Skip to main content

AutoFNS is a utility for automatically calling functions when interacting with the OpenAI Completions.

Project description

AutoFNS

Introduction

AutoFNS is a wrapper around OpenAI's Chat Completion API.

It allows you to define functions as you normally would, and have them be called automatically when a message containing tool calls is detected. This allows you to focus on more important things, like the logic of your application.

Note: 🧪 This is a work in progress and may not be ready for production use.

Requirements

  • python >= 3.10
  • openai

Installation

pip install autofns

Usage

from autofns import AutoFNS

FUNCTION_DEFINITIONS = [
    {
        "type": "function",
        "function": {
            "name": "get_temp_units",
            "description": "Get a list of temperature units",
        }
    },
    {
        "type": "function",
        "function": {
            "name": "get_current_temperature",
            "description": "Get the current temperature in a city",
        },
        "parameters": {
            "type": "object",
            "properties": {
                "city": {
                    "type": "string",
                    "description": "The city to get the temperature of",
                },
                "unit": {
                    "type": "string",
                    "description": "The unit to get the temperature in",
                    "enum": ["Fahrenheit", "Celsius", "Kelvin"],
                }
            },
            "required": ["city", "unit"],
        }
    },
]


def get_temp_units():
    return ["Fahrenheit", "Celsius", "Kelvin"]


def get_current_temperature(city: str, unit: str):
    return "The current temperature in {} is {} degrees {}".format(
        city, 72, unit
    )


fns = AutoFNS(
    "gpt-4-32k",
    fns_mapping={
        "get_temp_units": get_temp_units,
        "get_current_temperature": get_current_temperature
    },
    fns_definitions=FUNCTION_DEFINITIONS,
)

result = fns.create_completion(messages=[...])

You can also use the AutoFNSAsync class to use async functions:

from autofns import AutoFNSAsync

fns = AutoFNSAsync(...)

result = await fns.create_completion(messages=[...])

License

This project is licensed under the terms of the MIT license.

Contributing

Contributions are welcome! Please open an issue or a pull request.

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

autofns-0.1.7.tar.gz (4.0 kB view details)

Uploaded Source

Built Distribution

autofns-0.1.7-py3-none-any.whl (4.4 kB view details)

Uploaded Python 3

File details

Details for the file autofns-0.1.7.tar.gz.

File metadata

  • Download URL: autofns-0.1.7.tar.gz
  • Upload date:
  • Size: 4.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/4.0.2 CPython/3.11.7

File hashes

Hashes for autofns-0.1.7.tar.gz
Algorithm Hash digest
SHA256 0a7ab25a77787c4f91dab2a39844170cf9a018465f73f06f01077979eb0b9e62
MD5 432fae7ade67133eb6bf48d80f95cb7d
BLAKE2b-256 dd2ea50aa0cfadc44ab9d9c0f91fdd81801048dc2ea49a758849dfb857200303

See more details on using hashes here.

File details

Details for the file autofns-0.1.7-py3-none-any.whl.

File metadata

  • Download URL: autofns-0.1.7-py3-none-any.whl
  • Upload date:
  • Size: 4.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/4.0.2 CPython/3.11.7

File hashes

Hashes for autofns-0.1.7-py3-none-any.whl
Algorithm Hash digest
SHA256 c6f1d2a1947a35680738a2cd04a0ba2a658ccdad6bf028f6011e031bfdf0228c
MD5 b2c82b393a0097f84c0dc3269d463a09
BLAKE2b-256 3f3ed69e93849163f6239b1a0e3d7fdcf90fee136be1b80b872b5f3165a1714c

See more details on using hashes here.

Supported by

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