Weaviate Vector Database

Deploy and operate Weaviate clusters for vector and hybrid search. Spin up local Kubernetes clusters with the right version, replicas, modules, and auth for RAG development, testing, bug repro, and CI/CD.

This skill provisions and manages Weaviate. It deploys local clusters in Kind (Kubernetes in Docker) with the weaviate-local-k8s tool, chooses the version, replica count, vectorizer modules, authentication, and features from your requirements, and supports upgrades and teardown — giving you a reproducible Weaviate for semantic search, hybrid search, and RAG.

When to use

Use when you need a Weaviate vector database for RAG or semantic search, or a local Weaviate cluster for development, testing, or CI/CD.

Examples

Spin up a local cluster

Weaviate in Kind for dev

Deploy a local 3-replica Weaviate cluster with the text2vec module and API-key auth for RAG development

Design a schema for search

Classes with hybrid search

Create a Weaviate schema for articles and run a hybrid search combining vector similarity with a keyword filter