Docling Studio — open-source visual inspection tool for Docling pipelines
Hey everyone I built Docling Studio , an open-source visual inspection layer for Docling. The problem: if you’ve used Docling, you know the extraction engine is powerful — but validating outputs means digging through JSON and mentally mapping bounding box coordinates back to the original pages. No visual feedback loop. What Docling Studio does: Upload a PDF, configure your pipeline (OCR engine, table extraction, enrichment) Run the conversion Visually inspect every detected element — bounding boxes overlaid on original pages, element types, content preview on click Two modes: local (embedded Docling) or remote (Docling Serve) Stack: Vue 3 / TypeScript + FastAPI / Python, fully Dockerized (multi-arch), 180+ tests. Why it matters for RAG workflows: without seeing what Docling extracts, it’s
Could not retrieve the full article text.
Read on discuss.huggingface.co →discuss.huggingface.co
https://discuss.huggingface.co/t/docling-studio-open-source-visual-inspection-tool-for-docling-pipelines/174983Sign in to highlight and annotate this article
Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
versionopen-sourcefeature
7 Key Benefits of Conversational AI for Business
Every business owner knows the frustration. A potential customer messages you at 11 PM, doesn’t get a reply, and buys from someone else by morning. That’s revenue lost to silence. Conversational AI fixes this problem and about a dozen others you probably haven’t considered yet. The market agrees. The global conversational AI market is projected to reach USD 41.39 billion by 2030 , growing at a 23.7% CAGR. That kind of growth isn’t hype. It’s businesses voting with their wallets because they see real returns. Whether you run a dental clinic, a car dealership, or a boutique hotel, the benefits of conversational AI for business are hard to ignore. From slashing support costs to turning casual browsers into paying customers, AI-powered conversations are reshaping how companies interact with th
GraphQL Is the Native Language of AI Agents
Your APIs were designed for humans. That’s about to be a problem. When Facebook’s engineering team designed GraphQL in 2012, they were solving a mobile problem: REST endpoints were returning too much data over slow networks, and iOS clients were paying the cost in latency. The solution — let the client declare exactly what it needs, enforce that contract through a typed schema, and expose everything about the API through introspection — turned out to solve a different problem entirely, one Facebook couldn’t have anticipated. Twelve years later, the most constrained consumer of your API isn’t a mobile client on a 3G network. It’s an AI agent with a finite context window. The constraint is different, but the logic is identical. Every field your API returns that an agent doesn’t need is a was
I Built a CLI That Measures AI Agent Judgment Tilt Through Blind Debates
We have lots of benchmarks for AI agent correctness and capability. We have far fewer tools for measuring something subtler: when an agent reads two competent, well-argued positions on a hard topic and picks one — what pattern is driving those picks? That’s what I mean by judgment tilt — the systematic tendency to reward certain arguments over others when both sides are internally consistent and well-structured. It’s shaped by training data, RLHF tuning, and system prompt conditioning. In my early validation runs, even a vanilla model with no system prompt showed measurable tilt — on one topic, the baseline scored -0.50 on a Stability axis and -0.40 on Tradition. In those runs, the pattern only became visible once I forced blind comparisons. So I extracted the engine from an earlier projec
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
More in Releases
scan-for-secrets 0.2
Release: scan-for-secrets 0.2 CLI tool now streams results as they are found rather than waiting until the end, which is better for large directories. -d/--directory option can now be used multiple times to scan multiple directories. New -f/--file option for specifying one or more individual files to scan. New scan_directory_iter() , scan_file() and scan_file_iter() Python API functions. New -v/--verbose option which shows each directory that is being scanned.
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!