`langchain.evaluation.parsing.json_schema`.JsonSchemaEvaluator¶

class langchain.evaluation.parsing.json_schema.JsonSchemaEvaluator(**kwargs: Any)[source]¶

An evaluator that validates a JSON prediction against a JSON schema reference.

This evaluator checks if a given JSON prediction conforms to the provided JSON schema. If the prediction is valid, the score is True (no errors). Otherwise, the score is False (error occurred).

requires_input¶

Whether the evaluator requires input.

Type: bool

requires_reference¶

Whether the evaluator requires reference.

Type: bool

evaluation_name¶

The name of the evaluation.

Type: str

Examples

evaluator = JsonSchemaEvaluator() result = evaluator.evaluate_strings(

prediction=’{“name”: “John”, “age”: 30}’, reference={

“type”: “object”, “properties”: {

“name”: {“type”: “string”}, “age”: {“type”: “integer”}

}

}

) assert result[“score”] is not None

Initializes the JsonSchemaEvaluator.

Parameters: **kwargs – Additional keyword arguments.
Raises: ImportError – If the jsonschema package is not installed.

Attributes

`evaluation_name`	Returns the name of the evaluation.
`requires_input`	Returns whether the evaluator requires input.
`requires_reference`	Returns whether the evaluator requires reference.

Methods

`__init__`(**kwargs)	Initializes the JsonSchemaEvaluator.
`aevaluate_strings`(*, prediction[, ...])	Asynchronously evaluate Chain or LLM output, based on optional input and label.
`evaluate_strings`(*, prediction[, reference, ...])	Evaluate Chain or LLM output, based on optional input and label.

__init__(**kwargs: Any) → None[source]¶

Initializes the JsonSchemaEvaluator.

Parameters: **kwargs – Additional keyword arguments.
Raises: ImportError – If the jsonschema package is not installed.

async aevaluate_strings(*, prediction: str, reference: Optional[str] = None, input: Optional[str] = None, **kwargs: Any) → dict¶

Asynchronously evaluate Chain or LLM output, based on optional input and label.

Parameters

prediction (str) – The LLM or chain prediction to evaluate.
reference (Optional[str], optional) – The reference label to evaluate against.
input (Optional[str], optional) – The input to consider during evaluation.
**kwargs – Additional keyword arguments, including callbacks, tags, etc.

Returns

The evaluation results containing the score or value.

Return type

dict

evaluate_strings(*, prediction: str, reference: Optional[str] = None, input: Optional[str] = None, **kwargs: Any) → dict¶

Evaluate Chain or LLM output, based on optional input and label.