Sublime

An inspiration engine for ideas

AllPeopleCollectionsArticlesAudioBooksFilesHighlightsImagesLinksNotesTextTweetsVideosSocial

Extract reliable PDF text at 1/32 GPT-4o cost using a 7B VLM (Fully open-source) Allen Institute for AI introduced an open-source OCR toolkit called olmOCR that extracts plain text from PDFs at over 3000 tokens/s for about 190 USD per million pages, or 1/32 GPT-4o cost—significant for large-scale document... See more

Rohan Paul

x.com

OCR and document analysis toolkit https://t.co/7yChPCjagz

Tom Dörr

x.com

test6

The document details an engineering order for mechanical equipment, including specifications, prices, and payment terms, related to a technical drawing project for a client.

Link

Tabula is a powerful tool I use to easily extract data from pdf for use in Excel & Google Sheets: https://t.co/UTkWPP9OJB https://t.co/luTUso7NFH

Mokaya

x.com

Using VLMs for OCR https://t.co/2UzEjX2laK

Tom Dörr

x.com

Just shipped `ai-sdk-tools/ocr` Extract structured data from invoices & receipts with one line of code. 1. Mistral OCR → check quality 2. If poor/fails → try Gemini 3. If both fail (PDFs) → extract text + LLM 4. Merge all successful... See more

Pontus Abrahamsson — oss/acc

x.com

Things you really want to avoid: 1) Having a lot of money without having time 2) Being married to someone you don't love 3) Having friends you can't be fully open with 4) Being smart without feeling mentally at... See more

Orange Book x.com

In this task Manus turned a stack of delivery bills into a well organized Excel file with custom columns, even creating individual rows for goods that were listed on a single delivery bill. Imagine doing this manually! https://t.co/II24pRa3vE

ManusAI x.com

B0DJN5MK96

Rutger Bregman's "Moral Ambition" encourages individuals to utilize their talents to address significant societal issues, highlighting the need for moral courage and inspiring action for positive change.

Link