| Name | Type | Description |
|---|---|---|
serialized* | dict[str, Any] | The serialized model. |
messages* | list[list[BaseMessage]] | The messages to start the chat with. |
run_id* | UUID | |
tags | list[str] | None | Default: None |
parent_run_id | UUID | None | Default: None |
metadata | dict[str, Any] | None | Default: None |
name | str | None | Default: None |
**kwargs | Any | Default: {} |
Start a trace for a chat model run.
Note:
Naming can be confusing here: there is on_chat_model_start, but no
corresponding on_chat_model_end callback. Chat model completion is
routed through on_llm_end / _on_llm_end, which are shared with
text LLM runs.
The run ID.
The tags for the run.
The parent run ID.
The metadata for the run.
The name of the run.
Additional arguments.