Generate Text

Parameters

• Destination Column: The column name that will hold the manipulated text. Defaults to manipulated_text.
• LLM: The large language model used for text generation. Defaults to gpt-3.5-turbo.
• Credential ID: The connector from your Mantium account. This is a required field.
• String Template: The template that guides the manipulation of text. Defaults to empty string.

Usage

To use the Generate Text transformation, you will need to have a valid API key configured in Mantium for the third-party service (e.g., OpenAI) you want to use. If you don't have one, see the guide here

To use this Mantium Enrichment, follow these steps:

1. Configure the Destination Column parameter by specifying the new name for the column that will hold the generated text.
2. Configure the LLM Model parameter by selecting the LLM model to use for the text generation.
3. Configure the Credential ID parameter by selecting the appropriate credential from the list of available credentials in your Mantium account.
4. Add text in the StringTemplate field to provide details to the model on how to generate the text. See example below.
5. Optional: Preview the transform to see how the generated text can look based on your data.
6. Run the transformation by clicking the Save and Run Transforms button. The resulting dataset will have a new column with the specified name containing the generated text data.

Example 1: Generate Product Descriptions

Suppose you have a dataset containing product names and features, and you want to generate a short description for each product. You can use the Generate Text transformation to create natural language descriptions based on the product features.

The video below demonstrates how to use the Generate Text transformation in just a few seconds. If you prefer text, please continue reading.

To do this, you would configure the transformation as follows:

Source Column: features
Destination Column: description
LLM Model: gpt-3.5-turbo
Credential ID: OpenAI
String Template: "Write a short description for a product with the following features: {features}"

The resulting dataset would look like this:

Example 2: Generate Frequently Asked Questions (FAQs) Responses

Suppose you have a dataset containing frequently asked questions about your products or services, and you want to generate responses for each question. You can use the Generate Text transformation to create natural language responses based on the given questions.

To do this, you would configure the transformation as follows:

Source Column: faq_question
Destination Column: faq_answer
LLM Model: gpt-3.5-turbo
Credential ID: OpenAI
String Template: "Provide a helpful response to this customer's question: {faq_question}"

The resulting dataset would look like this: