Welcome to RoboTF's AI Suite of tools for running Large Language Models (LLM's) locally or self-hosted. This will be a collection of Docker Compose and other such resources for helping people get start running such tools as LocalAI, ComfyUI, Open WebUI, and more!
Check out the Youtube series for Build an Ubuntu AI/LLM Server from scratch here: https://www.youtube.com/@RoboTFAI
Clone the Repo:
git clone https://github.com/kkacsh321/robotf-ai-suite.git
cd robotf-ai-suite
make help
Usage:
make <target>
Targets:
localai-up Start LocalAI in the background
localai-down Stop the LocalAI
localai-restart Restart LocalAI container
localai-exec Exec into the LocalAI container
localai-logs Get logs from LocalAI container
comfyui-up Start ComfyUI in the background
comfyui-down Stop the ComfyUI stack
comfyui-restart Restart ComfyUI container
comfyui-exec Exec into the ComfyUI container
comfyui-logs Get logs from ComfyUI container
openwebui-up Start Open-WebUI in the background
openwebui-down Stop the Open-WebUI stack
openwebui-restart Restart Open-WebUI container
openwebui-exec Exec into the Open-WebUI container
openwebui-logs Get logs from Open-WebUI container
help show this usage
Edit the LocalAI/localai-compose.yaml
to your liking and match the volume mount, and environment variables you want to use. See the docs at localai
Set Up Docker Compose: Ensure you have Docker and Docker Compose installed, then run:
make localai-up
To stop it
make localai-down
**Warning LocalAI will download several models on it's first startup to handle Chat, Image Generation, etc, etc as this calls the AIO image. See more info at localai
This calls docker-compose under the hood with the Makefile, to see more commands type
make help
Edit the ComfyUI/comfyui-compose.yaml
to your liking and match the volume mount, and environment variables you want to use. See the docs at comfyui and YanWenKun for docs on the container.
Set Up Docker Compose: Ensure you have Docker and Docker Compose installed, then run:
make comfyui-up
To stop it
make comfyui-down
**Warning ComfyUI will download several models on it's first startup to support Image Generation See more info at YanWenKun
This calls docker-compose under the hood with the Makefile, to see more commands type
make help
Visit http://:8188 to see the ComfyUI UI
Edit the Open-WebUI/openwebui-compose.yaml
to your liking and match the volume mount, and environment variables you want to use. See the docs at openwebui
Set Up Docker Compose: Ensure you have Docker and Docker Compose installed, then run:
make openwebui-up
To stop it
make openwebui-down
This calls docker-compose under the hood with the Makefile, to see more commands type
make help
Want to add your own compose stack or adjustments to these files:
Fork the repository. Create a new branch
git checkout -b feature/your-awesome-feature
# Make your changes.
# Commit your changes
git commit -m 'My awesome feature does X'
# Push to the branch
git push origin feature/your-awesome-feature
# Open a pull request and prepare to share your changes with the world after approval from codeowners.
Lots better docs More services such as Flowise, n8n, etc
This project is licensed under the MIT License - see the LICENSE file for details, but be warned: using this software may result in unintended consequences.
Shoutout to LocalAI for powering my Local LLM's localai
Thanks to openwebui
We love comfyui and YanWenKun for maintaining the docker images.
Shoutout to j4ys0n Who gave some original inspiration for this. See his repo in link.