An intelligent AI-powered travel assistant that helps users plan trips through natural language chat, interactive maps, and document analysis powered by Gemini API, Plotly, and Mapbox
# π AI Travel Assistant An intelligent travel assistant powered by Google's Gemini API with advanced function calling capabilities for interactive map display. ## β¨ Features ### π€ AI-Powered Travel Assistance - **Gemini API Integration**: Powered by Google's latest Gemini 1.5 Flash model - **Function Calling**: Automatically displays maps when discussing travel destinations - **Context-Aware**: Remembers conversation history and uploaded documents - **Travel-Focused**: Specialized in travel-related queries only ### πΊοΈ Interactive Map Display - **Automatic Map Generation**: Gemini automatically calls the `show_map` function when locations are mentioned - **Real-time Geocoding**: Converts location names to coordinates using OpenStreetMap - **Interactive Markers**: Clickable markers with location information and descriptions - **Sidebar Integration**: Maps are displayed in the sidebar for better space utilization - **Customizable Zoom**: Adjustable map zoom levels for optimal viewing ### π Document Analysis - **PDF Expense Reports**: Upload and analyze travel expense documents - **Smart Context**: AI uses uploaded documents to provide personalized travel advice - **Budget Insights**: Get travel budgeting recommendations based on your expenses - **File Icons**: Uploaded files are displayed with icons and file size information ### π Enhanced User Experience - **Clean Sidebar Layout**: Organized sidebar with file uploads, maps, and controls - **Visual Separators**: Clear sections with dividers for better organization - **Welcome Message**: Helpful introduction for new users - **Conversation Memory**: Full conversation history is maintained and sent to Gemini - **Responsive Design**: Better use of screen space with sidebar map integration ## π Getting Started ### Prerequisites - Python 3.12 or higher - Google Claude API key - Internet connection for geocoding and API calls ### Installation 1. **Clone the repository** ```bash git clone <repository-url>
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.