Metadata-Version: 2.4
Name: gatrag_extract
Version: 0.1.0
Summary: PDF, DOCX, and web document extraction for RAG pipelines
Author: gattupalli saketh
License: MIT
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: OS Independent
Classifier: Typing :: Typed
Requires-Python: >=3.9
Description-Content-Type: text/markdown
Requires-Dist: python-docx>=1.0
Requires-Dist: httpx>=0.25
Requires-Dist: beautifulsoup4>=4.12
Provides-Extra: pymupdf
Requires-Dist: pymupdf>=1.23; extra == "pymupdf"
Provides-Extra: pdfplumber
Requires-Dist: pdfplumber>=0.10; extra == "pdfplumber"
Provides-Extra: pypdf
Requires-Dist: pypdf>=3.0; extra == "pypdf"
Provides-Extra: pdf
Requires-Dist: pymupdf>=1.23; extra == "pdf"
Provides-Extra: all
Requires-Dist: pymupdf>=1.23; extra == "all"
Requires-Dist: pdfplumber>=0.10; extra == "all"
Requires-Dist: pypdf>=3.0; extra == "all"
Provides-Extra: dev
Requires-Dist: pytest>=7.0; extra == "dev"
Requires-Dist: pytest-cov; extra == "dev"
Requires-Dist: respx; extra == "dev"
Requires-Dist: reportlab; extra == "dev"

###gatrag Extractor###

GATRAG Extractor is a package exclusively designed for extraction of texts from PDF's,docs and HTML files for the New RAG Gramework called GATRAG,Which focuses on eliminating the hallucination part of the answers and also protects the knowledge base from bot attacts 

The extractor package is well designed for the users for ecxtractions of texts for the net part of the RAG framework ,The package automatically chooses the best PDF libraries for your files(If they are already installed in your env) and extracts the texts for next process.

The doc files extracts the data seamlessly and gets the texts extracted from the files 

The HTML extractor uses bs4 package for the extraction of data from the HTML files 


Note: User can use Pypdf's ,docx or bs4 packages seperately as well,I am publishing this packages for the convience of the users to get everthing required from one framework. 
