🖥 PDF CRAFT-a python library for converting PDF (primarily scanned books) in Markdown and EPUB using local AI models and LLM to structure the contents Github
Basic possibilities
- extracting text and layout Uses the combination of Doclayout-Yolo and its own algorithms for detecting and filtering headlines, columns, footnotes and page numbers
- Local OCR Recognizes the text on the page via Onnxocr, supports acceleration on GPU (CUDA)
- Determining the order of reading With the help of LayoutReader, it builds a flow of text in the order in which it is perceived by a person
- Converting in Markdown Generates .MD with relative links to images (illustrations, tables, formulas) in the Assets folder
Installation and requirements Python ≥ 3.10 (recommended 3.10.16).
Pip Install PDF-Craft and PIP Install Onnxruntime == 1.21.0 (or Onnxruntime-GPU == 1.21.0 for CUDA).
For an EPUB conveier, you need access to the LLM service (for example, Deepseek).
🖥 PDF CRAFT-a python library for converting PDF (primarily scanned books) in Markdown and EPUB using local AI models and LLM to structure the contents Github
Basic possibilities
- extracting text and layout Uses the combination of Doclayout-Yolo and its own algorithms for detecting and filtering headlines, columns, footnotes and page numbers
- Local OCR Recognizes the text on the page via Onnxocr, supports acceleration on GPU (CUDA)
- Determining the order of reading With the help of LayoutReader, it builds a flow of text in the order in which it is perceived by a person
- Converting in Markdown Generates .MD with relative links to images (illustrations, tables, formulas) in the Assets folder
Installation and requirements Python ≥ 3.10 (recommended 3.10.16).
Pip Install PDF-Craft and PIP Install Onnxruntime == 1.21.0 (or Onnxruntime-GPU == 1.21.0 for CUDA).
For an EPUB conveier, you need access to the LLM service (for example, Deepseek).
For some time, Mr. Durov and a few dozen staffers had no fixed headquarters, but rather traveled the world, setting up shop in one city after another, he told the Journal in 2016. The company now has its operational base in Dubai, though it says it doesn’t keep servers there.Mr. Durov maintains a yearslong friendship from his VK days with actor and tech investor Jared Leto, with whom he shares an ascetic lifestyle that eschews meat and alcohol.
Telegram today rolling out an update which brings with it several new features.The update also adds interactive emoji. When you send one of the select animated emoji in chat, you can now tap on it to initiate a full screen animation. The update also adds interactive emoji. When you send one of the select animated emoji in chat, you can now tap on it to initiate a full screen animation. This is then visible to you or anyone else who's also present in chat at the moment. The animations are also accompanied by vibrations. This is then visible to you or anyone else who's also present in chat at the moment. The animations are also accompanied by vibrations.
