AI weather assistant with intelligent tool-calling architecture.
- Agentic AI: LLM decides which tools to use
- Tool Calling: Weather and Air Quality APIs
- Hallucination Management: Confidence scoring and risk assessment
- Setup:
cp .env.example .env
# Add your API keys to .env file- Run:
go run . chat # Interactive mode
go run . query "weather in Tokyo" # Single queryGEMINI_API_KEY- Google Gemini AIWEATHERAPI_KEY- WeatherAPI.com (free 1M calls/month)
main.go - Core logic, agentic LLM client
tools.go - Tool definitions and execution
cli.go - Command-line interface
weather_client.go - Weather and air quality API clients
llm_hallucination_detector.go - AI risk assessment and confidence scoring
You: What's the weather in Tokyo?
AI: I'll check the current weather data for you.
🌤️ Tokyo is currently 18°C with clear skies and good air quality (AQI: 42)
Built with Go, demonstrating agentic AI patterns, tool calling, and hallucination detection.
