Podman is a popular open-source container runtime that allows you to run applications in isolated environments. This directory contains resources for running Deepgram products in a self-hosted environment using Podman.
There are several Podman Compose templates for deploying Deepgram services as containers with Podman.
- Podman Compose template for a standard deployment
- Podman Compose template for a deployment with the Deepgram License Proxy
- Read the Deepgram self-hosted introduction, then proceed to the Docker/Podman deployment path. Complete the series of guides until you have a deployment environment configured and are ready to begin the Deploy Deepgram Services guide.
- Download a copy of your chosen Podman Compose template and copies of the associated Deepgram
toml
configuration files. - Replace placeholder paths in your chosen Podman Compose template with the paths to your data and configuration files:
/path/to/api.toml
/path/to/engine.toml
/path/to/models
/path/to/license-proxy.toml
, if applicable
- Export your Deepgram self-hosted API key in your deployment environment.
$ export DEEPGRAM_API_KEY=<your api key here>
- Finish the walkthrough documentation by completing the Deploy Deepgram Service guide.
See the Getting Help section in the root of this repository for a list of resources to help you troubleshoot and resolve issues.
If you encounter issues while deploying or using Deepgram, consider the following troubleshooting steps:
-
Check the pod status and logs:
- Use
podman ps
to check the status of the Deepgram containers. - Use
podman logs <container-id>
to view the logs of a specific container. - Use
podman inspect <container-id>
to view the configuration and status of a specific container.
- Use
-
Verify resource availability:
- Ensure that the host machine has sufficient CPU, memory, and storage resources to accommodate the Deepgram components.
- Check for any resource constraints or limits imposed by your Podman Compose file or
podman run
command.
-
Check the network connectivity:
- Verify that the Deepgram components can communicate with each other and with the Deepgram license server (license.deepgram.com).
- Check the network policies and firewall rules to ensure that the necessary ports and protocols are allowed.
-
Collect diagnostic information:
- Gather relevant logs and metrics.
- Collect your existing configuration files:
api.toml
engine.toml
podman-compose.yml
license-proxy.toml
, if applicable
- Provide the collected diagnostic information to Deepgram for assistance.