Skip to content

CustomizeData.md

Latest commit

 

History

History
37 lines (24 loc) · 1.81 KB

CustomizeData.md

File metadata and controls

37 lines (24 loc) · 1.81 KB

Customize the solution with your own data

If you would like to update the solution to leverage your own data please follow the steps below.

Note: you will need to complete the deployment steps here before proceeding.

Prerequisites:

  1. Your data will need to be in JSON or wav format with the file name formated prefixed with "convo" then a GUID followed by a timestamp. For more examples of the data format, please review the sample transcripts and audio data included here

    • Example: convo_32e38683-bbf7-407e-a541-09b37b77921d_2024-12-07 04%3A00%3A00

  2. Navigate to the storage account in the resource group you are using for this solution.

  3. Open the data container

Note for WAF-aligned deployments: If your deployment uses private networking, you'll need to log into a VM within the virtual network to upload files. See VM login instructions below.

  1. If you have audio files, upload them to custom_audiodata folder. If you have call transcript files, upload them to custom_transcripts folder.
  2. Navigate to the terminal and run the run_process_data_scripts.sh to process the new data into the solution with the following commands. 
    cd infra/scripts

az login

bash run_process_data_scripts.sh resourcegroupname_param
    a. resourcegroupname_param - the name of the resource group.

How to Login to VM Using Azure Bastion

For WAF-aligned deployments with private networking:

  1. Navigate to your VM in the Azure portal
  2. Click Connect → Bastion
  3. Enter your VM credentials (username and password) and click Connect
  4. Wait for the Bastion connection to establish - this may take a few moments
  5. Once connected, you'll have access to the VM desktop/terminal interface