How to Build an Extraction Model with Promptrepo?

Extraction models identify and extract structured information from raw text. In this tutorial, we’ll build a model that extracts ingredients and nutritional values from food descriptions.

Step 1: Preparing Training Data

For extraction, our dataset consists of:

  1. Nutrition per serving: The nutritional values per serving
  2. Web page content: The contents of the web page
  3. Web page title: Title of the page
  4. Ingredients: The extracted list of ingredients
  5. Nutritional category: Categories such as beverage, red meat, etc
  6. Serving size (grams or mL): The food amount per serving

Step 2: Uploading Data to Promptrepo

  1. Open Google Sheets and add or import the training dataset
  2. Click Extensions > Promptrepo > Train AI
  3. Promptrepo sidebar widget will be displayed
  4. Enter the AI model name and click Next
  5. Select Web page title & Web page content as input columns and click Next
  6. Choose all other columns as output columns and click Next

Step 3: Training & Testing the Model

  1. Click Publish and let Promptrepo fine tune the extraction model
  2. Once trained, test the model by inputting a food name and its description
  3. The model should extract structured data (ingredients & nutrition) from the text

Extraction models enable AI to understand and process textual data. Now, let’s move on to generative models to create new data based on learned patterns.