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
Pythonlangsmithtypesonline_evaluatorOnlineEvaluator
Classā—Since v0.14

OnlineEvaluator

Copy
OnlineEvaluator()

Bases

BaseModel

Attributes

Inherited fromBaseModel

Attributes

Amodel_fields_set: set[str]Amodel_configAmodel_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
—

Return the report as a JSON-serializable dict (raw JSON shape).

Mconstruct
Mmodel_dump
—

Dump the feedback, including its address.

Mmodel_dump_json
—

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

Classes

CConfig
attribute
id: Optional[str]
attribute
code_evaluator: Optional[OnlineCodeEvaluator]
attribute
created_at: Optional[str]
attribute
created_by: Optional[str]
attribute
feedback_keys: Optional[List[str]]
attribute
is_managed: Optional[bool]
attribute
llm_evaluator: Optional[OnlineLlmEvaluator]
attribute
name: Optional[str]
attribute
run_rules: Optional[List[OnlineEvaluatorRunRule]]
attribute
tenant_id: Optional[str]
attribute
type: Optional[OnlineEvaluatorType]
attribute
updated_at: Optional[str]

IsManaged marks a LangChain Tuned Evaluator (currently the tuned Perceived Error judge). NULL in the DB is read as false via COALESCE.

Embedded child evaluator (populated based on type)