Weaviate
The open-source vector database for AI-native applications.
Company Type
Venture-backed
Integrations
100+
Deployment
Cloud & Self-hosted
About Weaviate
Weaviate is an open-source, AI-native vector database designed to store, index, and retrieve data through vector similarities. It enables developers to build powerful applications featuring semantic search, recommendation systems, and Retrieval-Augmented Generation (RAG) with high speed and scalability. Weaviate supports a wide range of integrations with popular AI/ML frameworks and models from providers like OpenAI, Cohere, and Hugging Face, allowing for flexible vectorization strategies. It offers multiple deployment options, including a fully managed Weaviate Cloud Service and the ability to self-host the open-source version, catering to everyone from individual developers to large enterprises seeking production-ready performance.
Core Features
Vector Search
Fast and scalable similarity search on vector embeddings.
Retrieval-Augmented Generation (Rag)
Store and retrieve contextual data for large language models.
Hybrid Search
Combines keyword-based (BM25) and vector search for more relevant results.
Built-In Vectorization
Integrates with models from OpenAI, Cohere, Hugging Face and more to vectorize data on the fly.
Scalability
Horizontally scalable architecture to handle billions of data objects.
Deployment Options
Weaviate Cloud (Wcs)
A fully managed, serverless vector database service.
Self-Hosted
Run Weaviate on your own infrastructure using Docker, Kubernetes, or from source.
Hybrid Cloud
Deploy on any major cloud provider (AWS, GCP, Azure).