langchain.agents.openai_assistant.base.OpenAIAssistantAction¶

class langchain.agents.openai_assistant.base.OpenAIAssistantAction[source]¶

Bases: AgentAction

AgentAction with info needed to submit custom tool output to existing run.

Parameters
  • tool_call_id – Tool call id.

  • run_id – Run id.

  • thread_id – Thread id

param log: str [Required]¶

Additional information to log about the action. This log can be used in a few ways. First, it can be used to audit what exactly the LLM predicted to lead to this (tool, tool_input). Second, it can be used in future iterations to show the LLMs prior thoughts. This is useful when (tool, tool_input) does not contain full information about the LLM prediction (for example, any thought before the tool/tool_input).

param run_id: str [Required]¶
param thread_id: str [Required]¶
param tool: str [Required]¶

The name of the Tool to execute.

param tool_call_id: str [Required]¶
param tool_input: Union[str, dict] [Required]¶

The input to pass in to the Tool.

param type: Literal['AgentAction'] = 'AgentAction'¶
property messages: Sequence[BaseMessage]¶

Return the messages that correspond to this action.