Skip to main content

基于Google Gemini 2模型的高精度OCR识别

Weekly Pick

github.com

一个利用Google Gemini 2模型实现高精度OCR识别的开源项目,支持多种图片上传方式并可一键部署至Vercel。

Developer Tools & APIsOpen source#ocr#gemini-api#deployment
Visit website
基于Google Gemini 2模型的高精度OCR识别 preview

该项目基于Google Gemini 2模型开发,具有高精度的OCR识别能力。项目特点包括支持链接、拖拽和复制粘贴板上传图片,并且可以一键部署到Vercel平台。用户只需在环境变量中填写自己的Gemini API密钥即可使用。项目由Cursor编写,利用了谷歌提供的免费额度。

More in Developer Tools & APIs

SolveHub

API for CAPTCHA and anti-bot tasks in authorized testing

Dev Tools ·

liarjs.dev

Scanner that cross-checks browser JavaScript fingerprint against network layer

Dev Tools ·

AntiBrow

Antidetect browser for managing multiple browser identities with real-device

Dev Tools ·

HostlessWP

Open source CLI to move WordPress to Cloudflare Workers

Dev Tools ·

deed.page

Permanent web hosting with an API for AI agents

Dev Tools ·

Rowflare

Open-source Airtable alternative running on your Cloudflare account

Dev Tools ·