Skip to content

Welcome to GraphAide

GraphAide Logo

GraphAide is a multi-agentic platform for building intelligent applications powered by Large Language Models (LLMs). Knowledge graph construction is one powerful example—transforming documents into queryable knowledge graphs by extracting entities and relationships. But GraphAide's capabilities extend far beyond KGs.

Whether you work with PDFs, text files, images, or web data, GraphAide can: - Extract structured information and entities from any source - Process diverse data with multiple LLM providers and models - Ground information to external knowledge bases and sources - Build intelligent workflows with minimal setup - Track data provenance and attribution throughout - Scale from single documents to large datasets

Why GraphAide?

Capability Benefit
Flexible LLM Support Use OpenAI, Anthropic, Google, AWS Bedrock, or local models—choose what works for you
Extensible Architecture Build custom agents and workflows beyond KG construction
Multi-Retriever RAG Combine multiple knowledge sources for richer, more accurate results
Any Data Source Extract from PDFs, text, images, APIs, databases, or web data
Production Ready Deploy as CLI, Docker, Python library, REST API, or embedded
Enterprise Grade Track provenance, ensure compliance, audit all operations

Quick Start

Before installing GraphAide, create an isolated environment to manage dependencies:

Option 1: Using uv (Fastest) ⚡ 

uv venv graphaide-env
# On macOS/Linux:
source graphaide-env/bin/activate
# On Windows:
graphaide-env\Scripts\activate

Option 2: Using Conda 

conda create -n graphaide python=3.12
conda activate graphaide

Basic Usage

1. Install GraphAide (latest version 0.6.6):

We recommend uv for fast, reliable installation: 

uv pip install graphaide==0.6.6

Or use pip: 

pip install graphaide==0.6.6

2. Extract knowledge graph: 

from graphaide import GraphAide, ModelConfig, get_sample_data_path

# Initialize GraphAide with your LLM
graphaide = GraphAide(
    model_config=ModelConfig(
        provider="openai", 
        model_name="gpt-5.6-luna",
        api_key="..."
    )
)

# Extract from sample document
sample_pdf = get_sample_data_path("PNNL_About.pdf")
sample_ontology = get_sample_data_path("ontology_cyber.nt")
result = graphaide.extract(file_path=sample_pdf, ontology_path=sample_ontology)
print(f"✓ Extracted {len(result.nodes)} entities, {len(result.edges)} relationships")

Use Cases

  • Knowledge Management — Build searchable knowledge graphs from company documents
  • Research Analysis — Extract and connect findings across papers and reports
  • Data Integration — Merge information from multiple sources with automatic entity linking
  • Compliance Auditing — Track relationships and dependencies with full provenance
  • Domain Expertise — Answer questions requiring reasoning across documents

What You'll Learn

Start with Installation to get GraphAide running, then explore:

  1. Configuration — Set up models, databases, and vector stores
  2. Extraction — Extract entities and relationships from documents
  3. Ontologies — Use domain knowledge to guide extraction
  4. Ingestion — Load extracted data into Neo4j
  5. Vector Stores — Enhance extraction with semantic search

Get Help

Citation

If you use GraphAide in your research, please cite:

@inproceedings{purohit2024graphaide,
  title={GraphAide: Advanced Graph-Assisted Query and Reasoning System},
  author={Purohit, Sumit and Chin, George and Mackey, Patrick S and Cottam, Joseph A},
  booktitle={2024 IEEE International Conference on Big Data (BigData)},
  pages={3485--3493},
  year={2024},
  organization={IEEE}
}

Please review the important legal documents:

Ready to build your first knowledge graph? Start with Installation.