OpenAI ChatGPT and Zoho DataPrep

Feature control

Under the Feature controls tab, you can manage the General feature control for DataPrep and Open AI Integration.

General

Clear storage

The General feature controls for Zoho DataPrep helps you manage and clear storage space by defining how long raw and prepared data should be retained. 
Notes
Note: This setting will be visible only to the account and organization admins.




Retain raw and prepared data for the last - Use this setting to specify how long Zoho DataPrep should retain older raw and prepared data.
Once the selected retention period expires, the data is automatically deleted to clear storage space in Zoho DataPrep. You can choose a data retention period from 1 to 6 months, with up to 2 months for the Standard plan and up to 6 months for the Enterprise plan, based on your subscription.

Alert
Important: This is a global setting and applies across all workspaces in your organization. All raw and prepared data older than the selected retention period will be permanently deleted from every workspace.

Manually clearing storage space

In addition to this setting, you can also manually clear storage space by deleting pipelines and workspaces from Trash, as items in Trash continue to consume storage until they are permanently removed.
Idea As a best practice, always permanently delete unused pipelines and workspaces after moving them to Trash.

Prepare data using Code Studio[BETA]

Enable this toggle if you want to Prepare data using Code Studio. This option deeply analyzes and trains your ML models using raw Python code right within the context of your data pipeline. By enabling this feature, you authenticate and authorize all users who can create or access a pipeline in your DataPrep organization to use the Code Studio feature. Learn more about this option here.

Notes
Note: The toggle will be disabled by default. This setting will be visible only to the account admin


Open AI Integration with Zoho DataPrep

Open AI integration with Zoho DataPrep helps you enrich your data with advanced AI-based features using ChatGPT, a generative artificial intelligence developed by OpenAI.

Info
OpenAI in Zoho DataPrep works in a BYOK (Bring Your Own Key) model, in which users bring their own ChatGPT API Key and OpenAI Organization ID. If you are already an OpenAI user, you can use your API key and organization ID to unlock AI features in DataPrep. 

Here's a quick video on ChatGPT integration with Zoho DataPrep. 



Info Data Privacy Notice : Zoho DataPrep utilizes OpenAI's ChatGPT API, an external service based in the USA, subject to OpenAI's Terms of Use . Please be aware that the information sent to OpenAI depends on the access provided by you, the user. The data shared with ChatGPT is based on the features you enable. Details such as column names and/or selected cell data will be shared based on each feature. You can choose to enable or disable each feature based on the level of data you want to share. Therefore, exercise caution while using this service and ensure that the data you provide does not contain confidential or personal information. 


Notes
Notes
  1. The generative response are coming in from ChatGPT's training data. Accuracy, consistency, and relevance of the response are subjective to the type of prompts and the data available in its training set. 
  2. ChatGPT doesn't respond to prompts about personal information.
Here's a short demo that illustrates the various features in Zoho DataPrep powered by OpenAI's ChatGPT integration. 



To configure and enable OpenAI's ChatGPT integration

1. Go to the OpenAI Integration tab in the Settings page by clicking the settings icon at the top-right corner in the top bar. 
Alert
Note: The OpenAI configuration in DataPrep's Settings page will be visible to only the Account admin.
The features can enabled for your DataPrep organization only by the Account admin.



2. Provide the Organization ID and API Key of your OpenAI organization to configure OpenAI integration in your DataPrep organization. 
Notes Note : The key will be encrypted and securely stored in Zoho DataPrep. Learn how to get the Organization ID and the API key from OpenAI

3. Click the Save button. Consent popup will be shown. Please read the data privacy notice carefully before you proceed. By proceeding, you acknowledge and accept the risks, and OpenAI's terms of use policy. 





4. Once saved, you can choose to enable the OpenAI's ChatGPT features you want. 
  1. Prepare data using Ask Zia
  2. Dataset Finder
  3. Formula Generator
  4. Transform by Example


      
5. After enabling the features, you will be able to use them in your DataPrep organization. 
  1. You can find the External dataset finder feature while importing data using the +Add dataset button. 
  2. You can find the Formula suggester feature in the "Add formula" transform available in the Transform menu in the DataPrep studio page.
  3. You can find the Transform by example feature in the right-click menu of your data column.
  4. You can find the Prepare data using Ask Zia feature from the top right corner of the Studio page.

Info
Notes
1. The ChatGPT powered features, when enabled can be used by the Account admin and the Organization admins in your DataPrep organization.
2. The API key entered is specific to the particular organization that it is configured in. If you are a part of multiple Zoho DataPrep organizations, the API key still won't be shared across organizations.
3. The API key entered is specific to Zoho DataPrep, and will not be shared with any other Zoho service.

Organization ID and API key in OpenAI

1. Go to your settings page in Open AI to get the Organization name and ID. Here's a snapshot for reference. Read more from OpenAI



2. Go to the API keys tab under the Organization section to get your API Key. Here's a snapshot for reference. Read more from OpenAI




SEE ALSO
Learn about Dataset finder using ChatGPT
Learn about Transform by example powered by ChatGPT
Learn about generating formula using OpenAI ChatGPT