Commit History

Author SHA1 Message Date
  myhloli e17ca99350 refactor: rename vertical text threshold constant for clarity in span_block_fix.py 4 months ago
  myhloli 1c491e7d36 refactor: rename vertical text thresholds for clarity in span_block_fix.py 4 months ago
  Xiaomeng Zhao e56eec0d78 Update mineru/utils/span_block_fix.py 4 months ago
  Xiaomeng Zhao 0508df994a Update mineru/utils/span_block_fix.py 4 months ago
  myhloli 18691cfde2 refactor: enhance span merging logic for vertical text blocks in span_block_fix.py and ocr_utils.py 4 months ago
  myhloli a2f0099c1c refactor: adjust minimum confidence threshold and enhance merging logic in ocr_utils.py 4 months ago
  myhloli 7d8f68cbb9 refactor: improve overlap handling by removing smaller blocks in block_pre_proc.py and pipeline_magic_model.py 4 months ago
  myhloli 6094699cdf refactor: enhance overlap handling in pipeline_magic_model.py for image and table bodies 4 months ago
  myhloli f2666385b6 refactor: remove unused title merging logic in model_json_to_middle_json.py 4 months ago
  myhloli df15393cac refactor: optimize overlap detection logic in block_pre_proc.py for efficiency 4 months ago
  myhloli cd78980cef refactor: update comments in block_pre_proc.py for clarity and accuracy 4 months ago
  myhloli 20bfa58b41 fix: correct typos in parameter names in fast_api.py for consistency 4 months ago
  myhloli dec4fdef70 fix: update sglang version constraint in pyproject.toml for compatibility 5 months ago
  myhloli 9a16d3c74f feat: add server name and port options to Gradio app for enhanced configuration 5 months ago
  myhloli b78551af7c fix: update error messages in fast_api.py for improved clarity and consistency 5 months ago
  myhloli 54cf49dfc9 fix: update output file documentation for mineru command and enhance content descriptions in output_file_en_us.md and output_file_zh_cn.md 5 months ago
  myhloli 1b6e5e89f1 fix: update FAQ entries for installation issues and error resolutions in FAQ_en_us.md and FAQ_zh_cn.md 5 months ago
  myhloli 46bfb77488 fix: add content existence checks for inline and interline equations in pipeline_middle_json_mkcontent.py 5 months ago
  myhloli 07eeda1037 fix: standardize variable naming and improve interface visibility logic in gradio_app.py 5 months ago
  myhloli 5d4263d4ad fix: standardize variable naming and improve interface visibility logic in gradio_app.py 5 months ago
  myhloli 67715001cf fix: update environment variable names for formula and table enable in common.py and vlm_middle_json_mkcontent.py 5 months ago
  myhloli 804a3cd6ef fix: standardize parameter names for formula enable and table enable in fast_api.py 5 months ago
  myhloli 677a301a9f fix: standardize parameter names for formula and table options across modules 5 months ago
  myhloli 05c6f0b152 fix: improve block filtering and cleanup in para_split.py 5 months ago
  myhloli fefe2d36d4 fix: remove unnecessary fields from block data in para_split.py 5 months ago
  myhloli 7c95c62d8e fix: change default value for torch compile option and clean up code 5 months ago
  myhloli 89107628cb fix: update memory fraction handling in SgLang engine initialization 5 months ago
  myhloli 06db3d173b feat: enhance title block processing with average height calculation and padding for OCR 5 months ago
  myhloli 35cb414f1c feat: integrate LLM optimization for title enhancement in PDF processing 5 months ago
  myhloli 2b17dee136 fix: extend OCR text conditions for category assignment in batch analysis 5 months ago