Disable Vision AI

By default, Tokkio utilizes the user’s webcam to stream and analyze video, enhancing the conversational experience. However, users have the option to disable this feature by configuring the Tokkio UI to refrain from streaming the video. Once the UI is adjusted accordingly, the webcam video will not be utilized, and only the audio feed will be transmitted to the cloud.

It’s important to note that the Tokkio backend will continue to include the necessary microservices for consuming video streams. If you wish to remove these services from the app, please follow the guidelines outlined below:

UI frontend modifications

• The UI can be configured to not stream the video to the cloud by setting the enable_camera flag to false. In the one-click scripts, this corresponds to the environment variable ENABLE_CAMERA. See UI, or your CSP setup guide (AWS CSP Automated Setup Guide, Azure CSP Automated Setup Guide, and GCP CSP Automated Setup Guide) for more information.

Tokkio backend modifications (optional)

When the Tokkio UI is set up to disable video streaming, it is possible to configure the Tokkio backend to exclude the vision microservices. This can be accomplished through one of the following methods:

Method 1: Using UCS Studio

1. Set credential to pull MS specs from UCS repo (one time only unless ngc-api-key is changed)

   $ ucf_ms_builder_cli registry repo set-api-key -a <ngc-api-key>
   

2. Clone the latest ACE code from the Github repository.

$ git clone https://github.com/NVIDIA/ACE.git

3. Navigate to the Tokkio reference apps source directory.

$ cd ACE/workflows/tokkio/

4. Launch UCS Studio

5. Click on Open Graph and select tokkio-app.yaml from the location the ucs-tokkio-audio-video-app-<v> is available. To open LLM app’s graph, open tokkio-llm-app.yaml instead.

6. Once the graph is loaded, right click on an empty space on the canvas and click Load parameters. Select tokkio-app-params.yaml (tokkio-llm-app-params.yaml for LLM app)to load the parameters for Tokkio. For more information on importing parameters, refer to UCS Studio Import Parameters.

7. Delete the microservices occupancy-alerts, occupancy-alerts-api, ds-visionai, and tokkio-ds-wdm-envoy using right click delete selection

8. Build the Tokkio app using the Build the current app button on UCS Studio. For more information refer to UCS Studio Building the App.

9. Once the application is built successfully, deploy it on cloud using the infrastructure set up with the help of the CSP setup guide (AWS CSP Automated Setup Guide, Azure CSP Automated Setup Guide, and GCP CSP Automated Setup Guide).

Method 2: Manual

A video tutorial for disabling vision AI in Tokkio is available here: https://youtu.be/gc5vNmr8iYw. Alternatively, one can follow the steps below to manually disable vision AI.

1. Set credential to pull MS specs from UCS repo (one time only unless ngc-api-key is changed)

   $ ucf_ms_builder_cli registry repo set-api-key -a <ngc-api-key>
   

2. Clone the latest ACE code from the Github repository.

$ git clone https://github.com/NVIDIA/ACE.git

3. Navigate to the Tokkio reference apps source directory.

$ cd ACE/workflows/tokkio/

4. Open the tokkio-app.yaml (or tokkio-llm-app.yaml) amd remove the vision micro-services by following the steps below:

   1. Under dependencies, delete the dependencies for:

      • ucf.svc.ds.visionai:<version>

      • ucf.svc.metropolis.occupancy-alerts-api:<version>

      • ucf.svc.metropolis.occupancy-alerts:<version>

      • ucf.svc.tokkio.ds-sdr-envoy:<version>

   2. Under components, delete the components with the following names:

      • tokkio-ds-sdr

      • ds-visionai

      • occupancy-alerts-api

      • occupancy-alerts

   3. Under connections, delete the following connections:

      • ds-visionai/redis: redis-timeseries/redis

      • occupancy-alerts-api/redis: redis-timeseries/redis

      • occupancy-alerts-api/mongodb: mongodb/mongo

      • occupancy-alerts/redis: redis-timeseries/redis

      • occupancy-alerts/occupancy-alerts-api: occupancy-alerts-api/http-api

      • tokkio-ds-sdr/redis: redis-timeseries/redis

      • tokkio-ds-sdr/httpds: ds-visionai/http-api

      • tokkio-ds-sdr/vms: vms/vms

5. Build the app with UCS app builder to create a helm chart:

   $ ucf_app_builder_cli app build <app-spec-yaml> <param-yaml>
   # <param-yaml> is optional
   

6. Upon successful build, the confirmation message below will be shown:

   Syncing any missing service versions to cache...
   Building application ucs-tokkio-audio-video-app-<v> ...
   Application Helm Chart generated in ucs-tokkio-audio-video-app-<v>
   App built
   

7. Deploy the application on cloud using the infrastructure set up with the help of the CSP setup guide (AWS CSP Automated Setup Guide, Azure CSP Automated Setup Guide , and GCP CSP Automated Setup Guide).