技巧精选

配对 Amazon Nova 2 Lite 与 Claude Sonnet 4.6 优化文档处理成本

Pair Nova 2 Lite with Claude for cost-optimized document processing

精选理由

用 Nova 2 Lite 做粗提取,Claude Sonnet 4.6 做精准匹配,文档数字化省心又省钱。

AI 摘要

AWS 博客展示如何用 Amazon Nova 2 Lite 和 Claude Sonnet 4.6 构建两模型管道,用于扫描文档的数字化。Nova 2 Lite 在单次调用中完成多模态提取(检测照片、提取姓名坐标、返回页面元数据)。Claude Sonnet 4.6 根据版面布局进行空间推理,将姓名和面孔匹配。该管道在 Amazon Bedrock 上运行,通过分工降低总处理成本。

图片来源 · AWS Machine Learning Blog
原文 · AWS Machine Learning Blog

Pair Nova 2 Lite with Claude for cost-optimized document processing

In this post, we show how pairing Amazon Nova 2 Lite with Anthropic’s Claude Sonnet 4.6 delivers an efficient solution for digitizing scanned documents at scale. We built a two-model pipeline on Amazon Bedrock for digitizing scanned yearbook pages. Amazon Nova 2 Lite handles native multimodal extraction in a single call: detecting photos, extracting visible names with coordinates, and returning page-level metadata. Claude Sonnet 4.6 then performs spatial reasoning to match names to faces based on page layout.