Show HN: LLM-aided OCR – Correcting Tesseract OCR errors with LLMs(github.com)

439 points by eigenvalue 2 years ago | 155 comments

GitHub repository for LLM-aided OCR, a Python tool that corrects Tesseract OCR output from scanned PDFs using multi-stage LLM prompts and outputs markdown.

Show HN: Ocrbase – pdf → .md/.json document OCR and structured extraction API(github.com)

80 points by adammajcher 9 months ago | 29 comments

Verifiable science on modified PCR machine(github.com)

45 points by kotaKat 1 year ago | 15 comments

Show HN: I built an offline, open‑source desktop Pixel Art Editor in Python(github.com)

183 points by danterolle 1 year ago | 55 comments

GLM-OCR – A multimodal OCR model for complex document understanding(github.com)

285 points by ms7892 8 months ago | 73 comments

Qwen3-Omni: Native Omni AI model for text, image and video(github.com)

527 points by meetpateltech 1 year ago | 133 comments

GitHub repository for Qwen3-Omni, Alibaba Cloud's natively end-to-end omni-modal LLM that understands text, audio, images and video and generates real-time speech.

UnoDOS(github.com)

15 points by nicoloren 26 days ago | 11 comments

GitHub repository for UnoDOS, a hobby operating system under active development targeting pc64 x86-64/UEFI, with Amiga and Apple II directories.

Show HN: We open sourced our entire text-to-SQL product(github.com)

437 points by aazo11 2 years ago | 140 comments

GitHub repository for Dataherald, an open-sourced natural-language-to-SQL engine using LLM agents, with admin console, enterprise backend, and Slackbot services.

PrivateGPT(github.com)

392 points by antouank 3 years ago | 97 comments

GitHub repository for privateGPT, an open-source tool for querying your own documents with GPT-style LLMs locally and privately without data leaks.

FastUI: Build Better UIs Faster(github.com)

319 points by realsarm 2 years ago | 149 comments

GitHub repository for FastUI by Pydantic, a library for building web user interfaces declaratively in Python with React rendering.

Sj.h: A tiny little JSON parsing library in ~150 lines of C99(github.com)

445 points by simonpure 1 year ago | 218 comments

GitHub repository for sj.h, a tiny single-header JSON parsing library written in about 150 lines of C99 by rxi.

GridFTP: A Brief History of Fast File Transfer (2024)(globus.org)

3 points by QuantumNomad_ 6 days ago | 0 comments

Globus blog post recounting the history of GridFTP, a protocol for high-speed bulk file transfer used in scientific and grid computing.