An intelligent assistant for document analysis. Upload a PDF, JPG, or PNG, and ask any question about its content.
This project is built with Next.js, Genkit (Google Gemini), and PostgreSQL.
- Document Upload: Upload documents in PDF, JPG, PNG formats via an intuitive interface.
- Text Extraction (OCR): Extracts text from images and documents using advanced OCR technology.
- Intelligent Question Answering: Ask questions in natural language and get context-aware answers from the document content.
- Interaction History: All document uploads, questions, and AI answers are saved for tracking and analysis.
Azwar Riyadh Subarkah
- LinkedIn: linkedin.com/in/azwarriyadh
- GitHub Repository: github.com/sazwarriyadhs/visionask