Async invoke assistant.
ainvoke(
self,
input: dict,
config: RunnableConfig | None = None,
**kwargs: Any = {}
) -> OutputType| Name | Type | Description |
|---|---|---|
input* | dict | Runnable input dict that can have: content: User message when starting a new run. thread_id: Existing thread to use. run_id: Existing run to use. Should only be supplied when providing the tool output for a required action after an initial invocation. message_metadata: Metadata to associate with a new message. thread_metadata: Metadata to associate with new thread. Only relevant when a new thread is created. instructions: Overrides the instructions of the assistant. additional_instructions: Appends additional instructions. model: Override Assistant model for this run. tools: Override Assistant tools for this run. parallel_tool_calls: Allow Assistant to set parallel_tool_calls for this run. top_p: Override Assistant top_p for this run. temperature: Override Assistant temperature for this run. max_completion_tokens: Allow setting max_completion_tokens for this run. max_prompt_tokens: Allow setting max_prompt_tokens for this run. run_metadata: Metadata to associate with new run. |
config | RunnableConfig | None | Default: NoneRunnable config. |
kwargs | Any | Default: {}Additional arguments. |