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 character

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 = character.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 word

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 = word.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 sentence

sentence = "Natalia sold clips to 48 of her friends in April, and then she sold half as many clips in May."
sentence_tool = sentence.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-0.1.6.tar.gz (14.3 kB view details)

Uploaded Source

Built Distribution

promptcraft-0.1.6-py3-none-any.whl (14.9 kB view details)

Uploaded Python 3

File details

Details for the file promptcraft-0.1.6.tar.gz.

File metadata

  • Download URL: promptcraft-0.1.6.tar.gz
  • Upload date:
  • Size: 14.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.9

File hashes

Hashes for promptcraft-0.1.6.tar.gz
Algorithm Hash digest
SHA256 2dc35ed09bd682a10e9266ab2576a618ca4dabb7f685ae982e1d63fff461d4df
MD5 1def52067d2aa9b0e2d77146fe8d9302
BLAKE2b-256 4c28e2be003dfe802776d1be1a5e6ca8504389f1d85046f220999a043fac0ef9

See more details on using hashes here.

File details

Details for the file promptcraft-0.1.6-py3-none-any.whl.

File metadata

  • Download URL: promptcraft-0.1.6-py3-none-any.whl
  • Upload date:
  • Size: 14.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.9

File hashes

Hashes for promptcraft-0.1.6-py3-none-any.whl
Algorithm Hash digest
SHA256 7661a21a43f743f0d6cb1b6c712471ec409de965cb3bf226732204d3b36c012a
MD5 65db1d2906ce1f23b5e9491f69c52db0
BLAKE2b-256 5f1e762375dd31ecc3a18fa0318bd4b73a5d96e0c54027bc02517b49d8596316

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