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/coremessagesSystemMessage
Class●Since v1.0

SystemMessage

Represents a system message in a conversation.

Copy
class SystemMessage

Bases

BaseMessage<TStructure, "system">

Used in Docs

  • Agents
  • Build a custom SQL agent
  • Build a RAG agent with LangChain
  • Build a SQL agent
  • Custom middleware

Constructors

constructor
constructor

Properties

property
[MESSAGE_SYMBOL]: true
property
content: TStructure["outputVersion"] extends "v1" ? $InferMessageContentBlocks<TStructure, "system">[] : string | ContentBlock | Text[]

Array of content blocks that make up the message content

property
id: string

An optional identifier for the document.

Ideally this should be unique across the document collection and formatted as a UUID, but this will not be enforced.

property
lc_kwargs: SerializedFields
property
lc_namespace: string[]

A path to the module that contains the class, eg. ["langchain", "llms"] Usually should be the same as the entrypoint the class is exported from.

property
lc_serializable: boolean
property
name: string
property
response_metadata: NonNullable<BaseMessageFields<TStructure, TRole>["response_metadata"]>

Metadata about the message

property
type: "system"
property
_printableFields: Record<string, unknown>
property
[toStringTag]: any
property
contentBlocks: Standard[]
property
lc_aliases: __type | undefined
property
lc_attributes: __type | undefined
property
lc_id: string[]
property
lc_secrets: __type | undefined
property
lc_serializable_keys: string[] | undefined
property
text: string

Block text.

deprecatedproperty
additional_kwargs: __type

Methods

method
_updateId
method
concat→ AIMessageChunk<TStructure>
method
toDict→ StoredMessage
method
toFormattedString→ string
method
toJSON→ Serialized
method
toJSONNotImplemented→ SerializedNotImplemented
method
isInstance→ obj is BaseMessage<T, MessageType> & AIMessage<T>

Type guard to check if an object is an AIMessage. Preserves the MessageStructure type parameter when called with a typed BaseMessage. When called with a typed BaseMessage, preserves the TStructure type

method
lc_name→ string

The name of the serializable. Override to provide an alias or to preserve the serialized module name in minified environments.

Implemented as a static method to support loading logic.

deprecatedmethod
_getType→ MessageType
deprecatedmethod
getType→ MessageType

Inherited fromBaseMessage

Properties

Padditional_kwargs: __typePcontent: TStructure["outputVersion"] extends "v1" ? $InferMessageContentBlocks<TStructure, "ai">[] : string | ContentBlock | Text[]
—

Array of content blocks that make up the message content

Pid: string
—

An optional identifier for the document.

Plc_kwargs: SerializedFieldsPlc_namespace: ["langchain_core", "callbacks", string]
—

A path to the module that contains the class, eg. ["langchain", "llms"]

Plc_serializable: booleanPname: stringPresponse_metadata: NonNullable<BaseMessageFields<TStructure, TRole>["response_metadata"]>
—

Metadata about the message

Ptype: "function"P_printableFields: Record<string, unknown>PcontentBlocks: Standard[]Plc_aliases: __type | undefinedPlc_attributes: __type | undefinedPlc_id: string[]Plc_secrets: __type | undefinedPlc_serializable_keys: string[] | undefinedPtext: string
—

Block text.

Methods

M_getType→ MessageTypeM_updateIdMgetType→ MessageTypeMtoDict→ StoredMessageMtoFormattedString→ stringMtoJSON→ SerializedMtoJSONNotImplemented→ SerializedNotImplementedMisInstance→ obj is BaseMessage<T, MessageType> & AIMessage<T>
—

Type guard to check if an object is an AIMessage.

Mlc_name→ string
—

The name of the serializable. Override to provide an alias or

Inherited fromSerializable

Properties

Plc_kwargs: SerializedFieldsPlc_namespace: ["langchain_core", "callbacks", string]
—

A path to the module that contains the class, eg. ["langchain", "llms"]

Plc_serializable: booleanPlc_aliases: __type | undefinedPlc_attributes: __type | undefinedPlc_id: string[]Plc_secrets: __type | undefinedPlc_serializable_keys: string[] | undefined

Methods

MtoJSON→ SerializedMtoJSONNotImplemented→ SerializedNotImplementedMlc_name→ string
—

The name of the serializable. Override to provide an alias or

View source on GitHub