Data Normalization

Data processing and normalization tasks evaluate structured output from messy prose and different structures. This capability is essential for catalogue and product pipelines where data needs to be extracted from unstructured text and formatted consistently. Models must understand the desired output format and extract relevant information accurately.

50
Input Tokens
0
Output Tokens
0
Duration
0
Cost
0
Context
Input
Return a list of all ingredients part of this recipe, ordered alphabetically. Only ingredients , not quantities
Expected output
{
  "ingredients": [
    "basmati rice",
    "bay leaf",
    "chicken",
    "cilantro",
    "cinnamon",
    "cloves",
    "garam masala",
    "ghee",
    "ginger-garlic paste",
    "green cardamom",
    "lemon",
    "milk",
    "mint",
    "oil",
    "onions",
    "red chili powder",
    "saffron",
    "salt",
    "turmeric",
    "water",
    "yogurt"
  ]
}
Model output
{
  "ingredients": [
    "Basmati rice",
    "Bay leaf",
    "Cardamom pods",
    "Chicken",
    "Cilantro",
    "Cinnamon stick",
    "Cloves",
    "Garam masala",
    "Ghee",
    "Ginger-garlic paste",
    "Lemon",
    "Milk",
    "Mint",
    "Oil",
    "Onions",
    "Red chili powder",
    "Saffron",
    "Salt",
    "Turmeric",
    "Yogurt"
  ]
}