Merge pull request #1614 from opendatalab/release-1.1.0

Release 1.1.0

magic_pdf/resources/model_config/model_configs.yaml

 weights:
   layoutlmv3: Layout/LayoutLMv3/model_final.pth
-  doclayout_yolo: Layout/YOLO/doclayout_yolo_ft.pt
+  doclayout_yolo: Layout/YOLO/doclayout_yolo_docstructbench_imgsz1280_2501.pt
   yolo_v8_mfd: MFD/YOLO/yolo_v8_ft.pt
-  unimernet_small: MFR/unimernet_small
+  unimernet_small: MFR/unimernet_small_2501
   struct_eqtable: TabRec/StructEqTable
   tablemaster: TabRec/TableMaster
   rapid_table: TabRec/RapidTable
\ No newline at end of file

projects/gradio_app/header.html

@@ -102,7 +102,7 @@
 
         <!-- Homepage Link. -->
         <span class="link-block">
-          <a href="https://mineru.org.cn/home?source=online" class="external-link button is-normal is-rounded is-dark" style="text-decoration: none; cursor: pointer">
+          <a href="https://mineru.net/home?source=online" class="external-link button is-normal is-rounded is-dark" style="text-decoration: none; cursor: pointer">
             <span class="icon" style="margin-right: 8px">
               <i class="fas fa-home" style="color: white"></i>
             </span>
@@ -112,7 +112,7 @@
 
         <!-- Client Link. -->
         <span class="link-block">
-          <a href="https://mineru.org.cn/client?source=online" class="external-link button is-normal is-rounded is-dark" style="text-decoration: none; cursor: pointer">
+          <a href="https://mineru.net/client?source=online" class="external-link button is-normal is-rounded is-dark" style="text-decoration: none; cursor: pointer">
             <span class="icon" style="margin-right: 8px">
               <i class="fas fa-download" style="color: white"></i>
             </span>

requirements.txt

@@ -5,7 +5,7 @@ fast-langdetect>=0.2.3
 loguru>=0.6.0
 numpy>=1.21.6,<2.0.0
 pydantic>=2.7.2
-PyMuPDF>=1.24.9
+PyMuPDF>=1.24.9,<=1.24.14
 scikit-learn>=1.0.2
 torch>=2.2.2
 transformers

scripts/download_models.py

@@ -16,7 +16,7 @@ def download_and_modify_json(url, local_filename, modifications):
     if os.path.exists(local_filename):
         data = json.load(open(local_filename))
         config_version = data.get('config_version', '0.0.0')
-        if config_version < '1.1.0':
+        if config_version < '1.1.1':
             data = download_json(url)
     else:
         data = download_json(url)
@@ -35,7 +35,7 @@ if __name__ == '__main__':
         "models/Layout/LayoutLMv3/*",
         "models/Layout/YOLO/*",
         "models/MFD/YOLO/*",
-        "models/MFR/unimernet_small/*",
+        "models/MFR/unimernet_small_2501/*",
         "models/TabRec/TableMaster/*",
         "models/TabRec/StructEqTable/*",
     ]

scripts/download_models_hf.py

@@ -16,7 +16,7 @@ def download_and_modify_json(url, local_filename, modifications):
     if os.path.exists(local_filename):
         data = json.load(open(local_filename))
         config_version = data.get('config_version', '0.0.0')
-        if config_version < '1.1.0':
+        if config_version < '1.1.1':
             data = download_json(url)
     else:
         data = download_json(url)
@@ -36,7 +36,7 @@ if __name__ == '__main__':
         "models/Layout/LayoutLMv3/*",
         "models/Layout/YOLO/*",
         "models/MFD/YOLO/*",
-        "models/MFR/unimernet_small/*",
+        "models/MFR/unimernet_small_2501/*",
         "models/TabRec/TableMaster/*",
         "models/TabRec/StructEqTable/*",
     ]

setup.py

@@ -48,10 +48,10 @@ if __name__ == '__main__':
                      "struct-eqtable==0.3.2",  # 表格解析
                      "einops",  # struct-eqtable依赖
                      "accelerate",  # struct-eqtable依赖
-                     "doclayout_yolo==0.0.2",  # doclayout_yolo
+                     "doclayout_yolo==0.0.2b1",  # doclayout_yolo
                      "rapidocr-paddle",  # rapidocr-paddle
                      "rapidocr_onnxruntime",
-                     "rapid_table==0.3.0",  # rapid_table
+                     "rapid_table>=1.0.3,<2.0.0",  # rapid_table
                      "PyYAML",  # yaml
                      "openai",  # openai SDK
                      "detectron2"