Open-source Document Parser to Markdown with OCR/LLMs
Megaparse is a file parser optimized for LLM Ingestion. It can parse PDFs, DOCX, PPTX in a format that is ideal for LLMs. All of that accessible from a python package, an API, or a queue.
Hi everyone,
Today I’d like to introduce you to the new Quivr project. It a simple python package, API that helps you take in documents such as PDFs, Docx, PPTx, ... and turn them into Markown
It has several new abilities:
* OCR
* Vision Models
* Table Optimization in the extraction
* Open-source
You can use it in any of your products where you need to parse file to then send them to an LLM or simply store it
Here is how to get started:
* Go to https://github.com/QuivrHQ/MegaP...
* pip install megaparse
* Have fun
Give it a try! We’d love to hear your feedback and ideas in the comments.
This is part of Supabase mega Launch Week -> https://launchweek.dev/HOME
