pynumaflow 0.3.3

Provides the interfaces of writing Python User Defined Functions and Sinks for NumaFlow.

Python SDK for Numaflow

This SDK provides the interface for writing UDFs and UDSinks in Python.

Implement a User Defined Function (UDF)

Map

from pynumaflow.function import Messages, Message, Datum, UserDefinedFunctionServicer


def my_handler(key: str, datum: Datum) -> Messages:
    val = datum.value
    _ = datum.event_time
    _ = datum.watermark
    messages = Messages(Message.to_vtx(key, val))
    return messages


if __name__ == "__main__":
    grpc_server = UserDefinedFunctionServicer(map_handler=my_handler)
    grpc_server.start()

Reduce

import asyncio
from typing import Iterator
from pynumaflow.function import Messages, Message, Datum, Metadata, UserDefinedFunctionServicer


async def my_handler(key: str, datums: Iterator[Datum], md: Metadata) -> Messages:
    interval_window = md.interval_window
    counter = 0
    async for _ in datums:
        counter += 1
    msg = (
        f"counter:{counter} interval_window_start:{interval_window.start} "
        f"interval_window_end:{interval_window.end}"
    )
    return Messages(Message.to_vtx(key, str.encode(msg)))


if __name__ == "__main__":
    grpc_server = UserDefinedFunctionServicer(reduce_handler=my_handler)
    asyncio.run(grpc_server.start())
    asyncio.run(*grpc_server.cleanup_coroutines)

Sample Image

A sample UDF Dockerfile is provided under examples.

Implement a User Defined Sink (UDSink)

from typing import Iterator
from pynumaflow.sink import Datum, Responses, Response, UserDefinedSinkServicer


def my_handler(datums: Iterator[Datum]) -> Responses:
    responses = Responses()
    for msg in datums:
        print("User Defined Sink", msg.value.decode("utf-8"))
        responses.append(Response.as_success(msg.id))
    return responses


if __name__ == "__main__":
    grpc_server = UserDefinedSinkServicer(my_handler)
    grpc_server.start()

Sample Image

A sample UDSink Dockerfile is provided under examples.