Commit History

Автор SHA1 Съобщение Дата
  myhloli 6bfc17119d refactor(pdf_parse): comment out performance measurement and logging преди 9 месеца
  myhloli e516cf535c feat(performance): add performance monitoring and optimization преди 9 месеца
  myhloli 6ec440d6f1 feat(pdf_parse): implement multi-threaded page processing преди 9 месеца
  myhloli 0a246f0f40 refactor(magic_pdf): simplify device selection in model initialization преди 9 месеца
  myhloli 9b00f988ac refactor(magic_pdf): remove bfloat16 support checks and usage преди 9 месеца
  myhloli 30bd3a83c7 fix(pdf_parse): Fixed the issue where some headings were missing in certain complex layouts. преди 9 месеца
  myhloli 5561ac9555 fix(pdf_parse): improve image processing and OCR accuracy преди 10 месеца
  myhloli 9f18ca2019 feat(pdf_parse): improve OCR processing and contrast filtering преди 10 месеца
  myhloli 10e848b39d feat(pdf_parse_union_core_v2): add timing log for LLM aided processes преди 10 месеца
  myhloli 1d08865f4a refactor(pdf_parse): uncomment char bbox validation logic преди 10 месеца
  myhloli ba6c17a9d9 feat(pdf_parse): remove tilted lines for better text extraction преди 10 месеца
  myhloli 8570e006f8 refactor(magic_pdf): improve title block merging logic преди 10 месеца
  Xiaomeng Zhao 206fcb3900 Merge pull request #1537 from myhloli/doclayoutyolo-fix преди 10 месеца
  myhloli c20e9a1e84 feat(layout): improve title block handling and layout detection преди 10 месеца
  Xiaomeng Zhao 9f12c39817 Update pdf_parse_union_core_v2.py преди 10 месеца
  myhloli aaff1a2616 fix(llm_aided): add enable flag check for LLM aided optimizations преди 11 месеца
  myhloli 3f93b895bc feat(pdf_parse): add internal block sorting for images and tables преди 11 месеца
  myhloli 6b55fcfd43 fix(pdf_parse): ensure block bounding boxes do not have negative values преди 11 месеца
  Xiaomeng Zhao 8a0aa7a479 Merge branch 'dev' into dev преди 11 месеца
  myhloli 9951a17026 style(pdf_parse_union_core_v2): remove unnecessary spaces and improve code formatting- Remove extra space in conditional statement for character spacing logic преди 11 месеца
  myhloli c93950dc5d refactor(pdf_parse): improve character spacing handling in PDF text extraction преди 11 месеца
  myhloli 7c5cdcd4d7 refactor(pdf_parse): improve character spacing handling in PDF text extraction преди 11 месеца
  myhloli 2684e7753b fix(npu): correct module name for NPU operations преди 11 месеца
  myhloli 50f4841716 refactor(device): optimize memory cleaning and device selection преди 11 месеца
  myhloli 7990e7dfbb feat(model): add npu support and optimize table model преди 11 месеца
  myhloli 0a468eca6e feat(llm_aided): add title optimization feature преди 11 месеца
  Xiaomeng Zhao da3257a631 Merge pull request #1352 from myhloli/add-llm-aided преди 11 месеца
  myhloli c660fdc8f0 feat(llm): add LLM-aided formula and text correction преди 11 месеца
  myhloli 15e876677d refactor(pre_proc): improve character overlap handling in spans преди 11 месеца
  myhloli 2f4d4b0c80 feat(pre_proc): add function to remove overlapping characters in spans преди 11 месеца