Opper

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.

Data Normalization – fireworks/glm-4.5 Task | Opper AI

Input Tokens

0

Output Tokens

0

Duration

0

Cost

0

Context

Input

Analyze the following cooking instructions and return a structured response following these criteria:
1. Return a list of all ingredients present in the recipe even if they are optional (only ingredients, not quantities)
2. Ingredients should only be mentioned once
3. Exclude the title

Expected output

{
  "ingredients": [
    "potatoes",
    "oil",
    "salt",
    "mince",
    "pepper",
    "bacon",
    "cheese",
    "bread",
    "lettuce",
    "tomato",
    "onion",
    "mustard",
    "ketchup",
    "mayonnaise"
  ]
}

Model output

{
  "ingredients": [
    "Potatoes",
    "Oil",
    "Salt",
    "Mince",
    "Pepper",
    "Bacon",
    "Cheese",
    "Bread",
    "Lettuce",
    "Tomato",
    "Onion",
    "Mustard",
    "Ketchup",
    "Mayonnaise"
  ]
}