JSONSchemaScorer
Validates that JSON output conforms to a specified JSON Schema. Checks JSON validity and ensures the structure matches expected fields, types, and constraints defined in a provided schema.
Overview
Validates that JSON output conforms to a specified JSON Schema. Checks JSON validity and ensures the structure matches expected fields, types, and constraints defined in a provided schema.
Use Cases
- Autonomous AI agent evaluation
- Structured output validation
How It Works
This scorer uses deterministic rule-based evaluation to validate outputs against specific criteria. It applies predefined rules and patterns to assess the response, providing consistent and reproducible results without requiring LLM inference.
Input Schema
| Parameter | Type | Required | Description |
|---|---|---|---|
| prediction | str | Yes | JSON text to validate |
| context.schema | dict | Yes | JSON Schema for validation |
Output Schema
| Field | Type | Description |
|---|---|---|
| score | float | 10.0 if schema-compliant, 0.0 otherwise |
| passed | bool | True if compliant |
| reasoning | str | Validation errors if any |
| metadata | dict | Schema validation details |
Score Interpretation
Default threshold: 10/10
Related Scorers
IsJSONScorer
Validates whether the prediction is valid JSON. This rule-based scorer attempts to parse the predict...
FormatValidLinksScorer
Validates that URLs in the prediction are properly formatted and optionally accessible. Extracts URL...
FormatIsEmailScorer
Validates whether the prediction contains a valid email address format. Uses regular expression matc...
ConversationalConversationalRoleAdherenceScorer
Measures how well an AI maintains its assigned role or persona throughout a conversation. Evaluates ...
Frequently Asked Questions
When should I use this scorer?
Use JSONSchemaScorer when you need to evaluate format and agent aspects of your AI outputs. It's particularly useful for autonomous ai agent evaluation.
Why doesn't this scorer need expected output?
This scorer evaluates quality aspects that don't require comparison against a reference answer. It uses the system prompt and context as the implicit ground truth.
Can I customize the threshold?
Yes, the default threshold of 10 can be customized when configuring the scorer.
Quick Info
Ready to try JSONSchemaScorer?
Start evaluating your AI agents with Noveum.ai's comprehensive scorer library.
Explore More Scorers
Discover 106 calibrated LLM-as-Judge scorers for comprehensive AI evaluation