Skip to main content

PromptCraft: A Prompt Perturbation Toolkit for Prompt Robustness Analysis

Project description

PromptCraft

A Prompt Perturbation Toolkit for Prompt Robustness Analysis

Code License License Python 3.9+

Table of Contents

Installation

pip install promptcraft

Character Editing

from promptcraft import CharacterPerturb

sentence = "Natalia sold clips to 48 of her friends in April, and then she sold half as many clips in May."
level = 0.25  # Number of characters that will be edited
character_tool = CharacterPerturb(sentence=sentence, level=level)

Character Replacement

char_replace = character_tool.character_replacement()

Character Deletion

char_delete = character_tool.character_deletion()

Character Insertion

char_insert = character_tool.character_insertion()

Character Swap

char_swap = character_tool.character_swap()

Keyboard Typos

char_keyboard = character_tool.keyboard_typos()

Optical Character Recognition

char_ocr = character_tool.optical_character_recognition()

Word Manipulation

from promptcraft import WordPerturb

sentence = "Natalia sold clips to 48 of her friends in April, and then she sold half as many clips in May."
level = 0.25  # Number of words that will be manipulated
word_tool = WordPerturb(sentence=sentence, level=level)

Synonym Replacement

word_synonym = word_tool.synonym_replacement()

Word Insertion

word_insert = word_tool.word_insertion()

Word Swap

word_swap = word_tool.word_swap()

Word Deletion

word_delete = word_tool.word_deletion()

Insert Punctuation

word_punctuation = word_tool.insert_punctuation()

Word Split

word_split = word_tool.word_split()

Sentence Paraphrasing

from promptcraft import SentencePerturb

sentence = "Natalia sold clips to 48 of her friends in April, and then she sold half as many clips in May."
sentence_tool = SentencePerturb(sentence=sentence)

Back Translation by Hugging Face

back_trans_hf = sentence_tool.back_translation_hugging_face()

Back Translation by Google Translator

back_trans_google = sentence_tool.back_translation_google()

Paraphrasing

sen_paraphrase = sentence_tool.paraphrase()

Formal Style

sen_formal = sentence_tool.formal()

Casual Style

sen_casual = sentence_tool.casual()

Passive Style

sen_passive = sentence_tool.passive()

Active Style

sen_active = sentence_tool.active()

Structure of the code

At the root of the project, you will see:

.
├── LICENSE
├── README.md
├── __init__.py
├── character.py
├── parrot.py
├── sentence.py
├── setup.py
├── styleformer.py
└── word.py

Acknowledgement

This work was finished during my 2023 fall semester research rotation at the Dependable Computing Laboratory, Department of Electrical and Computer Engineering, Boston University, under the supervision of Prof. Wenchao Li.

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

promptcraft-0.1.3.tar.gz (3.7 kB view details)

Uploaded Source

Built Distribution

promptcraft-0.1.3-py3-none-any.whl (3.5 kB view details)

Uploaded Python 3

File details

Details for the file promptcraft-0.1.3.tar.gz.

File metadata

  • Download URL: promptcraft-0.1.3.tar.gz
  • Upload date:
  • Size: 3.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.9

File hashes

Hashes for promptcraft-0.1.3.tar.gz
Algorithm Hash digest
SHA256 10aaae16a8040e2d92073551035967d91cdfcb34590c2aadca247546c1ddb4de
MD5 ae312a85e165d4f626abd6d879fdf9ad
BLAKE2b-256 ab10c7ce91c2a5efb25730ae47dba2d2d4d58ba449657dcd801c6f264416df8e

See more details on using hashes here.

File details

Details for the file promptcraft-0.1.3-py3-none-any.whl.

File metadata

  • Download URL: promptcraft-0.1.3-py3-none-any.whl
  • Upload date:
  • Size: 3.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.9

File hashes

Hashes for promptcraft-0.1.3-py3-none-any.whl
Algorithm Hash digest
SHA256 7c22f3c2bf6d55454b81d768988353e41b3d1c9fd98037924d18b648c325a78e
MD5 3d3aa1615de4f96cc786139e1a35367f
BLAKE2b-256 fedba417a5053e6e78d9389950c6114b61f26e19c857fc276e93800862347a41

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