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
PythonlangsmithschemasRunBase
Class●Since v0.0

RunBase

Copy
RunBase()

Bases

BaseModel

Attributes

View source on GitHub
attribute
id: UUID

Unique identifier for the run.

attribute
name: str

Human-readable name for the run.

attribute
start_time: datetime

Start time of the run.

attribute
run_type: str

The type of run, such as tool, chain, llm, retriever, embedding, prompt, parser.

attribute
end_time: Optional[datetime]

End time of the run, if applicable.

attribute
extra: Optional[dict]

Additional metadata or settings related to the run.

attribute
error: Optional[str]

Error message, if the run encountered any issues.

attribute
serialized: Optional[dict]

Serialized object that executed the run for potential reuse.

attribute
events: Optional[list[dict]]

List of events associated with the run, like start and end events.

attribute
inputs: dict

Inputs used for the run.

attribute
outputs: Optional[dict]

Outputs generated by the run, if any.

attribute
reference_example_id: Optional[UUID]

Reference to an example that this run may be based on.

attribute
parent_run_id: Optional[UUID]

Identifier for a parent run, if this run is a sub-run.

attribute
tags: Optional[list[str]]

Tags for categorizing or annotating the run.

attribute
attachments: Union[Attachments, dict[str, AttachmentInfo]]

Attachments associated with the run.

Each entry is a tuple of (mime_type, bytes).

attribute
metadata: dict[str, Any]

Retrieve the metadata (if any).

attribute
revision_id: Optional[UUID]

Retrieve the revision ID (if any).

attribute
latency: Optional[float]

Latency in seconds.

attribute
model_config

Base Run schema.

A Run is a span representing a single unit of work or operation within your LLM app. This could be a single call to an LLM or chain, to a prompt formatting call, to a runnable lambda invocation. If you are familiar with OpenTelemetry, you can think of a run as a span.