LlamaIndex (formerly known as GPT Index) is a project that provides a central interface to connect your large language model (LLM) with external data sources.

These containers provide options for an NVIDIA GPU-enabled lightweight (Miniconda) Anaconda installation. Anaconda is an open data science platform based on Python 3. Based on a container with installed Anaconda into the /usr/local/anaconda directory. The default user, anaconda runs a Tini shell /usr/bin/tini, and comes preloaded with the conda command in the environment $PATH. Additional versions with NVIDIA/CUDA support and Jupyter Notebooks tags are available.

This container enables the conda command with a lightweight version of Anaconda (Miniconda) and the conda-forge repository in the /usr/local/anaconda directory. The default user, anaconda runs a Tini shell /usr/bin/tini, and comes preloaded with the conda command in the environment $PATH. Additional versions with NVIDIA/CUDA support and Jupyter Notebooks tags are available.

Two flavors provide an NVIDIA GPU-enabled container with Anaconda.

The base container, based on the ubuntu:latest from Ubuntu running a Tini shell. For the container with a /usr/bin/tini entry point, use:

docker pull xychelsea/llama_index:latest

With Jupyter Notebooks server pre-installed, pull with:

docker pull xychelsea/llama_index:latest-jupyter

Modified version of nvidia/cuda:latest container, with support for NVIDIA/CUDA graphical processing units through the Tini shell. For the container with a /usr/bin/tini entry point:

docker pull xychelsea/llama_index:latest-gpu

With Jupyter Notebooks server pre-installed, pull with:

docker pull xychelsea/llama_index:latest-gpu-jupyter

To run the containers with the generic Docker application or NVIDIA enabled Docker, use the docker run command.

docker run --rm -it xychelsea/llama_index:latest

With Jupyter Notebooks server pre-installed, run with:

docker run --rm -it -d -p 8888:8888 xychelsea/llama_index:latest-jupyter

docker run --gpus all --rm -it xychelsea/llama_index:latest-gpu /bin/bash

With Jupyter Notebooks server pre-installed, run with:

docker run --gpus all --rm -it -d -p 8888:8888 xychelsea/llama_index:latest-gpu-jupyter

To build either a GPU-enabled container or without GPUs, use the xychelsea/llama_index-docker GitHub repository.

git clone git:https://github.com/xychelsea/llama_index-docker.git

The base container, based on the ubuntu:latest from Ubuntu running Tini shell:

docker build -t xychelsea/llama_index:latest -f Dockerfile .

With Jupyter Notebooks server pre-installed, build with:

docker build -t xychelsea/llama_index:latest-jupyter -f Dockerfile.jupyter .

docker build -t xychelsea/llama_index:latest-gpu -f Dockerfile.nvidia .

With Jupyter Notebooks server pre-installed, build with:

docker build -t xychelsea/llama_index:latest-gpu-jupyter -f Dockerfile.nvidia-jupyter .

• llama_index
• Anaconda 3
• conda-forge