Activity
Stars and mentions · Last 30 days, Oct 8 – Nov 6
Top repositories
Sumanth077’s repositories ranked by new forks, as on trending.
Contributes to
Repositories outside Sumanth077’s account where Sumanth077 opened or reviewed pull requests in the past 365 days.
Who noticed Sumanth077
Everyone who starred or forked Sumanth077’s repositories since the archive began in 2011.
Notable accounts
Ordered by the stars their own repositories have received.
Biggest fans
Accounts that starred the most of these repositories.
Breakout weeks
Each repository’s best week of new stars, with the release published around it.
Achievements
Awards earned by the repositories Sumanth077 owns. Select an award to embed its badge.
No awards yet
Repositories earn awards by reaching the top three in a completed trending day or week.
A repository earns an award for finishing first, second or third in a completed trending day or week, ranked by new stars, new forks or pull request authors. Awards follow a repository through renames and transfers and count toward its current owner. Weeks run Monday to Sunday, UTC.
Mentions
给技术文档检查时效性：从 PDF 提取关键说法，再用实时网页逐条核对 来自 @Sumanth_077 的分享：先找出 PDF 里容易过期的接口、版本和模型信息，再联网核对，标记为「仍有效」「已过时」或「需复核」，并提供来源供人工判断。 github.com/Sumanth077/Hands-On-AI-Engineering/tre… 它解决什么问题 技术文档不一定整篇失效，往往只是某个 API 路径、模型名称、价格或依赖版本已经变了。作者没有让 AI 直接重写全文，而是先定位这些容易变化的说法，再逐项检查，缩小人工审查范围。 核心流程 上传 PDF 后，LandingAI 的文档提取服务 ADE 将其转为保留结构的 Markdown，并抽取版本、API、配置、弃用提示和依赖等信息。 程序去重后，把每条说法连同原句和上下文，分别交给 Parallel Decisions API。这个接口结合实时网页检索，在预设选项中作出判断，返回结论、概率和引用来源。证据不足或互相矛盾时，归入「需复核」，而不是强行判定。 按项目说明，Parallel 收到的是抽取后的说法及简短上下文，不是整份 PDF；但 PDF 本身仍需交给 ADE 解析。 演示结果 Sumanth 用一份旧 OpenAI API Beta 文档测试，抽出 12 条说法：7 条过时、1 条仍有效、4 条需复核。过时项包括旧的 Engines 路由、davinci 示例和历史价格。