LangChain Reference home pageLangChain ReferenceLangChain Reference
  • GitHub
  • Main Docs
Deep Agents
LangChain
LangGraph
Integrations
LangSmith
LangChain
  • Universal
  • Hub
  • Node
  • Load
  • Serializable
  • Encoder Backed
  • File System
  • In Memory
LangChain Core
  • Agents
  • Caches
  • Base
  • Dispatch
  • Web
  • Manager
  • Promises
  • Chat History
  • Context
  • Base
  • Langsmith
  • Documents
  • Embeddings
  • Errors
  • Example Selectors
  • Indexing
  • Base
  • Chat Models
  • Llms
  • Profile
  • Load
  • Serializable
  • Memory
  • Messages
  • Tool
  • Output Parsers
  • Openai Functions
  • Openai Tools
  • Outputs
  • Prompt Values
  • Prompts
  • Retrievers
  • Document Compressors
  • Runnables
  • Graph
  • Singletons
  • Stores
  • Structured Query
  • Tools
  • Base
  • Console
  • Log Stream
  • Run Collector
  • Tracer Langchain
  • Stream
  • Async Caller
  • Chunk Array
  • Context
  • Env
  • Event Source Parse
  • Format
  • Function Calling
  • Hash
  • Json Patch
  • Json Schema
  • Math
  • Ssrf
  • Stream
  • Testing
  • Tiktoken
  • Types
  • Vectorstores
Text Splitters
MCP Adapters
⌘I

LangChain Assistant

Ask a question to get started

Enter to send•Shift+Enter new line

Menu

LangChain
UniversalHubNodeLoadSerializableEncoder BackedFile SystemIn Memory
LangChain Core
AgentsCachesBaseDispatchWebManagerPromisesChat HistoryContextBaseLangsmithDocumentsEmbeddingsErrorsExample SelectorsIndexingBaseChat ModelsLlmsProfileLoadSerializableMemoryMessagesToolOutput ParsersOpenai FunctionsOpenai ToolsOutputsPrompt ValuesPromptsRetrieversDocument CompressorsRunnablesGraphSingletonsStoresStructured QueryToolsBaseConsoleLog StreamRun CollectorTracer LangchainStreamAsync CallerChunk ArrayContextEnvEvent Source ParseFormatFunction CallingHashJson PatchJson SchemaMathSsrfStreamTestingTiktokenTypesVectorstores
Text Splitters
MCP Adapters
Language
Theme
JavaScript@langchain/corelanguage_modelsllmsBaseLLMCallOptions
Interface●Since v1.0

BaseLLMCallOptions

Copy
interface BaseLLMCallOptions

Bases

BaseLanguageModelCallOptions

Properties

property
callbacks: Callbacks

Callbacks for this call and any sub-calls (eg. a Chain calling an LLM). Tags are passed to all callbacks, metadata is passed to handle*Start callbacks.

property
configurable: Record<string, any>

Runtime values for attributes previously made configurable on this Runnable, or sub-Runnables.

property
ls_structured_output_format: __type

Describes the format of structured outputs. This should be provided if an output is considered to be structured

property
maxConcurrency: number

Maximum number of parallel calls to make.

property
metadata: Record<string, unknown>
property
recursionLimit: number

Maximum number of times a call can recurse. If not provided, defaults to 25.

property
runId: string
property
runName: string

Name for the tracer run for this call. Defaults to the name of the class.

property
signal: AbortSignal

Abort signal for this call. If provided, the call will be aborted when the signal is aborted.

property
stop: string[]

Stop tokens to use for this call. If not provided, the default stop tokens for the model will be used.

property
tags: string[]
property
timeout: number

Timeout for this call in milliseconds.

Inherited fromBaseLanguageModelCallOptions

Properties

Pcallbacks: Callbacks
—

Callbacks for this call and any sub-calls (eg. a Chain calling an LLM).

Pconfigurable: Record<string, any>
—

Runtime values for attributes previously made configurable on this Runnable,

Pls_structured_output_format: __type
—

Describes the format of structured outputs.

PmaxConcurrency: number
—

Maximum number of parallel calls to make.

Pmetadata: Record<string, unknown>PrecursionLimit: number
—

Maximum number of times a call can recurse. If not provided, defaults to 25.

PrunId: stringPrunName: string
—

Name for the tracer run for this call. Defaults to the name of the class.

Psignal: AbortSignal
—

Abort signal for this call.

Pstop: string[]
—

Stop tokens to use for this call.

Ptags: string[]Ptimeout: number
—

Timeout for this call in milliseconds.

Inherited fromRunnableConfig

Properties

Pcallbacks: Callbacks
—

Callbacks for this call and any sub-calls (eg. a Chain calling an LLM).

Pconfigurable: Record<string, any>
—

Runtime values for attributes previously made configurable on this Runnable,

PmaxConcurrency: number
—

Maximum number of parallel calls to make.

Pmetadata: Record<string, unknown>PrecursionLimit: number
—

Maximum number of times a call can recurse. If not provided, defaults to 25.

PrunId: stringPrunName: string
—

Name for the tracer run for this call. Defaults to the name of the class.

Psignal: AbortSignal
—

Abort signal for this call.

Ptags: string[]Ptimeout: number
—

Timeout for this call in milliseconds.

Inherited fromBaseLanguageModelTracingCallOptions

Properties

Pls_structured_output_format: __type
—

Describes the format of structured outputs.

Inherited fromBaseCallbackConfig

Properties

Pcallbacks: Callbacks
—

Callbacks for this call and any sub-calls (eg. a Chain calling an LLM).

Pmetadata: Record<string, unknown>PrunId: stringPrunName: string
—

Name for the tracer run for this call. Defaults to the name of the class.

Ptags: string[]
View source on GitHub