Skip to main content

This python library is useful to perform serveral functions needed to structure unstructured text,

Project description

Pasqui

Pasqui is a Python library created in Google Colab. It is useful to perform serveral functions needed to structure unstructured text. It was created based on my dissertation work at University of Cambridge with the support of chatGPT and Gemini for coding. Pasqui is designed to handly large amounts of long files, and gracefully deal with errors avoiding repeated processing. It works with both pdfs and docs.

###It has 4 functions.

  • pasqui_conveting -> converts pdfs and docs into texts and moves them to a new folder.
  • pasqui_embedding -> creates embeddings using cosine similarity.
  • pasqui_summarising -> creates summaries based on customisable topics.
  • pasqui_structuring -> creates structured data from unstructured text.

Pasqui requires kor package knowledge and google drive.

Installation

pip install pasqui

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

pasqui-0.1.0.tar.gz (8.0 kB view details)

Uploaded Source

Built Distribution

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

pasqui-0.1.0-py3-none-any.whl (9.3 kB view details)

Uploaded Python 3

File details

Details for the file pasqui-0.1.0.tar.gz.

File metadata

  • Download URL: pasqui-0.1.0.tar.gz
  • Upload date:
  • Size: 8.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.11

File hashes

Hashes for pasqui-0.1.0.tar.gz
Algorithm Hash digest
SHA256 3b78ce6dd77fe75494693c0ab4763e612dd257addb23e840528cf106abad7d72
MD5 19ffdf05f9a551c34c772ae67fde16d7
BLAKE2b-256 181424ab2ef19d3f58ae3436916083ff37be24c2ac732d156c92af2d35079e9d

See more details on using hashes here.

File details

Details for the file pasqui-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: pasqui-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 9.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.11

File hashes

Hashes for pasqui-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 9a9a6af9f33af9a56fac9bfbc86b7aabda9cf1bf4796d391f9d1b79db8fd18ae
MD5 bec115497d2458e7a7ec8d9a6ab80c52
BLAKE2b-256 f0ee6b6e61ebdfd4710d220b26dd1a164ca31e049ac8e167600f10949a4bd8b8

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