on_llm_new_token(
self,
token: str,
*,
chunk: GenerationChunk | ChatGenerationChunk | | Name | Type | Description |
|---|---|---|
token* | str | The new token. |
chunk | GenerationChunk | ChatGenerationChunk | None | Default: NoneThe new generated chunk, containing content and other information. |
run_id* | UUID | The ID of the current run. |
parent_run_id | UUID | None | Default: None |
tags | list[str] | None | Default: None |
**kwargs | Any | Default: {} |
Run on new output token. Only available when streaming is enabled.
For both chat models and non-chat models (legacy text completion LLMs).
The ID of the parent run.
The tags.
Additional keyword arguments.