Guide
Adding NVIDIA NIM as a Provider

- Navigate to Settings -> AI Providers
- Click Add New Integration
- Select NVIDIA as the provider
Fill in the details of your endpoint
- Name: the name you wish to give your endpoint - this is the name it will appear as in other areas of the UI such as in the prompt playground
- Base Url: the url of your NVIDIA NIM endpoint - only needed if you are not using the default NVIDIA API endpoint (https://integrate.api.nvidia.com/v1)
- Model Names: model names that are not part of the default list - useful when deploying NVIDIA NIM in a container with only one model
- API Key: key used to access your NVIDIA NIM endpoint
- Headers: optional headers to add in your request
