←back to thread

Llama-OCR: Document to Markdown

(llamaocr.com)
293 points lapnect | 4 comments | 16 Nov 24 04:57 UTC | HN request time: 0.839s | source
1. AmazingTurtle ◴[16 Nov 24 08:46 UTC] No.42155326[source]▶
One can combine apache tika OCR and feed it together with the image into LLM to fix typos.
replies(1): >>42156396 #
2. cess11 ◴[16 Nov 24 13:49 UTC] No.42156396[source]▶
While I'm a fan of Tika a lot of people get queasy from Java and XML, they might be better served by their preferred scripting language and https://github.com/ocrmypdf/OCRmyPDF, which has the same OCR engine.
replies(1): >>42163052 #
3. AmazingTurtle ◴[17 Nov 24 09:28 UTC] No.42163052[source]▶
May I introduce you to `apache/tika:2.9.2.1-full` with a REST API on 9998.
replies(1): >>42163432 #
4. cess11 ◴[17 Nov 24 11:04 UTC] No.42163432{3}[source]▶
Not sure what you mean. Are they making Graal-builds you can run standalone now? I only use Tika through Maven at work, might not be up to date on what happens in the project.