docling-graph

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.

797 82 Python MITupdated 5 days ago

knowledge-graphs ocr

View on GitHubDispute this mapping →

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.

Mapped by ShipWithAI editors · links verified

README.md

Docling Graph

Docling-Graph turns documents into validated Pydantic objects, then builds a directed knowledge graph with explicit semantic relationships.

This transformation enables high-precision use cases in chemistry, finance, and legal domains, where AI must capture exact entity connections (compounds and reactions, instruments and dependencies, properties and measurements) rather than rely on approximate text embeddings.

This toolkit supports two extraction paths: local VLM extraction via Docling, and LLM-based extraction routed through LiteLLM for local runtimes (vLLM, Ollama) and API providers (OpenAI, Gemini, IBM watsonx, Mistral and more), all orchestrated through a flexible, config-driven pipeline.

Key Capabilities

✍🏻 Input formats: Docling’s supported inputs: PDF, images, DocLang, markdown, Office and more.
🧠 Extraction: LLM or VLM backends, with chunking and processing modes.
💎 Graphs: Pydantic to NetworkX directed graphs with stable IDs, edge and provenance metadata.
📦 Export: CSV, Cypher, and other K

Continue your stack

What teams reach for next — and why each earns a place beside docling-graph. Ranked by curator confidence.

Alternative to See all + compare →

Hyper-Extract

Knowledge-extraction CLI: LLMs turn documents into structured graphs, hypergraphs and spatio-temporal knowledge — with an MCP server for agents and Obsidian vault export.

Why it fitsBoth 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.

unstract

LLM-driven platform turning unstructured documents into structured data: a no-code Prompt Studio to define extractions, then deploy as APIs or ETL pipelines. Self-hosted, AGPL + enterprise.

Why it fitsSame starting point — unstructured documents — different deliverable: Unstract gives you structured records behind an API or ETL job, docling-graph gives you a typed graph with explicit relationships you can export as Cypher.

Built with / on

litellm

Open-source AI gateway: call 100+ LLM providers in OpenAI format via a Python SDK or self-hosted proxy — with cost tracking, virtual keys, guardrails, load balancing and logging.

Why it fitsLLM extraction is routed through LiteLLM, so the same config reaches vLLM and Ollama locally or OpenAI, Gemini, watsonx and Mistral as APIs — swap the extraction model without touching the pipeline.