Ivanhoe

A feature-rich Rust GUI application that provides a ChatGPT-like interface using Amazon Bedrock with Claude 3.5 Sonnet.

Features

Chat Management

• Multiple chat sessions - Create and switch between different conversations using tabs
• Persistent conversations - Each tab maintains its own message history and file attachments
• Loading indicators - Visual feedback while waiting for Claude's responses
• Auto-scroll - Automatically scrolls to show new messages
• Copy functionality - Copy Claude's responses or code blocks to clipboard

File Support

• Drag and drop files - Simply drag files into the window to attach them
• File picker button - Click the 📎 button to browse and select files
• Multiple file types - Support for text files, images (PNG, JPG, JPEG), and documents
• File management - Clear attached files with one click
• Smart file handling - Automatic content extraction and appropriate formatting

User Interface

• Tabbed interface - Multiple chat sessions with easy switching and "+" button for new tabs
• Adjustable font size - Slider control (10px - 24px) for better readability
• Markdown rendering - Proper formatting for Claude's responses with syntax highlighting
• Code block support - Specially formatted code blocks with copy buttons
• Tooltips - Helpful descriptions for all interactive controls
• Status bar - Shows AWS profile, model info, and real-time token usage
• Professional branding - Proper title case in application menus and title bar
• Version display - Application version shown in title bar

Token Tracking

• Real-time monitoring - Track input and output tokens for each request
• Usage display - See total token consumption in the status bar
• Cost awareness - Monitor API usage for billing estimates
• Cumulative tracking - Tokens tracked across all chat sessions

Code Quality

• Modular architecture - Clean separation of concerns across multiple modules
• Clippy compliance - Passes all Rust clippy pedantic checks
• Type safety - Full Rust type system benefits with error handling
• Maintainable codebase - Well-organized structure for future development

Prerequisites

Rust Installation

1. Install Rust (if not already installed):

   curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
   source ~/.cargo/env

2. Verify installation:

   rustc --version
   cargo --version

3. Update Rust (if already installed):

   rustup update

System Dependencies

• macOS: No additional dependencies required

• Linux: Install development packages:

  # Ubuntu/Debian
  sudo apt-get install build-essential libxcb1-dev libxrandr-dev libxss-dev libxcursor-dev libxcomposite-dev libasound2-dev libxi-dev libgl1-mesa-dev
  
  # Fedora/RHEL
  sudo dnf install gcc-c++ libxcb-devel libXrandr-devel libXss-devel libXcursor-devel libXcomposite-devel alsa-lib-devel libXi-devel mesa-libGL-devel

Setup

1. Configure AWS credentials:

   aws configure

2. Ensure Bedrock access:

   • You need access to Claude 3.5 Sonnet in Amazon Bedrock
   • US East 1 (us-east-1) region is recommended

3. Build and run:

   cargo run

Usage

Basic Chat

• Type messages in the input field at the bottom
• Press Enter or click Send to submit
• Claude's responses appear with markdown formatting and syntax highlighting
• Use the 📋 button to copy responses or code blocks to clipboard

File Attachments

• Drag & Drop: Drag files directly into the window
• File Picker: Click the 📎 button to browse for files
• Supported formats: Text files, images (PNG/JPG/JPEG), PDFs, Office documents
• Management: Use Clear files to remove all attachments
• Smart processing: Images show size info, documents show type descriptions

Multiple Chats

• Click + to create a new chat session
• Click on tab names to switch between conversations
• Each tab has independent message history and file attachments
• Token usage is tracked across all sessions

Customization

• Font Size: Use the slider in the top panel to adjust text size (10px-24px)
• Token Monitoring: View real-time usage statistics in the status bar
• Tooltips: Hover over any control for helpful descriptions

Development

Building

make build          # Build the project
make run            # Run the application
make release        # Build optimized release version

Code Quality Targets

make check          # Check code without building
make clippy         # Run clippy linter (fails on warnings)
make fmt            # Format code
make test           # Run tests
make qa             # Run all quality checks

Quality Assurance

make clippy && make run    # Only run if clippy passes

Docker Support

make docker-build   # Build Docker image
make docker-run     # Run in container (Linux with X11)
make docker-clean   # Remove Docker image

Note: Docker GUI support requires X11 (Linux) or XQuartz (macOS).

Architecture

Module Structure

src/
├── main.rs           # Application entry point
├── app.rs           # Main application logic and coordination
├── chat/            # Chat session management
├── bedrock/         # AWS Bedrock API integration
├── ui/              # User interface components
└── utils/           # Utility functions (files, clipboard)

Technical Details

• Framework: Built with egui/eframe for cross-platform GUI
• AWS Integration: Uses AWS SDK for Bedrock API calls
• Model: Claude 3.5 Sonnet (us.anthropic.claude-3-5-sonnet-20241022-v2:0)
• File Processing: Automatic content extraction and formatting
• Async Architecture: Non-blocking UI with tokio runtime
• Memory Management: Efficient handling of large conversations and files

Requirements

• Rust 1.70+
• AWS credentials configured
• Amazon Bedrock access with Claude 3.5 Sonnet permissions