Transform unstructured industrial documents into actionable, AI-driven intelligence β in real-time.
Industrial plants generate enormous volumes of unstructured data β equipment manuals, P&IDs (Piping & Instrumentation Diagrams), SCADA telemetry logs, maintenance records, compliance reports, and safety SOPs. Plant engineers currently spend 60%+ of their time manually searching through scattered documents to find answers during critical operations.
IntelliPlant solves this by creating a unified AI-powered knowledge layer that ingests all facility documentation, builds an intelligent vector index, and provides instant, citation-backed answers through a natural language AI Copilot β while simultaneously powering a Digital Twin visualization, predictive analytics, and compliance tracking.
- Upload any industrial document (PDF, DOCX, XLSX, TXT) and chat with it instantly
- AI provides precise, grounded answers with verifiable source citations (document name, section, page)
- Powered by LLaMA 3.3 70B via Groq with LangChain RAG pipeline
- Intelligent fallback engine ensures zero downtime β always returns answers even during API failures
- Futuristic Neural Scanner Loading Animation with real-time pipeline stage indicators
- Drag-and-drop asset positioning on a 2D plant map with real-time health indicators
- Dynamic asset management β Add, connect, reposition, and delete equipment directly from the UI
- Animated process flow lines showing connections between assets with pulsing health-based colors
- No hardcoded data β every position, connection, and asset is stored in the database
- Any new client/factory can start from a blank canvas and build their plant layout visually
- Auto-extracts physical assets (Pumps, Compressors, Valves, Motors) from uploaded documents using Named Entity Recognition (NER)
- Real-time KPI cards: Total Assets, Health Score, Open Incidents, Compliance Rate
- Failure pattern detection with AI-generated maintenance recommendations
- Severity distribution charts and incident trend analysis
- Upload industrial documents with automatic AI processing (summarization + entity extraction)
- FAISS vector indexing for lightning-fast semantic search across all documents
- Documents are automatically linked to physical equipment tags (e.g., P-101, C-401)
- Track regulatory requirements (ISO 55000, OSHA, API 653) against asset compliance status
- Visual risk-level indicators: Compliant, Non-Compliant, Overdue
- Gap analysis with automated audit readiness scoring
- AI-powered failure pattern recognition across the asset fleet
- Thermal anomaly detection, vibration analysis, and seal degradation tracking
- Maintenance recommendations ranked by severity and recurrence count
- Responsive, dark/light mode landing page with Three.js bioluminescent particle background
- Asymmetric Bento Grid showcasing platform capabilities
- Interactive AI Copilot preview with live step-by-step demonstration
- Footer pages: Privacy Policy, Terms of Service, Enterprise Security, System Status
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β FRONTEND (React 19 + Vite 8) β
β ββββββββββββ ββββββββββββ ββββββββββββ ββββββββββββββββββββββ β
β βDashboard β βAI Copilotβ βDocuments β β Digital Twin β β
β β(KPIs) β β(RAG Chat)β β(Upload) β β (Plant Map) β β
β ββββββ¬ββββββ ββββββ¬ββββββ ββββββ¬ββββββ ββββββββββ¬ββββββββββββ β
β β β β β β
β ββββββ΄ββββββββββββββ΄βββββββββββββ΄βββββββββββββββββ΄βββββββββββ β
β β Axios API Service Layer β β
β ββββββββββββββββββββββββββββββ¬ββββββββββββββββββββββββββββββββ β
βββββββββββββββββββββββββββββββββΌβββββββββββββββββββββββββββββββββββ
β REST API (HTTP)
βββββββββββββββββββββββββββββββββΌβββββββββββββββββββββββββββββββββββ
β BACKEND (FastAPI) β
β ββββββββββββββββββββββββββββββ΄βββββββββββββββββββββββββββββββ β
β β API Router Layer β β
β β /api/chat /api/assets /api/documents /api/analytics β β
β ββββββ¬βββββββββββββββ¬βββββββββββββββ¬βββββββββββββββ¬ββββββββββ β
β β β β β β
β ββββββ΄βββββ βββββββ΄βββββ βββββββ΄ββββββ ββββββ΄ββββββ β
β βLLM β βEntity β βDocument β βAnalytics β β
β βService β βExtractor β βProcessor β βEngine β β
β β(Groq/ β β(NER) β β(PDF/DOCX) β β(Patterns)β β
β β Gemini) β ββββββββββββ βββββββββββββ ββββββββββββ β
β ββββββ¬βββββ β
β β β
β ββββββ΄βββββββββββββββββββββββββββββββββββββββββββββββββββββββ β
β β FAISS Vector Store (CPU) β β
β β Sentence-Transformers (all-MiniLM-L6-v2) β β
β βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ β
β β
β βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ β
β β SQLite Database β β
β β Assets β Incidents β Documents β Compliance β Entities β β
β βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ β
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
| Layer | Technology | Purpose |
|---|---|---|
| Frontend | React 19, Vite 8, React Router 7 | SPA with component-based architecture |
| UI Framework | Custom CSS (Glassmorphism), Lucide Icons | Premium dark-mode industrial control room UI |
| 3D Effects | Three.js | Bioluminescent particle background on landing page |
| Backend | FastAPI 0.115, Python 3.12+ | Async REST API with auto-generated Swagger docs |
| Database | SQLite + SQLAlchemy 2.0 | Zero-config relational storage with ORM |
| Vector DB | FAISS-CPU 1.14 | Facebook AI Similarity Search for document embeddings |
| Embeddings | Sentence-Transformers (all-MiniLM-L6-v2) | Lightweight, high-quality text embeddings |
| LLM | Groq (LLaMA 3.3 70B Versatile) | Ultra-fast inference for RAG answers |
| RAG Framework | LangChain 0.3 | Orchestrates retrieval, context assembly, and generation |
| Doc Processing | PyPDF2, python-docx, openpyxl | Multi-format document text extraction |
- Python 3.12+
- Node.js 18+
- Groq API Key (free at console.groq.com)
git clone https://github.com/Husam26/IntelliPlant.git
cd IntelliPlantcd backend
python -m venv venv
# Windows
venv\Scripts\activate
# macOS / Linux
source venv/bin/activate
pip install -r requirements.txtCreate a .env file in the project root:
GROQ_API_KEY=your_groq_api_key_herecd backend
python seed_demo_data.pyThis populates the database with 7 industrial assets, 4 incidents, and 4 compliance records for a realistic demonstration.
uvicorn app.main:app --reloadBackend runs at http://localhost:8000 | Swagger Docs at http://localhost:8000/docs
cd frontend
npm install
npm run devFrontend runs at http://localhost:5173
run_project.batIntelliPlant/
βββ backend/
β βββ app/
β β βββ main.py # FastAPI application entry point
β β βββ config.py # Environment configuration (Pydantic Settings)
β β βββ database.py # SQLAlchemy engine & session management
β β βββ models/
β β β βββ models.py # ORM models (Asset, Document, Incident, etc.)
β β βββ schemas/
β β β βββ schemas.py # Pydantic request/response schemas
β β βββ routers/
β β β βββ assets.py # CRUD endpoints for assets + Digital Twin
β β β βββ chat.py # RAG-powered AI Copilot endpoint
β β β βββ documents.py # Document upload & processing
β β β βββ analytics.py # Dashboard KPIs & pattern detection
β β β βββ search.py # Semantic search endpoint
β β βββ services/
β β β βββ llm_service.py # LangChain RAG pipeline + Groq integration
β β β βββ document_processor.py # PDF/DOCX/XLSX parsing & FAISS indexing
β β β βββ entity_extractor.py # NER for equipment tag extraction
β β βββ utils/
β βββ seed_demo_data.py # Demo data seeder script
β βββ requirements.txt
βββ frontend/
β βββ src/
β β βββ App.jsx # Root router & layout
β β βββ pages/
β β β βββ Landing.jsx # Public landing page
β β β βββ Dashboard.jsx # Analytics dashboard
β β β βββ Copilot.jsx # AI chat interface
β β β βββ Documents.jsx # Document management
β β β βββ Assets.jsx # Asset registry
β β β βββ Compliance.jsx # Compliance tracker
β β β βββ Insights.jsx # Predictive insights
β β β βββ PlantMap.jsx # Digital Twin (interactive plant map)
β β β βββ InfoPages.jsx # Privacy, Terms, Security, Status
β β βββ components/
β β β βββ layout/Sidebar.jsx
β β β βββ HeroMockup.jsx
β β β βββ WhiteboardBioluminescent.jsx
β β βββ services/
β β β βββ api.js # Axios API service layer
β β βββ styles/ # CSS modules (Glassmorphism theme)
β βββ package.json
βββ data/ # FAISS index & uploaded documents
βββ sample_docs/ # Sample industrial documents for testing
βββ .env # Environment variables
βββ .gitignore
βββ run_project.bat # One-click Windows launcher
βββ README.md
| Method | Endpoint | Description |
|---|---|---|
GET |
/api/analytics/overview |
Dashboard KPI summary |
GET |
/api/analytics/patterns |
AI-detected failure patterns |
GET |
/api/assets |
List all assets (with filters) |
POST |
/api/assets |
Create new asset (Digital Twin) |
PUT |
/api/assets/{id}/position |
Update asset position on map |
PUT |
/api/assets/{id}/connections |
Update asset flow connections |
DELETE |
/api/assets/{id} |
Delete an asset |
GET |
/api/assets/{id}/incidents |
Asset incident history |
POST |
/api/chat |
Send question to AI Copilot (RAG) |
GET |
/api/chat/history/{session} |
Retrieve chat history |
POST |
/api/documents/upload |
Upload & process document |
GET |
/api/documents |
List all documents |
GET |
/api/search?q=... |
Semantic search across documents |
- Responsive dark/light mode with Three.js particle animation
- Asymmetric Bento Grid with live asset health telemetry widgets
- Interactive AI Copilot preview section
- Real-time KPI cards (Total Assets, Health Score, Incidents, Compliance)
- Glassmorphism-inspired premium dark UI
- Natural language chat with industrial document intelligence
- Verifiable source citations with document name and section
- Cyber-Emerald Neural Scanner loading animation with live pipeline stages
- Interactive 2D plant layout with draggable asset nodes
- Real-time health colors (Green/Amber/Red) with pulsing animations
- Add Asset modal with connection picker for process flow lines
- Edit connections from the detail panel after creation
| Feature | IntelliPlant | Traditional Systems |
|---|---|---|
| Document Intelligence | AI-powered RAG with citations | Manual keyword search |
| Asset Monitoring | Dynamic Digital Twin | Static P&ID printouts |
| Knowledge Access | Natural language Q&A | Browse folder hierarchies |
| Compliance | Automated real-time tracking | Manual spreadsheet audits |
| Setup Time | < 5 minutes | Weeks of configuration |
| Infrastructure | Local-first (SQLite + FAISS-CPU) | Heavy enterprise servers |
Team IntelliPlant β Built during the ETA Hackathon 2026
This project was built for the ETA Hackathon 2026. All rights reserved.
π IntelliPlant β Operate your plant with certainty.