Class StructuredChatAgent

Agent that interoperates with Structured Tools using React logic.

Deprecated

Use the method instead.

Hierarchy (view full)

Agent
- StructuredChatAgent

Constructors

constructor

new StructuredChatAgent(input): StructuredChatAgent
Parameters
- input: StructuredChatAgentInput
Returns StructuredChatAgent
Overrides Agent.constructor
- Defined in langchain/src/agents/structured_chat/index.ts:69

Properties

ToolType

ToolType: StructuredToolInterface<ZodObjectAny>

llmChain

llmChain: LLMChain<string, LLMType>

outputParser

outputParser: undefined | AgentActionOutputParser

Accessors

allowedTools

get allowedTools(): undefined | string[]
Returns undefined | string[]
Inherited from Agent.allowedTools
- Defined in langchain/src/agents/agent.ts:491

inputKeys

get inputKeys(): string[]
Returns string[]
Inherited from Agent.inputKeys
- Defined in langchain/src/agents/agent.ts:495

returnValues

get returnValues(): string[]
Returns string[]
Inherited from Agent.returnValues
- Defined in langchain/src/agents/agent.ts:57

Methods

constructScratchPad

constructScratchPad(steps): Promise<string>
Constructs the agent's scratchpad from a list of steps. If the agent's scratchpad is not empty, it prepends a message indicating that the agent has not seen any previous work.
Parameters
- steps: AgentStep[]
  Array of AgentStep instances to construct the scratchpad from.
Returns Promise<string>
A Promise that resolves to a string representing the agent's scratchpad.
Overrides Agent.constructScratchPad
- Defined in langchain/src/agents/structured_chat/index.ts:134

finishToolName

finishToolName(): string
Name of tool to use to terminate the chain.

Returns string
Inherited from Agent.finishToolName
- Defined in langchain/src/agents/agent.ts:569

llmPrefix

llmPrefix(): string
Prefix to append the LLM call with.

Returns string
Overrides Agent.llmPrefix
- Defined in langchain/src/agents/structured_chat/index.ts:83

observationPrefix

observationPrefix(): string
Prefix to append the observation with.

Returns string
Overrides Agent.observationPrefix
- Defined in langchain/src/agents/structured_chat/index.ts:79

plan

plan(steps, inputs, callbackManager?): Promise<AgentAction | AgentFinish>
Decide what to do given some input.
Parameters
- steps: AgentStep[]
  Steps the LLM has taken so far, along with observations from each.
- inputs: ChainValues
  User inputs.
- OptionalcallbackManager: CallbackManager
  Callback manager to use for this call.
Returns Promise<AgentAction | AgentFinish>
Action specifying what tool to use.
Inherited from Agent.plan
- Defined in langchain/src/agents/agent.ts:623

prepareForOutput

prepareForOutput(_returnValues, _steps): Promise<Record<string, any>>
Prepare the agent for output, if needed
Parameters
- _returnValues: Record<string, any>
- _steps: AgentStep[]
Returns Promise<Record<string, any>>
Inherited from Agent.prepareForOutput
- Defined in langchain/src/agents/agent.ts:99

returnStoppedResponse

returnStoppedResponse(earlyStoppingMethod, steps, inputs, callbackManager?): Promise<AgentFinish>
Return response when agent has been stopped due to max iterations
Parameters
- earlyStoppingMethod: StoppingMethod
- steps: AgentStep[]
- inputs: ChainValues
- OptionalcallbackManager: CallbackManager
Returns Promise<AgentFinish>
Inherited from Agent.returnStoppedResponse
- Defined in langchain/src/agents/agent.ts:634

toJSON

toJSON(): Serialized
Returns Serialized
Inherited from Agent.toJSON
- Defined in langchain-core/dist/load/serializable.d.ts:69

toJSONNotImplemented

toJSONNotImplemented(): SerializedNotImplemented
Returns SerializedNotImplemented
Inherited from Agent.toJSONNotImplemented
- Defined in langchain-core/dist/load/serializable.d.ts:70

`Static`createPrompt

createPrompt(tools, args?): ChatPromptTemplate<any, any>
Create prompt in the style of the agent.
Parameters
- tools: StructuredToolInterface<ZodObjectAny>[]
  List of tools the agent will have access to, used to format the prompt.
- Optionalargs: StructuredChatCreatePromptArgs
  Arguments to create the prompt with.
Returns ChatPromptTemplate<any, any>
Overrides Agent.createPrompt
- Defined in langchain/src/agents/structured_chat/index.ts:168

`Static`createToolSchemasString

createToolSchemasString(tools): string
Creates a string representation of the schemas of the provided tools.
Parameters
- tools: StructuredToolInterface<ZodObjectAny>[]
  Array of StructuredTool instances to create the schemas string from.
Returns string
A string representing the schemas of the provided tools.
- Defined in langchain/src/agents/structured_chat/index.ts:147

`Static`deserialize

deserialize(data): Promise<Agent>
Load an agent from a json-like object describing it.
Parameters
- data: SerializedZeroShotAgent & {
  llm?: BaseLanguageModelInterface<any, BaseLanguageModelCallOptions>;
  tools?: ToolInterface<ZodObjectAny>[];
  }
Returns Promise<Agent>
Inherited from Agent.deserialize
- Defined in langchain/src/agents/agent.ts:676

`Static`fromLLMAndTools

fromLLMAndTools(llm, tools, args?): StructuredChatAgent
Creates a StructuredChatAgent from an LLM and a list of tools. Validates the tools, creates a prompt, and sets up an LLM chain for the agent.
Parameters
- llm: BaseLanguageModelInterface<any, BaseLanguageModelCallOptions>
  BaseLanguageModel instance to create the agent from.
- tools: StructuredToolInterface<ZodObjectAny>[]
  Array of StructuredTool instances to create the agent from.
- Optionalargs: StructuredChatCreatePromptArgs & AgentArgs
  Optional arguments to customize the creation of the agent. Can include arguments for creating the prompt and AgentArgs.
Returns StructuredChatAgent
A new instance of StructuredChatAgent.
Overrides Agent.fromLLMAndTools
- Defined in langchain/src/agents/structured_chat/index.ts:211

`Static`getDefaultOutputParser

getDefaultOutputParser(fields?): StructuredChatOutputParserWithRetries
Returns a default output parser for the StructuredChatAgent. If an LLM is provided, it creates an output parser with retry logic from the LLM.
Parameters
- Optionalfields: OutputParserArgs & {
  toolNames: string[];
  }
  Optional fields to customize the output parser. Can include an LLM and a list of tool names.
Returns StructuredChatOutputParserWithRetries
An instance of StructuredChatOutputParserWithRetries.
Overrides Agent.getDefaultOutputParser
- Defined in langchain/src/agents/structured_chat/index.ts:112

`Static`validateTools

validateTools(tools): void
Validates that all provided tools have a description. Throws an error if any tool lacks a description.
Parameters
- tools: StructuredToolInterface<ZodObjectAny>[]
  Array of StructuredTool instances to validate.
Returns void
Overrides Agent.validateTools
- Defined in langchain/src/agents/structured_chat/index.ts:96

Class StructuredChatAgent

Deprecated

Hierarchy (view full)

Index

Constructors

Properties

Accessors

Methods

Constructors

constructor

Parameters

Returns StructuredChatAgent

Properties

ToolType

llmChain

outputParser

Accessors

allowedTools

Returns undefined | string[]

inputKeys

Returns string[]

returnValues

Returns string[]

Methods

constructScratchPad

Parameters

Returns Promise<string>

finishToolName

Returns string

llmPrefix

Returns string

observationPrefix

Returns string

plan

Parameters

Returns Promise<AgentAction | AgentFinish>

prepareForOutput

Parameters

Returns Promise<Record<string, any>>

returnStoppedResponse

Parameters

Returns Promise<AgentFinish>

toJSON

Returns Serialized

toJSONNotImplemented

Returns SerializedNotImplemented

StaticcreatePrompt

Parameters

Returns ChatPromptTemplate<any, any>

StaticcreateToolSchemasString

Parameters

Returns string

Staticdeserialize

Parameters

Returns Promise<Agent>

StaticfromLLMAndTools

Parameters

Returns StructuredChatAgent

StaticgetDefaultOutputParser

Parameters

Returns StructuredChatOutputParserWithRetries

StaticvalidateTools

Parameters

Returns void

Settings

On This Page

`Static`createPrompt

`Static`createToolSchemasString

`Static`deserialize

`Static`fromLLMAndTools

`Static`getDefaultOutputParser

`Static`validateTools