End a trace for an LLM or chat model run.
Whether to raise an error if an exception occurs.
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.
| Name | Type | Description |
|---|---|---|
example_id | UUID | str | None | Default: NoneThe example ID. |
project_name | str | None | Default: NoneThe project name. Resolved together with |
client | Client | None | Default: None |
tags | list[str] | None | Default: None |
metadata | Mapping[str, str] | None | Default: None |
address | AgentAddress | None | Default: None |
**kwargs | Any | Default: {} |
Implementation of the SharedTracer that POSTS to the LangChain endpoint.
The client.
Defaults to the global client.
The tags.
Defaults to an empty list.
Additional metadata to include if it isn't already in the run.
Defaults to None.
The agent address to send traces to instead of a project.
Agent addressing is in beta and must be enabled for the LangSmith workspace.
Additional keyword arguments.