weaviate

Search, query, and manage Weaviate vector database collections. Use for semantic search, hybrid search, keyword search, natural language queries with AI-generated answers, collection management, data exploration, filtered fetching, data imports from PDF/CSV/JSON/JSONL files, create example data and collection creation.

Use this skill when the user wants to build AI applications with Weaviate. It contains a high-level index of architectural patterns, 'one-shot' blueprints, and best practices for common use cases. Currently, it includes references for building a Query Agent Chatbot, Data Explorer, Multimodal PDF RAG (Document Search), Basic RAG, Advanced RAG, Basic Agent, Agentic RAG, and optional guidance on how to build a frontend for each of them.

Operates Weaviate vector databases through the weaviate-cli tool. Use this skill whenever "weaviate-cli" appears in the prompt, or when the user wants to interact with a running Weaviate cluster. Trigger if the request: mentions weaviate-cli explicitly; asks to create, query, update, or delete collections, tenants, or data in Weaviate; needs to manage RBAC roles and users; wants to run, restore, or cancel backups; asks about cluster health, node status, or shards; needs to manage replication or aliases; wants to benchmark a Weaviate cluster; or is testing/verifying Weaviate functionality from the command line (even if the primary task is testing code changes). Do NOT use for developing or modifying the weaviate-cli source code — use contributing-to-weaviate-cli for that.

Develops, tests, and reviews weaviate-cli source code. Use this skill when the task involves modifying the weaviate-cli codebase itself. Trigger if the request: asks to add a new command or flag to weaviate-cli; needs to fix a bug in the CLI source code (weaviate_cli/ Python files); involves reviewing a PR that changes weaviate-cli; wants to write or update unit or integration tests for the CLI; asks about the Click-based architecture, command-to-manager pattern, or defaults system; or the working directory is the weaviate-cli repository and Python source files need to be modified. Do NOT use for running weaviate-cli commands against a Weaviate cluster — use operating-weaviate-cli for that.

Expert knowledge for contributing to and reviewing weaviate-local-k8s code. Covers bash script architecture, Helm values generation, Kind cluster management, GitHub Actions integration, and testing patterns. Use when implementing features, reviewing PRs, fixing bugs, or improving test coverage in the weaviate-local-k8s repository.

Deploys, upgrades, and manages local Weaviate clusters in Kind (Kubernetes in Docker) using the weaviate-local-k8s tool. Determines optimal cluster configuration from requirements including version, replicas, modules, authentication, and features. Use when deploying Weaviate for testing, development, bug reproduction, CI/CD integration, or when the user describes a cluster scenario to set up.