​

Requirements

• Git
• Docker with compose (docker version >= 1.13.0)

​

Setup

Note: This is just one way to run Onyx. Onyx can also be run on Kubernetes, there are provided Kubernetes manifests and Helm charts in the deployment directory.

1. Clone the Onyx repo:

git clone https://github.com/onyx-dot-app/onyx.git

2. Navigate to onyx/deployment/docker_compose

cd onyx/deployment/docker_compose

3. (Optional) configure Onyx

4. Bring up your docker engine and run:

   • To pull images from DockerHub and run Onyx:
   Copy

   Ask AI

   docker compose -f docker-compose.dev.yml -p onyx-stack up -d --pull always --force-recreate
   

   • Alternatively, to build the containers from source and start Onyx, run:
   Copy

   Ask AI

   docker compose -f docker-compose.dev.yml -p onyx-stack up -d --build --force-recreate
   

   • This may take 15+ minutes depending on your internet speed.
     • Additionally, once the images have been pulled / built, the initial startup of the api_server may take some time. If you see This site can’t be reached in your browser despite all containers being up and running, check the api_server logs and make sure you see Application startup complete.
     • If you see Killed in the logs, you may need to increase the amount of memory given to Docker. For recommendations, check the system requirements here.

5. Onyx will now be running on http://localhost:3000.

​

Generative AI API Key

Note: On the initial visit, Onyx will prompt for a GenAI API key.

Onyx relies on Generate AI models to provide parts of its functionality. You can choose any LLM provider from the admin panel or even self-host a local LLM for a truely airgapped deployment.

​

Shutting Down

docker compose -f docker-compose.dev.yml -p onyx-stack down