sieve.function

​

Overview

Functions are the fundamental building blocks on Sieve. They have a single entry point and exit point and are defined using standard Python function syntax along with a header that annotates any required dependencies.

Functions can be defined in two ways:

1. Simple functions with a single entry point
2. Class-based functions with __setup__() and __predict__() methods

The __setup__() method is run once during initialization and is typically used for heavy one-time operations, such as loading machine learning model weights into memory. The __predict__() method has the same attributes as a standard function, with a single entry point and exit point.

All code is mounted by default into /src of the container.

​

Creating Functions

Functions can be defined in two ways:

​

Simple Functions

Simple functions are defined with the @sieve.function decorator:

import sieve

@sieve.function(name="multiplier")
def multiply(x1: int, x2: int) -> int:
    return x1 * x2

​

Class-based Functions

For more complex functions that require setup or state management, you can use a class-based approach:

import sieve

@sieve.function(name="adder")
class Adder:
    def __setup__(self):
        print("setting up!")
    def __predict__(self, x1: int, x2: int) -> int:
        return x1 + x2

Note the type hints in the function’s arguments. These are not strictly required, but are recommended. Type hints are picked up by the Sieve dashboard, and are used to generate the job submission form.

​

Calling Functions

Functions already deployed on Sieve can be referenced by using

referenced_function = sieve.function.get("{username}/{function name}")

There are two options for running referenced_function on the Sieve cloud.

​

run

The .run() method blocks and waits for the function to complete, and directly returns the value returned by the function.

import sieve

mult = sieve.function.get("username/multiplier")
product1 = mult.run(2, 3)
product2 = mult.run(product1, 4)

​

push

The .push() method returns a SieveFuture object, which contains information about the job. You can later access the output using the .result() method, for example. This is useful for when you are pushing several jobs at once, like when processing frames from a video. This ensures that you are not waiting for previous frames to finish processing before pushing the next ones, and are taking full advantage of parallel processing.

import sieve

mult = sieve.function.get("username/multiplier")
multiplication_inputs = [4, 8, 15, 16, 23, 42]
multiplication_jobs = []

# send all of the jobs first
for multiplication_input in multiplication_inputs:
    multiplication_jobs.append(mult.push(2, multiplication_input))

# then, once everything is submitted, grab the results
for multiplication_job in multiplication_jobs:
    print(multiplication_job.result())

Note: SieveFuture objects don’t work with traditional concurrent.futures methods like concurrent.futures.as_completed or concurrent.futures.wait.

You can call both .run() and .push() locally, or within another Sieve function. Calling .run() or .push() within Sieve allows you to chain function calls together, enabling powerful AI applications!

​

Specifying Additional Data for Functions

By default, Sieve functions live inside Linux containers without a GPU and a limited number of python packages installed. You can use a number of key word arguments in the function decorator in order to customize the environment.

​

Using Metadata

Metadata can be used to provide additional information on the dashboard, including a full title, a description, a code reference, tags, and a readme. You can create a metadata object as follows:

metadata = sieve.Metadata(
    title="Adder",
    description="adds two numbers together",
    code_url="https://github.com/username/repo/blob/main/adder/main.py",
    image=sieve.File(
        "https://example.com/cover.gif"
    ),
    tags=["Math", "Example"],
    readme="This is an example readme",
)

Then, pass it into the decorator:

@sieve.function(
    name="adder",
    metadata=metadata
)
def adder

​

Restart Behavior

By default, when errors occur, all Sieve functions are restarted. This means that dependencies, modules, etc., are reloaded into memory, along with the __setup__() function for class-based functions. This behavior is intended as a safeguard against irreversible errors, including GPU errors and state-related errors. For production applications, you may choose to disable this so that functions don’t restart during more trivial errors, such as invalid inputs or edge cases in code. Restarting functions takes longer but guarantees a brand new state after every function error.

To disable this behavior, you can set the restart_on_error parameter in the function header as follows:

@sieve.function(
    name="adder",
    restart_on_error=False,
)
def adder

In the event that you disable this behavior by default but also do want to trigger a hard restart in certain scenarios, you can raise a sieve.FatalException.

​

sieve.FatalException

A sieve.FatalException is a special Python Exception in the Sieve ecosystem that allows you to trigger a hard restart of the function when certain irreversible errors are caught, even if the restart_on_error parameter is set to False. Here is a brief example of this in action.

import sieve

@sieve.function(
    name="multiplier",
    restart_on_error=False,
)
def multiply(x1: int, x2: int) -> int:
    if (x1 == 5):
        # This will not restart the function, and subsequent calls will happen instantaneously.
        raise ValueError("x1 is an invalid value")
    if (x2 == 10):
        # This will restart the function, which will give fresh state for the function but may take a bit more time.
        raise sieve.FatalException("x2 is an invalid value, will restart")
    return x1 * x2

​

Cuda Versions

The CUDA version can be specified with the cuda_version parameter in the function decorator. You can specify parts of versions as well (e.g. '12.2' for '12.2.2'). Possible values for cuda_version are:

'8.0'
'9.0'
'9.1'
'9.2'
'10.0'
'10.1'
'10.2'
'11.0.3'
'11.1.1'
'11.2.0'
'11.2.1'
'11.2.2'
'11.3.0'
'11.3.1'
'11.4.0'
'11.4.1'
'11.4.2'
'11.4.3'
'11.5.0'
'11.5.1'
'11.5.2'
'11.6.0'
'11.6.1'
'11.6.2'
'11.7.0'
'11.7.1'
'11.8.0'
'12.0.0'
'12.0.1'
'12.1.0'
'12.1.1'
'12.2.2'
'12.3.2'