using-weaviatelisted

# Weaviate Vector Database Skill **Version**: 1.0.0 | **Target**: <500 lines | **Purpose**: Fast reference for Weaviate operations --- ## Overview **What is Weaviate**: Open-source vector database for AI-native applications combining vector search with structured filtering and keyword search. **When to Use This Skill**: - Storing and querying vector embeddings - Implementing semantic/similarity search - Building RAG (Retrieval-Augmented Generation) pipelines - Hybrid search (vector + keyword) - Multi-tenant vector applications **Auto-Detection Triggers**: - `weaviate-client` in `requirements.txt` or `pyproject.toml` - `weaviate-client` or `weaviate-ts-client` in `package.json` - `WEAVIATE_URL`, `WEAVIATE_API_KEY`, or `WCD_URL` environment variables - `docker-compose.yml` with `semitechnologies/weaviate` image **Progressive Disclosure**: - **This file (SKILL.md)**: Quick reference for immediate use - **REFERENCE.md**: Comprehensive patterns, modules, and advanced configuration --- ## Table of Contents 1. [Core Concepts](#core-concepts) 2. [Quick Start](#quick-start) 3. [CLI Decision Tree](#cli-decision-tree) 4. [Collection Schema](#collection-schema) 5. [Data Operations](#data-operations) 6. [Search Operations](#search-operations) 7. [Generative Search (RAG)](#generative-search-rag) 8. [Multi-Tenancy](#multi-tenancy) 9. [Docker Setup](#docker-setup) 10. [Error Handling](#error-handling) 11. [Best Practices](#best-practices) 12. [Quick Reference Card](#quick-reference