL.
Popular options in 2026
- Pinecone: most popular cloud, scalable, expensive at scale ($70-1000+/month).
- Qdrant: open-source, self-hostable, excellent performance, free.
- Supabase pgvector: built-in Postgres extension, perfect for projects already using Supabase. Generous free tier.
- Weaviate: cloud + self-hosted, advanced hybrid search.
- Milvus: enterprise-grade, scales to billions of vectors.
Concrete applications
- RAG for AI chatbot - most common use
- Product recommendations on e-commerce ("customers like you bought...")
- Semantic search in internal documentation
- Fraud and anomaly detection
- Image similarity search
- Content recommendation (videos, articles)
Typical costs
For SMB: Supabase pgvector free tier covers up to 100k-500k vectors. Above that: Pinecone $70/month starter or self-hosted Qdrant on Hetzner $10/month. For enterprise (1M+ vectors): $200-2000/month.
Frequently asked questions
Which embedding model to use?
+
Pinecone vs Qdrant?
+
Can I use Postgres as vector DB?
+
Vector dimensions - 384, 1024, 1536? What's the difference?
+
Related terms
RAG (Retrieval Augmented Generation)
Technique where an AI chatbot answers from YOUR documents (catalog, FAQ, policies), not just from what the model learned. That makes it accurate and updatable without retraining.
LLM (Large Language Model)
AI model trained on billions of words that understands and generates natural language. 2026 examples: GPT-5, Claude 4.7, Gemini 2.5 Pro.