Firecrawl Open Source AnyDoc: Office Document Conversion to Markdown Takes Only 4.4 Milliseconds
2026-08-07 14:18:00
According to CoinMeta, AnyDoc, which is open-sourced by Firecrawl, is a document parsing library written in Rust. It is capable of directly converting files such as Word, PPT, Excel, and PDF into a format suitable for large models to read, namely Markdown. Based on self-tests, the median time taken to convert a single document using AnyDoc is 4.4 milliseconds, whereas Microsoft's Markitdown takes 134.8 milliseconds, which is about 31 times slower. The second-fastest option, Mammoth, also requires 52.5 milliseconds. In terms of quality scoring, AnyDoc received a score of 81, Markitdown scored 65, and Docling scored 57.
Source:Internet
This content is for market information only and does not constitute investment advice.
Follow HKWDB official accounts to stay updated
Hot Articles
Refresh

Web3: Circle obtains New York trust license, expanding USDC custody business.
07-31 22:04

Tesla reportedly plans to divest its China business to pave the way for integration with SpaceX.
07-31 21:54

web3: Foreign media: RWA perpetual contracts may expand faster than tokenization
07-31 21:24

Web3: Foreign media: Analysts say the real catalyst for XRP is not the Clarity Act.
07-31 20:55

Foreign media: Trump's children's accounts are unlikely to replace comprehensive family financial planning
07-31 20:24

