Thanks for participating! We’ve put together this quick guide to everything you need to know about LlamaIndex.

Beginners

• What is Retrieval-Augmented Generation (RAG)? What is any of this?
• We have libraries in Python and TypeScript; the Python lib has more features
• Installation and getting started:
  • Python
  • TypeScript
• I want to customize…
• LlamaHub is a collection of data connectors, vector stores, LLMs, agent tools, pre-written code and more!
• create-llama is a command-line tool that sets up a starter full-stack app for you
  • Installation instructions
  • We strongly recommend starting with this if you’re not sure where to start!
• The RAG CLI is a command-line tool that will index and query files for you
  • Good for quickly checking if indexing documents works
• Building a low-code chatbot with Streamlit (this tool is called RAGs)
• What can I use?
  • All the LLMs we support
  • All the vector stores we support
  • All the embedding models we support
• What’s the best way load and parse data?
  • The ingestion pipeline
• How do I get full control over how my query engine works?
  • Workflows
  • Workflows cookbook and other examples
• LlamaParse is our free-to-use industry-leading document parsing service
  • If you’re dealing with complex PDFs or other documents we recommend using it!

NVIDIA-specific resources

• Using NVIDIA NIMS with LlamaIndex (you’re most likely to want this one!)
• NVIDIA TensorRT-LLM with LlamaIndex
• NVIDIA Triton with LlamaIndex

Intermediate