docling-Studio

Chunkless RAG for AI agents, powered by Docling. Parse your PDFs, inspect every title, table and box on the page, then let any MCP client (Claude, Cursor…) read

What is docling-Studio?

Chunkless RAG for AI agents, powered by Docling. Parse your PDFs, inspect every title, table and box on the page, then let any MCP client (Claude, Cursor…) read only the sections it needs under a token budget and cite exact, server-verified passages. No chunks, no embeddings, no vector store.

Overview of docling-Studio

What it is

Docling Studio is a visual document analysis studio powered by Docling. It allows users to upload a PDF, configure the extraction pipeline, and visualize results — text, tables, images, formulas, and bounding boxes — directly from a browser.

Key features

  • Home page with quick upload and recent documents
  • PDF viewer with page navigation, bounding box overlay, and resizable results panel
  • Configurable Docling pipeline: OCR, table extraction, code/formula enrichment, picture classification & description, image generation
  • Bounding box visualization with color-coded element overlay on the PDF
  • Chunking: split extracted content into semantic chunks (hierarchical, hybrid, or page-based) with configurable token limits and inline editing
  • Ingestion pipeline: Docling → chunking → embedding → OpenSearch vector indexing (one-click from Studio)
  • Graph storage (Neo4j): full DoclingDocument tree mirrored as a graph with relations, with an in-app graph view powered by Cytoscape.js

Use cases

The tool is designed for visual document analysis, extraction, and indexing. It can be used to inspect and extract structured content from PDFs, then chunk, embed, and index into OpenSearch and Neo4j for retrieval-augmented generation (RAG) pipelines.

Getting started

One command, nothing else to install:docker run -p 3000:3000 ghcr.io/scub-france/docling-studio:latest-localOpen http://localhost:3000, upload a PDF, and get results. The first analysis takes longer as Docling downloads its ML models (~400 MB). Subsequent runs are fast.

License and pricing

License: MIT. Pricing: open source (free).

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/scub-francedocling-studio.svg)](https://yunodb.com/tools/scub-francedocling-studio?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/scub-francedocling-studio?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/scub-francedocling-studio.svg" alt="Featured on YunoDB" height="20"></a>