System Requirements Document (SRD)

Project Name: proud-calories

1. Introduction

The proud-calories project is a sophisticated, AI-driven calorie tracking application tailored specifically for users in Israel. The app is designed to provide precise calorie calculations, leveraging a comprehensive database of Israeli food products and advanced AI capabilities to ensure accuracy and usability. The system emphasizes user-friendliness, natural language interaction, and detailed nutritional insights, making it a valuable tool for individuals aiming to manage their dietary habits effectively.

This document outlines the functional and non-functional requirements, user personas, design concepts, and technical specifications for the proud-calories application.

2. System Overview

The proud-calories application is a calorie management system that allows users to track their daily, weekly, and historical calorie consumption. The app is built with a focus on the Israeli market, incorporating a localized food database and AI-powered calorie calculations for three distinct food categories:

1. Complex dishes (e.g., soups with multiple ingredients).
2. Specific products (e.g., delicacies, eggs).
3. Weighed items (e.g., cheese, sugary drinks, fruits, meats).

Key features include:

• AI-powered calorie recognition based on user habits and past inputs.
• Barcode scanning for automatic product identification.
• Weekly analytics with progress charts.
• Alerts for exceeding daily calorie goals.
• Manual calorie input for users who prefer simplicity.
• Natural language processing for intuitive interaction.

The system is designed to be fast, reliable, and capable of providing actionable insights, including weight loss tips and detailed nutritional breakdowns (e.g., calorie, fat, and protein content).

3. Functional Requirements

• As a User, I should be able to input my daily calorie goal.
• As a User, I should be able to view my calorie consumption for today, yesterday, and previous days.
• As a User, I should be able to add food items manually with calorie values.
• As a User, I should be able to scan barcodes to automatically add food items from the IsraeliProduct database.
• As a User, I should be able to delete food entries for any day.
• As a User, I should receive alerts when I exceed my daily calorie goal.
• As a User, I should be able to view weekly calorie consumption charts compared to my goals.
• As a User, I should be able to see weight progress trends over time.
• As a User, I should receive AI-generated weight loss tips based on my consumption patterns.
• As a User, I should be able to interact with the system in natural language.
• As a User, I should be able to view detailed nutritional information, including calorie, fat, and protein content.

4. User Personas

4.1 Regular User

• Description: Individuals in Israel who want to track their calorie intake and manage their diet.
• Goals:
  • Maintain or lose weight.
  • Gain insights into their eating habits.
  • Use a localized, accurate calorie tracking tool.
• Pain Points:
  • Inaccurate calorie data.
  • Lack of localized food options in existing apps.

4.2 Health Enthusiast

• Description: Fitness-conscious individuals who require precise nutritional data to optimize their diet.
• Goals:
  • Track macronutrient intake (calories, fat, protein).
  • Monitor progress over time with detailed analytics.
• Pain Points:
  • Slow or unreliable AI responses.
  • Limited customization options for calorie goals.

5. Visuals Colors and Theme

The proud-calories app will feature a modern, vibrant color palette inspired by health and wellness, with a focus on clarity and readability:

• Background: #F5F9F6 (soft mint green for a fresh, clean look).
• Surface: #FFFFFF (pure white for contrast and simplicity).
• Text: #2E3A3F (dark slate gray for readability).
• Accent: #FF6F61 (vivid coral for actionable elements like buttons and alerts).
• Muted Tones: #A3B4B8 (soft gray-blue for secondary information).

6. Signature Design Concept

The proud-calories app will feature an interactive "Food Journey Map" on the homepage.

Concept Details:

• Visual Design: A dynamic, scrollable timeline that visually represents the user's daily calorie intake. Each food entry appears as a colorful, animated "tile" on the timeline, with icons representing the food type (e.g., a bowl for soup, a carton for milk).
• Interactions:
  • Users can tap on a tile to expand it, revealing detailed nutritional information and the time of consumption.
  • Swiping left or right navigates between days, with smooth transitions and subtle animations.
• Animations:
  • When a new food item is added, its tile "slides" into place with a bounce effect.
  • Alerts for exceeding calorie goals appear as a glowing red border around the day's timeline.
• Color Shifts:
  • The timeline background subtly changes color based on the user's progress (e.g., green for staying within the goal, yellow for approaching the limit, red for exceeding it).

This design ensures the homepage is both functional and visually engaging, making calorie tracking an enjoyable experience.

7. Non-Functional Requirements

• The system must respond to user inputs within 2 seconds.
• The AI must achieve at least 95% accuracy in calorie calculations.
• The app must support Hebrew as the primary language, with optional English support.
• The database must be updated monthly to include new Israeli food products.
• The system must handle up to 10,000 concurrent users without performance degradation.

8. Tech Stack

Frontend

• React for Web
• React Native for Mobile

Backend

• Python
• FastAPI

Database

• MySQL for structured data (e.g., user profiles, food entries).
• MongoDB for unstructured data (e.g., AI training data).

AI Models

• GPT 5.4 for user-friendly responses.
• Claude 4.6 Opas for coding and academic tasks.
• Google Nano Banana for image generation (e.g., barcode recognition).

AI Tools

• Litellm for LLM Routing.
• Langchain for AI workflow orchestration.

Orchestration

• Docker for local development.
• Kubernetes for server-side orchestration.

9. Assumptions and Constraints

• The app will only support food products available in Israel.
• Users must have an internet connection for AI and database queries.
• The system will not track user weight directly but will allow users to input progress manually.

10. Glossary

• AI: Artificial Intelligence.
• NLP: Natural Language Processing.
• RDBMS: Relational Database Management System.
• Barcode Scanning: Using a device's camera to read product barcodes.
• IsraeliProduct Database: A localized database of food products available in Israel.