Class RunCollectorCallbackHandler

A callback handler that collects traced runs and makes it easy to fetch the traced run object from calls through any langchain object. For instance, it makes it easy to fetch the run ID and then do things with that, such as log feedback.

Hierarchy (view full)

Constructors

constructor

Properties

awaitHandlers exampleId? ignoreAgent ignoreChain ignoreCustomEvent ignoreLLM ignoreRetriever name raiseError runMap tracedRuns

Methods

copy handleAgentAction handleAgentEnd handleChainEnd handleChainError handleChainStart handleChatModelStart handleCustomEvent? handleLLMEnd handleLLMError handleLLMNewToken handleLLMStart handleRetrieverEnd handleRetrieverError handleRetrieverStart handleText handleToolEnd handleToolError handleToolStart onAgentAction? onAgentEnd? onChainEnd? onChainError? onChainStart? onLLMEnd? onLLMError? onLLMNewToken? onLLMStart? onRetrieverEnd? onRetrieverError? onRetrieverStart? onRunCreate? onRunUpdate? onText? onToolEnd? onToolError? onToolStart? persistRun stringifyError toJSON toJSONNotImplemented fromMethods

Constructors

constructor

Properties

awaitHandlers

awaitHandlers: boolean = ...

OptionalexampleId

exampleId?: string

The ID of the example.

ignoreAgent

ignoreAgent: boolean = false

ignoreChain

ignoreChain: boolean = false

ignoreCustomEvent

ignoreCustomEvent: boolean = false

ignoreLLM

ignoreLLM: boolean = false

ignoreRetriever

ignoreRetriever: boolean = false

name

name: string = "run_collector"

The name of the callback handler.

raiseError

raiseError: boolean = false

ProtectedrunMap

runMap: Map<string, Run> = ...

tracedRuns

tracedRuns: Run[]

An array of traced runs.

Methods

copy

handleAgentAction

handleAgentEnd

handleChainEnd

  • handleChainEnd(outputs, runId, _parentRunId?, _tags?, kwargs?): Promise<Run>

  • 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[]
    • Optionalkwargs: {
          inputs?: Record<string, unknown>;
      }
      • Optionalinputs?: Record<string, unknown>

    Returns Promise<Run>

handleChainError

  • handleChainError(error, runId, _parentRunId?, _tags?, kwargs?): Promise<Run>

  • Called if a Chain run encounters an error

    Parameters

    • error: unknown
    • runId: string
    • Optional_parentRunId: string
    • Optional_tags: string[]
    • Optionalkwargs: {
          inputs?: Record<string, unknown>;
      }
      • Optionalinputs?: Record<string, unknown>

    Returns Promise<Run>

handleChainStart

  • handleChainStart(chain, inputs, runId, parentRunId?, tags?, metadata?, runType?, name?): Promise<Run>

  • 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
    • OptionalparentRunId: string
    • Optionaltags: string[]
    • Optionalmetadata: KVMap
    • OptionalrunType: string
    • Optionalname: string

    Returns Promise<Run>

handleChatModelStart

  • handleChatModelStart(llm, messages, runId, parentRunId?, extraParams?, tags?, metadata?, name?): Promise<Run>

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

    Parameters

    • llm: Serialized
    • messages: BaseMessage[][]
    • runId: string
    • OptionalparentRunId: string
    • OptionalextraParams: KVMap
    • Optionaltags: string[]
    • Optionalmetadata: KVMap
    • Optionalname: string

    Returns Promise<Run>

OptionalhandleCustomEvent

handleLLMEnd

handleLLMError

handleLLMNewToken

  • handleLLMNewToken(token, idx, runId, _parentRunId?, _tags?, fields?): Promise<Run>

  • 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[]
    • Optionalfields: HandleLLMNewTokenCallbackFields

    Returns Promise<Run>

handleLLMStart

  • handleLLMStart(llm, prompts, runId, parentRunId?, extraParams?, tags?, metadata?, name?): Promise<Run>

  • 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
    • OptionalparentRunId: string
    • OptionalextraParams: KVMap
    • Optionaltags: string[]
    • Optionalmetadata: KVMap
    • Optionalname: string

    Returns Promise<Run>

handleRetrieverEnd

handleRetrieverError

handleRetrieverStart

handleText

handleToolEnd

handleToolError

handleToolStart

  • handleToolStart(tool, input, runId, parentRunId?, tags?, metadata?, name?): Promise<Run>

  • 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
    • OptionalparentRunId: string
    • Optionaltags: string[]
    • Optionalmetadata: KVMap
    • Optionalname: string

    Returns Promise<Run>

OptionalonAgentAction

OptionalonAgentEnd

OptionalonChainEnd

OptionalonChainError

OptionalonChainStart

OptionalonLLMEnd

OptionalonLLMError

OptionalonLLMNewToken

OptionalonLLMStart

OptionalonRetrieverEnd

OptionalonRetrieverError

OptionalonRetrieverStart

OptionalonRunCreate

OptionalonRunUpdate

OptionalonText

OptionalonToolEnd

OptionalonToolError

OptionalonToolStart

ProtectedpersistRun

ProtectedstringifyError

toJSON

toJSONNotImplemented

StaticfromMethods

Settings

Member Visibility

On This Page

Constructors
Properties
Methods