langchain.smith.evaluation.config.RunEvalConfig

class langchain.smith.evaluation.config.RunEvalConfig(*, evaluators: List[Union[EvaluatorType, EvalConfig]] = None, custom_evaluators: Optional[List[Union[RunEvaluator, StringEvaluator]]] = None, reference_key: Optional[str] = None, prediction_key: Optional[str] = None, input_key: Optional[str] = None, eval_llm: Optional[BaseLanguageModel] = None)[source]

Bases: BaseModel

Configuration for a run evaluation.

Parameters

  • evaluators (List[Union[EvaluatorType, EvalConfig]]) – Configurations for which evaluators to apply to the dataset run. Each can be the string of an EvaluatorType, such as EvaluatorType.QA, the evaluator type string (“qa”), or a configuration for a given evaluator (e.g., RunEvalConfig.QA).

  • custom_evaluators (Optional[List[Union[RunEvaluator, StringEvaluator]]]) – Custom evaluators to apply to the dataset run.

  • reference_key (Optional[str]) – The key in the dataset run to use as the reference string. If not provided, it will be inferred automatically.

  • prediction_key (Optional[str]) – The key from the traced run’s outputs dictionary to use to represent the prediction. If not provided, it will be inferred automatically.

  • input_key (Optional[str]) – The key from the traced run’s inputs dictionary to use to represent the input. If not provided, it will be inferred automatically.

  • eval_llm (Optional[BaseLanguageModel]) – The language model to pass to any evaluators that use a language model.

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

param custom_evaluators: Optional[List[Union[langsmith.evaluation.evaluator.RunEvaluator, langchain.evaluation.schema.StringEvaluator]]] = None

Custom evaluators to apply to the dataset run.

param eval_llm: Optional[langchain.schema.language_model.BaseLanguageModel] = None

The language model to pass to any evaluators that require one.

param evaluators: List[Union[langchain.evaluation.schema.EvaluatorType, langchain.smith.evaluation.config.EvalConfig]] [Optional]

Configurations for which evaluators to apply to the dataset run. Each can be the string of an EvaluatorType, such as EvaluatorType.QA, the evaluator type string (“qa”), or a configuration for a given evaluator (e.g., RunEvalConfig.QA).

param input_key: Optional[str] = None

The key from the traced run’s inputs dictionary to use to represent the input. If not provided, it will be inferred automatically.

param prediction_key: Optional[str] = None

The key from the traced run’s outputs dictionary to use to represent the prediction. If not provided, it will be inferred automatically.

param reference_key: Optional[str] = None

The key in the dataset run to use as the reference string. If not provided, we will attempt to infer automatically.

class CoTQA[source]

Bases: EvalConfig

Configuration for a context-based QA evaluator.

Parameters

  • prompt (Optional[BasePromptTemplate]) – The prompt template to use for generating the question.

  • llm (Optional[BaseLanguageModel]) – The language model to use for the evaluation chain.

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

Fields

  • evaluator_type (langchain.evaluation.schema.EvaluatorType)

  • llm (Optional[langchain.schema.language_model.BaseLanguageModel])

  • prompt (Optional[langchain.schema.prompt_template.BasePromptTemplate])

param evaluator_type: langchain.evaluation.schema.EvaluatorType = EvaluatorType.CONTEXT_QA
param llm: Optional[langchain.schema.language_model.BaseLanguageModel] = None
param prompt: Optional[langchain.schema.prompt_template.BasePromptTemplate] = None
get_kwargs() → Dict[str, Any]

Get the keyword arguments for the load_evaluator call.

Returns

The keyword arguments for the load_evaluator call.

Return type

Dict[str, Any]

class ContextQA[source]

Bases: EvalConfig

Configuration for a context-based QA evaluator.

Parameters

  • prompt (Optional[BasePromptTemplate]) – The prompt template to use for generating the question.

  • llm (Optional[BaseLanguageModel]) – The language model to use for the evaluation chain.

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

Fields

  • evaluator_type (langchain.evaluation.schema.EvaluatorType)

  • llm (Optional[langchain.schema.language_model.BaseLanguageModel])

  • prompt (Optional[langchain.schema.prompt_template.BasePromptTemplate])

param evaluator_type: langchain.evaluation.schema.EvaluatorType = EvaluatorType.CONTEXT_QA
param llm: Optional[langchain.schema.language_model.BaseLanguageModel] = None
param prompt: Optional[langchain.schema.prompt_template.BasePromptTemplate] = None
get_kwargs() → Dict[str, Any]

Get the keyword arguments for the load_evaluator call.

Returns

The keyword arguments for the load_evaluator call.

Return type

Dict[str, Any]

class Criteria[source]

Bases: EvalConfig

Configuration for a reference-free criteria evaluator.

Parameters

  • criteria (Optional[CRITERIA_TYPE]) – The criteria to evaluate.

  • llm (Optional[BaseLanguageModel]) – The language model to use for the evaluation chain.

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

Fields

  • criteria (Optional[Union[Mapping[str, str], langchain.evaluation.criteria.eval_chain.Criteria, langchain.chains.constitutional_ai.models.ConstitutionalPrinciple]])

  • evaluator_type (langchain.evaluation.schema.EvaluatorType)

  • llm (Optional[langchain.schema.language_model.BaseLanguageModel])

param criteria: Optional[Union[Mapping[str, str], langchain.evaluation.criteria.eval_chain.Criteria, langchain.chains.constitutional_ai.models.ConstitutionalPrinciple]] = None
param evaluator_type: langchain.evaluation.schema.EvaluatorType = EvaluatorType.CRITERIA
param llm: Optional[langchain.schema.language_model.BaseLanguageModel] = None
get_kwargs() → Dict[str, Any]

Get the keyword arguments for the load_evaluator call.

Returns

The keyword arguments for the load_evaluator call.

Return type

Dict[str, Any]

class EmbeddingDistance[source]

Bases: EvalConfig

Configuration for an embedding distance evaluator.

Parameters

  • embeddings (Optional[Embeddings]) – The embeddings to use for computing the distance.

  • distance_metric (Optional[EmbeddingDistanceEnum]) – The distance metric to use for computing the distance.

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

Fields

  • distance_metric (Optional[langchain.evaluation.embedding_distance.base.EmbeddingDistance])

  • embeddings (Optional[langchain.embeddings.base.Embeddings])

  • evaluator_type (langchain.evaluation.schema.EvaluatorType)

param distance_metric: Optional[langchain.evaluation.embedding_distance.base.EmbeddingDistance] = None
param embeddings: Optional[langchain.embeddings.base.Embeddings] = None
param evaluator_type: langchain.evaluation.schema.EvaluatorType = EvaluatorType.EMBEDDING_DISTANCE
get_kwargs() → Dict[str, Any]

Get the keyword arguments for the load_evaluator call.

Returns

The keyword arguments for the load_evaluator call.

Return type

Dict[str, Any]

class LabeledCriteria[source]

Bases: EvalConfig

Configuration for a labeled (with references) criteria evaluator.

Parameters

  • criteria (Optional[CRITERIA_TYPE]) – The criteria to evaluate.

  • llm (Optional[BaseLanguageModel]) – The language model to use for the evaluation chain.

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

Fields

  • criteria (Optional[Union[Mapping[str, str], langchain.evaluation.criteria.eval_chain.Criteria, langchain.chains.constitutional_ai.models.ConstitutionalPrinciple]])

  • evaluator_type (langchain.evaluation.schema.EvaluatorType)

  • llm (Optional[langchain.schema.language_model.BaseLanguageModel])

param criteria: Optional[Union[Mapping[str, str], langchain.evaluation.criteria.eval_chain.Criteria, langchain.chains.constitutional_ai.models.ConstitutionalPrinciple]] = None
param evaluator_type: langchain.evaluation.schema.EvaluatorType = EvaluatorType.LABELED_CRITERIA
param llm: Optional[langchain.schema.language_model.BaseLanguageModel] = None
get_kwargs() → Dict[str, Any]

Get the keyword arguments for the load_evaluator call.

Returns

The keyword arguments for the load_evaluator call.

Return type

Dict[str, Any]

class QA[source]

Bases: EvalConfig

Configuration for a QA evaluator.

Parameters

  • prompt (Optional[BasePromptTemplate]) – The prompt template to use for generating the question.

  • llm (Optional[BaseLanguageModel]) – The language model to use for the evaluation chain.

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

Fields

  • evaluator_type (langchain.evaluation.schema.EvaluatorType)

  • llm (Optional[langchain.schema.language_model.BaseLanguageModel])

  • prompt (Optional[langchain.schema.prompt_template.BasePromptTemplate])

param evaluator_type: langchain.evaluation.schema.EvaluatorType = EvaluatorType.QA
param llm: Optional[langchain.schema.language_model.BaseLanguageModel] = None
param prompt: Optional[langchain.schema.prompt_template.BasePromptTemplate] = None
get_kwargs() → Dict[str, Any]

Get the keyword arguments for the load_evaluator call.

Returns

The keyword arguments for the load_evaluator call.

Return type

Dict[str, Any]

class StringDistance[source]

Bases: EvalConfig

Configuration for a string distance evaluator.

Parameters

distance (Optional[StringDistanceEnum]) – The string distance metric to use.

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

Fields

  • distance (Optional[langchain.evaluation.string_distance.base.StringDistance])

  • evaluator_type (langchain.evaluation.schema.EvaluatorType)

  • normalize_score (bool)

param distance: Optional[langchain.evaluation.string_distance.base.StringDistance] = None

The string distance metric to use. damerau_levenshtein: The Damerau-Levenshtein distance. levenshtein: The Levenshtein distance. jaro: The Jaro distance. jaro_winkler: The Jaro-Winkler distance.

param evaluator_type: langchain.evaluation.schema.EvaluatorType = EvaluatorType.STRING_DISTANCE
param normalize_score: bool = True

Whether to normalize the distance to between 0 and 1. Applies only to the Levenshtein and Damerau-Levenshtein distances.

get_kwargs() → Dict[str, Any]

Get the keyword arguments for the load_evaluator call.

Returns

The keyword arguments for the load_evaluator call.

Return type

Dict[str, Any]

model Config[source]

Bases: object

arbitrary_types_allowed = True

Examples using RunEvalConfig