Class BaseCallbackHandlerAbstract

Abstract base class for creating callback handlers in the LangChain framework. It provides a set of optional methods that can be overridden in derived classes to handle various events during the execution of a LangChain application.

Hierarchy (view full)

  • BaseCallbackHandlerMethodsClass

Implements

Constructors

constructor

Properties

awaitHandlers ignoreAgent ignoreChain ignoreLLM ignoreRetriever name

Methods

copy toJSON toJSONNotImplemented handleAgentAction? handleAgentEnd? handleChainEnd? handleChainError? handleChainStart? handleChatModelStart? handleLLMEnd? handleLLMError? handleLLMNewToken? handleLLMStart? handleRetrieverEnd? handleRetrieverError? handleRetrieverStart? handleText? handleToolEnd? handleToolError? handleToolStart? fromMethods

Constructors

constructor

Properties

awaitHandlers

awaitHandlers: boolean = ...

ignoreAgent

ignoreAgent: boolean = false

ignoreChain

ignoreChain: boolean = false

ignoreLLM

ignoreLLM: boolean = false

ignoreRetriever

ignoreRetriever: boolean = false

Abstract name

name: string

Methods

copy

toJSON

toJSONNotImplemented

Optional handleAgentAction

  • handleAgentAction(action, runId, parentRunId?, tags?): void | Promise<void>

  • Called when an agent is about to execute an action, with the action and the run ID.

    Parameters

    • action: AgentAction
    • runId: string
    • Optional parentRunId: string
    • Optional tags: string[]

    Returns void | Promise<void>

Optional handleAgentEnd

  • handleAgentEnd(action, runId, parentRunId?, tags?): void | Promise<void>

  • Called when an agent finishes execution, before it exits. with the final output and the run ID.

    Parameters

    • action: AgentFinish
    • runId: string
    • Optional parentRunId: string
    • Optional tags: string[]

    Returns void | Promise<void>

Optional handleChainEnd

  • handleChainEnd(outputs, runId, parentRunId?, tags?, kwargs?): any

  • Called at the end of a Chain run, with the outputs and the run ID.

    Parameters

    • outputs: ChainValues
    • runId: string
    • Optional parentRunId: string
    • Optional tags: string[]
    • Optional kwargs: {
          inputs?: Record<string, unknown>;
      }
      • Optional inputs?: Record<string, unknown>

    Returns any

Optional handleChainError

  • handleChainError(err, runId, parentRunId?, tags?, kwargs?): any

  • Called if a Chain run encounters an error

    Parameters

    • err: any
    • runId: string
    • Optional parentRunId: string
    • Optional tags: string[]
    • Optional kwargs: {
          inputs?: Record<string, unknown>;
      }
      • Optional inputs?: Record<string, unknown>

    Returns any

Optional handleChainStart

  • handleChainStart(chain, inputs, runId, parentRunId?, tags?, metadata?, runType?, name?): any

  • Called at the start of a Chain run, with the chain name and inputs and the run ID.

    Parameters

    • chain: Serialized
    • inputs: ChainValues
    • runId: string
    • Optional parentRunId: string
    • Optional tags: string[]
    • Optional metadata: Record<string, unknown>
    • Optional runType: string
    • Optional name: string

    Returns any

Optional handleChatModelStart

  • handleChatModelStart(llm, messages, runId, parentRunId?, extraParams?, tags?, metadata?, name?): any

  • Called at the start of a Chat Model run, with the prompt(s) and the run ID.

    Parameters

    • llm: Serialized
    • messages: BaseMessage[][]
    • runId: string
    • Optional parentRunId: string
    • Optional extraParams: Record<string, unknown>
    • Optional tags: string[]
    • Optional metadata: Record<string, unknown>
    • Optional name: string

    Returns any

Optional handleLLMEnd

  • handleLLMEnd(output, runId, parentRunId?, tags?): any

  • Called at the end of an LLM/ChatModel run, with the output and the run ID.

    Parameters

    • output: LLMResult
    • runId: string
    • Optional parentRunId: string
    • Optional tags: string[]

    Returns any

Optional handleLLMError

  • handleLLMError(err, runId, parentRunId?, tags?): any

  • Called if an LLM/ChatModel run encounters an error

    Parameters

    • err: any
    • runId: string
    • Optional parentRunId: string
    • Optional tags: string[]

    Returns any

Optional handleLLMNewToken

  • handleLLMNewToken(token, idx, runId, parentRunId?, tags?, fields?): any

  • Called when an LLM/ChatModel in streaming mode produces a new token

    Parameters

    • token: string
    • idx: NewTokenIndices

      idx.prompt is the index of the prompt that produced the token (if there are multiple prompts) idx.completion is the index of the completion that produced the token (if multiple completions per prompt are requested)

    • runId: string
    • Optional parentRunId: string
    • Optional tags: string[]
    • Optional fields: HandleLLMNewTokenCallbackFields

    Returns any

Optional handleLLMStart

  • handleLLMStart(llm, prompts, runId, parentRunId?, extraParams?, tags?, metadata?, name?): any

  • Called at the start of an LLM or Chat Model run, with the prompt(s) and the run ID.

    Parameters

    • llm: Serialized
    • prompts: string[]
    • runId: string
    • Optional parentRunId: string
    • Optional extraParams: Record<string, unknown>
    • Optional tags: string[]
    • Optional metadata: Record<string, unknown>
    • Optional name: string

    Returns any

Optional handleRetrieverEnd

  • handleRetrieverEnd(documents, runId, parentRunId?, tags?): any

  • Parameters

    • documents: DocumentInterface<Record<string, any>>[]
    • runId: string
    • Optional parentRunId: string
    • Optional tags: string[]

    Returns any

Optional handleRetrieverError

  • handleRetrieverError(err, runId, parentRunId?, tags?): any

  • Parameters

    • err: any
    • runId: string
    • Optional parentRunId: string
    • Optional tags: string[]

    Returns any

Optional handleRetrieverStart

  • handleRetrieverStart(retriever, query, runId, parentRunId?, tags?, metadata?, name?): any

  • Parameters

    • retriever: Serialized
    • query: string
    • runId: string
    • Optional parentRunId: string
    • Optional tags: string[]
    • Optional metadata: Record<string, unknown>
    • Optional name: string

    Returns any

Optional handleText

  • handleText(text, runId, parentRunId?, tags?): void | Promise<void>

  • Parameters

    • text: string
    • runId: string
    • Optional parentRunId: string
    • Optional tags: string[]

    Returns void | Promise<void>

Optional handleToolEnd

  • handleToolEnd(output, runId, parentRunId?, tags?): any

  • Called at the end of a Tool run, with the tool output and the run ID.

    Parameters

    • output: string
    • runId: string
    • Optional parentRunId: string
    • Optional tags: string[]

    Returns any

Optional handleToolError

  • handleToolError(err, runId, parentRunId?, tags?): any

  • Called if a Tool run encounters an error

    Parameters

    • err: any
    • runId: string
    • Optional parentRunId: string
    • Optional tags: string[]

    Returns any

Optional handleToolStart

  • handleToolStart(tool, input, runId, parentRunId?, tags?, metadata?, name?): any

  • Called at the start of a Tool run, with the tool name and input and the run ID.

    Parameters

    • tool: Serialized
    • input: string
    • runId: string
    • Optional parentRunId: string
    • Optional tags: string[]
    • Optional metadata: Record<string, unknown>
    • Optional name: string

    Returns any

Static fromMethods

Settings

Member Visibility

Theme

On This Page

Generated using TypeDoc