Skip to content
HALOWERK

Denkwerk

prompt set diversity

For up to 20,000 prompts computes length statistics, language shares (franc-min, trigram based), exact duplicates after normalisation, near-duplicate pairs by word 3-gram Jaccard ≥ 0.8 (sampled for large sets), distinct-1 and distinct-2 ratios and the terms that dominate the set. Useful before running evaluations or fine-tuning on a synthetic prompt set.

POST https://denk.halowerk.com/v1/prompt-set-diversity

Inputs

Fields of the published input schema
FieldTypeRequiredDescription
promptsarrayYes
Show full input schema
{
  "type": "object",
  "additionalProperties": false,
  "required": [
    "prompts"
  ],
  "properties": {
    "prompts": {
      "type": "array",
      "minItems": 2,
      "maxItems": 20000,
      "items": {
        "type": "string",
        "maxLength": 20000
      }
    }
  }
}

Open original schema

Published input example

{
  "prompts": [
    "Summarise this contract.",
    "Summarise this contract!",
    "Fasse den Vertrag zusammen.",
    "List the invoice positions."
  ]
}

Result & documentation

Machine-readable documentation of this hub

Source of this page: the published HALOWERK catalog. Updated: 2026-11-17 UTC.

More endpoints in this hub

All endpoints in this hub →