Abstract
Optional
input: BaseCallbackHandlerInputAbstract
nameA map of aliases for constructor args. Keys are the attribute names, e.g. "foo". Values are the alias that will replace the key in serialization. This is used to eg. make argument names match Python.
A map of additional attributes to merge with constructor args. Keys are the attribute names, e.g. "foo". Values are the attribute values, which will be serialized. These attributes need to be accepted by the constructor as arguments.
The final serialized identifier for the module.
A path to the module that contains the class, eg. ["langchain", "llms"] Usually should be the same as the entrypoint the class is exported from.
A map of secrets, which will be omitted from serialization. Keys are paths to the secret in constructor args, e.g. "foo.bar.baz". Values are the secret ids, which will be used when deserializing.
A manual list of keys that should be serialized. If not overridden, all fields passed into the constructor will be serialized.
Optional
handleCalled when an agent is about to execute an action, with the action and the run ID.
Optional
parentRunId: stringOptional
tags: string[]Optional
handleCalled when an agent finishes execution, before it exits. with the final output and the run ID.
Optional
parentRunId: stringOptional
tags: string[]Optional
handleCalled at the end of a Chain run, with the outputs and the run ID.
Optional
parentRunId: stringOptional
tags: string[]Optional
kwargs: { inputs?: Record<string, unknown> }Optional
handleCalled if a Chain run encounters an error
Optional
parentRunId: stringOptional
tags: string[]Optional
kwargs: { inputs?: Record<string, unknown> }Optional
handleCalled at the start of a Chain run, with the chain name and inputs and the run ID.
Optional
parentRunId: stringOptional
tags: string[]Optional
metadata: Record<string, unknown>Optional
runType: stringOptional
runName: stringOptional
handleCalled at the start of a Chat Model run, with the prompt(s) and the run ID.
Optional
parentRunId: stringOptional
extraParams: Record<string, unknown>Optional
tags: string[]Optional
metadata: Record<string, unknown>Optional
runName: stringOptional
handleOptional
handleCalled at the end of an LLM/ChatModel run, with the output and the run ID.
Optional
parentRunId: stringOptional
tags: string[]Optional
extraParams: Record<string, unknown>Optional
handleCalled if an LLM/ChatModel run encounters an error
Optional
parentRunId: stringOptional
tags: string[]Optional
extraParams: Record<string, unknown>Optional
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: HandleLLMNewTokenCallbackFieldsOptional
handleCalled at the start of an LLM or Chat Model run, with the prompt(s) and the run ID.
Optional
parentRunId: stringOptional
extraParams: Record<string, unknown>Optional
tags: string[]Optional
metadata: Record<string, unknown>Optional
runName: stringOptional
handleOptional
parentRunId: stringOptional
tags: string[]Optional
handleOptional
parentRunId: stringOptional
tags: string[]Optional
handleOptional
parentRunId: stringOptional
tags: string[]Optional
metadata: Record<string, unknown>Optional
name: stringOptional
handleOptional
handleCalled at the end of a Tool run, with the tool output and the run ID.
Optional
parentRunId: stringOptional
tags: string[]Optional
handleCalled if a Tool run encounters an error
Optional
parentRunId: stringOptional
tags: string[]Optional
handleCalled at the start of a Tool run, with the tool name and input and the run ID.
Optional
parentRunId: stringOptional
tags: string[]Optional
metadata: Record<string, unknown>Optional
runName: stringStatic
fromStatic
lc_The name of the serializable. Override to provide an alias or to preserve the serialized module name in minified environments.
Implemented as a static method to support loading logic.
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.