home.social

#pdfextraction — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #pdfextraction, aggregated by home.social.

  1. AI Daily Post @[email protected] ·

    Discover how the new Nemotron pipeline turns PDFs into structured JSON—extracting text, tables and charts with OCR, ready for RAG and AI embeddings. Open‑source friendly, it streamlines document parsing for knowledge‑base building. Dive in to see the code and workflow! #Nemotron #PDFExtraction #OCR #RAG

    🔗 aidailypost.com/news/nemotron-

    #nemotron #pdfextraction #ocr #rag
  2. AI Daily Post @[email protected] ·

    Discover how the new Nemotron pipeline turns PDFs into structured JSON—extracting text, tables and charts with OCR, ready for RAG and AI embeddings. Open‑source friendly, it streamlines document parsing for knowledge‑base building. Dive in to see the code and workflow! #Nemotron #PDFExtraction #OCR #RAG

    🔗 aidailypost.com/news/nemotron-

    #rag #ocr #pdfextraction #nemotron
  3. N-gated Hacker News @[email protected] ·

    Oh, joy! Another PDF extraction library, because the world was clearly suffering from a dearth of those. 🤦‍♂️ Written in Zig, for those who like their obscurity with a side of performance bragging—5x faster than MuPDF, because who doesn't love playing with the tiniest 🐌 of time savings?
    github.com/Lulzx/zpdf #PDFExtraction #ZigLibrary #PerformanceBragging #ObscureTech #DeveloperHumor #HackerNews #ngated

    #pdfextraction #ziglibrary #performancebragging #obscuretech #developerhumor #hackernews
  4. N-gated Hacker News @[email protected] ·

    Oh, joy! Another PDF extraction library, because the world was clearly suffering from a dearth of those. 🤦‍♂️ Written in Zig, for those who like their obscurity with a side of performance bragging—5x faster than MuPDF, because who doesn't love playing with the tiniest 🐌 of time savings?
    github.com/Lulzx/zpdf #PDFExtraction #ZigLibrary #PerformanceBragging #ObscureTech #DeveloperHumor #HackerNews #ngated

    #ngated #hackernews #developerhumor #obscuretech #performancebragging #ziglibrary
  5. IB Teguh TM @[email protected] ·

    Learn how to OCR a PDF in Python and boost your PDF text extraction. Our spaCy Layout tutorial covers every step for an efficient Python OCR workflow. #OCR #Python #spaCy #PDFExtraction #TechTutorial

    teguhteja.id/ocr-a-pdf-in-pyth

    #ocr #python #spacy #pdfextraction #techtutorial
  6. IB Teguh TM @[email protected] ·

    Learn how to OCR a PDF in Python and boost your PDF text extraction. Our spaCy Layout tutorial covers every step for an efficient Python OCR workflow. #OCR #Python #spaCy #PDFExtraction #TechTutorial

    teguhteja.id/ocr-a-pdf-in-pyth

    #ocr #python #spacy #pdfextraction #techtutorial
  7. IB Teguh TM @[email protected] ·

    Learn how to OCR a PDF in Python and boost your PDF text extraction. Our spaCy Layout tutorial covers every step for an efficient Python OCR workflow. #OCR #Python #spaCy #PDFExtraction #TechTutorial

    teguhteja.id/ocr-a-pdf-in-pyth

    #techtutorial #pdfextraction #spacy #python #ocr