Start a trace for an LLM run.
on_chat_model_start(
self,
serialized: dict[str, Any],
messages: list[list[BaseMessage]],
*,
run_id: UUID,
tags: list[str] | None = None,
parent_run_id: UUID | None = None,
metadata: dict[str, Any] | None = None,
name: str | None = None,
**kwargs: Any = {}
) -> Run| Name | Type | Description |
|---|---|---|
serialized* | dict[str, Any] | The serialized model. |
messages* | list[list[BaseMessage]] | The messages to start the chat with. |
run_id* | UUID | The run ID. |
tags | list[str] | None | Default: NoneThe tags for the run. |
parent_run_id | UUID | None | Default: NoneThe parent run ID. |
metadata | dict[str, Any] | None | Default: NoneThe metadata for the run. |
name | str | None | Default: NoneThe name of the run. |
**kwargs | Any | Default: {}Additional arguments. |