Prompt as Function
"Don't write any code, just tell what to do!"
This is a significant milestone for Large Language Models (LLMs) and the coding process. The prompt-as library serves as a foundation for using prompts to perform tasks in Python. We are currently developing this mindset for several features in our products. With our open-source initiative <3, you can use it just like we do.
pip install prompt-as
from prompt_as import prompt_as_config, pf
prompt_as_config.OPENAI_API_KEY = "sk-**"
@pf
def sleep(second:str) -> bool:
"""
Sleeps for the given seconds and returns True.
"""
Testing and Settings
Model Settings
You can change the OpenAI model that have been used for `prompt-as`.from prompt_as import prompt_as_config, pf
prompt_as_config.OPENAI_MODEL = "gpt-4-turbo"
# Model Setting
prompt_as_config.OPENAI_API_KEY = "sk-**"
@pf
def sleep(second:str) -> bool:
"""
Sleeps for the given seconds and returns True.
"""
Testing
If you want to test this library on a large scale, you can use our test system as well.
from prompt_as import prompt_as_config, pf
prompt_as_config.OPENAI_API_KEY = "sk-**"
@pf
def sleep(second:str) -> bool:
"""
Sleeps for the given seconds and returns True.
"""
# Testing
from prompt_as import Prompt_As_Test_System
Prompt_As_Test_System(sleep_time, [(["2"], {})], [True], [False]).run_test()
# (function_name, test_args_and_kwargs, expected_outputs, bad_outputs)
Release files for prompt-as 0.2.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| prompt_as-0.2.0.tar.gz | 7.1 kB | Details |
Release files / prompt_as-0.2.0.tar.gz
| Download URL | prompt_as-0.2.0.tar.gz |
|---|---|
| Size | 7.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
2ab92a8cd5da8cbe06e8106e34c227d1bc3b330dd9e197918c82d0963d6e2c59
|
|
BLAKE2b-256 checksum How to use checksums |
011a9220ea4ca4f8f2bbf312d43b6bbfd994bd744fa0d92f98683eacbb123afb
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.1 CPython/3.8.18
|