An autonomous AI data science agent. Ask a question about the future, and Delphi finds the data, trains the best model, explains why, and tells you the story.
Built at WildHacks 2026 — Northwestern University
- You ask a question — "Predict diabetes risk based on patient health indicators"
- AI agent finds data — Searches Kaggle, HuggingFace, and World Bank APIs
- Databricks processes it — Spark cleaning, feature engineering, Delta Lake storage
- Model arena trains 5 models — XGBoost, LightGBM, Random Forest, Linear, SVM — tracked with MLflow
- SHAP explains — Feature importance and model explainability
- ElevenLabs narrates — A voice data story summarizes the findings
| Name | Role | Owns |
|---|---|---|
| Jose | ML Architect | Databricks, MLflow, model training, SHAP |
| ND | Backend + Agent | FastAPI, Gemini agent, dataset discovery |
| Wilson | Product + Frontend | React UI, design, video, presentation |
| Enrique | Infrastructure | DigitalOcean, ElevenLabs, deployment, PDF |
- AI Orchestration: Google Gemini API (function calling agent)
- Data Processing: Databricks Free Edition, Apache Spark, Delta Lake
- ML Tracking: MLflow 3 (experiment tracking + model registry)
- Models: scikit-learn, XGBoost, LightGBM, SHAP, Optuna
- Voice: ElevenLabs Text-to-Speech API
- Backend: FastAPI, Python
- Frontend: React, Vite, Recharts
- Hosting: DigitalOcean Droplet
- Domain: delphi.tech
# Clone
git clone https://github.com/YOUR_TEAM/Delphi.git
cd Delphi
# Backend
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
pip install -r backend/requirements.txt
pip install -r ml/requirements.txt
# Copy env file and add your keys
cp .env.example .env
# Run backend
cd backend && python -m app.main
# Frontend (separate terminal)
cd frontend
npm install
npm run devData Storytelling — Train, predict, and visualize models to predict the future.
- Google Gemini API — AI agent orchestration
- ElevenLabs — Voice narration of data stories
- DigitalOcean — Cloud hosting
- .Tech Domain — delphi.tech
#Delphi Bridging the gap of AI to a General Public.