How to Build a Generative Model with Promptrepo?

"generating product descriptions based on data in other columns"- Google Docs Editors Community

Some rows in your Google Sheet are missing values, or need text written from the other columns, such as a product description or a nutrition estimate for a food with no data. Writing them by hand takes hours. A general AI model can draft them, but its answers change from one try to the next and don't follow your columns. With Promptrepo, you build a generative model from your examples, and it fills in your own output fields when real data is missing. You can test it in a form before you use it, with no code.

Let's start. Create your AI model and follow the steps below.

Step 1: Prepare your training data

  • Web page title: The name of the Web page.
  • Web page content: The content of the web page.
  • Nutritional category: Category of the nutrition such as beverages, general food etc.
  • Ingredients: Source ingredients of the food product.
  • Nutrition per serving: Nutritional values per serving of the food item.
  • Serving size (grams or mL): size of one serving of the food item
  • Nutrition information available in the input: the nutritional values of the food available in the input
  • Guessed nutrition: the nutritional information of the food that weren't given and was predicted instead
Each row is one example with these columns. You can start with one, as below, and add the rest to its Google Sheet later.

Step 2: Creating the model in Promptrepo

Input with Document, Email and Text to choose from, with Text marked
  • Enter one example in the box: a web page title and its content, such as "Classic beef burger. A quarter pound patty with onions and cheese in a soft bun."
  • Click Done. AI fills in the Output on the right.
Enter Text with the example typed in the box, with the Done button marked
  • Under Editing input, click + Add input field if you need another input.
  • Click Done
Editing input on the left and the Output filled in by AI on the right, with the Done button marked
  • Under Editing output, check that the output fields are the ones you need, such as Nutrition per serving and Guessed nutrition. Click + Add output field for any that is missing.
  • Click Done
Input on the left and Editing output on the right, with the Done button marked
  • Click Publish
Input and Output side by side, with the Publish button marked at the top
  • Enter the AI model name and click Publish Now
The AI model name box with Food generation typed in, with the Publish Now button marked
  • When it says Model is ready!, click Proceed.
The Model is ready! message, with the Proceed button marked

Step 3: Training & Testing the Model

  • Click PREVIEW
The top of the model page with EDIT, CODE and PREVIEW, with PREVIEW marked
  • Enter a food name and its description and click PROCEED.
  • The model should extract structured data (ingredients & nutrition) from the input text. If real data is missing, the model will generate a reasonable estimate based on similar foods.
  • Click ADD TO TRAINING DATA on a result you like, to teach the model with one more example
The Input and the Output the model gave, with the Add to training data button marked
To add many examples at once, on the model page, click on the edit icon on the Training data tab. Its Google Sheet will open and you can add rows there.
The Training data tab of Food generation-V1 with the example in a row, with the edit icon marked
Generative models fill gaps where real data is missing. With Promptrepo, you can fine-tune models for classification, extraction and generation from examples in Google Sheets.

Summary

When rows are missing data, filling them by hand takes hours and a general model doesn't follow your columns. With Promptrepo, you enter an example, check the output fields and publish a generative model that fills in your own fields. Create your AI model and complete the steps above. If you have any questions, write to support.

Last updated: