Class GraphIteratorNode

scrapegraphai/nodes/graph_iterator_node.py:16–147

A node responsible for instantiating and running multiple graph instances in parallel. It creates as many graph instances as the number of elements in the input list. Attributes: verbose (bool): A flag indicating whether to show print statements during execution. Args:

class GraphIteratorNode(BaseNode):
    """
    A node responsible for instantiating and running multiple graph instances in parallel.
    It creates as many graph instances as the number of elements in the input list.

    Attributes:
        verbose (bool): A flag indicating whether to show print statements during execution.

    Args:
        input (str): Boolean expression defining the input keys needed from the state.
        output (List[str]): List of output keys to be updated in the state.
        node_config (dict): Additional configuration for the node.
        node_name (str): The unique identifier name for the node, defaulting to "Parse".
    """

    def __init__(
        self,
        input: str,
        output: List[str],
        node_config: Optional[dict] = None,
        node_name: str = "GraphIterator",
        schema: Optional[Type[BaseModel]] = None,
    ):
        super().__init__(node_name, "node", input, output, 2, node_config)

        self.verbose = (
            False if node_config is None else node_config.get("verbose", False)
        )
        self.schema = schema

    def execute(self, state: dict) -> dict:
        """
        Executes the node's logic to instantiate and run multiple graph instances in parallel.

        Args:
            state (dict): The current state of the graph. The input keys will be used to fetch
                            the correct data from the state.

        Returns:
            dict: The updated state with the output key c
            ontaining the results of the graph instances.

        Raises:
            KeyError: If the input keys are not found in the state,
            indicating that thenecessary information for running
            the graph instances is missing.
        """
        batchsize = self.node_config.get("batchsize", DEFAULT_BATCHSIZE)

        self.logger.info(
            f"--- Executing {self.node_name} Node with batchsize {batchsize} ---"
        )

        try:
            eventloop = asyncio.get_event_loop()
        except RuntimeError:
            eventloop = None