init

__all__ = ['Configurable', 'GraphInputs', 'configurable_from_values', 'make_graph'] module-attribute

Configurable

Bases: TypedDict

The raw config that is passed to langgraph client.

Note: ONLY use primitive types otherwise they don't show up in langgraph studio Note: This should not be used directly by nodes. They should use FullConfig.from_run_config(config)

assistant_name instance-attribute

assistant_type instance-attribute

assistant_version instance-attribute

conversation_uid instance-attribute

conversation_version instance-attribute

running_as_subgraph instance-attribute

use_latest_assistant instance-attribute

user_id instance-attribute

GraphInputs

Bases: BaseModel

in_subgraph = False class-attribute instance-attribute

remaining_steps = -1 class-attribute instance-attribute

sub_assistant_state_datas = Field(default_factory=dict) class-attribute instance-attribute

user_input instance-attribute

configurable_from_values(assistant, user_id, conversation_id, use_latest_assistant=True)

make_graph(checkpointer=None, default_config=None, debug=False)