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
  • Traceable
  • Jestlike
  • Vercel
  • Anthropic
  • Sandbox
⌘I

LangChain Assistant

Ask a question to get started

Enter to send•Shift+Enter new line

Menu

LangSmith
ClientRun TreesTraceableEvaluationSchemasLangchainJestVitestWrappersAnonymizerTraceableJestlikeVercelAnthropicSandbox
Language
Theme
JavaScriptlangsmithindex
Module●Since v0.0

index

Copy
import { ... } from "langsmith";

Functions

function
getDefaultProjectName→ string
function
overrideFetchImplementation
function
uuid7FromTime→ string
function
configureGlobalPromptCache
function
uuid7→ string

Classes

class
Client
class
PromptCache
class
RunTree
deprecatedclass
Cache

Interfaces

interface
CacheConfig
interface
CacheMetrics
interface
ClientConfig
interface
Dataset
interface
Example
interface
Feedback
interface
FeedbackConfigSchema
interface
LangSmithTracingClientInterface
interface
Run
interface
RunTreeConfig
interface
TracerSession

Type Aliases

Variables

View source on GitHub
typeAlias
RetrieverOutput: __type[]

Represents the expected output schema returned by traceable or by run tree output for LangSmith to correctly display documents in the UI

variable
__version__: "0.5.5"
variable
promptCacheSingleton: PromptCache

Global singleton instance of PromptCache. Use configureGlobalPromptCache(), enableGlobalPromptCache(), or disableGlobalPromptCache() instead.

Overrides the fetch implementation used for LangSmith calls. You should use this if you need to use an implementation of fetch other than the default global (e.g. for dealing with proxies).

Generate a UUID v7 from a timestamp.

Configure the global prompt cache.

This should be called before any cache instances are created.

Generate a random UUID v7 string.

LRU cache with background refresh for prompts.

Features:

  • In-memory LRU cache with configurable max size
  • Background refresh using setInterval
  • Stale-while-revalidate: returns stale data while refresh happens
  • Uses the most recently used client for a key for refreshes
  • JSON dump/load for offline use

A run can represent either a trace (root run) or a child run (~span).

Configuration options for Cache.

Cache performance metrics.

Describes properties of a run when loaded from the database. Extends the BaseRun interface.