Build Full-Stack Weaviate AI Apps from Blueprints
Indexes official Weaviate cookbook blueprints for RAG, agentic RAG, chatbots, and data explorer apps with setup guidance.
Why it matters
Scaffold production-ready Weaviate-powered applications-RAG systems, chatbots, data explorers, and agentic workflows-using official implementation guides that cover connection management, environment setup, and application architecture best practices.
Outcomes
What it gets done
Generate query agent chatbots with streaming and chat history
Build multimodal RAG systems for document search with embeddings
Create data explorer interfaces with sorting and keyword search
Implement tool-calling AI agents with structured outputs using DSPy
Install
Add it to your toolbox
Run in your project directory:
curl -fsSL https://spark.entire.vc/get/ag-weaviate-cookbooks | bash Overview
Weaviate Cookbooks
This skill indexes official Weaviate cookbook blueprints - chatbot, data explorer, basic/advanced RAG, multimodal RAG, and agentic RAG patterns - plus shared setup, environment, frontend, and async-client guides for scaffolding a full-stack Weaviate app. Use it when building a Weaviate-backed RAG, agent, chatbot, or data explorer app and want an official blueprint rather than a generic vector-database recipe - blueprints still need adapting to the actual data model and deployment target.
What it does
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.
When to use - and when NOT to
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.
Inputs and outputs
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.
Integrations
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).
Who it's for
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.
Source README
Weaviate Cookbooks
Overview
This skill provides an index of implementation guides and foundational requirements for building Weaviate-powered AI applications. Use the references to quickly scaffold full-stack applications with best practices for connection management, environment setup, and application architecture.
When to Use This Skill
- Use when the user wants a Weaviate-backed RAG, agentic RAG, chatbot, data explorer, or multimodal document-search application.
- Use when selecting between cookbook patterns before writing a full-stack Weaviate app.
- Use when the project needs Weaviate environment, setup, async-client, or frontend guidance.
- Use when the user asks for an official Weaviate blueprint rather than a generic vector database recipe.
Weaviate Cloud Instance
If the user does not have an instance yet, direct them to the cloud console to register and create a free sandbox. Create a Weaviate instance via Weaviate Cloud.
Before Building Any Cookbook
Follow these shared guidelines before generating any cookbook app:
Then proceed to the specific cookbook reference below.
Cookbook Index
- Query Agent Chatbot: Build a full-stack chatbot using Weaviate Query Agent with streaming and chat history support.
- Data Explorer: Build a full-stack data explorer app including sorting, keyword search and tabular view of weaviate data.
- Multimodal RAG: Building Document Search: Build a multimodal Retrieval-Augmented Generation (RAG) system using Weaviate Embeddings (ModernVBERT/colmodernvbert) and Ollama with Qwen3-VL for generation.
- Basic RAG: Implement basic retrieval and generation with Weaviate. Useful for most forms of data retrieval from a Weaviate collection.
- Advanced RAG: Improve on basic RAG by adding extra features such as re-ranking, query decomposition, query re-writing, LLM filter selection.
- Basic Agent: Build a tool-calling AI agent with structured outputs using DSPy. Covers AgentResponse signatures, RouterAgent, tool design, and sequential multi-step loops.
- Agentic RAG: Build RAG-powered AI agents with Weaviate. Covers naive RAG tools, hierarchical RAG with LLM-created filters, vector DB memory, Weaviate Query Agent, and Elysia integration.
Interface (Optional)
Use this when the user explicitly asks for a frontend for their Weaviate backend.
- Frontend Interface: Build a Next.js frontend to interact with the Weaviate backend.
Client Usage
- Async Client: Guide for using the Weaviate Python async client in production applications (FastAPI, async frameworks). Covers connection patterns, lifecycle management, common pitfalls, and multi-cluster setups.
Limitations
- Cookbook blueprints still need adaptation to the user's 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 unless the user provides and approves the relevant environment.
- Generated apps should be reviewed for security, data privacy, prompt injection exposure, and production observability before launch.
FAQ
Common questions
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.