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
PythonlangsmithschemasFeedbackBase
Class●Since v0.0

FeedbackBase

Feedback schema.

Copy
FeedbackBase()

Bases

BaseModel

Attributes

attribute
id: UUID

The unique ID of the feedback.

attribute
created_at: Optional[datetime]

The time the feedback was created.

attribute
modified_at: Optional[datetime]

The time the feedback was last modified.

attribute
run_id: Optional[UUID]

The associated run ID this feedback is logged for.

attribute
trace_id: Optional[UUID]

The associated trace ID this feedback is logged for.

attribute
key: str

The metric name, tag, or aspect to provide feedback on.

attribute
score: SCORE_TYPE

Value or score to assign the run.

attribute
value: VALUE_TYPE

The display value, tag or other value for the feedback if not a metric.

attribute
comment: Optional[str]

Comment or explanation for the feedback.

attribute
correction: Union[str, dict, None]

Correction for the run.

attribute
feedback_source: Optional[FeedbackSourceBase]

The source of the feedback.

attribute
session_id: Optional[UUID]

The associated project ID (Session = Project) this feedback is logged for.

attribute
start_time: Optional[datetime]

The start time of the run this feedback is associated with.

attribute
comparative_experiment_id: Optional[UUID]

If logged within a 'comparative experiment', this is the ID of the experiment.

attribute
feedback_group_id: Optional[UUID]

For preference scoring, this group ID is shared across feedbacks for each

run in the group that was being compared.

attribute
extra: Optional[dict]

The metadata of the feedback.

attribute
model_config
View source on GitHub