NVIDIA NIM MicroServices - Rafay Product Documentation
Use
In this step, we will use the end user facing "developer hub" self service portal to deploy a NIM service onto the host Kubernetes Cluster.
Navigate to Developer Hub
Select the project where the template was previously created
Click "Workspaces"
Click "New Workspace"
Enter a name for the workspace
Click Save
Click "Custom Services"
Click "New Custom Service"
Click "Select" on the NIM Microservices card
Enter a name for the instance
Set "enable_cache" to false
Click Deploy
After a few minutes, the instance will be deployed.
Utilize
Next, we will use the newly deployed NIM Service
- Copy the Curl Command from the output and run the command within your terminal
You will receive a response from the model with an answer to the question asked within the curl command. The question within the command can be updated and the command can be rerun to obtain a new answer.