Docling Graph turns documents into queryable knowledge graphs using Pydantic
techNmak · x · 2026-08-19
Docling Graph converts PDFs, scans, Markdown, and Office files into typed knowledge graphs where entities and relationships are validated, queryable, and traceable to the source.
The Problem
- Standard document extraction yields text or chunks, which works for search but fails when you need structured data about relationships (e.g., who works for which organization, which measurement belongs to which experiment).
How It Works
- Uses Pydantic models as the extraction schema.
- You define entities, fields, identity rules, and relationships, which directly structure the resulting directed graph.
- Fields like employees: list[Person] = edge("EMPLOYS") become explicit graph edges rather than inferences drawn from nearby text.
Related event: IBM Open-Sources Docling-Graph to Turn Documents into Knowledge Graphs(3 posts)→
More from Infra
- Qwen 3.8 in 4-bit hits 25 tok/s on an M3 Max — fully usable locally — AIandDesign · 2026-08-19
- Building Real Offline AI: Local Agent with Cognitive Loops — HotEstablishment7184 · 2026-08-19
- OpenAI uses ~20% compute for inference during training — eliebakouch · 2026-08-19
- Vercel KMS Lets You Sign JWTs Without Managing Private Keys — cramforce · 2026-08-19
- Ling-3.0-tiny Runs 128K Context on $249 8GB Orin Nano — Puzzleheaded_Base302 · 2026-08-19
- Apple's Foundation Model Framework: Hybrid AI Routing with Dynamic Profiles — Scobleizer · 2026-08-19