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

Chat LangChain

What can I help with?

Enter to send·Shift+Enter new line

Menu

OverviewClientAsyncClientRun HelpersRun TreesEvaluationSchemasUtilitiesWrappersAnonymizerTestingExpect APIMiddlewarePytest PluginDeployment SDK
Language
Theme
Pythonlangsmithtypessession_feedback_statSessionFeedbackStat
Class●Since v0.15

SessionFeedbackStat

Copy
SessionFeedbackStat()

Bases

BaseModel

Attributes

Inherited fromBaseModel

Attributes

Amodel_fields_set: set[str]Amodel_config: ConfigDictAmodel_construct: construct

Methods

Mto_dict
—

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

View source on GitHub
Mto_json
—

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
avg: Optional[float]
attribute
contains_thread_feedback: bool
attribute
errors: int
attribute
max: Optional[float]
attribute
median: Optional[float]
attribute
min: Optional[float]
attribute
n: int
attribute
stdev: Optional[float]
attribute
type: Literal['PRIMARY', 'COMPOSITE']
attribute
values: Dict[str, int]

Aggregate feedback for one feedback key.

Mean numeric score.

Whether any feedback was left on a thread.

Number of feedback entries recorded as errors.

Highest numeric score.

Median numeric score.

Lowest numeric score.

Number of feedback scores for this key.

Standard deviation of numeric scores.

PRIMARY for recorded feedback, COMPOSITE for a score computed from other feedback keys.

Count of each categorical value.