How can I enable entity detection or redaction in my self-hosted deployment?
Last updated
Was this helpful?
Last updated
Was this helpful?
Deepgram's feature for pre-recorded audio, which identifies and extracts key entities from content in submitted audio, is a powerful tool for audio intelligence. Like all generally available features, you can use this in both our hosted API and your own self-hosted deployment.
Our feature is also built upon entity detection, and you may similarly enable it in your self-hosted deployment following these instructions.
Request an entity detection model from your Deepgram Account Representative.
Place the entity detection model in your models directory, accessible to your Deepgram Engine containers.
Update your configuration based on your container orchestrator.
Docker/Podman
Update your api.toml configuration file to enable the entity detection feature flag, as seen in the api.toml Configuration Update code block below.
Update your Compose file to use a supported release. Update the image tag for API and Engine containers to release-240725 or later.
Restart the API and Engine containers.
Kubernetes
Using a v0.4.0+ release of the deepgram-self-hosted Helm chart, set api.features.entityDetection to true in your values.yaml file.
If you have overridden the default values for api.image.tag or engine.image.tag, make sure to use release-240725 or later.
your Helm installation.
To verify your setup, send a test request with detect_entities=true in your query string.
If you receive a 400 Bad Request response like the following, the entity detection feature flag may not be enabled for your Deepgram API container.
Check that your api.toml configuration file has been updated, as described in Updating your self-hosted deployment.
If your configuration file is valid, check the API container logs to verify the configuration file is being found. If you see a log line warning you about not finding your configuration file, check your Compose file or other configuration to verify all volume paths are correct.
You may receive a 400 Bad Request response where the requested model is defined as Some("latest"). If so, the entity detection model is not currently available to your Engine container.
Verify the model is present in your models directory, restart the Engine container(s), and check the logs to see if the model is being loaded. You should see a line like the following in the startup section of the Engine logs:
If you receive a 400 Bad Request response where the requested model is defined as Semantic Tagging Key .... If so, your Deepgram Engine container is an old version that does not support entity detection. Please update your container to release-240725 or later.