wisupai/e2m
E2M converts various file types (doc, docx, epub, html, htm, url, pdf, ppt, pptx, mp3, m4a) into Markdown. It’s easy to install, with dedicated parsers and converters, supporting custom configs. E2M offers an all-in-one, flexible, and open-source solution.
Language:Jupyter Notebook
Total stars: 766
Stars trend:
#jupyternotebook
#doc2x, #e2m, #llm, #markdown, #pdftomarkdown, #textcleaning
E2M converts various file types (doc, docx, epub, html, htm, url, pdf, ppt, pptx, mp3, m4a) into Markdown. It’s easy to install, with dedicated parsers and converters, supporting custom configs. E2M offers an all-in-one, flexible, and open-source solution.
Language:Jupyter Notebook
Total stars: 766
Stars trend:
14 Jan 2025
7pm ▉ +7
8pm ▊ +6
9pm ▊ +6
10pm ▌ +4
11pm ▍ +3
15 Jan 2025
12am █ +8
1am ▌ +4
2am ▉ +7
3am ▏ +1
4am █▌ +12
5am █▏ +9
6am █▎ +10#jupyternotebook
#doc2x, #e2m, #llm, #markdown, #pdftomarkdown, #textcleaning
opendataloader-project/opendataloader-pdf
Safe, Open, High-Performance — PDF for AI
Language:Java
Total stars: 290
Stars trend:
#java
#ai, #dataloader, #documentparser, #documentparsing, #documents, #html, #json, #markdown, #ocrrecognition, #pdf, #pdfconverter, #pdftohtml, #pdftojson, #pdftomarkdown, #recognition, #sdk, #tables
Safe, Open, High-Performance — PDF for AI
Language:Java
Total stars: 290
Stars trend:
23 Sep 2025
3pm ██▌ +20
4pm ██ +16
5pm █▋ +13
6pm █▉ +15
7pm █▍ +11
8pm █▋ +13
9pm ▉ +7#java
#ai, #dataloader, #documentparser, #documentparsing, #documents, #html, #json, #markdown, #ocrrecognition, #pdf, #pdfconverter, #pdftohtml, #pdftojson, #pdftomarkdown, #recognition, #sdk, #tables