Skip to main content
POST
/
api
/
classify
Classify
curl --request POST \
  --url https://whetdata.com/api/classify \
  --header 'Content-Type: application/json' \
  --data '
{
  "text": "This is a great product with awesome features",
  "criteria": [
    "is_positive"
  ]
}
'
{
  "success": true,
  "scores": {
    "is_positive": 80
  }
}

​
Overview

Classify text against custom criteria. It analyzes your text and provides scores (0-100) for each specified criterion, indicating how well the text matches each criteria.

​
Use This Action To

  • Evaluate text against custom criteria
  • Score content based on specific attributes
  • Classify documents by custom metrics
  • Measure how well text matches defined criteria

​
Parameters

​
text
string
required
Text to classify (max 5,000 characters)
​
criteria
array
required
Array of criteria names to evaluate the text against

​
Example

cURL
curl -X POST https://whetdata.com/api/classify \
  -H "x-api-key: whet_your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "This is a great product with awesome features",
    "criteria": ["is_positive"]
  }'
JavaScript
const url = "https://whetdata.com/api/classify";
const options = {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "x-api-key": "whet_your_api_key_here",
  },
  body: JSON.stringify({
    text: "This is a great product with awesome features",
    criteria: ["is_positive"],
  }),
};

fetch(url, options)
  .then((response) => response.json())
  .then((data) => console.log(data))
  .catch((error) => console.error("Error:", error));

​
Response

{
  "success": true,
  "scores": {
    "is_positive": 100,
    "would_order_again": 100,
    "mentions_taste": 100,
    "is_actionable": 1
  }
}

​
Tips

The maximum text length is 5,000 characters. For longer texts, split them into chunks.

Body

application/json
​
text
string
required

Text to classify (max 5,000 characters)

Maximum string length: 5000
​
criteria
string[]
required

Array of criteria names to evaluate the text against

Response

200 - application/json

Success

​
success
boolean
​
scores
object

Scores for each criterion (0-100)