centersl/MinerU
1
0
Fork 0
mirror of https://github.com/opendatalab/MinerU.git synced 2026-03-27 11:08:32 +07:00
Code Issues Packages Projects Releases Wiki Activity

feat(pdf_parse_union_core_v2): add timing log for LLM aided processes

Browse Source 
- Add timing measurement for formula, text, and title optimization using LLM
- Log the execution time for each LLM aided process
This commit is contained in:
myhloli
2025-01-22 15:46:43 +08:00
parent c38060d5b9
commit 10e848b39d
1 changed files with 6 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
magic_pdf/pdf_parse_union_core_v2.py
View File

@@ -957,17 +957,23 @@ def pdf_parse_union(
formula_aided_config = llm_aided_config.get('formula_aided', None)
if formula_aided_config is not None:
if formula_aided_config.get('enable', False):
llm_aided_formula_start_time = time.time()
llm_aided_formula(pdf_info_dict, formula_aided_config)
logger.info(f'llm aided formula time: {round(time.time() - llm_aided_formula_start_time, 2)}')
"""文本优化"""
text_aided_config = llm_aided_config.get('text_aided', None)
if text_aided_config is not None:
if text_aided_config.get('enable', False):
llm_aided_text_start_time = time.time()
llm_aided_text(pdf_info_dict, text_aided_config)
logger.info(f'llm aided text time: {round(time.time() - llm_aided_text_start_time, 2)}')
"""标题优化"""
title_aided_config = llm_aided_config.get('title_aided', None)
if title_aided_config is not None:
if title_aided_config.get('enable', False):
llm_aided_title_start_time = time.time()
llm_aided_title(pdf_info_dict, title_aided_config)
logger.info(f'llm aided title time: {round(time.time() - llm_aided_title_start_time, 2)}')
"""dict转list"""
pdf_info_list = dict_to_list(pdf_info_dict)