LangChain Reference home pageLangChain ReferenceLangChain Reference
  • GitHub
  • Main Docs
Deep Agents
LangChain
LangGraph
Integrations
LangSmith
  • Overview
  • Client
  • AsyncClient
  • Run Helpers
  • Run Trees
  • Evaluation
  • Schemas
  • Utilities
  • Wrappers
  • Anonymizer
  • Testing
  • Expect API
  • Middleware
  • Pytest Plugin
  • Deployment SDK
⌘I

LangChain Assistant

Ask a question to get started

Enter to send•Shift+Enter new line

Menu

OverviewClientAsyncClientRun HelpersRun TreesEvaluationSchemasUtilitiesWrappersAnonymizerTestingExpect APIMiddlewarePytest PluginDeployment SDK
Language
Theme
PythonlangsmithevaluationevaluatorEvaluationResult
Class●Since v0.0

EvaluationResult

Copy
EvaluationResult()

Bases

BaseModel

Attributes

Methods

Inherited fromBaseModel

Attributes

Amodel_fields_set: set[str]Amodel_construct: construct

Methods

Mto_dict
—

Recursively generate a dictionary representation of the model, optionally specifying which fields to include or exclude.

Mto_json
View source on GitHub
—

Generates a JSON string representing this model as it would be received from or sent to the API (but with indentation).

Mconstruct
Mmodel_dump
—

Usage docs: https://docs.pydantic.dev/2.4/concepts/serialization/#modelmodel_dump

Mmodel_dump_json
—

Usage docs: https://docs.pydantic.dev/2.4/concepts/serialization/#modelmodel_dump_json

Classes

CConfig
attribute
key: str
attribute
score: SCORE_TYPE
attribute
value: VALUE_TYPE
attribute
metadata: Optional[dict]
attribute
comment: Optional[str]
attribute
correction: Optional[dict]
attribute
evaluator_info: dict
attribute
feedback_config: Optional[Union[FeedbackConfig, dict]]
attribute
source_run_id: Optional[Union[uuid.UUID, str]]
attribute
target_run_id: Optional[Union[uuid.UUID, str]]
attribute
extra: Optional[dict]
attribute
model_config
method
check_value_non_numeric

Evaluation result.

The aspect, metric name, or label for this evaluation.

The numeric score for this evaluation.

The value for this evaluation, if not numeric.

Arbitrary metadata attached to the evaluation.

An explanation regarding the evaluation.

What the correct value should be, if applicable.

Additional information about the evaluator.

The configuration used to generate this feedback.

The ID of the trace of the evaluator itself.

The ID of the trace this evaluation is applied to.

If none provided, the evaluation feedback is applied to the root trace being.

Metadata for the evaluator run.

Warn when numeric values are passed via the value field.