StackMap
Subscribe

docling-graph vs Hyper-Extract

Documents to validated knowledge graphs: Docling parses, an LLM or VLM fills Pydantic schemas, and you get a directed NetworkX graph with provenance, Cypher/CSV export and HTML views. — versus — Knowledge-extraction CLI: LLMs turn documents into structured graphs, hypergraphs and spatio-temporal knowledge — with an MCP server for agents and Obsidian vault export.

The curated verdict

Both turn documents into graphs with an LLM in the loop. hyper-extract emits hypergraphs and spatio-temporal knowledge with an MCP server for agents; docling-graph insists on validated Pydantic types and per-element provenance for high-precision domains.

docling-graphHyper-Extract
Stars7973.3k
Forks82396
LanguagePythonPython
LicenseMITNOASSERTION
Last activity5 days ago12 days ago
Topicsknowledge-graphs, ocrknowledge-graphs, rag
Curated connections38

docling-graph — the curator's take

Built for the domains where an approximate embedding is worthless — chemistry, finance, legal — because what you need is the exact edge between a compound and a reaction or an instrument and its dependency. Pydantic schemas make extraction validated rather than hopeful, template generation bootstraps those schemas from example documents or an OWL/RDFS ontology, the provenance ledger carries bounding-box geometry with no extra LLM calls, and graph fusion merges multiple graphs deterministically. Under the Linux Foundation AI & Data umbrella with the Docling project's engineering behind it. Caveats: you own the schema design, which is the actual work; VLM extraction needs the heavy `vlm` extra plus local GPU or a served model; and the output is a NetworkX graph you export, not a queryable graph database.

Hyper-Extract — the curator's take

The pitch beyond ordinary KG extraction is the hypergraph: relations that connect MORE than two entities survive instead of being flattened into pairwise triples. One command per document, query the abstracts over MCP from Claude Desktop or your IDE, export to Obsidian wikilinks. NOT a graph database (it extracts, storage stays simple) and no standard license resolution at review time — verify before building on it; extraction quality tracks the LLM you plug in.