# Weaviate

> An open-source AI-native vector database for building search, RAG, and agentic AI applications at scale.

Weaviate is an open-source, AI-native vector database designed to power search, retrieval-augmented generation (RAG), and agentic AI applications. It enables developers to store, index, and query high-dimensional vector embeddings alongside traditional data, making it ideal for building intelligent applications that require semantic understanding. With over 20 million open-source downloads and thousands of customers, Weaviate serves as a core infrastructure component for startups, scale-ups, and enterprises building AI-powered products.

- **Hybrid Search** combines vector similarity search with keyword-based search, allowing developers to leverage both semantic understanding and exact matching for optimal retrieval results.

- **Built-in Embeddings** provides native embedding services and integrations with major model providers including OpenAI, Cohere, Google, AWS, and Hugging Face, eliminating the need for separate embedding pipelines.

- **Multi-tenancy Support** enables efficient data isolation for SaaS applications, allowing thousands of tenants to share infrastructure while maintaining strict data separation.

- **Vector Compression** offers multiple quantization techniques (including rotational quantization) to reduce memory requirements by up to 4x while maintaining search accuracy.

- **Weaviate Agents** includes pre-built agents like Query Agent, Transformation Agent, and Personalization Agent that automate common database operations and enhance data interactions.

- **Flexible Deployment Options** supports shared cloud, dedicated cloud, and self-hosted deployments across AWS, GCP, and Azure with enterprise-grade security including RBAC, SSO/SAML, HIPAA compliance, and PrivateLink.

- **Language-agnostic SDKs** provide client libraries for Python, Go, TypeScript, and JavaScript, plus GraphQL and REST APIs for seamless integration into any tech stack.

- **Scalable Architecture** handles billion-scale vector workloads with dynamic indexing, replication, and auto-scaling capabilities to grow with your application needs.

To get started, sign up for Weaviate Cloud and create a free sandbox cluster. Use the quickstart guide to connect your data, configure embeddings, and run your first semantic search queries within minutes. The platform includes comprehensive documentation, an academy with structured courses, and an active community forum for support.

## Features
- Hybrid search (vector + keyword)
- Built-in embedding service
- Multi-tenancy support
- Vector compression and quantization
- Weaviate Agents (Query, Transformation, Personalization)
- RBAC and SSO/SAML authentication
- HIPAA compliance
- Multi-cloud deployment (AWS, GCP, Azure)
- GraphQL and REST APIs
- Python, Go, TypeScript, JavaScript SDKs
- Replication and high availability
- Dynamic indexing
- Backup and restore
- Metrics endpoint for monitoring
- Model provider integrations

## Integrations
OpenAI, Cohere, Google, AWS, Hugging Face, Snowflake, Databricks, DSPy, LlamaIndex, LangChain, Azure, GCP

## Platforms
LINUX, WEB, API, DEVELOPER_SDK

## Pricing
Freemium — Free tier available with paid upgrades

## Links
- Website: https://weaviate.io
- Documentation: https://docs.weaviate.io/weaviate
- Repository: https://github.com/weaviate/weaviate
- EveryDev.ai: https://www.everydev.ai/tools/weaviate