Skip to main content

Words Count

The Words count guardrail validates that the message content falls within a specified word count range. This is useful to enforce minimum prompt lengths or prevent excessively long inputs.

It can be applied before sending the prompt to the LLM and after to validate the LLM response.

How it works​

The guardrail splits the message content by whitespace and counts the resulting words. If the count falls outside the configured min and max bounds, the message is blocked.

Configuration​

"guardrails": [
  {
    "enabled": true,
    "before": true,
    "after": true,
    "id": "words",
    "config": {
      "min": 3,
      "max": 1000
    }
  }
]

Field explanations​

  • enabled: true — The guardrail is active
  • before: true — The guardrail applies to user input before sending to the LLM
  • after: true — The guardrail applies to the LLM response

Config section​

ParameterTypeRequiredDefaultDescription
minnumberNo0Minimum number of words allowed in the message
maxnumberNounlimitedMaximum number of words allowed in the message

Guardrail example​

If a user sends a single-word message like "Hello" and the minimum is set to 3 words, the request will be blocked with:

This message has been blocked by the 'words count' guardrail !