Unlocking Visual Intelligence: Picture Annotation with Remote VLM PowerImplementing Picture Annotation using Remote Visual Language Models and Docling!6d ago6d ago
Fun project of the week, Mermaid flowcharts generator!Using a LLM to generate Mermaid flowcharts!Jul 5Jul 5
Published inGoPenAIMaximize Your Documents: Exploring the Advantages of Full OCR of PDF files and chat with your…A reflection on benfits of full text OCRization and how it becomes handy with LLM enables applications.Jul 5A response icon1Jul 5A response icon1
Published inGoPenAISmall Model, Big Impact: IBM Granite Vision Dominates Document UnderstandingA New Leader Emerges: IBM Granite Vision Excels in Document AIJun 30A response icon1Jun 30A response icon1
Published inGoPenAI⚡️ BREAKING: Docling Unlocks ASR (automatic speech recognition) Power!Breaking News: Transform Your Audio with Docling’s New ASR Capacities and use withing a RAG!Jun 25Jun 25
Published inGoPenAILocal Elasticsearch Playground: A Practical Introduction and hands-on test (and moving to a RAG…Hands-on experience to demonstrate advantages of RAG vs. classic search toolsJun 24Jun 24
Published inAI Simplified in Plain EnglishFrom Jargon to Genius: Chunking as the Key to Explainable AI GenerationBeyond the Prompt: Why Chunking is Generative AI’s Unsung HeroJun 21Jun 21
What Are Vision-Language Models (VLMs) and How Do They Work?Decoding VLMs: A Simple Explanation of Vision-Language ModelsJun 17Jun 17
Published inArtificial Intelligence in Plain EnglishChatterbox: Testing an Open-Source TTS Tool & My ImpressionsExperience generating audio from text with chatterboxJun 17Jun 17
From Speech to Text: A Guide to IBM Granite Speech for Audio TranscriptionsHarnessing IBM Granite for Accurate Audio TranscriptionJun 13Jun 13
