Skip to main content

Welcome to Weaviate Docs

Weaviate (we-vee-eight) is an open source, AI-native vector database. Use this documentation to get started with Weaviate and to learn how to get the most out of Weaviate's features.

New to Weaviate?

Start with the Quickstart tutorial - an end-to-end demo that takes 15-30 minutes.

Questions

Please visit our forum. The Weaviate team and our awesome community can help.


Getting Started

Step 1 - Choose your deployment

Multiple deployment options are available to cater for different users and use cases. All options offer vectorizer and RAG module integration.

Evaluation
Deployment
Production
Weaviate Cloud Services
  • From evaluation (sandbox) to production
  • Serverless (infrastructure managed by Weaviate)
  • (Optional) Data replication (high-availability)
  • (Optional) Zero-downtime updates
Evaluation
Deployment
Production
Docker
  • For local evaluation & development
  • Local inference containers
  • Multi-modal models
  • Customizable configurations

Evaluation
Deployment
Production
Kubernetes
  • For development to production
  • Local inference containers
  • Multi-modal models
  • Customizable configurations
  • Self-deploy or Marketplace deployment
  • (Optional) Zero-downtime updates
Evaluation
Deployment
Production
Embedded Weaviate
  • For basic, quick evaluation
  • Conveniently launch Weaviate directly from Python or TS/JS

Step 2 - Choose your scenario

Choose your next step. Weaviate is flexible and can be used in many contexts and scenarios.

Work with text data

Just bring your text data to Weaviate and it will do the rest.

Just populate Weaviate with your text data and start using powerful vector, keyword and hybrid search capabilities.

And use our integrations to build generative ai tools with your data.

Bring your own vectors

Do you prefer to work with your own vectors? No problem.

You can add your own vectors to Weaviate and still benefit from all of its indexing and search capabilities..

Our integrations to build generative ai tools work just as well with your data and vectors.

Multimodality

For many, data comes in multiple forms beyond text.

Weaviate's multimodal modules can import text, audio and video and more as well as perform multimodal searches.

Use these modules to build generative ai tools from your entire dataset.

What Next

We recommend starting with these sections:

What is Weaviate?

Weaviate is an open source vector search engine that stores both objects and vectors.

What can you do with Weaviate?

Features, examples, demo applications, recipes, use cases, etc..

Installation

Learn about the available options for running Weaviate, along with instructions on installation and configuration.

How-to: Configure

Discover how to configure Weaviate to suit your specific needs.

Concepts

Get the most out of Weaviate and learn about its architecture and various features.

Client Libraries