Weaviate is an open-source AI vector database for storing, indexing, and searching high-dimensional vectors. It is designed as infrastructure for search, retrieval-augmented generation (RAG), and agents. Hybrid search combines vector retrieval with BM25 keyword search, alongside semantic and keyword search. Other listed capabilities include advanced filtering, vectorizer modules, configurable backups, native multi-tenancy, vector-index compression, and tenant isolation. Weaviate can run as a hosted service or as a self-managed instance locally or with a cloud provider, with Docker and Kubernetes among its deployment options. Its integrations include AWS, Google Cloud, Azure, OpenAI, Anthropic, Cohere, Hugging Face, and Ollama. Weaviate Cloud encrypts data in transit and at rest, supports role-based access controls, and provides automated daily backups. The Free plan allows 100,000 objects, one collection, and up to three tenants, but does not include backups or high-availability replication. Flex starts at $45.00 USD per month; Premium costs $400.00 USD per month.
Who it is for
Weaviate is aimed at developers building search, RAG, or agent systems. Its hosted and self-managed options are described for startups, scale-ups, and enterprises.
What is good
- Combines vector and BM25 keyword search
- Supports hosted and self-managed deployment
- Offers multi-tenancy and tenant isolation
- Weaviate Cloud includes encryption and daily backups
- Integrates with major cloud and model providers
What to know first
- Free plan has no backups or high-availability replication
- Free plan permits one collection
- Windows lacks native support
- Flex starts at $45.00 USD per month
Verdict
Weaviate offers vector search infrastructure with hybrid search and both hosted and self-managed deployment. The free tier has collection and tenant limits and excludes backups and high-availability replication.
Weaviate plans and pricing
All plansCompared on database software
- Free plan
- Yes
- Paid from
- $45/mo
