
This project is a modular, multilingual AI assistant that combines retrieval-augmented generation (RAG), knowledge graphs, and dynamic domain orchestration to deliver intelligent, contextual, and personalized responses. Users can interact through text or voice, with support for Indonesian and English. The system detects the userβs intent and domainβfood, travel, marketplace, or generalβthen builds a context-rich prompt using the userβs preferences, recent behavior, and relevant documents retrieved via semantic search (FAISS). A Groq-hosted LLaMA model generates responses with fallback logic per domain. The assistant evolves with user interactions, stores feedback, and enables visual graph exploration for transparency.
8 Jul 2025

Paperia Overview: Paperia is a tool designed to digitize printed and handwritten documents (invoices, receipts, purchase orders, etc.) and integrate them into a record-keeping system. It automates the storage and organization of documents, linking them with other business software systems. Paperia provides standard and customizable reports, utilizes data analysis, charts, and dashboards to offer valuable business insights. Key Benefits: Efficiency: Reduces manual effort in document management. Accuracy: Minimizes errors through automation. Compliance: Helps maintain regulatory compliance. Decision-Making: Provides actionable insights for strategic decisions. Frontend: html,boostrap, jquery Backend:Flask and MySQLL). OCR and Data Extraction: Implement OCR (Optical Character Recognition) for digitizing printed and handwritten documents easyOCR. Integration: Ensure the system can integrate with other business software via APIs.
4 Jul 2024