Optional
_fields: BaseCallbackHandlerInputProtected
runMethod used to get a string representation of the run's lineage, which is used in logging.
The run whose lineage is to be retrieved.
A string representation of the run's lineage.
Called when an agent is about to execute an action, with the action and the run ID.
Called when an agent finishes execution, before it exits. with the final output and the run ID.
Called at the end of a Chain run, with the outputs and the run ID.
Optional
_parentRunId: stringOptional
_tags: string[]Optional
kwargs: { Optional
inputs?: Record<string, unknown>Called if a Chain run encounters an error
Optional
_parentRunId: stringOptional
_tags: string[]Optional
kwargs: { Optional
inputs?: Record<string, unknown>Called at the start of a Chain run, with the chain name and inputs and the run ID.
Optional
parentRunId: stringOptional
tags: string[]Optional
metadata: KVMapOptional
runType: stringOptional
name: stringCalled at the start of a Chat Model run, with the prompt(s) and the run ID.
Optional
parentRunId: stringOptional
extraParams: KVMapOptional
tags: string[]Optional
metadata: KVMapOptional
name: stringOptional
handleCalled when an LLM/ChatModel in streaming
mode produces a new token
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)
Optional
_parentRunId: stringOptional
_tags: string[]Optional
fields: HandleLLMNewTokenCallbackFieldsCalled at the start of an LLM or Chat Model run, with the prompt(s) and the run ID.
Optional
parentRunId: stringOptional
extraParams: KVMapOptional
tags: string[]Optional
metadata: KVMapOptional
name: stringOptional
parentRunId: stringOptional
tags: string[]Optional
metadata: KVMapOptional
name: stringCalled at the start of a Tool run, with the tool name and input and the run ID.
Optional
parentRunId: stringOptional
tags: string[]Optional
metadata: KVMapOptional
name: stringMethod used to log the action selected by the agent.
The run in which the agent action occurred.
void
Optional
onMethod used to log the end of a chain run.
The chain run that has ended.
void
Method used to log any errors of a chain run.
The chain run that has errored.
void
Method used to log the start of a chain run.
The chain run that has started.
void
Method used to log the end of an LLM run.
The LLM run that has ended.
void
Method used to log any errors of an LLM run.
The LLM run that has errored.
void
Optional
onLLMNewOptional
kwargs: { Method used to log the start of an LLM run.
The LLM run that has started.
void
Method used to log the end of a retriever run.
The retriever run that has ended.
void
Method used to log any errors of a retriever run.
The retriever run that has errored.
void
Method used to log the start of a retriever run.
The retriever run that has started.
void
Optional
onOptional
onOptional
onMethod used to log the end of a tool run.
The tool run that has ended.
void
Method used to log any errors of a tool run.
The tool run that has errored.
void
Method used to log the start of a tool run.
The tool run that has started.
void
Protected
persistMethod used to persist the run. In this case, it simply returns a resolved promise as there's no persistence logic.
The run to persist.
A resolved promise.
Protected
stringifyStatic
from
A tracer that logs all events to the console. It extends from the
BaseTracer
class and overrides its methods to provide custom logging functionality.Example