Large Language Models (Latest)
Large Language Models (Latest)

Deployment Steps

Intelligent Virtual Assistant

This section will walk through an end-to-end workflow deployment using the example software stack components previously described.

Ensure that the previous Cloud Native Software Requirements section has been completed prior to proceeding with the deployment steps.

  1. Complete the Audio Transcription Training Pipeline section. The steps for the Intelligent Virtual Assistant Training workflow are identical.

  2. SSH into the training VMI (this is the VMI without Cloud Native Stack or Kubernetes installed).

  3. Ensure the NGC CLI is configured.

    Copy
    Copied!
                

    ngc config set


  4. Download https://catalog.ngc.nvidia.com/enterprise/orgs/nvaie/resources/intelligent-virtual-assistant-training

    Copy
    Copied!
                

    ngc registry resource download-version "nvaie/intelligent-virtual-assistant-training:0.1"


  5. Switch to the training directory.

    Copy
    Copied!
                

    cd intelligent-virtual-assistant-training_v0.1/


  6. Make the set-up script executable.

    Copy
    Copied!
                

    chmod +x ./run.sh


  7. Run the setup script.

    Copy
    Copied!
                

    sudo ./run.sh <YOUR-API-KEY>

    Note

    The installer may fail if dpkg does not run cleanly or entirely during the instance provisioning. If this occurs, run the following command to resolve the issue, then retry the installation.

    Copy
    Copied!
                

    sudo dpkg --configure -a


  8. From a browser, navigate to the Jupyter Notebook URL displayed once the setup script is completed. It is part of the CUSTOM STATES output, e.g.

    Copy
    Copied!
                

    RUN: { "services": [ { "name": "notebook", "url":"**http://<External-IP>/notebook**" } ]}


  9. Select and run through the Jupyter Notebooks, starting with the Welcome Notebook.

    iva-image1.png


  10. The Training Deployment steps are complete

  1. SSH into the inference/deployment VMI.

  2. Ensure the NGC CLI is configured.

    Copy
    Copied!
                

    ngc config set


  3. Download https://catalog.ngc.nvidia.com/enterprise/orgs/nvaie/resources/intelligent-virtual-assistant-deployment

    Copy
    Copied!
                

    ngc registry resource download-version "nvaie/intelligent-virtual-assistant-deployment:0.1"


  4. Switch to the transcription Helm chart directory.

    Copy
    Copied!
                

    cd intelligent-virtual-assistant-deployment_v0.1/helm_charts


  5. Install Haystack Helm chart.

    Copy
    Copied!
                

    helm -n cciva install haystack haystack --create-namespace


  6. Note down the haystack url from the output of the Helm install.

  7. Install the Rasa Helm chart.

    Copy
    Copied!
                

    helm -n cciva install rasa rasa/ --set -ngcCredentials.password=<NGC_KEY> --set haystackUrl=<HAYSTACK_URL>


  8. Note down the Rasa URL from the Helm chart output.

    Important

    If you have already installed the Audio Transcription Riva Helm Chart, ensure you delete it before proceeding if you only have a single GPU attached to your VMI.

    Copy
    Copied!
                

    cd ~/audio-transcription-deployment_v0.1/helm_charts helm del transcription -n riva


  9. Install Riva via Helm.

    Copy
    Copied!
                

    helm -n cciva install riva riva/ --set ngcCredentials.password=<NGC_KEY> --set workflow.keycloak.keycloakrealm=<WORKFLOW_REALM> --create-namespace --set haystackUrl=<HAYSTACK_URL> --set rasaUrl=<RASA_URL>

    iva-image2.png

  10. Reference the output from the Helm install and launch the Jupyter Notebook from a browser once the transcription pods are running.

  11. Validate that all of the iva pods are running

    Copy
    Copied!
                

    kubectl get pods -n cciva

    Note

    It can take about half an hour for the Riva pod to initialize


  12. Once all pods are running, access the Jupyter Notebook for instructions to run the workflow

Previous Cloud Native Software Requirements
Next Contact Information
© Copyright 2022-2023, NVIDIA. Last updated on Feb 1, 2023.