Weaviate
Open-source vector database with native hybrid search
Weaviate is profiled here as a Vector Database tool for engineering teams. Read about features, pricing, and how it compares to related options in the tools directory.
Description
Weaviate is an open-source, AI-native vector database created by Bob van Luijt and developed by the Dutch company of the same name since 2019. It stores objects and vectors together and answers hybrid queries that fuse BM25 keyword scoring with dense vector similarity in a single request. Built-in modules vectorize data at import time using OpenAI, Cohere, Google, and other embedding providers. Weaviate Cloud offers serverless and dedicated clusters, while the embedded mode runs the full database inside a Python or JavaScript process for local development.
Key Capabilities:
Hybrid search combining BM25 and vector similarity
Built-in vectorizer modules for major embedding providers
Multimodal search across text and images
Multi-tenancy with per-tenant isolation
GraphQL, REST, and gRPC APIs with client SDKs
BSD-3 license, self-hostable, with Weaviate Cloud as the managed option
Alternative tools
- Deep Lake
Database for AI that stores tensors and embeddings
- Marqo
Open-source vector search with built-in embedding inference
- Chalk
Feature platform for real-time machine learning data
- Hopsworks
Feature store and ML platform for batch and real-time data
- turbopuffer
Serverless vector and full-text search on object storage
- LanceDB
Embedded multimodal vector database on the Lance format