* add conversion from pdf to latex-like (.mmd) format with nougat

* change vector_db_manager.py to handle .mmd
* add "conversion" tab
* add math mode checkbox in maintab
This commit is contained in:
Crizomb 2024-04-18 08:00:03 +02:00
parent 356f72fedc
commit 11b92baaa8
17 changed files with 247 additions and 33 deletions

16
backend/pdf_to_mmd.py Normal file
View file

@ -0,0 +1,16 @@
import subprocess
def pdf_to_mmd(path_input: str):
"""
Convert a PDF file to MMD format using the Nougat library
https://github.com/facebookresearch/nougat
stream stderr to the front end
"""
output_dir = "../documents/mmds"
command = ['nougat', path_input, "-o", output_dir]
subprocess.run(command)