Export and import a topic model

You can export models that you have already trained to back them up. You can use these backups to roll back an existing model or to transfer a model to a new project.

Export a model

Permissions required for this task

To perform this task, you must have the following permissions:

contactcenterinsights.issueModels.export

Exporting a topic model to Cloud Storage lets you save a backup copy of the model so that you can restore it later if needed.

REST

To export a topic model, call the export method on the issueModel resource.

Export Topic Model

Before using any of the request data, make the following replacements:

PROJECT_ID: Your project ID.
ISSUE_MODEL_ID: The ID of the topic model to export.
GCS_DESTINATION: A Cloud Storage URI where the topic model is exported to.

HTTP method and URL:

POST https://contactcenterinsights.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/issueModels/ISSUE_MODEL_ID:export

Request JSON body:

{ 
  gcs_destination: { 
    object_uri: 'GCS_DESTINATION'
  }
}

To send your request, expand one of these options:

curl (Linux, macOS, or Cloud Shell)

Note: The following command assumes that you have logged in to the gcloud CLI with your user account by running gcloud init or gcloud auth login , or by using Cloud Shell, which automatically logs you into the gcloud CLI . You can check the currently active account by running gcloud auth list.

Save the request body in a file named request.json, and execute the following command:

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://contactcenterinsights.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/issueModels/ISSUE_MODEL_ID:export"

PowerShell (Windows)

Note: The following command assumes that you have logged in to the gcloud CLI with your user account by running gcloud init or gcloud auth login . You can check the currently active account by running gcloud auth list.

Save the request body in a file named request.json, and execute the following command:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://contactcenterinsights.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/issueModels/ISSUE_MODEL_ID:export" | Select-Object -Expand Content

You should receive a JSON response similar to the following:

{
  "name": "projects/PROJECT_ID/locations/us-central1/operations/OPERATION_ID"
}

Import a model

Permissions required for this task

To perform this task, you must have the following permissions:

contactcenterinsights.issueModels.create
contactcenterinsights.issueModels.import

Importing a topic model from Cloud Storage lets you replace an existing topic model or create a new topic model based on an existing model. Starting from an existing model can be useful when you want to make tweaks without changing the original model.

To replace an existing topic model, call the import method with a Cloud Storage object URI, pointing to a previously exported topic model from the same project. Conversational Insights pulls the replacement model ID from the exported file.
If the topic model does not exist in the project or is being imported into a new project, Conversational Insights automatically creates a new topic model.
Optionally, you can set the create_new_model flag if you don't want to replace the existing model.

REST

Import Topic Model

Before using any of the request data, make the following replacements:

PROJECT_ID: Your project ID.
GCS_SOURCE: The Cloud Storage URI where the topic model is saved.
CREATE_NEW_MODEL: Boolean flag to create a new model, rather than replacing an existing model.

HTTP method and URL:

POST https://contactcenterinsights.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/issueModels:import

Request JSON body:

{
  gcs_source: {
    object_uri: 'GCS_SOURCE'
  }
  create_new_model: CREATE_NEW_MODEL
}

To send your request, expand one of these options:

curl (Linux, macOS, or Cloud Shell)

Save the request body in a file named request.json, and execute the following command:

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://contactcenterinsights.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/issueModels:import"

PowerShell (Windows)

Save the request body in a file named request.json, and execute the following command:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://contactcenterinsights.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/issueModels:import" | Select-Object -Expand Content

You should receive a JSON response similar to the following:

{
  "name": "projects/PROJECT_ID/locations/us-central1/operations/OPERATION_ID"
}