Commit History

Author SHA1 Message Date
  myhloli 83f7c26fb3 refactor: enhance PPHGNetV2 architecture with new layer implementations and improve padding logic 5 months ago
  myhloli 7230bfe343 refactor: add DonutSwin model implementation and enhance character decoding logic 5 months ago
  myhloli 8f0cc14872 refactor: update OCR model configurations to use v5 and enhance language handling 5 months ago
  myhloli 4eaa85fd31 refactor: update make mode constants to improve content list handling 5 months ago
  myhloli c01b780bc5 refactor: enhance PDF classification logic and improve resource management 5 months ago
  myhloli 02898cdd81 refactor: simplify file reading function and improve input validation 5 months ago
  myhloli 7eed5ee9c8 refactor: streamline PDF parsing and enhance formula recognition handling 5 months ago
  myhloli 1be66f985a refactor: update version to 2.0.0 5 months ago
  myhloli 3ff994c45e refactor: close PDF document after processing to improve resource management 5 months ago
  myhloli ab93f856f5 refactor: add 'local' option for model source and comment out timing logs 5 months ago
  myhloli 29d262618a refactor: add method option for PDF parsing and improve resource management 5 months ago
  myhloli a2a8b459e8 refactor: update dependencies in pyproject.toml for models and pydantic 5 months ago
  myhloli c8d14789d9 refactor: fix entry point for sglang server in pyproject.toml and setup.py 5 months ago
  myhloli 53cd91033f refactor: update project configuration and dependencies in pyproject.toml and setup.py 5 months ago
  myhloli 20790663b1 refactor: enhance model downloading with logging and new entry points 5 months ago
  myhloli cacf79fa70 refactor: add models_download.py for downloading and configuring MinerU models 5 months ago
  myhloli a8747f1deb refactor: comment out warning logs for missing config values in config_reader.py 5 months ago
  myhloli 8155480433 refactor: rename environment variable from MINERU_BACKEND to MINERU_MODEL_SOURCE 5 months ago
  myhloli 284cec041a refactor: replace get_file_from_repos with auto_download_and_get_model_root_path in multiple files 5 months ago
  myhloli 57f44dd8ac refactor: update PDF library import from PyPDF2 to pypdf 5 months ago
  myhloli 983aef759b refactor: clean up code formatting in batch_analyze.py 5 months ago
  myhloli c3531d72ae refactor: update model paths and enhance RapidTableModel initialization 5 months ago
  myhloli 83b965b77e refactor: update VLM model paths to version 2.0 5 months ago
  myhloli 4359b36f90 refactor: introduce SplitFlag class and update references in para_split and vlm_magic_model 5 months ago
  myhloli a29489ef51 refactor: update config file name and enhance model path handling 5 months ago
  myhloli a149a49cde refactor: add local models directory handling and update config version 5 months ago
  Xiaomeng Zhao 14d268d8bf Merge pull request #12 from general10/refactor-mineru2 5 months ago
  Yuefeng Sun 7e20339241 feat: modify get_file_from_repos 5 months ago
  myhloli 15dd9a0ff1 refactor: reorganize config_reader imports and enhance format utilities 5 months ago
  myhloli 3eef1218e4 refactor: improve environment variable initialization and enhance GPU memory handling 5 months ago