Bases de données vectorielles
Purpose-built stores for embedding vectors, compared on index type, filtering, recall and how they handle updates. The choice constrains retrieval quality more than most teams expect.
8 technologies
- Qdrant database Open-source vector database written in Rust, with payload filtering.
- Pinecone database Fully managed proprietary vector database with no self-hosted option.
- Milvus database Open-source distributed vector database designed for billion-scale collections.
- Weaviate database Open-source vector database with hybrid keyword and vector search built in.
- pgvector library Vector similarity search as a PostgreSQL extension, keeping embeddings beside your data.
- FAISS library Library for efficient similarity search over dense vectors.
- Chroma database Embedded vector database designed to be added to a Python application in minutes.
- LanceDB database Embedded vector database built on a columnar format for multimodal data.