Zoho DataPrep helps you clean and transform your data using natural language prompts in Ask Zia. Enter your prompt, and Zia will automatically generate the corresponding output.

Ask Zia is powered by generative AI and supports both Zoho LLM and OpenAI integrations.

To enable Ask Zia on the DataPrep Studio page, click the Ask Zia icon. You must authenticate first, and then choose your preferred AI model and configure the integration.

Click here to learn more about configuring AI integrations and enabling GenAI features in Zoho DataPrep.

The prompt and required contextual data will be shared with the selected AI vendor. Personally identifiable information (PII) is never shared with the selected AI Vendor.

The GenAI features, when enabled, can be used by the Account admin and Organization admins in your DataPrep organization.

The API key is specific to the DataPrep organization it is configured in and will not be shared across organizations or with any other Zoho service.

To configure and enable OpenAI's ChatGPT integration

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. 

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: 

1. The generative responses 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.
   

1. Click the Ask Zia icon in the top-right corner of the Studio page. The GenAI Configuration tab will open. Click Authenticate Now to authenticate with the selected AI vendor.

The GenAI Configuration tab opens when you use Ask Zia for the first time. From then on, you can edit the configuration from the GenAI Configuration option in the Ask Zia panel or from the GenAI Configuration tab on the Settings page.

Note: The GenAI configuration on DataPrep's Settings page will be visible only to the Account admin.

Only the Account admin can enable features for your DataPrep organization.

2. Click Authenticate now next to OpenAI. 

3. A consent pop-up 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. Provide the API Key and Organization ID of your OpenAI organization to configure OpenAI integration in your DataPrep organization. 

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

Organization ID and API key in OpenAI

To configure and enable Zoho LLM

Note: This setting is visible and accessible only to the Account admin.

1. Click the Ask Zia icon in the top-right corner of the Studio page. The GenAI Configuration tab will open. Click Authenticate Now to authenticate with the selected AI vendor.

The GenAI Configuration tab opens when you use Ask Zia for the first time. From then on, you can edit the configuration from the GenAI Configuration option in the Ask Zia panel or from the GenAI Configuration tab on the Settings page.

2. Locate Zoho LLM in the AI Vendor list and click Enable configuration.

3. A consent pop-up will be shown. Please read the data privacy notice carefully before you proceed.

4. In the Authentication panel, confirm that the Zoho LLM toggle is enabled and click Save.

5. Once saved, go to the GenAI Skills tab. Toggle on Build pipeline and Prepare data, and select Zoho LLM from the vendor dropdown to Prepare data using Ask Zia on the Studio page.

Prepare data using Ask Zia  

 1. Click the Ask Zia icon in the top right corner of the Studio page.

2. Provide a hint to clean and transform your data in Natural language in the Command Prompt section. For example, convert all date columns to the 'MM/DD/YYYY' format. You can also insert one of the prompts from the sample suggestions.

3. Click Enter or  the icon, and you will see a preview of the data generated by ChatGPT.

Info: You can hover over the preview data to view the original value before transformation.

Info: You can click on the column name displayed at the top left corner to navigate to the modified column.

4. Click Apply Transform to apply the transform to the entire data.

Info:

1. When you close the Ask Zia window, the chat entries, including all prompts and interpretations, will be cleared from memory.

2. Each prompt is treated independently. Unlike ChatGPT, where context from previous prompts is used, here, with Ask Zia on the studio page, you will have to provide prompts from scratch each time. Conversation threads aren't maintained with Ask Zia - Chat on the studio page, DataPrep feature.

5. Once the transform gets applied to the data, it is added as a new rule in the ruleset.

6. On clicking the Edit option, you can modify the rule.

Note: Please note that the transformation has already been applied. When you make edits to the prompt, it will modify the rule and affect the data again.

Note:

1. Only the prompt you type in is shared with ChatGPT.

2. For better results, please include an example with the prompt you provide.

Here are some sample prompts for you to try out  

1. I would like to fill the empty cells in all the columns with "Unknown". Below is a snapshot of the prompt and the preview of the output.

Prompt: Fill empty cells in all columns with "Unknown".

2. I want to clean the phone numbers in my dataset by removing the delimiters and standardising them. Below is a snapshot of the prompt and the preview of the output.

Prompt: Standardise the phone numbers by removing spaces and special characters in the 'Mobile' column

3. I want to remove the prefix 'mailto:' from the Email ID column. Below is a snapshot of the prompt and the preview of the output.

Prompt: Remove the prefix 'mailto:' from all the values in the 'Email' column.

4. I want to remove the duplicates from the data with the 'Email' column as reference, and I would like to remove all emails with public domains. Below is a snapshot of the prompt and the preview of the output.

Prompt: Remove duplicates from the data with the 'Email' column as reference and remove all the emails with public domains.

5. I need to merge the first name and last name into a full name. Below is a snapshot of the prompt and the preview of the output.

Prompt: Merge 'First name' and 'Last name' to create a new column 'Full Name'.

6. I want to count the total leads for each state, add this count as a new column, and then sort the data by this count in descending order. Below is a snapshot of the prompt and the preview of the output.

Prompt: Give the total lead count based on the 'State' column and add the Total lead count in a new column, retaining all other columns; sort in descending order.