Async tracer that calls listeners on run start, end, and error.
AsyncRootListenersTracer(
self,
*,
config: RunnableConfig,
on_start: AsyncListener | None,
on_end: AsyncListener | None,
on_error: AsyncListener | None
)| Name | Type | Description |
|---|---|---|
config* | RunnableConfig | The runnable config. |
on_start* | AsyncListener | None | The listener to call on run start. |
on_end* | AsyncListener | None | The listener to call on run end. |
on_error* | AsyncListener | None | The listener to call on run error |
| Name | Type |
|---|---|
| config | RunnableConfig |
| on_start | AsyncListener | None |
| on_end | AsyncListener | None |
| on_error | AsyncListener | None |
Run when the model starts running.
Run when a chat model starts running.
Run on new output token. Only available when streaming is enabled.
Run when the model ends running.
Run when LLM errors.
Run when a chain starts running.
Run when a chain ends running.
Run when chain errors.
Run when the tool starts running.
Run when the tool ends running.
Run when tool errors.
Run on an arbitrary text.
Run on a retry event.
Run on agent action.
Run on the agent end.
Run on the retriever start.
Run on the retriever end.
Run on retriever error.
Override to define a handler for custom events.
Whether to raise an error if an exception occurs.
Whether to run the callback inline.
Whether to ignore LLM callbacks.
Whether to ignore retry callbacks.
Whether to ignore chain callbacks.
Whether to ignore agent callbacks.
Whether to ignore retriever callbacks.
Whether to ignore chat model callbacks.
Ignore custom event.