IntelAI

Persona-Aware AI Analytics & RAG Copilot — 9-persona, role-scoped copilot with GraphRAG-lite retrieval, ML forecasting, bilingual (EN/FR) UI, and board-ready exports.

Live demo: https://intelai.ysiddo-ai-projects.app · password-less role login (DEMO_MODE). First request may take ~60 s to wake the on-demand backend.

Self-hosting: see SELF_HOSTING.md.

Features

Architecture

React + Vite (Recharts · TanStack Query · i18n)   → Vercel / Netlify
        │  HTTP / WebSocket  /api/v1/*
FastAPI  (src/api/server.py)
  auth · chat (9 personas) · KPIs · insights · forecasting · admin
        │
   PostgreSQL (Neon)          LLM  (Groq / Anthropic via LiteLLM)
   KPIs · auth · sessions ·   GraphRAG-lite · hybrid retrieval
   vectors (pgvector opt-in)  BGE reranker · BM25

Quickstart

Prerequisites: Python 3.11, Node 18+, Postgres URL, GROQ_API_KEY.

git clone https://github.com/Yacine-ai-tech/IntelAI.git
cd IntelAI
cp .env.example .env   # fill POSTGRES_URL, GROQ_API_KEY, SECRET_KEY

# Backend (port 8000 — tables & seed created automatically)
pip install -r requirements.txt
python main.py

# Frontend (port 5173, proxies /api → :8000)
cd frontend && npm install && npm run dev

Default login: admin / admin123 — change after first login.

Docker:

docker compose -f docker-compose.dev.yml up --build   # app only (uses .env DB)
docker compose up --build                              # app + bundled Postgres

Configuration (.env)

Key API Endpoints

/health  ·  /api/docs
POST /api/v1/auth/login   GET /api/v1/auth/me
POST /api/v1/chat         WS  /api/v1/ws/chat      GET /api/v1/personas
GET  /api/v1/kpis[/periods|/metrics|/categories]
GET  /api/v1/insights/{health,risk,summary,anomalies}
POST /api/v1/forecast      GET /api/v1/glossary
POST /api/v1/data/export   POST /api/v1/ingest/{metrics,csv,document}
GET  /api/v1/admin/{users,roles,audit,scenario}

Full interactive reference at /api/docs.

Tests

pytest tests/ -q                  # all in-process (no live server needed)
pytest tests/test_smoke.py -q     # 5 smoke checks (zero deps)
pytest tests/test_api.py -q       # 30+ auth/RBAC/endpoint checks
pytest tests/test_chat.py -q      # chat endpoint + answer-block assertions

DB-dependent tests run automatically when POSTGRES_URL is reachable and skip cleanly otherwise — CI is green without a database.

Benchmarking Scenarios (Research & Evaluation)

IntelAI provides seven seeded deterministic environments for evaluating RAG retrieval accuracy and forecasting models under structural stress. These scenarios are selectable via the Admin → Scenarios tab or API (POST /api/v1/admin/scenario):

Deploy

IntelAI deploys as one cloud service (render.yaml included). Connect the repo on Render, set the env vars above, and attach a Postgres add-on. Deploy the frontend separately on Vercel with VITE_API_BASE_URL pointing to the Render service URL.

License

AGPL-3.0 — see LICENSE.

⚖️ License & Enterprise Use (Dual-License)

This project is open-source under the AGPL-3.0 License. It is completely free for researchers, students, and open-source hobbyists.

Commercial Use: The AGPLv3 license requires that any proprietary network service (SaaS, internal corporate tools) that uses or modifies this code must also open-source its entire backend.

If you wish to use this framework in a closed-source commercial environment, or require Enterprise features (SSO, Active Directory, Custom VPC Deployment, Strict RBAC), you must obtain a Commercial License. Please reach out to discuss commercial licensing and integration consulting.

📡 Anonymous Telemetry

This project collects anonymous, GDPR-compliant startup pings to help the author understand usage volume and prioritize development.

• What is collected: Only the project name and a "startup" event timestamp. No PII, no API keys, no user data.
• How to disable: We respect your privacy. To opt-out, simply set TELEMETRY_OPT_OUT=true in your .env file.