Based on Foxit Quick PDF Library，python interface

A simple demonstration of how you can implement retrieval augmented generation (RAG) for a book.

Document Intelligence Platform — Extract, refine, and query documents with vision LLMs and config-driven RAG.

PDF 문서에서 GPU 가속 처리로 고품질 질의응답(QA) 데이터를 자동 생성하고 LLM을 효율적으로 파인튜닝하는 솔루션입니다. Unstructured 라이브러리와 AWS Bedrock Claude로 도메인 특화 QA 쌍을 생성하고, LoRA 기법으로 경량 모델을 훈련합니다.

Converts scanned documents and ordinary documents into speech mp3 using Amazon Polly

A Telegram bot which extract Text from PDF, also extract the Images of PDF Pages. Made with Python

NLP Pdf Minning Extracting text from pdf

A resume parser that extracts key details from PDF files using Groq's LLM

CLI for merging PDF contexts.

Highlights the key matches between your Given PDF and the description text

A PDF text extractor, processor and formatter. Supports regex based exclusions and other niceties.

Tests of OCR and RAG with LLMs

An AI-powered invoice and receipt analyzer that extracts structured invoice data from images (JPG/PNG) and PDF documents using a Large Language Model (LLM).

PDF Text Finder Console App along with page number

UnchainedText: Break free from PDFs! Easily extract raw text to .txt for preprocessing.

A local, Python-based GUI toolbox for common PDF operations such as merge, split, scan, OCR, and document preprocessing. Fully offline, extensible, and open source.

GPU-accelerated batch PDF text extraction wrapper for marker-pdf on NVIDIA GraceBlackwell.

Multiple File Format (PDF/DOC/DOCX/XLSX/XLS/CSV) Text Extraction Utility Project in Java Programming Language

This repository implements an end-to-end NLP pipeline for legal documents, including OCR-based text extraction, neural language modeling from scratch (NumPy), sentence and document embeddings, extractive and abstractive summarization, grammar refinement, and semantic case similarity retrieval using cosine similarity.

NITW Chatbot is a Retrieval-Augmented Generation (RAG) based AI system that answers queries using official institutional documents. It scrapes PDFs, generates embeddings, stores them in a FAISS vector index, and retrieves relevant context for LLM-based response generation, ensuring grounded and accurate answers.