使用Docling Graph将文档转换为经过验证的知识图谱
Convert documents into schema-enforced entities and graph relationships when the job is exact knowledge extraction rather than generic document parsing.
Prerequisites
Python 3.10+, docling-graph package, source documents supported by Docling, optional model provider credentials for remote LLM extraction
Installation
Use the upstream install or setup path that matches your environment:
- pip install docling-graph
- git clone https://github.com/1991513ccie-png/skills
- uv sync --extra dev
- uv run pre-commit run --all-files
Requirements and caveats from upstream:
-
- Python 3.10 or higher
- # Convert document from URL (each line except the last must end with )
Basic usage or getting-started notes:
- ✍🏻 Input formats: Docling’s supported inputs: PDF, images, markdown, Office, HTML, and more.
- 📐 Structured extraction: LLM output is schema-enforced by default; see CLI and API to disable.
- 🐛 Trace capture: Debug exports for extraction and fallback diagnostics.
- Source: https://github.com/1991513ccie-png/skills
- Extracted from upstream docs: https://raw.githubusercontent.com/docling-project/docling-graph/HEAD/README.md
Documentation
- https://docling-project.github.io/docling-graph/
