Popular GitHub Repositories for Text Extraction

Module for automatic summarization of text documents and HTML pages.

Entity Disambiguation as text extraction (ACL 2022)

Conversion of PDF documents to structured Markdown, optimized for Retrieval Augmented Generation (RAG) and other NLP tasks. Extract text, tables, and images with preserved formatting for enhanced information retrieval and processing.

The Doc Intelligence in-a-Box project leverages Azure AI Document Intelligence to extract data from PDF forms and store the data in a Azure Cosmos DB. This solution, part of the AI-in-a-Box framework by Microsoft Customer Engineers and Architects, ensures quality, efficiency, and rapid deployment of AI and ML solutions across various industries.

? Python Package to reconstruct the original continuous text from PDFs with language models

? Model Context Protocol (MCP) tool for parsing websites using the Jina.ai Reader

Python scripts that converts PDF files to text, splits them into chunks, and stores their vector representations using GPT4All embeddings in a Chroma DB. It also provides a script to query the Chroma DB for similarity search based on user input.

OCR feito em C# para recogni??o e extra??o de texto em pdfs, imagens, documentos word, planilhas, txt e de prints do clipboard.

Extract text from a YouTube video in a single command, using OpenAi's Whisper speech recognition model.

Extract vectors by setences and words with one layer or concat more layers

RAG with LM studio, local LLMs, Scientific PDF text extraction,

? Tool to transform files & dirs into structured prompts for LLMs. ? Generates file maps + extracts text. ? Copies to clipboard. macOS-ready with Automator support!

This assistant tool (WIP) will help you search, browse and summarize the answers to your questions from your uploaded PDF using advanced text analytics, semantic search and Large Language Model (LLM)

Solution for SemEval-2025 Task 9: The Food Hazard Detection Challenge. Utilized machine learning, fine-tuned LLMs (GPT-2, LLaMA, Flan-T5-XL), and ensemble learning to classify food hazards and detect specific products and hazards from unstructured text.

A complete Python pipeline that automates the creation of structured datasets from natural language search queries. This tool searches the web for content matching your query, scrapes and cleans the content, and outputs a structured dataset in multiple formats.

Snip2Text is a user-friendly application designed to help users capture specific areas of their screen, extract text from the selected region using Optical Character Recognition (OCR), and optionally analyze the extracted text using Claude, an AI-powered tool.

Presenting, Cubastion's HR chatbot - it can answer queries based on all the latest HR documents published by Cubastion's HR team. This conveniently saves time, allowing a Cubastion employee to resolve their query without having to comb through the actual documents. <<Developed with Python, sentence-transformers, Pinecone, llama3.2, and Streamlit>>

An interactive insurance policy query-answering notebook with a Retrieval-Augmented Generation (RAG) pipeline with semantic search, caching, and GPT-based response generation.