FileCallbackHandler#

class langchain_core.callbacks.file.FileCallbackHandler( filename: str, mode: str = 'a', color: str | None = None, )[source]#

Callback Handler that writes to a file.

This handler supports both context manager usage (recommended) and direct instantiation (deprecated) for backwards compatibility.

Examples

Using as a context manager (recommended):

with FileCallbackHandler("output.txt") as handler:
    # Use handler with your chain/agent
    chain.invoke(inputs, config={"callbacks": [handler]})

Direct instantiation (deprecated):

handler = FileCallbackHandler("output.txt")
# File remains open until handler is garbage collected
try:
    chain.invoke(inputs, config={"callbacks": [handler]})
finally:
    handler.close()  # Explicit cleanup recommended

Parameters:

filename (str) – The file path to write to.
mode (str) – The file open mode. Defaults to 'a' (append).
color (Optional[str]) – Default color for text output. Defaults to None.

Note

When not used as a context manager, a deprecation warning will be issued on first use. The file will be opened immediately in __init__ and closed in __del__ or when close() is called explicitly.

Initialize the file callback handler.

Parameters:

filename (str) – Path to the output file.
mode (str) – File open mode (e.g., 'w', 'a', 'x'). Defaults to 'a'.
color (Optional[str]) – Default text color for output. Defaults to None.

Attributes

`ignore_agent`	Whether to ignore agent callbacks.
`ignore_chain`	Whether to ignore chain callbacks.
`ignore_chat_model`	Whether to ignore chat model callbacks.
`ignore_custom_event`	Ignore custom event.
`ignore_llm`	Whether to ignore LLM callbacks.
`ignore_retriever`	Whether to ignore retriever callbacks.
`ignore_retry`	Whether to ignore retry callbacks.
`raise_error`	Whether to raise an error if an exception occurs.
`run_inline`	Whether to run the callback inline.

Methods

`__init__`(filename[, mode, color])	Initialize the file callback handler.
`close`()	Close the file if it's open.
`on_agent_action`(action[, color])	Handle agent action by writing the action log.
`on_agent_finish`(finish[, color])	Handle agent finish by writing the finish log.
`on_chain_end`(outputs, **kwargs)	Print that we finished a chain.
`on_chain_error`(error, *, run_id[, parent_run_id])	Run when chain errors.
`on_chain_start`(serialized, inputs, **kwargs)	Print that we are entering a chain.
`on_chat_model_start`(serialized, messages, *, ...)	Run when a chat model starts running.
`on_custom_event`(name, data, *, run_id[, ...])	Override to define a handler for a custom event.
`on_llm_end`(response, *, run_id[, parent_run_id])	Run when LLM ends running.
`on_llm_error`(error, *, run_id[, parent_run_id])	Run when LLM errors.
`on_llm_new_token`(token, *[, chunk, ...])	Run on new LLM token.
`on_llm_start`(serialized, prompts, *, run_id)	Run when LLM starts running.
`on_retriever_end`(documents, *, run_id[, ...])	Run when Retriever ends running.
`on_retriever_error`(error, *, run_id[, ...])	Run when Retriever errors.
`on_retriever_start`(serialized, query, *, run_id)	Run when the Retriever starts running.
`on_retry`(retry_state, *, run_id[, parent_run_id])	Run on a retry event.
`on_text`(text[, color, end])	Handle text output.
`on_tool_end`(output[, color, ...])	Handle tool end by writing the output with optional prefixes.
`on_tool_error`(error, *, run_id[, parent_run_id])	Run when tool errors.
`on_tool_start`(serialized, input_str, *, run_id)	Run when the tool starts running.

__init__( filename: str, mode: str = 'a', color: str | None = None, ) → None[source]#

Initialize the file callback handler.

Parameters:

filename (str) – Path to the output file.
mode (str) – File open mode (e.g., 'w', 'a', 'x'). Defaults to 'a'.
color (str | None) – Default text color for output. Defaults to None.

Return type:

None

close() → None[source]#

Close the file if it’s open.

This method is safe to call multiple times and will only close the file if it’s currently open.

Return type:: None

on_agent_action(

action: AgentAction,

color: str | None = None,

**kwargs: Any,

) → Any[source]#

Handle agent action by writing the action log.

Parameters:

action (AgentAction) – The agent action containing the log to write.
color (Optional[str]) – Color override for this specific output. If None, uses self.color.
**kwargs (Any) – Additional keyword arguments.

Return type:

Any

on_agent_finish(

finish: AgentFinish,

color: str | None = None,

**kwargs: Any,

) → None[source]#

Handle agent finish by writing the finish log.

Parameters:

finish (AgentFinish) – The agent finish object containing the log to write.
color (Optional[str]) – Color override for this specific output. If None, uses self.color.
**kwargs (Any) – Additional keyword arguments.

Return type:

None

on_chain_end(

outputs: dict[str, Any],

**kwargs: Any,

) → None[source]#

Print that we finished a chain.

Parameters:

outputs (dict[str, Any]) – The outputs of the chain.
**kwargs (Any) – Additional keyword arguments.

Return type:

None

on_chain_error(

error: BaseException,

*,

run_id: UUID,

parent_run_id: UUID | None = None,

**kwargs: Any,

) → Any#

Run when chain errors.

Parameters:

error (BaseException) – The error that occurred.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
kwargs (Any) – Additional keyword arguments.

Return type:

Any

on_chain_start(

serialized: dict[str, Any],

inputs: dict[str, Any],

**kwargs: Any,

) → None[source]#

Print that we are entering a chain.

Parameters:

serialized (dict[str, Any]) – The serialized chain information.
inputs (dict[str, Any]) – The inputs to the chain.
**kwargs (Any) – Additional keyword arguments that may contain 'name'.

Return type:

None

on_chat_model_start(

serialized: dict[str, Any],

messages: list[list[BaseMessage]],

*,

run_id: UUID,

parent_run_id: UUID | None = None,

tags: list[str] | None = None,

metadata: dict[str, Any] | None = None,

**kwargs: Any,

) → Any#

Run when a chat model starts running.

ATTENTION: This method is called for chat models. If you’re implementing a handler for a non-chat model, you should use on_llm_start instead.

Parameters:

serialized (dict[str, Any]) – The serialized chat model.
messages (list[list[BaseMessage]]) – The messages.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
tags (Optional[list[str]]) – The tags.
metadata (Optional[dict[str, Any]]) – The metadata.
kwargs (Any) – Additional keyword arguments.

Return type:

Any

on_custom_event(

name: str,

data: Any,

*,

run_id: UUID,

tags: list[str] | None = None,

metadata: dict[str, Any] | None = None,

**kwargs: Any,

) → Any#

Override to define a handler for a custom event.

Parameters:

name (str) – The name of the custom event.
data (Any) – The data for the custom event. Format will match the format specified by the user.
run_id (UUID) – The ID of the run.
tags (Optional[list[str]]) – The tags associated with the custom event (includes inherited tags).
metadata (Optional[dict[str, Any]]) – The metadata associated with the custom event (includes inherited metadata).
kwargs (Any)

Return type:

Any

Added in version 0.2.15.

on_llm_end(

response: LLMResult,

*,

run_id: UUID,

parent_run_id: UUID | None = None,

**kwargs: Any,

) → Any#

Run when LLM ends running.

Parameters:

response (LLMResult) – The response which was generated.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
kwargs (Any) – Additional keyword arguments.

Return type:

Any

on_llm_error(

error: BaseException,

*,

run_id: UUID,

parent_run_id: UUID | None = None,

**kwargs: Any,

) → Any#

Run when LLM errors.

Parameters:

error (BaseException) – The error that occurred.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
kwargs (Any) – Additional keyword arguments.

Return type:

Any

on_llm_new_token(

token: str,

*,

chunk: GenerationChunk | ChatGenerationChunk | None = None,

run_id: UUID,

parent_run_id: UUID | None = None,

**kwargs: Any,

) → Any#

Run on new LLM token. Only available when streaming is enabled.

Parameters:

token (str) – The new token.
chunk (GenerationChunk | ChatGenerationChunk) – The new generated chunk, containing content and other information.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
kwargs (Any) – Additional keyword arguments.

Return type:

Any

on_llm_start(

serialized: dict[str, Any],

prompts: list[str],

*,

run_id: UUID,

parent_run_id: UUID | None = None,

tags: list[str] | None = None,

metadata: dict[str, Any] | None = None,

**kwargs: Any,

) → Any#

Run when LLM starts running.

Attention

This method is called for non-chat models (regular LLMs). If you’re implementing a handler for a chat model, you should use on_chat_model_start instead.

Parameters:

serialized (dict[str, Any]) – The serialized LLM.
prompts (list[str]) – The prompts.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
tags (Optional[list[str]]) – The tags.
metadata (Optional[dict[str, Any]]) – The metadata.
kwargs (Any) – Additional keyword arguments.

Return type:

Any

on_retriever_end(

documents: Sequence[Document],

*,

run_id: UUID,

parent_run_id: UUID | None = None,

**kwargs: Any,

) → Any#

Run when Retriever ends running.

Parameters:

documents (Sequence[Document]) – The documents retrieved.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
kwargs (Any) – Additional keyword arguments.

Return type:

Any

on_retriever_error(

error: BaseException,

*,

run_id: UUID,

parent_run_id: UUID | None = None,

**kwargs: Any,

) → Any#

Run when Retriever errors.

Parameters:

error (BaseException) – The error that occurred.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
kwargs (Any) – Additional keyword arguments.

Return type:

Any

on_retriever_start(

serialized: dict[str, Any],

query: str,

*,

run_id: UUID,

parent_run_id: UUID | None = None,

tags: list[str] | None = None,

metadata: dict[str, Any] | None = None,

**kwargs: Any,

) → Any#

Run when the Retriever starts running.

Parameters:

serialized (dict[str, Any]) – The serialized Retriever.
query (str) – The query.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
tags (Optional[list[str]]) – The tags.
metadata (Optional[dict[str, Any]]) – The metadata.
kwargs (Any) – Additional keyword arguments.

Return type:

Any

on_retry(

retry_state: RetryCallState,

*,

run_id: UUID,

parent_run_id: UUID | None = None,

**kwargs: Any,

) → Any#

Run on a retry event.

Parameters:

retry_state (RetryCallState) – The retry state.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
kwargs (Any) – Additional keyword arguments.

Return type:

Any

on_text(

text: str,

color: str | None = None,

end: str = '',

**kwargs: Any,

) → None[source]#

Handle text output.

Parameters:

text (str) – The text to write.
color (str | None) – Color override for this specific output. If None, uses self.color.
end (str) – String appended after the text. Defaults to "".
**kwargs (Any) – Additional keyword arguments.

Return type:

None

on_tool_end(

output: str,

color: str | None = None,

observation_prefix: str | None = None,

llm_prefix: str | None = None,

**kwargs: Any,

) → None[source]#

Handle tool end by writing the output with optional prefixes.

Parameters:

output (str) – The tool output to write.
color (str | None) – Color override for this specific output. If None, uses self.color.
observation_prefix (str | None) – Optional prefix to write before the output.
llm_prefix (str | None) – Optional prefix to write after the output.
**kwargs (Any) – Additional keyword arguments.

Return type:

None

on_tool_error(

error: BaseException,

*,

run_id: UUID,

parent_run_id: UUID | None = None,

**kwargs: Any,

) → Any#

Run when tool errors.

Parameters:

error (BaseException) – The error that occurred.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
kwargs (Any) – Additional keyword arguments.

Return type:

Any

on_tool_start(

serialized: dict[str, Any],

input_str: str,

*,

run_id: UUID,

parent_run_id: UUID | None = None,

tags: list[str] | None = None,

metadata: dict[str, Any] | None = None,

inputs: dict[str, Any] | None = None,

**kwargs: Any,

) → Any#

Run when the tool starts running.

Parameters:

serialized (dict[str, Any]) – The serialized tool.
input_str (str) – The input string.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
tags (Optional[list[str]]) – The tags.
metadata (Optional[dict[str, Any]]) – The metadata.
inputs (Optional[dict[str, Any]]) – The inputs.
kwargs (Any) – Additional keyword arguments.

Return type:

Any