Build Full-Stack Weaviate AI Apps from Blueprints

Provides an index of implementation guides and foundational requirements for building Weaviate-powered AI applications, letting a full-stack app be scaffolded from official Weaviate blueprints with best practices for connection management, environment setup, and application architecture already worked out.

Before generating any cookbook app, it points to two shared references: a Project Setup Contract and Environment Requirements guide. It then indexes seven cookbook patterns: Query Agent Chatbot (a full-stack chatbot built on Weaviate's Query Agent, with streaming and chat-history support), Data Explorer (a full-stack app with sorting, keyword search, and a tabular view of Weaviate data), Multimodal RAG for Document Search (built on Weaviate Embeddings using ModernVBERT/colmodernvbert plus Ollama with Qwen3-VL for generation), Basic RAG (basic retrieval and generation from a Weaviate collection, for most standard retrieval needs), Advanced RAG (extends basic RAG with re-ranking, query decomposition, query re-writing, and LLM filter selection), Basic Agent (a tool-calling AI agent with structured outputs using DSPy, covering AgentResponse signatures, RouterAgent, tool design, and sequential multi-step loops), and Agentic RAG (RAG-powered AI agents covering naive RAG tools, hierarchical RAG with LLM-created filters, vector DB memory, the Weaviate Query Agent, and Elysia integration).

Two optional references extend a chosen cookbook: a Frontend Interface guide (a Next.js frontend for the Weaviate backend, used only when the user explicitly asks for a frontend) and an Async Client guide (using Weaviate's Python async client in production - FastAPI and other async frameworks - covering connection patterns, lifecycle management, common pitfalls, and multi-cluster setups). If the user doesn't yet have a Weaviate instance, it directs them to Weaviate Cloud's console to register and create a free sandbox.

Use it when a user wants a Weaviate-backed RAG, agentic RAG, chatbot, data explorer, or multimodal document-search application, when choosing between cookbook patterns before writing a full-stack Weaviate app, when the project needs Weaviate environment/setup/async-client/frontend guidance, or when the user specifically wants an official Weaviate blueprint rather than a generic vector-database recipe. Cookbook blueprints still need adaptation to the user's actual data model, embedding provider, auth model, deployment platform, and latency/cost targets - this skill does not validate live Weaviate credentials, cloud quotas, or model availability, and generated apps should be reviewed for security, data privacy, prompt injection exposure, and production observability before launch.

Input is the type of Weaviate application the user wants to build (chatbot, data explorer, RAG variant, agent) and whether a frontend is needed. Output is the matched cookbook reference(s) - project setup and environment requirements, the chosen application-pattern guide, and optionally the frontend and async-client guides - to scaffold the full-stack app from.

Indexes guides built on Weaviate (including its Query Agent and Python async client), DSPy (for structured-output agents), Ollama with Qwen3-VL (for multimodal RAG generation), Next.js (for the optional frontend), and Elysia (for agentic RAG integration).

Developers building a Weaviate-powered AI application who want an official blueprint - chatbot, RAG, agent, or data explorer - with setup, environment, and architecture guidance already worked out, rather than assembling one from generic vector-database tutorials.