[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-73858":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":16,"stars7d":16,"stars30d":17,"stars90d":16,"forks30d":16,"starsTrendScore":16,"compositeScore":18,"rankGlobal":10,"rankLanguage":10,"license":10,"archived":19,"fork":19,"defaultBranch":20,"hasWiki":19,"hasPages":19,"topics":21,"createdAt":10,"pushedAt":10,"updatedAt":22,"readmeContent":23,"aiSummary":24,"trendingCount":16,"starSnapshotCount":16,"syncStatus":25,"lastSyncTime":26,"discoverSource":27},73858,"llama-ocr","Nutlope\u002Fllama-ocr","Nutlope","Document to Markdown OCR library with Llama 3.2 vision","https:\u002F\u002FllamaOCR.com\u002F",null,"TypeScript",2425,237,18,17,0,1,56.23,false,"main",[],"2026-06-12 04:01:12","\u003Cdiv align=\"center\">\n  \u003Cdiv>\n    \u003Ch1 align=\"center\">Llama OCR\u003C\u002Fh1>\n  \u003C\u002Fdiv>\n\t\u003Cp>An npm library to run OCR for free with Llama 3.2 Vision.\u003C\u002Fp>\n\n\u003Ca href=\"https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Fllama-ocr\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fv\u002Fllama-ocr\" alt=\"Current version\">\u003C\u002Fa>\n\n\u003C\u002Fdiv>\n\n---\n\n## Installation\n\n`npm i llama-ocr`\n\n## Usage\n\n```js\nimport { ocr } from \"llama-ocr\";\n\nconst markdown = await ocr({\n  filePath: \".\u002Ftrader-joes-receipt.jpg\", \u002F\u002F path to your image (soon PDF!)\n  apiKey: process.env.TOGETHER_API_KEY, \u002F\u002F Together AI API key\n});\n```\n## Hosted Demo\n\nWe have a hosted demo at [LlamaOCR.com](https:\u002F\u002Fllamaocr.com\u002F) where you can try it out!\n\n## How it works\n\nThis library uses the free Llama 3.2 endpoint from [Together AI](https:\u002F\u002Ftogetherai.link\u002F) to parse images and return markdown. Paid endpoints for Llama 3.2 11B and Llama 3.2 90B are also available for faster performance and higher rate limits.\n\nYou can control this with the `model` option which is set to `Llama-3.2-90B-Vision` by default but can also accept `free` or `Llama-3.2-11B-Vision`.\n\n## Roadmap\n\n- [x] Add support for local images OCR\n- [x] Add support for remote images OCR\n- [ ] Add support for single page PDFs\n- [ ] Add support for multi-page PDFs OCR (take screenshots of PDF & feed to vision model)\n- [ ] Add support for JSON output in addition to markdown\n\n## Credit\n\nThis project was inspired by [Zerox](https:\u002F\u002Fgithub.com\u002Fgetomni-ai\u002Fzerox). Go check them out!\n","Llama OCR 是一个基于 Llama 3.2 视觉模型的文档到 Markdown 的 OCR 库。其核心功能是通过 Together AI 提供的免费或付费 API 端点，将图片中的文本识别并转换为 Markdown 格式，支持本地和远程图片处理，并计划在未来增加对 PDF 文件的支持。该库采用 TypeScript 编写，易于集成至 Node.js 项目中。适用于需要快速准确地从图像中提取文本并进行格式化输出的应用场景，如文档数字化、笔记应用等。",2,"2026-06-11 03:47:41","high_star"]