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
  • RemoteGraph
⌘I

LangChain Assistant

Ask a question to get started

Enter to send•Shift+Enter new line

Menu

OverviewClientAsyncClientRun HelpersRun TreesEvaluationSchemasUtilitiesWrappersAnonymizerTestingExpect APIMiddlewarePytest PluginDeployment SDKRemoteGraph
Language
Theme
PythonlangsmithschemasFeedbackBase
Class●Since v0.0

FeedbackBase

Feedback schema.

Copy
FeedbackBase()

Bases

BaseModel

Attributes

View source on GitHub
attribute
id: UUID
attribute
created_at: Optional[datetime]
attribute
modified_at: Optional[datetime]
attribute
run_id: Optional[UUID]
attribute
trace_id: Optional[UUID]
attribute
key: str
attribute
score: SCORE_TYPE
attribute
value: VALUE_TYPE
attribute
comment: Optional[str]
attribute
correction: Union[str, dict, None]
attribute
feedback_source: Optional[FeedbackSourceBase]
attribute
session_id: Optional[UUID]
attribute
start_time: Optional[datetime]
attribute
comparative_experiment_id: Optional[UUID]
attribute
feedback_group_id: Optional[UUID]
attribute
extra: Optional[dict]
attribute
model_config

The unique ID of the feedback.

The time the feedback was created.

The time the feedback was last modified.

The associated run ID this feedback is logged for.

The associated trace ID this feedback is logged for.

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

Value or score to assign the run.

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

Comment or explanation for the feedback.

Correction for the run.

The source of the feedback.

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

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

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

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

run in the group that was being compared.

The metadata of the feedback.