Requirements

  1. Railway account

Resources Created

Resource TypeComments
Clickhouse ServiceTo store traces.
Postgres ServiceFor login and dataset related info.
Langtrace ClientLangtrace app with frontend.

Setup

Setting up Langtrace on Railway is now effortless. Just follow these simple steps:

Step 1: Open the Railway Template

  • Navigate to the Langtrace GitHub repository and locate the “Deploy on Railway” button within the README file.
  • Clicking on this button will direct you to the Langtrace Railway template deployment page.

Step 2: Configure Authentication

When deploying the template, you’ll need to set up authentication for your Langtrace instance:

  • Click “Configure” on the langtrace-client service.
  • Add the following authentication-related environment variables:
    • ADMIN_EMAIL: Your desired admin email
    • ADMIN_PASSWORD: Your desired admin password
  • For additional authentication methods (e.g., Google OAuth, Azure AD), you can add the necessary environment variables here as well. Refer to our Authentication guide for detailed instructions on configuring other authentication methods.
  • Click “Save ConfigDeploy”.

Step 3. Deploy the Template

  • Click on the “Deploy Now” button.
  • Click “Configure” on langtrace-client service and add admin email and admin password and click “Save ConfigDeploy”.

Step 4. Access Langtrace

  • Once you start the deployment process, it may take around two minutes for Railway to bring up the services.

    If you want you can check the deploy logs of a particular service by clicking on the service and click “View Logs” under the Deployments tab.

  • Once all services are healthy, click on ‘langtrace-client’ service and open the URL to access the self-hosted Langtrace application.

Login to Langtrace using the previously supplied Admin email and password, and begin your journey for monitoring LLM apps by following the quickstart guide.

Cleanup

To cleanup the resources, click on Settings —> Danger Zone —> Delete Project.

Troubleshooting