Skip to content

Tutorial - LlamaIndex

Let's use LlamaIndex, to realize RAG (Retrieval Augmented Generation) so that an LLM can work with your documents!

What you need

  1. One of the following Jetson devices:

    Jetson AGX Orin 64GB Developer Kit Jetson AGX Orin (32GB) Developer Kit Jetson Orin Nano 8GB Developer Kit

  2. Running one of the following versions of JetPack:

    JetPack 5 (L4T r35.x) JetPack 6 (L4T r36.x)

  3. Sufficient storage space (preferably with NVMe SSD).

    • 5.5 GB for llama-index container image
    • Space for checkpoints
  4. Clone and setup jetson-containers:

    git clone
    bash jetson-containers/

How to start a container with samples

Use and autotag script to automatically pull or build a compatible container image.

jetson-containers run $(autotag llama-index:samples)

The container has a default run command (CMD) that will automatically start the Jupyter Lab server.

Open your browser and access http://<IP_ADDRESS>:8888.

The default password for Jupyter Lab is nvidia.

You can follow along LlamaIndex_Local-Models_L4T.ipynb (which is based on the official LlamaIndex tutorial).