langchain_community.agent_toolkits.openapi.planner
.create_openapi_agent¶
- langchain_community.agent_toolkits.openapi.planner.create_openapi_agent(api_spec: ReducedOpenAPISpec, requests_wrapper: TextRequestsWrapper, llm: BaseLanguageModel, shared_memory: Optional[Any] = None, callback_manager: Optional[BaseCallbackManager] = None, verbose: bool = True, agent_executor_kwargs: Optional[Dict[str, Any]] = None, allow_dangerous_requests: bool = False, **kwargs: Any) Any [source]¶
Construct an OpenAI API planner and controller for a given spec.
Inject credentials via requests_wrapper.
We use a top-level “orchestrator” agent to invoke the planner and controller, rather than a top-level planner that invokes a controller with its plan. This is to keep the planner simple.
You need to set allow_dangerous_requests to True to use Agent with BaseRequestsTool. Requests can be dangerous and can lead to security vulnerabilities. For example, users can ask a server to make a request to an internal server. It’s recommended to use requests through a proxy server and avoid accepting inputs from untrusted sources without proper sandboxing. Please see: https://python.langchain.com/docs/security for further security information.
- Parameters
api_spec (ReducedOpenAPISpec) –
requests_wrapper (TextRequestsWrapper) –
llm (BaseLanguageModel) –
shared_memory (Optional[Any]) –
callback_manager (Optional[BaseCallbackManager]) –
verbose (bool) –
agent_executor_kwargs (Optional[Dict[str, Any]]) –
allow_dangerous_requests (bool) –
kwargs (Any) –
- Return type
Any