11. Markdown is all you need. (Mostly.) A parser can get every word on the page right and still lose ... Markdown is all you need. (Mostly.) A parser can get every word on the page right and still lose which column a number belongs to. Then your model has to guess. Markdown keeps head 10/09 00:49 ♡
12. T Today we're announcing OpenDocRouter: every model for document parsing under one API. There are ~4,... Today we're announcing OpenDocRouter: every model for document parsing under one API. There are ~4,000 OCR models on Hugging Face, and the frontier labs ship a new one nearly e 10/08 00:01 ♡
13. R Request a spot here! https://t.co/7DlvDslr49 Request a spot here! partiful.com/e/ynm6aOPAPq4Q… 💬 0 🔄 1 ❤️ 1 👀 1159 📊 1 ⚡ Powered by xgo.ing 10/07 01:12 ♡
14. The biggest night of SF Tech Week is black tie. 120+ agent founders, 50 investors, and live jazz at... The biggest night of SF Tech Week is black tie. 120+ agent founders, 50 investors, and live jazz at the Redwood Room on Friday for the Agent Economy Gala. Invite only. We're ex 10/07 01:11 ♡
15. R Read our take here: https://t.co/xJsRJx7VGL Read our take here: llamaindex.ai/blog/ocr-is-de… 💬 0 🔄 5 ❤️ 27 👀 3655 📊 11 ⚡ Powered by xgo.ing 10/06 02:48 ♡
16. OCR is dead 🪦 Long live agentic OCR! Traditional OCR makes one pass and hands back whatever text i... OCR is dead 🪦 Long live agentic OCR! Traditional OCR makes one pass and hands back whatever text it got. Tables get flattened, charts disappear, and multi-column layouts co 10/06 02:47 ♡
17. The BEA's new Q2 GDP-by-state was released, but the key data is entirely in an infographic, without ... The BEA's new Q2 GDP-by-state was released, but the key data is entirely in an infographic, without a text-layer. LlamaParse's agentic parsing tier understands documents li 10/03 01:35 ♡
18. How many people show up on a Tuesday night to talk about document processing for AI agents? 🤔 In N... How many people show up on a Tuesday night to talk about document processing for AI agents? 🤔 In New York, enough to fill the room and start a waitlist. In San Francisco, a 10/01 02:32 ♡
19. D Document parsing requires a lot of on-the-fly decision making. We explored the early approaches to ... Document parsing requires a lot of on-the-fly decision making. We explored the early approaches to Jev and Jev-like models on several documents tasks like orientation detection, la 09/29 05:00 ♡
20. Parsing forms still trips up the latest frontier VLMs. A form isn't text on a page. It's a set of f... Parsing forms still trips up the latest frontier VLMs. A form isn't text on a page. It's a set of fields, grouped into sections, each tied to a specific box. That's why 09/29 03:25 ♡
