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
PythonlangsmithschemasExperimentRunStats
Class●Since v0.4

ExperimentRunStats

Run statistics for an experiment.

Copy
ExperimentRunStats()

Bases

TypedDict

Constructors

constructor
__init__
NameType
run_countOptional[int]
latency_p50Optional[timedelta]
latency_p99Optional[timedelta]
total_tokensOptional[int]
prompt_tokensOptional[int]
completion_tokensOptional[int]
last_run_start_timeOptional[datetime]
run_facetsOptional[list[dict[str, Any]]]
total_costOptional[Decimal]
prompt_costOptional[Decimal]
completion_costOptional[Decimal]
first_token_p50Optional[timedelta]
first_token_p99Optional[timedelta]
error_rateOptional[float]

Attributes

attribute
run_count: Optional[int]

The number of runs in the project.

attribute
latency_p50: Optional[timedelta]

The median (50th percentile) latency for the project.

attribute
latency_p99: Optional[timedelta]

The 99th percentile latency for the project.

attribute
total_tokens: Optional[int]

The total number of tokens consumed in the project.

attribute
prompt_tokens: Optional[int]

The total number of prompt tokens consumed in the project.

attribute
completion_tokens: Optional[int]

The total number of completion tokens consumed in the project.

attribute
last_run_start_time: Optional[datetime]

The start time of the last run in the project.

attribute
run_facets: Optional[list[dict[str, Any]]]

Facets for the runs in the project.

attribute
total_cost: Optional[Decimal]

The total estimated LLM cost associated with the completion tokens.

attribute
prompt_cost: Optional[Decimal]

The estimated cost associated with the prompt (input) tokens.

attribute
completion_cost: Optional[Decimal]

The estimated cost associated with the completion tokens.

attribute
first_token_p50: Optional[timedelta]

The median (50th percentile) time to process the first token.

attribute
first_token_p99: Optional[timedelta]

The 99th percentile time to process the first token.

attribute
error_rate: Optional[float]

The error rate for the project.

View source on GitHub