docling-graph 1.3.0

A tool to convert documents into knowledge graphs using Docling.

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 (Mistral, OpenAI, Gemini, IBM WatsonX), all orchestrated through a flexible, config-driven pipeline.

Key Capabilities

• ✍🏻 Input Formats: All inputs go through Docling for conversion (PDF, Office, HTML, images, markdown, etc.); DoclingDocument JSON skips conversion.

• 🧠 Data Extraction: Extract structured data using VLM or LLM. Supports intelligent chunking and flexible processing modes.

• 💎 Graph Construction: Convert validated Pydantic models into NetworkX directed graphs with semantic relationships and stable node IDs, and rich edge metadata.

• 📦 Export: Save graphs in multiple KG databases compatible formats like CSV, and Cypher for bulk import.

• 🔍 Visualization: Explore graphs with interactive HTML pages, and detailed Markdown reports.

Latest Changes

• 🪜 Multi-pass Extraction - Experimental: Use extraction_contract="delta" or extraction_contract="staged".

  • Delta extraction for long documents: chunk → token-batched LLM calls → normalize → merge → project to template.
  • Staged extraction for complex nested templates: Catalog → ID pass (skeleton) → Fill pass (bottom-up) → Merge.

• 📐 Structured Extraction: LLM extraction now uses API schema-enforced output by default (response_format=json_schema via LiteLLM). Disable with structured_output=False (API) or --no-schema-enforced-llm (CLI) to fall back to the legacy prompt-schema mode if your LLM provider doesn’t support it.

• ✨ LiteLLM abstraction: Unified interface to local and remote LLM providers (vLLM, Mistral, OpenAI, WatsonX, etc.) via LiteLLM, offering improved support and greater flexibility.

• 🐛 Trace Capture: Comprehensive debug data via event-based trace_data exports with diagnostics for extraction, staged passes, fallback behavior, and more.

Coming Soon

• 🧩 Interactive Template Builder: Guided workflows for building Pydantic templates.

• 🧲 Ontology-Based Templates: Match content to the best Pydantic template using semantic similarity.

• 💾 Graph Database Integration: Export data straight into Neo4j, ArangoDB, and similar databases.

Quick Start

Requirements

• Python 3.10 or higher
• uv package manager

Installation

# Clone the repository
git clone https://github.com/IBM/docling-graph
cd docling-graph

# Install with uv
uv sync                    # Core + LiteLLM + VLM

For detailed installation instructions, see Installation Guide.

API Key Setup (Remote Inference)

export OPENAI_API_KEY="..."        # OpenAI
export MISTRAL_API_KEY="..."       # Mistral
export GEMINI_API_KEY="..."        # Google Gemini

# IBM WatsonX
export WATSONX_API_KEY="..."       # IBM WatsonX API Key
export WATSONX_PROJECT_ID="..."    # IBM WatsonX Project ID
export WATSONX_URL="..."           # IBM WatsonX URL (optional)

Basic Usage

CLI

# Initialize configuration
uv run docling-graph init

# Convert document from URL (each line except the last must end with \)
uv run docling-graph convert "https://arxiv.org/pdf/2207.02720" \
    --template "docs.examples.templates.rheology_research.ScholarlyRheologyPaper" \
    --processing-mode "many-to-one" \
    --extraction-contract "staged" \
    --debug

# Visualize results
uv run docling-graph inspect outputs

Python API - Default Behavior

from docling_graph import run_pipeline, PipelineContext
from docs.examples.templates.rheology_research import ScholarlyRheologyPaper

# Create configuration
config = {
    "source": "https://arxiv.org/pdf/2207.02720",
    "template": ScholarlyRheologyPaper,
    "backend": "llm",
    "inference": "remote",
    "processing_mode": "many-to-one",
    "extraction_contract": "staged",  # robust for smaller models
    "provider_override": "mistral",
    "model_override": "mistral-medium-latest",
    "structured_output": True,  # default
    "use_chunking": True,
}

# Run pipeline - returns data directly, no files written to disk
context: PipelineContext = run_pipeline(config)

# Access results
graph = context.knowledge_graph
models = context.extracted_models
metadata = context.graph_metadata

print(f"Extracted {len(models)} model(s)")
print(f"Graph: {graph.number_of_nodes()} nodes, {graph.number_of_edges()} edges")

For debugging, use --debug with the CLI to save intermediate artifacts to disk; see Trace Data & Debugging. For more examples, see Examples.

Pydantic Templates

Templates define both the extraction schema and the resulting graph structure.

from pydantic import BaseModel, Field
from docling_graph.utils import edge

class Person(BaseModel):
    """Person entity with stable ID."""
    model_config = {
        'is_entity': True,
        'graph_id_fields': ['last_name', 'date_of_birth']
    }
    
    first_name: str = Field(description="Person's first name")
    last_name: str = Field(description="Person's last name")
    date_of_birth: str = Field(description="Date of birth (YYYY-MM-DD)")

class Organization(BaseModel):
    """Organization entity."""
    model_config = {'is_entity': True}
    
    name: str = Field(description="Organization name")
    employees: list[Person] = edge("EMPLOYS", description="List of employees")

For complete guidance, see:

• Schema Definition Guide
• Template Basics
• Example Templates

Documentation

Comprehensive documentation can be found on Docling Graph's Page.

Documentation Structure

The documentation follows the docling-graph pipeline stages:

1. Introduction - Overview and core concepts
2. Installation - Setup and environment configuration
3. Schema Definition - Creating Pydantic templates
4. Pipeline Configuration - Configuring the extraction pipeline
5. Extraction Process - Document conversion and extraction
6. Graph Management - Exporting and visualizing graphs
7. CLI Reference - Command-line interface guide
8. Python API - Programmatic usage
9. Examples - Working code examples
10. Advanced Topics - Performance, testing, error handling
11. API Reference - Detailed API documentation
12. Community - Contributing and development guide

Contributing

We welcome contributions! Please see:

• Contributing Guidelines - How to contribute
• Development Guide - Development setup
• GitHub Workflow - Branch strategy and CI/CD

Development Setup

# Clone and setup
git clone https://github.com/IBM/docling-graph
cd docling-graph

# Install with dev dependencies
uv sync --extra dev

# Run Execute pre-commit checks
uv run pre-commit run --all-files

License

MIT License - see LICENSE for details.

Acknowledgments

• Powered by Docling for advanced document processing
• Uses Pydantic for data validation
• Graph generation powered by NetworkX
• Visualizations powered by Cytoscape.js
• CLI powered by Typer and Rich

IBM ❤️ Open Source AI

Docling Graph has been brought to you by IBM.