Skip to content

Installation

Get GraphAide running in minutes. Choose the method that works best for you.

System Requirements

  • Python: 3.11 or later
  • Neo4j: 4.4 or later (optional for basic usage)
  • LLM API: OpenAI, Anthropic, Google, or AWS Bedrock account

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

The fastest way to install GraphAide. We recommend uv for significantly faster dependency resolution:

uv pip install graphaide

Verify installation:

graphaide --version

Method 2: pip

Standard Python package manager approach:

pip install graphaide

Verify installation:

graphaide --version

Method 3: Using GraphAide as a Python Library

Use GraphAide programmatically in your Python code.

from graphaide import GraphAide, ModelConfig

graphaide = GraphAide(
    model_config=ModelConfig(
        provider="openai",
        model_name="gpt-5.6-luna",
        api_key="..."
    )
)

# Use GraphAide functions
result = graphaide.extract(file_path="document.pdf")

Method 4: Docker

Run GraphAide in a containerized environment with all dependencies included.

git clone https://github.com/pnnl/GraphAide.git
cd GraphAide
docker compose up

Then access the REST API at http://localhost:8000.

Method 5: Development Setup

For developers who want to contribute or modify GraphAide.

With uv (recommended): 

git clone https://github.com/pnnl/GraphAide.git
cd GraphAide
uv venv
# On macOS/Linux:
source .venv/bin/activate
# On Windows:
.venv\Scripts\activate
uv pip install -e ".[testing]"

Or with pip: 

git clone https://github.com/pnnl/GraphAide.git
cd GraphAide
pip install -e ".[testing]"

Next Steps

  1. Configure GraphAide — Set up your LLM and databases
  2. Extract Your First Knowledge Graph — Learn extraction basics
  3. Explore Examples — See what's possible

Troubleshooting

Module not found error

If you get ModuleNotFoundError: No module named 'graphgen':

# Reinstall in development mode
pip install -e .

Neo4j connection error

If GraphAide can't connect to Neo4j, check:

# Neo4j should be running on default port 7687
neo4j-shell -u neo4j -p password

LLM API errors

Ensure your API key is valid and has quota:

from graphaide import ModelConfig

config = ModelConfig(
    provider="openai",
    model_name="gpt-5.6-luna",
    api_key="sk-your-key-here"
)
# Test connection during GraphAide initialization
graphaide = GraphAide(model_config=config)

Need help? See Resources or check GitHub Issues.