apunkt/PageIndex
1
0
Fork 0
mirror of https://github.com/VectifyAI/PageIndex.git synced 2026-05-28 19:05:29 +02:00
Code Issues Projects Releases Packages Wiki Activity

Merge pull request #3 from rejojer/feat/fix

Browse source 
Feat/fix
This commit is contained in:
Mingtian Zhang 2025-04-06 19:32:13 +08:00 • committed by GitHub
commit 6d06d0786e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 72 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

17
page_index.py
View file

@ -2,13 +2,10 @@ import os
import json
import copy
import math
import sys
import random
sys.path.append('../..')
import re
from utils import *
import os
from types import SimpleNamespace as config
from concurrent.futures import ThreadPoolExecutor, as_completed
import argparse
@ -1033,16 +1030,26 @@ def page_index_main(doc, opt=None):
if opt.if_add_doc_description == 'yes':
doc_description = generate_doc_description(structure, model=opt.model)
return {
'doc_name': os.path.basename(doc),
'doc_name': get_pdf_name(doc),
'doc_description': doc_description,
'structure': structure,
}
return {
'doc_name': os.path.basename(doc),
'doc_name': get_pdf_name(doc),
'structure': structure,
}
def page_index(doc, model=None, toc_check_page_num=None, max_page_num_each_node=None, max_token_num_each_node=None,
f_add_node_id=None, if_add_node_summary=None, if_add_doc_description=None):
user_opt = {
arg: value for arg, value in locals().items()
if arg != "doc" and value is not None
}
opt = ConfigLoader().load(user_opt)
return page_index_main(doc, opt)
if __name__ == "__main__":
# Set up argument parser