HugeGraph-AI

hugegraph-ai provides Python clients for HugeGraph, graph machine learning tools, and LLM tools for knowledge graph construction and GraphRAG applications.

Apache License 2.0 · Ask DeepWiki

Modules

• hugegraph-llm: knowledge graph construction, GraphRAG, and natural-language graph queries.
• hugegraph-ml: reads graph data from HugeGraph and runs graph learning models.
• hugegraph-python-client: a Python SDK for managing schemas and graph data and running Gremlin queries.
• vermeer-python-client: a Python SDK for the Vermeer graph computing service.

The repository uses a uv workspace to manage the LLM and Python client packages. HugeGraph-ML is a path dependency rather than a workspace member.

Requirements

• HugeGraph-LLM: Python 3.10 or 3.11
• HugeGraph-ML and the Python clients: Python 3.10 or later
• uv 0.7 or later
• HugeGraph Server 1.5 or later

Deploy with Docker Compose

The repository includes a Compose file that starts both HugeGraph Server and the RAG service:

1git clone https://github.com/apache/hugegraph-ai.git
2cd hugegraph-ai
3cp docker/env.template docker/.env
4# Edit docker/.env and set PROJECT_PATH to the absolute path of this repository
5touch hugegraph-llm/.env
6cd docker
7docker compose -f docker-compose-network.yml up -d

Default addresses:

• HugeGraph Server: http://localhost:8080
• RAG service and Web UI: http://localhost:8001

Start the RAG Service from Source

1git clone https://github.com/apache/hugegraph-ai.git
2cd hugegraph-ai
3uv sync --extra llm
4source .venv/bin/activate
5cd hugegraph-llm
6python -m hugegraph_llm.demo.rag_demo.app

uv sync creates .venv at the repository root. Do not create a separate environment under hugegraph-llm, because doing so can bypass the dependencies locked by the workspace.

Install ML Dependencies

1cd hugegraph-ai
2uv sync --extra ml
3source .venv/bin/activate
4cd hugegraph-ml/src

Example scripts are under hugegraph-ml/src/hugegraph_ml/examples/.

Next Steps

• HugeGraph-LLM
• Configuration reference
• REST API
• HugeGraph-ML
• Python client