-
Ollama installed and running
- Download from https://ollama.ai
- Install required models (see below)
-
Docker installed and running
-
Python 3.10+ and Node.js 18+
ollama pull qwen2.5:7b-instruct
ollama pull qwen3-embedding:4bdocker-compose up -dWait ~10 seconds for Neo4j to initialize.
cd backend
pip install -r requirements.txt
cd ..cd frontend
npm install
cd ..cd backend
uvicorn main:app --reloadBackend will run on http://localhost:8000
cd frontend
npm startFrontend will run on http://localhost:3000
- Create a Project: Click "New Project" on the dashboard
- Import Documents:
- Open your project
- Click "Import Document"
- Select file and domain
- Wait for processing
- View Graph: The graph will appear automatically after import
- View Evidence: Click on nodes or edges to see source evidence
- Edit Graph: Use the edit API endpoints (or add UI controls)
- Ensure Docker is running:
docker ps - Check Neo4j logs:
docker logs ideagraph-neo4j - Verify connection:
docker exec -it ideagraph-neo4j cypher-shell -u neo4j -p ideagraph
- Verify Ollama is running:
ollama list - Test model:
ollama run qwen2.5:7b-instruct "Hello"
- Check file format is supported (PDF, DOCX, MD, TXT, TEX, JSON)
- Ensure document has digital text (no scanned PDFs)
- Check backend logs for detailed error messages
Once the backend is running, visit:
- Swagger UI: http://localhost:8000/docs
- ReDoc: http://localhost:8000/redoc
Run backend tests:
cd backend
pytest