跳过导航
Introducing Document Extraction as an MCP Server ✂️📑
0:00 / 0:28

Introducing Document Extraction as an MCP Server ✂️📑

Jerry Liu

@jerryjliu07.5万 位关注者

在 X 上查看
384 个赞下载原帖

57,827 次观看

Introducing Document Extraction as an MCP Server ✂️📑 A huge use case for AI agents is being able to extract out items from a diverse set of complex documents in a repeatable manner - whether it’s legal contracts, invoices, financial statements, passports, and more. In this case, 🚫 prompting ChatGPT/Claude is too error-prone/not systematic. 💡We’ve created a plug-and-play MCP server around our core document extraction capabilities within LlamaCloud. 1. Build an extraction agent in LlamaCloud with a standardized schema. 2. Plug it as an MCP tool within ChatGPT/Claude. 3. For your next extraction job, get the outputs in a standardized format through the tool! Huge shoutout to Tuana and Logan Markewich for working on this - this is thanks to the latest updates to our llamacloud-mcp demo repo, which supports both extraction and retrieval as MCP tools. Repo: Sign up:

12 条评论

评论来自 X (Twitter) 上的原帖

  • Jesse Jr Lim (ハゲ殿)💩 的头像

    @chairmanmao74

    Interesting but no company with sensitive IP or legal is going to want to upload files to the cloud. Would be best deployed local

    2 个赞

  • Mobile Scanner 的头像

    @scanner_mobile

    Scan any documents, convert images into text, PDF files, etc. 👍

    78 个赞

  • Tsukuyomi 的头像

    @doomgpt

    ah, the art of document extraction. like a ninja slicing through red tape. but let’s hope the AI doesn’t start extracting more than just data. can’t have it getting too clever, right?

    1 个赞

  • Nilendu Pal 的头像

    @nilendu

    What's the benefit of using the MCP server instead of making a direct API call?

    1 个赞

  • Chandre Van der Westhuizen 的头像

    @Chan_vdw

    I always see these amazing screen recordings. Any suggestions to these cool tools anyone?

    1 个赞

  • Patrick C. Callahan 的头像

    @callahan1017

    I'm excited to test this out for some of our work with clinical data. Great stuff

  • Himanshu Kumar 的头像

    @codewithimanshu

    Interesting, isn't it how AI might reshape bureaucratic processes for the better?

  • Crypto Daddy ֎ 的头像

    @cryptodaaddy

    This will be a game changer

  • Ian Nuttall 的头像

    @iannuttall

    Nice little Claude Code development kit. Lots of people have asked me about custom rules/commands for: - Code reviews - Creating code docs - Refactoring - Handing off to a new agent This has examples for all of these (link below)

    889 个赞

  • Andrej Karpathy 的头像

    @karpathy

    How to build a thriving open source community by writing code like bacteria do 🦠. Bacterial code (genomes) are: - small (each line of code costs energy) - modular (organized into groups of swappable operons) - self-contained (easily "copy paste-able" via horizontal gene transfer) If chunks of code are small, modular, self-contained and trivial to copy-and-paste, the community can thrive via horizontal gene transfer. For any function (gene) or class (operon) that you write: can you imagine someone going "yoink" without knowing the rest of your code or having to import anything new, to gain a benefit? Could your code be a trending GitHub gist? This coding style guide has allowed bacteria to colonize every ecological nook from cold to hot to acidic or alkaline in the depths of the Earth and the vacuum of space, along with an insane diversity of carbon anabolism, energy metabolism, etc. It excels at rapid prototyping but... it can't build complex life. By comparison, the eukaryotic genome is a significantly larger, more complex, organized and coupled monorepo. Significantly less inventive but necessary for complex life - for building entire organs and coordinating their activity. With our advantage of intelligent design, it should possible to take advantage of both. Build a eukaryotic monorepo backbone if you have to, but maximize bacterial DNA.

    7,749 个赞

  • Deedy 的头像

    @deedydas

    Claude Code just revealed that it's used by 115k developers and has changed 195M lines of code last week. With many assumptions, this implies a $130M ARR business with $1k+ per dev per yr. I'm not just hyping this. Claude Code Opus is a junior software engineer.

    2,157 个赞

  • Tom Dörr 的头像

    @tom_doerr

    scrape Linkedin user data and profiles

    1,434 个赞