Deployment Lifecycle Management
Introduction to Deployments
Now that you’ve used Vellum Playground for prompt engineering or Workflow Builder for creating workflows, and have assets that clear your test cases, you’re ready to start making requests against them. In production, Vellum acts as a high reliability, low latency proxy between your application and the underlying model providers.
By deploying a Prompt or Workflow through Vellum and integrating a 10-line code snippet you get:
- Observability into individual completions and their quality: Tracking completions & measuring quality
- Version Controlled changes to prompts/model without updating code: Changing deployments in production & versioning
- Monitoring of aggregate data to spot trends: Monitoring production traffic
- Environment Management with separate releases and monitoring per Environment: Managing releases across Environments
Let’s take a look at how to actually deploy Prompts and Workflows in Vellum
Creating a Deployment
When creating a Prompt or Workflow Deployment, you can choose which Environment(s) to deploy to. Each Environment maintains its own separate Release history, allowing you to deploy different versions across your different Environments independently.
We recommend using one Deployment per Sandbox (whether Prompt or Workflow) and leveraging Release Tags for version management (e.g., semantic versioning) rather than creating separate deployments for each environment.
View Deployment Details
The Deployment Overview page shows you details about the currently live version of your Prompt or Workflow.
Integrating w/ Vellum’s API
The Deployment Overview page also contains code snippets to make integration simple. Vellum provides language-specific clients for interacting with the API. Optionally, you can also integrate with our Actuals Endpoint to start keeping track of output quality for monitoring and eventually fine tuning. More details about this in the observability documentation.
Important: API Keys are Environment-scoped. When you call an API, it performs actions within the context of the Environment from which the API key was created. Make sure to use the appropriate API key for each Environment.
Note that our full API docs can be found at docs.vellum.ai
Changing Deployments in Production
With Vellum, you can make changes to your prompts and workflows in production without having to make any code changes! This might be useful for a variety of reasons:
- When you encounter edge cases in production, you may want to tweak the prompt or workflow logic to accommodate for them
- A new model comes out and can provide similar quality at lower cost or lower latency
- Product requirements change and a non-technical member of the team with the proper permissions wants to make changes
You can do this by updating a Deployment. All updates are version-controlled and past versions can be immediately reverted to at any time (no code changes required).
Updating a Deployment
Find the Sandbox (Prompt or Workflow) you’d like to deploy and click the “Deploy” button.
This’ll provide the option to update an existing deployment or create a new one. Select “Update Existing Deployment” and choose the deployment you’d like to update.
Note that code changes will likely be required if you change which input variables the Prompt or Workflow relies on.
Deployment Versioning
After a Deployment is updated, you’ll find a new entry in the “History” tab. You can visually inspect how the Prompt or Workflow has changed over time across versions. You can also revert to prior versions at any time. After reverting to a prior version, it’s immediately live – no code changes required.