openllmetry-js
OCRmyPDF
| openllmetry-js | OCRmyPDF | |
|---|---|---|
| 2 | 87 | |
| 371 | 32,049 | |
| 2.7% | 1.5% | |
| 9.0 | 8.7 | |
| 6 days ago | 8 days ago | |
| TypeScript | Python | |
| Apache License 2.0 | Mozilla Public License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
openllmetry-js
OCRmyPDF
- Llama-Scan: Convert PDFs to Text W Local LLMs
- PuTTY Has a New Website
- OCRmyPDF: The Magic Wand for Your Scanned PDFs
View the Project on GitHub
- 13 GitHub Projects that Supercharge Your AI and Development Journey 🚀
Stars: 19899 Author: ocrmypdf Star the OCRmyPDF repository⭐
- Ask HN: What is the best method for turning a scanned book as a PDF into text?
I haven’t seen anyone else mention this tool yet, but I’ve found great accuracy and flexibility with [OCRmyPDF](https://github.com/ocrmypdf/OCRmyPDF). It (usually) detects and fixes page rotation, and works quite well on slanted text or A | B pages in regards to copying and formatting. I believe it uses tesseract in the background, but using it is very simple and it has the just works factor.
- Z-Library Helps Students to Overcome Academic Poverty, Study Finds
and the good old sci-hub.
For paper management Zotero + https://github.com/ethanwillis/zotero-scihub plugin makes browsing google scholar very efficient.
Also Calibre fulltext search with OCR-ed PDFs:
https://github.com/ocrmypdf/OCRmyPDF
makes learning a concept/finding test exercises even easier.
Soon a local LLM to "RAG retrieval on my library" might be the next step.
- Llama-OCR: An Open-Source Llama 3.2 Based OCR Tool
While I'm a fan of Tika a lot of people get queasy from Java and XML, they might be better served by their preferred scripting language and https://github.com/ocrmypdf/OCRmyPDF, which has the same OCR engine.
- A return to hand-written notes by learning to read and write
I’ve been really impressed with Tesseract - I used it last month to add invisible OCR text to PDFs books I reference a lot (1). My scans are quite good, but I was still impressed with the accuracy.
I also OCRed the TOC, playing with the page segmentation setting (2) in the terminal until I got output I could copy & paste to add a navigable table of contents.
1: https://github.com/ocrmypdf/OCRmyPDF
2: https://tesseract-ocr.github.io/tessdoc/Command-Line-Usage.h..., “ Using different Page Segmentation Modes”
- TextSnatcher: Copy text from images, for the Linux Desktop
Try https://github.com/ocrmypdf/OCRmyPDF - it uses Tesseract behind the scenes and it absolutely brilliant.
- FLaNK Stack Weekly 19 Feb 2024
What are some alternatives?
ssebowa-UI - Ssebowa is an open-source generative AI platform offering free access to powerful AI models for everyone. Use 100% of revenue got from ads and apis to plant trees and give meals to children in need. Think of us as the ChatGPT4 that serves humanity!
PaddleOCR - Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
openllmetry - Open-source observability for your GenAI or LLM application, based on OpenTelemetry
tesserocr - A Python wrapper for the tesseract-ocr API
nifi - Apache NiFi
pdfplumber - Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.