Class OpenAIAgent

Class representing an agent for the OpenAI chat model in LangChain. It extends the Agent class and provides additional functionality specific to the OpenAIAgent type.

Deprecated

Use the method instead.

Hierarchy (view full)

Agent
- OpenAIAgent

Index

Constructors

constructor

new OpenAIAgent(input): OpenAIAgent
Parameters
- input: Omit<OpenAIAgentInput, "outputParser">
Returns OpenAIAgent
Overrides Agent.constructor
- Defined in langchain/src/agents/openai_functions/index.ts:128

Properties

ToolType

ToolType: StructuredToolInterface<ZodObjectAny>

llmChain

llmChain: LLMChain<string, LLMType>

outputParser

outputParser: OpenAIFunctionsAgentOutputParser = ...

tools

tools: StructuredToolInterface<ZodObjectAny>[]

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 | BaseMessage[]>
Constructs a scratch pad from a list of agent steps.
Parameters
- steps: AgentStep[]
  The steps to include in the scratch pad.
Returns Promise<string | BaseMessage[]>
A string or a list of BaseMessages representing the constructed scratch pad.
Overrides Agent.constructScratchPad
- Defined in langchain/src/agents/openai_functions/index.ts:187

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/openai_functions/index.ts:115

observationPrefix

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

Returns string
Overrides Agent.observationPrefix
- Defined in langchain/src/agents/openai_functions/index.ts:111

plan

plan(steps, inputs, callbackManager?): Promise<AgentAction | AgentFinish>
Plans the next action or finish state of the agent based on the provided steps, inputs, and optional callback manager.
Parameters
- steps: AgentStep[]
  The steps to consider in planning.
- inputs: ChainValues
  The inputs to consider in planning.
- OptionalcallbackManager: CallbackManager
  Optional CallbackManager to use in planning.
Returns Promise<AgentAction | AgentFinish>
A Promise that resolves to an AgentAction or AgentFinish object representing the planned action or finish state.
Overrides Agent.plan
- Defined in langchain/src/agents/openai_functions/index.ts:201

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, fields?): BasePromptTemplate<any, BasePromptValueInterface, any>
Creates a prompt for the OpenAIAgent using the provided tools and fields.
Parameters
- _tools: StructuredToolInterface<ZodObjectAny>[]
  The tools to be used in the prompt.
- Optionalfields: OpenAIAgentCreatePromptArgs
  Optional fields for creating the prompt.
Returns BasePromptTemplate<any, BasePromptValueInterface, any>
A BasePromptTemplate object representing the created prompt.
Overrides Agent.createPrompt
- Defined in langchain/src/agents/openai_functions/index.ts:140

`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?): OpenAIAgent
Creates an OpenAIAgent from a BaseLanguageModel and a list of tools.
Parameters
- llm: BaseLanguageModelInterface<any, BaseLanguageModelCallOptions>
  The BaseLanguageModel to use.
- tools: StructuredToolInterface<ZodObjectAny>[]
  The tools to be used by the agent.
- Optionalargs: OpenAIAgentCreatePromptArgs & Pick<AgentArgs, "callbacks">
  Optional arguments for creating the agent.
Returns OpenAIAgent
An instance of OpenAIAgent.
Overrides Agent.fromLLMAndTools
- Defined in langchain/src/agents/openai_functions/index.ts:160

`Static`getDefaultOutputParser

getDefaultOutputParser(_fields?): AgentActionOutputParser
Get the default output parser for this agent.
Parameters
- Optional_fields: OutputParserArgs
Returns AgentActionOutputParser
Inherited from Agent.getDefaultOutputParser
- Defined in langchain/src/agents/agent.ts:525

`Static`validateTools

validateTools(_tools): void
Validate that appropriate tools are passed in
Parameters
- _tools: StructuredToolInterface<ZodObjectAny>[]
Returns void
Inherited from Agent.validateTools
- Defined in langchain/src/agents/agent.ts:560

Class OpenAIAgent

Deprecated

Hierarchy (view full)

Index

Constructors

Properties

Accessors

Methods

Constructors

constructor

Parameters

Returns OpenAIAgent

Properties

ToolType

llmChain

outputParser

tools

Accessors

allowedTools

Returns undefined | string[]

inputKeys

Returns string[]

returnValues

Returns string[]

Methods

constructScratchPad

Parameters

Returns Promise<string | BaseMessage[]>

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 BasePromptTemplate<any, BasePromptValueInterface, any>

Staticdeserialize

Parameters

Returns Promise<Agent>

StaticfromLLMAndTools

Parameters

Returns OpenAIAgent

StaticgetDefaultOutputParser

Parameters

Returns AgentActionOutputParser

StaticvalidateTools

Parameters

Returns void

Settings

On This Page

`Static`createPrompt

`Static`deserialize

`Static`fromLLMAndTools

`Static`getDefaultOutputParser

`Static`validateTools