This project provides an end-to-end pipeline to generate a dataset of (question, SPARQL query) pairs for a given Knowledge Graph (KG). The backend (Gen²KGBot) can be found at this repo.
It provides the following feature:
- KG Configuration and Pre-processing (read more).
- Competency question generator (read more).
- SPARQL query generator (read more).
- SPARQL query refinement (read more).
The following diagram shows the pipeline and how Q²Forge integrates with other systems
To run locally you need to:
- Install the dependencies: run the command:
npm run i- Start a local development server: run the command:
ng serve- Visualise the result: once the server is running, open your browser and navigate to http://localhost:4200/.
To build the project run the command:
npm run dcThis will run the following command:
ng build --base-href=/q2forge/ --deploy-url=/q2forge/ --configuration=productionwhich will compile the project and store the build artifacts in the dist/q2forge directory.
See the LICENSE file.
Yousouf TAGHZOUTI, Franck MICHEL, Tao JIANG, Louis-Félix NOTHIAS, Fabien GANDON (2025). Q²Forge. https://github.com/Wimmics/q2forge
