Project Mission: The mission of this project is to create a MVP for the knowledge graph generation in order to visually see clusters of information and how they're linked. The knowledge graph will include a basic search function to query information.
Core functionality: ingesting user document(s), processing the data and extracting relationship entities through the use of LLMs, building and storing the knowledge graph, an interactive visual representation of the knowledge graph, and a basic search function for entities in the knowledge graph.
- Document upload (PDFs)
- Knowledge Graph Creation from the uploaded document
- Graph Data with nodes & edges for visualization
- Pytest
- Pytest Sugar
- FastAPI
- Docker & Docker Compose
- Python 3.11 or higher
- Make (optional for shortcuts)
-
Setup:
- Clone the repository and change into the project directory
- Copy the
.env.examplefile to.envand update the values as needed
-
Run the application:
- Create and activate a virtual environment
- Install the development requirements
- Build the Docker image and run the container with
make build-dev
For detailed instructions, see the Getting Started Guide.
- Build and run the development environment:
make build-dev - Stop the development environment:
make stop-dev - Start components separately:
make frontend-build-devormake backend-build-dev - Run backend tests:
make backend-tests - Show help:
make help
For detailed instructions, see the Shortcuts Guide.
Visual tool to generate knowledge graphs from documents, showing core concepts and their relationships.
- Drag and drop the document or click the "Browse" button to select the document from your computer.
- Click the “Generate Graph” button to create a knowledge graph from the uploaded document.
- For details see the User-Documentation