HomeProjectsBlogAbout

All Posts

  • spark (7)
  • spark-pdf (6)
  • scaledp (3)
  • object-detection (2)
  • databricks (2)
  • benchmarking (1)
  • gpu (1)
  • data-extraction (1)
  • ai (1)
  • llm (1)
  • spark-connect (1)
  • Benchmarking YOLO Models on Spark Using ScaleDP

    sparkobject-detectionbenchmarkingScaleDPGPU

    Performance benchmarking of YOLO inference on Spark using ScaleDP with CPU and GPU acceleration.

    Mykola Melnyk
    Mykola Melnyk

    Machine Learning & Data Processing Expert

    November 19, 2025
  • Running YOLO Models on Spark Using ScaleDP

    sparkobject-detectionspark-pdfScaleDP

    Inference YOLO Models in scale on Spark using ScaleDP with ONNX.

    Mykola Melnyk
    Mykola Melnyk

    Machine Learning & Data Processing Expert

    November 7, 2025
  • Read PDF files from the Databricks Unity Catalog volumes using Spark PDF Datasource

    sparkspark-pdfdatabricks

    We improved support for the Databricks by adding support for the Unity Catalog in the Spark PDF Datasource

    Mykola Melnyk
    Mykola Melnyk

    Machine Learning & Data Processing Expert

    April 15, 2025
  • Structured Data Extraction from PDFs with AI

    sparkdata-extractionAIspark-pdfScaleDPLLM

    Discover how ScaleDP and Spark-PDF simplify document processing with AI-driven structured data extraction, all powered by the scalability of Apache Spark.

    Mykola Melnyk
    Mykola Melnyk

    Machine Learning & Data Processing Expert

    Olga Druchek
    Olga Druchek

    Data / ML Engineer

    March 19, 2025
  • Spark PDF with Spark Connect

    sparkspark-pdfspark-connect

    This blog post introduces Spark PDF, a custom data source for Apache Spark that empowers users to seamlessly integrate PDF data into their Spark workflows.

    Mykola Melnyk
    Mykola Melnyk

    Machine Learning & Data Processing Expert

    March 6, 2025
Page 1 of 2Next

Document Processing Solutions

Scalable by the Spark. Process structured and unstructured data with ease.

Project
Spark PDFScaleDPPDF RedactionDe-identify
Legal
Privacy PolicyTerms of ServiceBlog
Contact Us

Wilcza 19i, lok. 2, Marki, Mazovezkie, Poland, 05-270

[email protected]
+48-790-844-156
mailMail
githubGitHub
linkedinLinkedin
© 2025
•
StabRise: Scalable AI-Powered Document Processing Solutions.