create-llama (LlamaIndex)

Dependency freshness

Declared = lowest version the kit's dependency file (package.json, pyproject.toml or requirements.txt) allows. Latest = the npm "latest" tag or the newest PyPI release. TypeScript, the Stripe SDK, FastAPI and other 0.x packages are shown but not counted in the verdict.

What's in the stack

Testing

Playwright

Detected from declared dependencies. A listed package means it's installed, not necessarily fully wired up.

What the README says you get

• AI
  Pre-configured use casesA set of pre-configured use cases to get you started
• AI
  OpenAI default modelsThe app uses OpenAI by default
• AI
  Customizable LLM supportcustomize it to use any of the dozens of LLMs we support
• AI
  Default GPT-4.1 LLMThe app will default to OpenAI's `gpt-4.1` LLM
• AI
  Default embedding model`text-embedding-3-large` embedding model
• AI
  Model selection CLI flagadd the `--ask-models` CLI parameter
• API
  Python FastAPI optionfull-stack Python application powered by the llama-index Python package
• API
  LlamaIndex Server APIserves LlamaIndex Workflows and Agent Workflows via an API server
• Content
  Data folder ingestionYour generated app will have a folder called `data`
• Content
  PDF and document ingestioningest any PDF, text, CSV, Markdown, Word and HTML files
• Content
  Video and audio ingestionThe Python backend can read even more types, including video and audio files
• Deploy
  Next.js full-stack optiona full-stack Next.js application that you can deploy
• Deploy
  Non-interactive CLI setuppass command line arguments to set up a new project non-interactively
• UI
  shadcn/ui chat interfaceA front-end using components from shadcn/ui

Extracted from the kit's README by a local AI model (deepseek-flash) on Sep 29, 2026. Every item is checked against an exact README quote. A README claim is the maker's description, not something we tested.