This directory contains the necessary files to build a Red Hat compatible container image for the llama-stack.
- Python >=3.11
llamaCLI tool installed:pip install llama-stack- Podman or Docker installed
The Containerfile is auto-generated from a template. To generate it:
- Make sure you have the
llamaCLI tool installed - Run the build script from root of this git repo:
./distribution/build.py
This will:
- Check for the
llamaCLI installation - Generate dependencies using
llama stack build - Create a new
Containerfilewith the required dependencies
The Containerfile is auto-generated from a template. To edit it, you can modify the template in distribution/Containerfile.in and run the build script again.
NEVER edit the generated Containerfile manually.
Once the Containerfile is generated, you can build the image using either Podman or Docker:
podman build --platform linux/amd64 -f distribution/Containerfile -t rh .- The generated Containerfile should not be modified manually as it will be overwritten the next time you run the build script
podman push <build-ID> quay.io/opendatahub/llama-stack:rh-distribution