LangChain Reference home pageLangChain ReferenceLangChain Reference
  • GitHub
  • Main Docs
Deep Agents
LangChain
LangGraph
Integrations
LangSmith
LangSmith
  • Client
  • Run Trees
  • Traceable
  • Evaluation
  • Schemas
  • Langchain
  • Jest
  • Vitest
  • Wrappers
  • Anonymizer
  • Jestlike
  • Vercel
  • Anthropic
  • Sandbox
⌘I

LangChain Assistant

Ask a question to get started

Enter to send•Shift+Enter new line

Menu

LangSmith
ClientRun TreesTraceableEvaluationSchemasLangchainJestVitestWrappersAnonymizerJestlikeVercelAnthropicSandbox
Language
Theme
JavaScriptlangsmithexperimentalvercelLangSmithTelemetryConfig
Interface●Since v0.8

LangSmithTelemetryConfig

Configuration options for creating a LangSmith telemetry integration for the Vercel AI SDK.

Copy
interface LangSmithTelemetryConfig

Properties

property
client: Client

The LangSmith client to use.

property
extra: KVMap
property
metadata: KVMap
property
name: string
property
processChildLLMRunInputs: (inputs: KVMap) => KVMap

Transform inputs before logging on child LLM step spans.

property
processChildLLMRunOutputs: (outputs: KVMap) => KVMap

Transform outputs before logging on child LLM step spans.

property
processInputs: (inputs: KVMap) => KVMap

Transform inputs before logging on the root span.

property
processOutputs: (outputs: KVMap) => KVMap

Transform outputs before logging on the root span.

property
projectName: string
property
runType: string

Run type for the root span. Defaults to "chain".

property
tags: string[]
property
traceRawHttp: boolean

Whether to include raw HTTP request/response bodies.

property
traceResponseMetadata: boolean

Whether to include intermediate step details in the output.

property
tracingEnabled: boolean

Whether to enable tracing.

View source on GitHub