Smart Multimodal Invoice & Expense Analyzer

Description

This web app leverages Google Gemini 2.5 multimodal capabilities to analyze invoices, receipts, and expense records from images, videos, or audio recordings. It extracts structured data, categorizes expenses, detects anomalies, and generates interactive reports for users.

Features

• Upload image, video, or audio of receipts/invoices
• Automatic extraction: vendor, date, items, total, taxes, currency
• Categorizes expenses: personal, business, tax-related
• Detects anomalies: duplicates, missing data, incorrect totals
• Generates interactive summaries and reports

Technology Stack

• Google AI Studio (Gemini 2.5 Flash/Pro)
• Cloud Run for deployment
• Frontend: HTML + JavaScript
• Backend: Python Flask

How to Use

1. Upload your invoice, receipt, or expense video/audio
2. AI parses and displays structured data
3. View categorized summary and anomaly detection
4. Download or share the report

Demo Video

[Insert YouTube or video link showing the app in action]

GitHub Repository

[Insert link to your code]