Local Install of Helix on Windows (WSL2)

Requirements

Created on Windows (WSL2)

1. Following instructions assume that you have WSL installed
   1. Open PowerShell or Windows Command Prompt in administrator mode by right-clicking and selecting Run as administrator

wsl --install

2. Install Docker Desktop Install Docker NOTE: Make sure that you’re signed on to your Docker account

3. Install Ollama Install Ollama

4. Download Ollama Model

ollama pull llama3:instruct

Confirm that the model exists - values proceeding name of the model may differ ollama ls | grep “llama3:instruct”

You should get a confirmation similar to this:

llama3:instruct 365c0bd3c000 4.7 GB 43 hours ago

Install Helix Windows (WSL2) with an NVIDIA GPU

This will set up the CLI, the controlplane and a runner on localhost if an NVIDIA GPU is available:

curl -sL -O https://get.helix.ml/install.sh
chmod +x install.sh
./install.sh --openai-api-key ollama --openai-base-url http://host.docker.internal:11434/v1

Successful completion of the installation

Spin up Helix Docker Instances

1. Change directory to location of HelixML payload is downloaded

cd /Users/"<yourLocalUser>"/HelixML

2. Launch Docker Desktop on your computer
3. Launch Docker Containers

docker compose up -d --remove-orphans

3. Confirm that all container are running and show a healthy status

Login to Helix UI

1. In a web browser go to: http://localhost:8080/
2. Register local user
   1. Bottom left pane - click on “Login/Register”
   2. Click on “Register” to begin the user registeration process
   3. Complete user registration
3. To access the app, log in to the local HelixML UI with your registered user credentials