mineru 2.5.0__py3-none-any.whl → 2.5.2__py3-none-any.whl

mineru/backend/vlm/vlm_analyze.py

@@ -14,6 +14,7 @@ from ...utils.model_utils import get_vram
 from ...utils.models_download_utils import auto_download_and_get_model_root_path
 
 from mineru_vl_utils import MinerUClient
+from packaging import version
 
 
 class ModelSingleton:
@@ -52,7 +53,6 @@ class ModelSingleton:
                     except ImportError:
                         raise ImportError("Please install transformers to use the transformers backend.")
 
-                    from packaging import version
                     if version.parse(transformers_version) >= version.parse("4.56.0"):
                         dtype_key = "dtype"
                     else:
@@ -88,24 +88,32 @@ class ModelSingleton:
                 elif backend == "vllm-engine":
                     try:
                         import vllm
+                        vllm_version = vllm.__version__
+                        from mineru_vl_utils import MinerULogitsProcessor
                     except ImportError:
                         raise ImportError("Please install vllm to use the vllm-engine backend.")
                     if "gpu_memory_utilization" not in kwargs:
                         kwargs["gpu_memory_utilization"] = 0.5
                     if "model" not in kwargs:
                         kwargs["model"] = model_path
+                    if version.parse(vllm_version) >= version.parse("0.10.1") and "logits_processors" not in kwargs:
+                        kwargs["logits_processors"] = [MinerULogitsProcessor]
                     # 使用kwargs为 vllm初始化参数
                     vllm_llm = vllm.LLM(**kwargs)
                 elif backend == "vllm-async-engine":
                     try:
                         from vllm.engine.arg_utils import AsyncEngineArgs
                         from vllm.v1.engine.async_llm import AsyncLLM
+                        from vllm import __version__ as vllm_version
+                        from mineru_vl_utils import MinerULogitsProcessor
                     except ImportError:
                         raise ImportError("Please install vllm to use the vllm-async-engine backend.")
                     if "gpu_memory_utilization" not in kwargs:
                         kwargs["gpu_memory_utilization"] = 0.5
                     if "model" not in kwargs:
                         kwargs["model"] = model_path
+                    if version.parse(vllm_version) >= version.parse("0.10.1") and "logits_processors" not in kwargs:
+                        kwargs["logits_processors"] = [MinerULogitsProcessor]
                     # 使用kwargs为 vllm初始化参数
                     vllm_async_llm = AsyncLLM.from_engine_args(AsyncEngineArgs(**kwargs))
             self._models[key] = MinerUClient(

mineru/backend/vlm/vlm_middle_json_mkcontent.py

@@ -54,7 +54,7 @@ def mk_blocks_to_markdown(para_blocks, make_mode, formula_enable, table_enable,
         elif para_type == BlockType.LIST:
             for block in para_block['blocks']:
                 item_text = merge_para_with_text(block, formula_enable=formula_enable, img_buket_path=img_buket_path)
-                para_text += f"{item_text}\n"
+                para_text += f"{item_text}  \n"
         elif para_type == BlockType.TITLE:
             title_level = get_title_level(para_block)
             para_text = f'{"#" * title_level} {merge_para_with_text(para_block)}'

mineru/model/vlm_vllm_model/server.py

@@ -1,7 +1,10 @@
 import sys
 
 from mineru.utils.models_download_utils import auto_download_and_get_model_root_path
+
 from vllm.entrypoints.cli.main import main as vllm_main
+from vllm import __version__ as vllm_version
+from packaging import version
 
 
 def main():
@@ -9,6 +12,7 @@ def main():
 
     has_port_arg = False
     has_gpu_memory_utilization_arg = False
+    has_logits_processors_arg = False
     model_path = None
     model_arg_indices = []
 
@@ -18,6 +22,8 @@ def main():
             has_port_arg = True
         if arg == "--gpu-memory-utilization" or arg.startswith("--gpu-memory-utilization="):
             has_gpu_memory_utilization_arg = True
+        if arg == "--logits-processors" or arg.startswith("--logits-processors="):
+            has_logits_processors_arg = True
         if arg == "--model":
             if i + 1 < len(args):
                 model_path = args[i + 1]
@@ -38,6 +44,8 @@ def main():
         args.extend(["--gpu-memory-utilization", "0.5"])
     if not model_path:
         model_path = auto_download_and_get_model_root_path("/", "vlm")
+    if not has_logits_processors_arg and version.parse(vllm_version) >= version.parse("0.10.1"):
+        args.extend(["--logits-processors", "mineru_vl_utils:MinerULogitsProcessor"])
 
     # 重构参数，将模型路径作为位置参数
     sys.argv = [sys.argv[0]] + ["serve", model_path] + args

mineru/version.py

@@ -1 +1 @@
-__version__ = "2.5.0"
+__version__ = "2.5.2"

{mineru-2.5.0.dist-info → mineru-2.5.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mineru
-Version: 2.5.0
+Version: 2.5.2
 Summary: A practical tool for converting PDF to Markdown
 License: AGPL-3.0
 Project-URL: homepage, https://mineru.net/
@@ -37,7 +37,7 @@ Requires-Dist: scikit-image<1.0.0,>=0.25.0
 Requires-Dist: openai<2,>=1.70.0
 Requires-Dist: beautifulsoup4<5,>=4.13.5
 Requires-Dist: magika<0.7.0,>=0.6.2
-Requires-Dist: mineru-vl-utils<1,>=0.1.6
+Requires-Dist: mineru-vl-utils<1,>=0.1.7
 Provides-Extra: test
 Requires-Dist: mineru[core]; extra == "test"
 Requires-Dist: pytest; extra == "test"
@@ -127,7 +127,7 @@ Dynamic: license-file
 
 # Changelog
 
-- 2025/09/19 2.5.0 Released
+- 2025/09/19 2.5.2 Released
 
   We are officially releasing MinerU2.5, currently the most powerful multimodal large model for document parsing.
   With only 1.2B parameters, MinerU2.5's accuracy on the OmniDocBench benchmark comprehensively surpasses top-tier multimodal models like Gemini 2.5 Pro, GPT-4o, and Qwen2.5-VL-72B. It also significantly outperforms leading specialized models such as dots.ocr, MonkeyOCR, and PP-StructureV3.

{mineru-2.5.0.dist-info → mineru-2.5.2.dist-info}/RECORD

@@ -1,5 +1,5 @@
 mineru/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
-mineru/version.py,sha256=fMbNgIJqxiZEaSBLadLBt4rZpCHqarzb4Okt-aWsp2E,22
+mineru/version.py,sha256=V-NiKyTdzd5WY2b4iSwaM1JcbOEyZ0IH2WQKBnjN2DI,22
 mineru/backend/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
 mineru/backend/pipeline/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
 mineru/backend/pipeline/batch_analyze.py,sha256=rp9nHYmuBBytlJIc3oRwqTtgFd5mhRak5UMhQ4mu02Y,21896
@@ -12,9 +12,9 @@ mineru/backend/pipeline/pipeline_magic_model.py,sha256=w8jGx8f6yZN0Wf2yPP3L9rYKc
 mineru/backend/pipeline/pipeline_middle_json_mkcontent.py,sha256=xWWOFmYL6hB8PLrxQFyRJ72dAmTIDHtqiWV-WFUfR44,14081
 mineru/backend/vlm/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
 mineru/backend/vlm/model_output_to_middle_json.py,sha256=e4Yc98_Cth2cjVPybPGehD5cpjGcTka4D2qKKrP_qqo,5121
-mineru/backend/vlm/vlm_analyze.py,sha256=Li5peZS4YTYl7WI0Zcz2v_wPcHSCsZnYSI-_lZZOsOo,7639
+mineru/backend/vlm/vlm_analyze.py,sha256=jR5DTHT0qtOLVos5-qSGPvlRCdYREoAshFej98FY5ao,8282
 mineru/backend/vlm/vlm_magic_model.py,sha256=o1WKwgArV0f4lp7ufmSq9zRZaM5bnfOdx1AQtKnosro,16379
-mineru/backend/vlm/vlm_middle_json_mkcontent.py,sha256=DX2TRpfSIqpuhWqou5QXNtCW40ddQi0kdQxXi4QgzKs,13375
+mineru/backend/vlm/vlm_middle_json_mkcontent.py,sha256=Ie95XpwTgi7EmidcwE_scvXMRQjE2xASU_Rm_F8EP-I,13377
 mineru/cli/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
 mineru/cli/client.py,sha256=uo7db9Wqj1Mc11MYuaM-bi54BfKKU3SFB9Urc8md5X4,6641
 mineru/cli/common.py,sha256=yJPdrwSYVidl2hTJ2Hn2YhnfH97GJ-QZi20dGFz7h5c,14025
@@ -143,7 +143,7 @@ mineru/model/table/rec/unet_table/utils.py,sha256=CYAqJW0wePJk4NAemb8W203N7E32v0
 mineru/model/table/rec/unet_table/utils_table_line_rec.py,sha256=zrCdPwI4M8nu0FEfd7lRJAe0z8kYq3KFbzwElM82USE,11174
 mineru/model/table/rec/unet_table/utils_table_recover.py,sha256=XksJsY82ZS0kqUnNT-jvaYzxJ3V3svMSzj0puwIau1k,10651
 mineru/model/vlm_vllm_model/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-mineru/model/vlm_vllm_model/server.py,sha256=TLgiScQCTfuY3g5mkI43I_uxuSJJ2ItC19HDeypB7jI,1578
+mineru/model/vlm_vllm_model/server.py,sha256=v07x1esggP7Wbw0r8NeAbqG2kuJN9x5Xl2CmE2x0qzk,2003
 mineru/resources/header.html,sha256=NO8ZZdCYLqu_E72AtNcuRnA2NbFBamScjjGhtg9PKiM,4409
 mineru/resources/fasttext-langdetect/lid.176.ftz,sha256=jzRyz-hzintgmejpmcPL-uDc0VaWqsfXc4qAOdtgPoM,938013
 mineru/utils/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
@@ -172,9 +172,9 @@ mineru/utils/run_async.py,sha256=rPeP4BCZerR8VByRDhiYzfZiahLVqoZEBVAS54dAjNg,128
 mineru/utils/span_block_fix.py,sha256=0eVQjJCrT03woRt9hoh6Uu42Tp1dacfGTv2x3B9qq94,8797
 mineru/utils/span_pre_proc.py,sha256=h41q2uQajI0xQbc_30hqaju1dv3oVYxBAlKgURl8HIc,13692
 mineru/utils/table_merge.py,sha256=zYUpYLrfhBCnbHCYZi6rG8-s38NDnTbiNTObvLdYwJk,11494
-mineru-2.5.0.dist-info/licenses/LICENSE.md,sha256=jVa0BUaKrRH4erV2P5AeJ24I2WRv9chIGxditreJ6e0,34524
-mineru-2.5.0.dist-info/METADATA,sha256=m404n7vO2GrWJbpksXY_tMCKxbjAux71JRg2tby2Gw0,64460
-mineru-2.5.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-mineru-2.5.0.dist-info/entry_points.txt,sha256=luXmbhPiZK_tKlRgWuYOaW_V6EFpG-yJcAevVv9MEqE,252
-mineru-2.5.0.dist-info/top_level.txt,sha256=zuGQfZcbsHv4I4oKI9gaKPqEWBFm6xJroKuug2LnKP8,7
-mineru-2.5.0.dist-info/RECORD,,
+mineru-2.5.2.dist-info/licenses/LICENSE.md,sha256=jVa0BUaKrRH4erV2P5AeJ24I2WRv9chIGxditreJ6e0,34524
+mineru-2.5.2.dist-info/METADATA,sha256=TlgabU5BQLlL7bZ9LqeMhW2fWvA14NmubtgTVrul94k,64460
+mineru-2.5.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+mineru-2.5.2.dist-info/entry_points.txt,sha256=luXmbhPiZK_tKlRgWuYOaW_V6EFpG-yJcAevVv9MEqE,252
+mineru-2.5.2.dist-info/top_level.txt,sha256=zuGQfZcbsHv4I4oKI9gaKPqEWBFm6xJroKuug2LnKP8,7
+mineru-2.5.2.dist-info/RECORD,,