Periodically, you will need to update configuration files and models, or install product updates for your on-premises deployment. A regularly updated system will be both more secure and more performant than a lagging one.
If you modify configuration files or download new models, then you will need to restart your existing containers to get changes to take effect.
docker compose -f /path/to/docker-compose.yml up -d --force-recreate
Deepgram periodically makes new product updates to the container images available. Some updates are recommended, while others are mandatory and, if not installed, will result in Deepgram products ceasing to function. To install product updates:
Identify the latest on-prem release in the Deepgram Changelog. Filter by "On-Prem", and select the latest release. You can use either the container image tag or the release tag listed for all images referenced in this documentation. Update your
Refresh your container image repository credentials:
docker login quay.io
Restart existing containers. The new image tags in your
docker-compose.ymlfile will be automatically detected and the necessary container images will be downloaded and deployed.
docker-compose -f /path/to/docker-compose.yml up -d
You may manage your own Deepgram licensing per the Self Service Licensing & Credentials guide, including rotation and expiration of credentials.
If you have ever been issued an on-prem license file for specialized, offline/air-gapped deployments, please contact your Deepgram Account Representative for additional documentation about maintaining your license.
When backing up a Deepgram installation, you should back up the following artifacts:
- directory housing the models that you use in your requests
We highly recommend backing up your whole server, if possible. Doing so will ensure that you can easily restore a running system.
Updated 4 months ago
Now that you understand how to maintain your deployed Deepgram on-premises system, it's time to take a look at best practices related to autoscaling your system based on demand.