Ask a question to get started
Enter to sendā¢Shift+Enter new line
on_llm_new_token( self, token: str | list[str | dict[str
token
str | list[str | dict[str, Any]]
The token, or a list of content blocks for structured output.
chunk
GenerationChunk | ChatGenerationChunk | None
None
run_id
UUID
parent_run_id
UUID | None
**kwargs
Any
{}
Run on new LLM token.
Only available when streaming is enabled.
The chunk.
The run ID.
The parent run ID.
Additional arguments.
