Create-llama

The command-line tool for generating full-stack, data-aware LlamaIndex applications with a single command: `npx create-llama`.

Create-llama is your direct path to a complete, production-ready LlamaIndex application. Execute `npx create-llama@latest` to instantly scaffold a full-stack Retrieval-Augmented Generation (RAG) web app. The tool provides key configuration choices: select your backend (Python FastAPI or Next.js/TypeScript), choose your frontend UI, and specify your LLM (e.g., OpenAI's GPT-4). It handles complex setup, including automatic data ingestion; simply drop your files (PDF, CSV, HTML) into the `/data` directory. This is the most efficient starting point for building sophisticated, data-connected LLM solutions.

https://docs.llamaindex.ai/en/stable/getting_started/create_llama.html