Firecrawl 推出开源 anydoc，以加速 AI 文档摄取

该 Rust 引擎可处理 PDF、Word 文件、幻灯片以及其他 10 种格式，并且现在为 Firecrawl 现有的 /parse 端点提供支持。

By · Published

Primary source: X

为何重要

Anydoc 将 Firecrawl 从网页提取扩展到为 RAG 和代理系统提供数据的文件。开源推动采用，而托管的 /parse 端点则承接付费工作负载。

Illustration of Firecrawl's open-source anydoc Rust engine ingesting and parsing PDFs, Word docs and slide decks into structured data.

Firecrawl, founded by Caleb Peffer (@CalebPeffer), Eric Ciarla (@ericciarla) and Nicolas Silberstein Camara (@nickscamara_), launched anydoc 在 X 的一条帖子中 on August 4th, pitching the open-source Rust engine as a faster way to turn business documents into Markdown for AI systems.…

When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.

Reader comments

Conversation for this story loads after sign-in.