Initial commit - MVP project setup

Created by AI Dev Factory init-mvp-project.sh
This commit is contained in:
AI Dev Factory 2025-12-06 00:03:36 +00:00
commit cf33cc08c1
5 changed files with 559 additions and 0 deletions

31
.gitignore vendored Normal file
View File

@ -0,0 +1,31 @@
# Dependencies
node_modules/
__pycache__/
*.pyc
*.pyo
*.pyd
.Python
venv/
.venv/
env/
.env
# IDE
.vscode/
.idea/
*.swp
*.swo
# OS
.DS_Store
Thumbs.db
# Build
dist/
build/
*.egg-info/
# Test
.coverage
.pytest_cache/
*.log

268
ARCHITECTURE.md Normal file
View File

@ -0,0 +1,268 @@
# Image Description AI - System Architecture
## High-Level System Design
The Image Description AI is a client-side single-page application (SPA) that enables users to upload images and receive AI-generated descriptions using the Minimax API. The architecture follows a modern, responsive web application pattern with clean separation of concerns.
```
┌─────────────────────────────────────────────────────────────┐
│ Client-Side Application │
├─────────────────────────────────────────────────────────────┤
│ ┌─────────────┐ ┌─────────────┐ ┌─────────────────────┐ │
│ │ Upload │ │ Preview │ │ AI Description │ │
│ │ Component │ │ Component │ │ Display │ │
│ └─────────────┘ └─────────────┘ └─────────────────────┘ │
├─────────────────────────────────────────────────────────────┤
│ Application State │
├─────────────────────────────────────────────────────────────┤
│ ┌─────────────┐ ┌─────────────┐ ┌─────────────────────┐ │
│ │ File │ │ Image │ │ API Response │ │
│ │ Validation │ │ Processing │ │ Handler │ │
│ └─────────────┘ └─────────────┘ └─────────────────────┘ │
├─────────────────────────────────────────────────────────────┤
│ Minimax API │
│ https://api.minimax.io/v1/text/chatcompletion_v2 │
└─────────────────────────────────────────────────────────────┘
```
## Technology Choices and Rationale
### Core Technologies
- **HTML5**: Semantic markup for accessibility and modern web standards
- **CSS3**: Modern styling with Flexbox/Grid for responsive layouts
- **Vanilla JavaScript**: Lightweight, no framework overhead, fast loading
- **File API**: Native browser API for file handling and validation
### UI Framework Decision: Vanilla JavaScript vs React
**Chosen: Vanilla JavaScript**
- **Rationale**:
- Single HTML file requirement simplifies deployment
- Minimal bundle size improves load times
- No build process needed
- Direct DOM manipulation gives precise control
- Sufficient for the application's complexity level
### Styling Approach
- **CSS Grid & Flexbox**: Modern, flexible layouts
- **CSS Custom Properties**: Maintainable theming
- **Mobile-First Responsive Design**: Works across all device sizes
- **CSS Animations**: Smooth transitions and loading states
## Database Schema
**Not Applicable**: This is a client-side only application with no persistent data storage. All processing is transient and happens in memory.
## API Endpoints
### External API Integration
**Endpoint**: `https://api.minimax.io/v1/text/chatcompletion_v2`
- **Method**: POST
- **Authentication**: Bearer token (API key)
- **Content-Type**: application/json
**Request Structure**:
```json
{
"model": "MiniMax-M2",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "Please provide a detailed description of this image in English"
},
{
"type": "image_url",
"image_url": {
"url": "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQ..."
}
}
]
}
],
"max_tokens": 500,
"temperature": 0.7
}
```
**Response Structure**:
```json
{
"id": "chatcmpl-abc123",
"object": "chat.completion",
"created": 1677652288,
"model": "MiniMax-M2",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "This image shows a beautiful sunset over..."
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 15,
"completion_tokens": 32,
"total_tokens": 47
}
}
```
## File Structure
```
image-description-ai/
├── index.html # Main application file (self-contained)
├── assets/
│ ├── styles/
│ │ └── main.css # (Optional separate CSS file)
│ └── scripts/
│ └── main.js # (Optional separate JS file)
├── README.md # Project documentation
└── docs/
├── ARCHITECTURE.md # This file
└── TASKS.md # Implementation tasks
```
### Single File Implementation
For production deployment as specified, the complete application exists in one HTML file:
- `index.html` - Contains all HTML, CSS, and JavaScript inline
- No external dependencies or build process required
- Immediate browser deployment ready
## Component Interactions
### 1. File Upload Flow
```
User Input → File Selection → Validation → Preview Display
↓ ↓ ↓ ↓
Drag&Drop → File API → Size/Type Check → Image Preview
Click → Reader → Convert to → Update UI
→ Base64 → Base64 → State Update
```
### 2. AI Processing Flow
```
Generate Click → API Request → Loading State → Response Handling
↓ ↓ ↓ ↓
Validate → Construct → Show Spinner → Display Result
Image → Payload → Disable UI → Handle Errors
↓ ↓ ↓ ↓
State Check → Send POST → Timeout → Success/Failure
→ Minimax API → Management → UI Update
```
### 3. Error Handling Flow
```
Any Error → Error Handler → User Notification → Recovery Option
↓ ↓ ↓ ↓
Network → Categorize → Clear Message → Reset/Retry
API → Error Type → Visual Alert → State Reset
File → Log Details → Action Required → User Guidance
Validation → Store State → UX Feedback → Continue Flow
```
## Data Flow Architecture
### Application State Management
```javascript
appState = {
currentImage: {
file: File | null,
base64: string | null,
preview: string | null,
metadata: {
name: string,
size: number,
type: string
}
},
apiStatus: {
isProcessing: boolean,
lastError: string | null,
requestId: string | null
},
ui: {
dragOver: boolean,
showPreview: boolean,
showResults: boolean
}
}
```
### Event-Driven Architecture
- **File Input Events**: Handle drag&drop, click-to-browse, file selection
- **Validation Events**: File size, type, and format checking
- **API Events**: Request initiation, response handling, error management
- **UI Events**: Loading states, animations, user feedback
## Security Considerations
### Client-Side Security
- **Input Validation**: Strict file type and size checking
- **XSS Prevention**: Sanitized content display
- **API Key Management**: Client-side exposure (note: production should use server-side proxy)
- **HTTPS Only**: Secure transmission to Minimax API
### Production Recommendations
1. **Server-Side API Proxy**: Move API calls to backend to hide API keys
2. **Rate Limiting**: Prevent API abuse
3. **File Scanning**: Server-side malware detection
4. **Content Security Policy**: Additional XSS protection
## Performance Optimizations
### Client-Side Optimizations
- **Lazy Loading**: Load UI components on demand
- **Debounced Validation**: Reduce unnecessary processing
- **Memory Management**: Clean up base64 strings after use
- **Progressive Enhancement**: Core functionality works without JavaScript
### API Optimizations
- **Request Compression**: Minimize payload size
- **Timeout Management**: Prevent hanging requests
- **Retry Logic**: Handle transient network failures
- **Caching**: Avoid duplicate API calls for same images
## Scalability Considerations
### Current Architecture Limits
- **Client-Only Processing**: Limited by user's device capabilities
- **File Size Constraints**: 5MB limit for practical performance
- **API Rate Limits**: Dependent on Minimax service limits
### Future Enhancements
- **Backend Integration**: Server-side processing and API management
- **Batch Processing**: Multiple image handling
- **User Accounts**: Save and manage image descriptions
- **Advanced Features**: Multiple language support, custom prompts
## Browser Compatibility
### Supported Features
- **File API**: Modern browsers (IE10+, all modern browsers)
- **Base64 Encoding**: Universal browser support
- **CSS Grid/Flexbox**: IE11+, all modern browsers
- **Fetch API**: IE11+, all modern browsers (polyfill available)
### Fallback Strategies
- **Older Browsers**: Graceful degradation with polyfills
- **No JavaScript**: Basic form submission (limited functionality)
- **Network Issues**: Offline mode with queued requests
## Deployment Architecture
### Static File Deployment
- **CDN Ready**: Single HTML file suitable for any CDN
- **Zero Dependencies**: No npm packages or build process
- **Instant Deployment**: Upload and serve immediately
- **Version Control**: Simple Git-based version management
### Environment Configuration
- **Development**: Direct API calls with test keys
- **Staging**: Mirror production with environment-specific settings
- **Production**: Server-side API proxy recommended for security

43
PROJECT_SPEC.md Normal file
View File

@ -0,0 +1,43 @@
Create a clean, modern web application that allows users to upload an image and get an AI-generated description using the Minimax API.
**Requirements:**
1. **Frontend Interface:**
- Single page application with a clean, centered layout
- File upload area (drag-and-drop support + click to browse)
- Image preview after upload
- "Generate Description" button
- Loading state while processing
- Display area for the AI-generated description
- Option to upload a new image after getting results
2. **Technical Implementation:**
- Use vanilla JavaScript, HTML, and CSS (or React if you prefer)
- Handle image file validation (accept common formats: jpg, png, webp)
- Convert uploaded image to base64 for API submission
- Make POST request to Minimax API endpoint
- Handle API responses and errors gracefully
- Display clear error messages if something goes wrong
3. **Minimax API Integration:**
- Endpoint: `https://api.minimax.io/v1/text/chatcompletion_v2`
- Use model: `MiniMax-M2`
- Send image as base64 in the messages array
- Prompt: "Please provide a detailed description of this image in English"
- Handle API key securely (note: for production, this should be handled server-side)
4. **UI/UX Details:**
- Responsive design that works on mobile and desktop
- Professional color scheme (suggest modern blues/grays)
- Smooth transitions and loading animations
- Clear visual feedback for all user actions
5. **Error Handling:**
- File size validation (max 5MB recommended)
- File type validation
- API error handling with user-friendly messages
- Network error handling
Please create a complete, production-ready single HTML file with inline CSS and JavaScript that I can immediately use in a browser.

174
TASKS.md Normal file
View File

@ -0,0 +1,174 @@
# Image Description AI - Implementation Tasks
## Task 1: Create Basic HTML Structure and Styling Foundation
**Objective**: Establish the foundational HTML structure with semantic markup and responsive CSS framework
**Deliverables**:
- Complete HTML skeleton with proper DOCTYPE and meta tags
- Responsive CSS Grid layout system for the main application container
- Modern color scheme implementation (blues/grays as specified)
- Typography system with readable fonts and proper spacing
- Mobile-first responsive breakpoints
**Acceptance Criteria**:
- [ ] HTML validates as HTML5 standard
- [ ] Layout is responsive across mobile (320px+), tablet (768px+), and desktop (1024px+)
- [ ] Color scheme uses professional blue/gray palette with proper contrast ratios
- [ ] Typography is legible across all device sizes
- [ ] Basic layout structure includes: header, main upload area, preview section, results section
- [ ] CSS is modular with clear section organization (layout, components, utilities)
## Task 2: Implement File Upload Interface with Drag & Drop
**Objective**: Create an intuitive file upload interface supporting both drag-and-drop and click-to-browse functionality
**Deliverables**:
- Drag-and-drop zone with visual feedback states (drag over, drop, default)
- Hidden file input element for click-to-browse functionality
- Visual upload area with icon, instructional text, and file format specifications
- File type icon display for different image formats
- Hover and focus states for accessibility
**Acceptance Criteria**:
- [ ] Drag-and-drop zone visually responds to drag events with proper styling
- [ ] Click-to-browse opens file dialog and triggers file selection
- [ ] Upload area shows clear instructions: "Drag an image here or click to browse"
- [ ] Supported formats are displayed: JPG, PNG, WebP
- [ ] Accessibility: Keyboard navigation and screen reader support
- [ ] Visual feedback on hover/focus with smooth transitions
## Task 3: Add File Validation and Error Handling System
**Objective**: Implement comprehensive file validation to ensure only valid images are processed
**Deliverables**:
- File type validation (accept only jpg, jpeg, png, webp)
- File size validation (maximum 5MB with user-friendly error messages)
- Validation feedback system with clear error messages
- File metadata extraction (name, size, type)
- Reset functionality to clear errors and start over
**Acceptance Criteria**:
- [ ] Invalid file types show error: "Please select a valid image file (JPG, PNG, WebP)"
- [ ] Files over 5MB show error: "File size must be less than 5MB"
- [ ] Error messages display in red text below upload area
- [ ] Successful validation clears previous errors
- [ ] Validation occurs immediately upon file selection
- [ ] Files with valid extensions but invalid content are caught
- [ ] Reset button clears all errors and upload area state
## Task 4: Implement Image Preview Functionality
**Objective**: Display uploaded image with proper sizing and formatting for user confirmation
**Deliverables**:
- Image preview container with proper aspect ratio handling
- Image resizing and optimization for preview (max 400px width/height)
- Base64 encoding of the selected image for API submission
- Metadata display (filename, file size, dimensions)
- Replace/change image functionality
**Acceptance Criteria**:
- [ ] Image preview displays within 2 seconds of file selection
- [ ] Preview maintains aspect ratio without distortion
- [ ] Large images are scaled appropriately for preview
- [ ] Base64 encoding completes successfully and is stored in memory
- [ ] Image metadata is extracted and displayed (filename, size in MB, dimensions)
- [ ] "Change Image" button allows uploading a different file
- [ ] Preview clears when starting over
## Task 5: Integrate Minimax API for Image Description Generation
**Objective**: Connect to Minimax API and implement the core AI description generation functionality
**Deliverables**:
- API request construction with proper payload format
- Base64 image embedding in the request body
- Proper error handling for network issues and API responses
- Response parsing and extraction of the AI-generated description
- API key management (client-side with security notes)
**Acceptance Criteria**:
- [ ] API request uses correct endpoint: `https://api.minimax.io/v1/text/chatcompletion_v2`
- [ ] Request payload includes model: "MiniMax-M2"
- [ ] Base64 image is properly formatted in the messages array
- [ ] Prompt "Please provide a detailed description of this image in English" is included
- [ ] Successful API response extracts the description text
- [ ] API errors are handled gracefully with user-friendly messages
- [ ] Network timeouts are handled with appropriate error messaging
- [ ] Loading state is shown during API calls
## Task 6: Create Loading States and User Feedback System
**Objective**: Implement comprehensive loading and feedback mechanisms to enhance user experience
**Deliverables**:
- Loading spinner and progress indicator during API calls
- Status messages for different processing stages
- Button state management (disabled during processing)
- Timeout handling with user notification
- Success and error state animations
**Acceptance Criteria**:
- [ ] Loading spinner appears immediately when "Generate Description" is clicked
- [ ] "Generate Description" button is disabled during processing to prevent duplicate requests
- [ ] Status message shows: "Analyzing image with AI..."
- [ ] Processing timeout (30 seconds) shows: "Processing is taking longer than expected"
- [ ] Success animation plays when description is generated
- [ ] Error state shows appropriate error message with red styling
- [ ] Loading states have smooth transitions and professional appearance
## Task 7: Display AI Description Results with Formatting
**Objective**: Present the AI-generated description in a clean, readable format with additional functionality
**Deliverables**:
- Results display area with proper typography and spacing
- Text formatting and paragraph handling for long descriptions
- Option to copy description to clipboard
- "Generate New Description" functionality for the same image
- "Upload New Image" reset functionality
- Responsive results layout
**Acceptance Criteria**:
- [ ] Description displays in a readable format with proper line breaks
- [ ] Long descriptions are scrollable if they exceed viewport
- [ ] "Copy to Clipboard" button works and shows confirmation
- [ ] "Generate New Description" button triggers new API call
- [ ] "Upload New Image" button clears all data and returns to upload state
- [ ] Results area is visually distinct from upload area
- [ ] Typography is large enough to read comfortably on mobile devices
## Task 8: Final Polish, Testing, and Production Readiness
**Objective**: Complete final testing, optimizations, and prepare for immediate browser deployment
**Deliverables**:
- Comprehensive error handling for all edge cases
- Performance optimization for large images and slow networks
- Cross-browser compatibility testing
- Accessibility improvements (ARIA labels, keyboard navigation)
- Final code organization and documentation
- Single HTML file consolidation with inline CSS and JavaScript
**Acceptance Criteria**:
- [ ] Application works in Chrome, Firefox, Safari, and Edge
- [ ] All functionality works on mobile devices (iOS and Android)
- [ ] Images up to 5MB process within 30 seconds on average connections
- [ ] Clear error messages for all failure scenarios (network, API, validation)
- [ ] Complete keyboard navigation support
- [ ] ARIA labels and semantic HTML for screen readers
- [ ] No console errors or warnings
- [ ] Single HTML file contains all code and loads immediately in any modern browser
- [ ] Professional appearance with smooth animations and transitions
- [ ] File size under 50KB for fast loading
## Implementation Notes
### Task Dependencies
- Tasks 1-2 can be implemented in parallel
- Task 3 depends on Task 2 (validation needs upload interface)
- Task 4 depends on Task 3 (preview needs validation)
- Task 5 depends on Task 4 (API needs base64 image)
- Task 6 depends on Task 5 (loading states during API calls)
- Task 7 depends on Task 6 (results display after processing)
- Task 8 depends on all previous tasks (final testing and polish)
### Technical Considerations
- Use vanilla JavaScript ES6+ features for modern browser support
- Implement CSS custom properties for maintainable theming
- Follow progressive enhancement principles
- Maintain separation of concerns within the single file
- Include comprehensive error boundaries
### Testing Approach
- Test with various image sizes and formats
- Test error scenarios (large files, invalid types, network issues)
- Verify responsive behavior across devices
- Validate accessibility with screen readers
- Performance test with slow network connections

43
prompt.md Normal file
View File

@ -0,0 +1,43 @@
Create a clean, modern web application that allows users to upload an image and get an AI-generated description using the Minimax API.
**Requirements:**
1. **Frontend Interface:**
- Single page application with a clean, centered layout
- File upload area (drag-and-drop support + click to browse)
- Image preview after upload
- "Generate Description" button
- Loading state while processing
- Display area for the AI-generated description
- Option to upload a new image after getting results
2. **Technical Implementation:**
- Use vanilla JavaScript, HTML, and CSS (or React if you prefer)
- Handle image file validation (accept common formats: jpg, png, webp)
- Convert uploaded image to base64 for API submission
- Make POST request to Minimax API endpoint
- Handle API responses and errors gracefully
- Display clear error messages if something goes wrong
3. **Minimax API Integration:**
- Endpoint: `https://api.minimax.io/v1/text/chatcompletion_v2`
- Use model: `MiniMax-M2`
- Send image as base64 in the messages array
- Prompt: "Please provide a detailed description of this image in English"
- Handle API key securely (note: for production, this should be handled server-side)
4. **UI/UX Details:**
- Responsive design that works on mobile and desktop
- Professional color scheme (suggest modern blues/grays)
- Smooth transitions and loading animations
- Clear visual feedback for all user actions
5. **Error Handling:**
- File size validation (max 5MB recommended)
- File type validation
- API error handling with user-friendly messages
- Network error handling
Please create a complete, production-ready single HTML file with inline CSS and JavaScript that I can immediately use in a browser.