If you have already set up a connector, skip to How to Use the Zendesk Connector.
To use the Abacus Zendesk connector, you must authorize your API requests by obtaining an API token from your Zendesk account.
- Log in to your Zendesk account and navigate to the Admin Center.
- Select "Apps and Integrations", then choose "Zendesk API" under the "APIs" section.
- Enable token access and generate a new API token. Remember to save the token securely as it will only be shown once.
![Zendesk API Token Access](/static/imgs/docs/zendesk-connector-1.webp)
- In the Abacus.AI interface, click on your profile picture in the top right corner.
![Abacus Profile](/static/imgs/docs/app-connector-profile.webp)
- From the dropdown menu, select "Manage Connectors".
![Manage Connectors](/static/imgs/docs/app-connector-dropdown.webp)
- Click on "Add New Connector", choose "Zendesk" from the list, and enter the required information including the API token you generated earlier. Click "Save" to complete the setup.
![Add New Zendesk Connector](/static/imgs/docs/zendesk-connector-4.webp)
Once the Zendesk connector is set up, you can fetch data to train models in Abacus.AI.
- Create a new project and select the use case, then go to the "Datasets" tab and click "Create Dataset".
![Create Dataset](/static/imgs/docs/create_dataset.webp)
- Click on "Create New".
![Create New Dataset](/static/imgs/docs/create_new.webp)
- Name the dataset, select the data type 'Custom Table', and click "Continue".
![Name Dataset](/static/imgs/docs/dataset_name.webp)
- Choose "Read from External Service" and select your Zendesk connector under "Application Connectors".
![Read from External Service](/static/imgs/docs/app_import.webp)
-
If only certain articles are needed, click Browse
to use the Application Browser to select the articles to fetch. All will be pulled by default.
![Fetch Zendesk Articles](/static/imgs/docs/zendesk_connector_dataset_configurataion.webp)
-
After the dataset is uploaded, configure the schema mapping and proceed to train models with the data.
![Train Model with Data](/static/imgs/docs/train_model.webp)