Update pdf_parse_union_core_v2.py

magic_pdf/pdf_parse_union_core_v2.py

@@ -6,6 +6,7 @@ from typing import List
 
 import torch
 from loguru import logger
+import configparser
 
 from magic_pdf.config.enums import SupportedPdfParseMethod
 from magic_pdf.data.dataset import Dataset, PageableData
@@ -555,6 +556,14 @@ def pdf_parse_union(config_path,local_image_dir,
 
     """初始化启动时间"""
     start_time = time.time()
+    config = configparser.ConfigParser()
+    config.read(config_path)
+    url = config.get('server', 'ocr_server')
+    client = PredictClient(url)
+    ocr_status = client.check_health()
+    if not ocr_status:
+        logger.warning(f'Health check failed. The server at "{url}" is not responding as expected.')
+        logger.info(f'Qwen ocr解析服务无法正常运行,暂不使用qwen解析表格服务')
 
     for page_id, page in enumerate(dataset):
         """debug时输出每页解析的耗时."""