Changelog

August 27, 2024

Container Images (release 240827)

  • quay.io/deepgram/self-hosted-api:release-240827

    • Equivalent image to:
      • quay.io/deepgram/self-hosted-api:1.119.1
      • quay.io/deepgram/onprem-api:release-240827
      • quay.io/deepgram/onprem-api:1.119.1

  • quay.io/deepgram/self-hosted-engine:release-240827

    • Equivalent image to:

      • quay.io/deepgram/self-hosted-engine:3.73.4
      • quay.io/deepgram/onprem-engine:release-240827
      • quay.io/deepgram/onprem-engine:3.73.4

    • Minimum required NVIDIA driver version: >=525.60.13

  • quay.io/deepgram/self-hosted-license-proxy:release-240827

    • Equivalent image to:
      • quay.io/deepgram/self-hosted-license-proxy:1.6.2
      • quay.io/deepgram/onprem-license-proxy:release-240827
      • quay.io/deepgram/onprem-license-proxy:1.6.2

  • quay.io/deepgram/self-hosted-billing:release-240827

    • Equivalent image to:
      • quay.io/deepgram/self-hosted-billing:1.9.3
      • quay.io/deepgram/onprem-billing:release-240827
      • quay.io/deepgram/onprem-billing:1.9.3

This Release Contains The Following Changes

  • Deepgram’s core products are available to host both on-premises and in the cloud. Official resources have been updated to refer to a “self-hosted” product offering, instead of an “onprem” product offering, to align the product name with industry naming standards.

    • The Deepgram image repositories have been updated to reflect this. Images should now be pulled from the self-hosted-* Quay repositories.
    • For the next twelve months, both onprem-* and self-hosted-* image repositories will receive identical image updates monthly, and we will announce image tags in the self-hosted repositories. Subsequently, we will only publish new images to self-hosted-* repos, deprecating onprem-* repository variants.

  • Enables entity detection of 50+ supported entity types for English pre-recorded audio. Previously, this feature has only been available on our hosted endpoint.

    • Requires a new entity-detection model; contact your Deepgram representative.
    • In your api.toml file, enable with the feature flag entity_detection = true.
    • Invoke with the URL parameter detect_entities=true.

  • Expands our redaction capabilities to support 50+ supported entity types for English pre-recorded audio.

    • Requires a new entity-detection model; contact your Deepgram representative.
    • In your api.toml file, enable with the feature flags entity_detection = true and entity_redaction = true.
    • Invoke with the URL parameter redact={class_to_redact}.

  • Keeps our software up-to-date.