I just finished his first book, $100M offer. I found it underwhelming tbh despite a lot of hype online. A lot of typos, frequent self-promotions, dry info dump towards the end. The framework at the beginning is useful though. What do you think about his 2nd and 3rd books? Is it worth reading?

Interesting! What program are you using?

Wait until they ask you to verify phone number 😆

Link: www.producthunt.com/products/pho...

I'm opening 10 spots for early access. Apply here❤️: docs.google.com/forms/d/e/1F....

Apply below and I'll give you 20 free credits as a thank for your time ❤️: docs.google.com/forms/d/e/1F....

How did you find testers and friends for your app?

I'm building a website to let people quickly try various document parsers. Hope it's useful for devs building RAG pipeline. Will focus on the opensource ones first.

Fellow Nuxt dev here 🙋‍♂️

Good luck! I love your transparency here

⭐text positions = can extract bounding box coordinates up to each line of text

⭐handwriting = can extract handwritten text

⭐table = can extract tabular data into markdown table

⭐scanned = supports OCR to extract text from scanned image

⭐VLM = Just a Vision Language model, requires prompt

⭐layouts = can return coordinates of bounding boxes representing the visual layout or structure of elements on the page.

⭐equations = can detect and extract mathematical equations as LaTeX

Attributes
⭐opensource = can be self-hosted; does not rely on proprietary APIs or cloud services.

⭐images = can extract images embedded in the PDF and optionally include them in the markdown

I haven't tried all of them, so I'm not sure if the data is accurate. Feel free to point out any errors or if there's any parser I missed.

Link: www.notion.so/1eb329e9a08e...