🖥 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).
Telegram’s stand out feature is its encryption scheme that keeps messages and media secure in transit. The scheme is known as MTProto and is based on 256-bit AES encryption, RSA encryption, and Diffie-Hellman key exchange. The result of this complicated and technical-sounding jargon? A messaging service that claims to keep your data safe.Why do we say claims? When dealing with security, you always want to leave room for scrutiny, and a few cryptography experts have criticized the system. Overall, any level of encryption is better than none, but a level of discretion should always be observed with any online connected system, even Telegram.
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.
