Vector databases
Stores text, images and other data as embeddings so your app can find items by meaning, not just keywords.
Search AirStackWhy teams use it
- Let an AI assistant answer from your own documents
- Search that finds results by meaning, not exact words
- Recommend similar products, articles or tickets
- Filter by metadata and permissions alongside similarity
Who uses it: AI engineer, ML engineer, Back-end engineer, Data engineer, Search engineer. Watch for: Cost and speed depend on data size and query volume; test with your real data, and check how hard it is to export. AirStack’s guide to the category.
8 products
| Product | What it says it does | Starting at |
|---|---|---|
| Weaviate | Vector search, RAG, and memory - all in one open-source platform. | Not observed |
| Chroma | Open-source search infrastructure for AI | Not observed |
| Qdrant | High-Performance Vector Search at Scale | Not observed |
| Pinecone | Pinecone is a fully managed vector database built for AI. | Not observed |
| LanceDB | Multimodal lakehouse for AI. | Not observed |
| turbopuffer | fast search engine built on object storage | Not observed |
| pgvector | Open-source vector similarity search for Postgres | Not observed |
| FAISS | Faiss is a library for efficient similarity search and clustering of dense vectors. | Not observed |
Prices are list prices as written on each pricing page; hover one for its quote. “Not observed” means AirStack has not found it on that product’s pages.
Open models for the job
- BAAI/bge-small-en-v1.5 48,832,479 downloads in 30 days · mit
- Qwen/Qwen3-Embedding-0.6B 9,025,219 downloads in 30 days · apache-2.0
- BAAI/bge-large-en-v1.5 8,946,958 downloads in 30 days · mit