Skip to main content

Run prediction functions locally in Python. Register at https://fxn.ai.

Project description

Function for Python

function logo

Dynamic JSON Badge

Run prediction functions (a.k.a "predictors") locally in your Python apps, with full GPU acceleration and zero dependencies.

[!TIP] Join our waitlist to bring your custom Python functions and run them on-device across Android, iOS, macOS, Linux, web, and Windows.

Installing Function

Function is distributed on PyPi. This distribution contains both the Python client and the command line interface (CLI). To install, open a terminal and run the following command:

# Install Function
$ pip install --upgrade fxn

[!NOTE] Function requires Python 3.10+

Retrieving your Access Key

Head over to fxn.ai to create an account by logging in. Once you do, generate an access key:

generate access key

Making a Prediction

First, create a Function client, specifying your access key:

from fxn import Function

# Create the Function client
fxn = Function(access_key="<Function access key>")

Then make a prediction:

# Create a prediction
prediction = fxn.predictions.create(
    tag="@fxn/greeting",
    inputs={ "name": "Peter" }
)
# Print the returned greeting
print(prediction.results[0])

Using the Function CLI

Open up a terminal and login to the Function CLI:

# Login to Function
$ fxn auth login <ACCESS KEY>

Then make a prediction:

# Make a prediction using the Function CLI
$ fxn predict @fxn/greeting --name Peter

Useful Links

Function is a product of NatML Inc.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

fxn-0.0.48.tar.gz (825.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

fxn-0.0.48-py3-none-any.whl (834.3 kB view details)

Uploaded Python 3

File details

Details for the file fxn-0.0.48.tar.gz.

File metadata

  • Download URL: fxn-0.0.48.tar.gz
  • Upload date:
  • Size: 825.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.12

File hashes

Hashes for fxn-0.0.48.tar.gz
Algorithm Hash digest
SHA256 5579a6252f9651b898a732612636bf6e08bd38a82ca28b2934fd05631997da9f
MD5 c3ca6674a223cacab1c455ad8e3dbc07
BLAKE2b-256 372bfa0d5da8307b58af5adaa854fc08c8dddf0f5169c04d7d2658b4faf1d8ef

See more details on using hashes here.

File details

Details for the file fxn-0.0.48-py3-none-any.whl.

File metadata

  • Download URL: fxn-0.0.48-py3-none-any.whl
  • Upload date:
  • Size: 834.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.12

File hashes

Hashes for fxn-0.0.48-py3-none-any.whl
Algorithm Hash digest
SHA256 2434af7038fea788c99a51f5ce71fdaf2fbf9e56873eeba5d58923dd8662e4b9
MD5 5b1d5e9bf04e8413768b71a27830c1f7
BLAKE2b-256 4732093eaeb32893907e7013c1e4642fea4d95a2f1a345ba0ab2589e3f9033e9

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page