plano/demos/weather-forecast
2024-09-10 14:24:46 -07:00
..
grafana Add workflow logic for weather forecast demo (#24) 2024-07-30 16:23:23 -07:00
prometheus Add workflow logic for weather forecast demo (#24) 2024-07-30 16:23:23 -07:00
docker-compose.yaml Add function calling support using bolt-fc-1b (#35) 2024-09-10 14:24:46 -07:00
katanemo-config.yaml Add support for local llm (mistral 7b) (#31) 2024-08-06 23:40:06 -07:00
README.md Add support for local llm (mistral 7b) (#31) 2024-08-06 23:40:06 -07:00

Weather forecasting

This demo shows how you can use intelligent prompt gateway to provide realtime weather forecast.

Startig the demo

  1. Ensure that submodule is up to date
    git submodule sync --recursive
    
  2. Create .env file and set OpenAI key using env var OPENAI_API_KEY
  3. Start services
    docker compose up
    
  4. Navigate to http://localhost:18080/
  5. You can type in queries like "how is the weather in Seattle"
    1. You can also ask follow up questions like "show me sunny days"
  6. To see metrics navigate to "http://localhost:3000/" (use admin/grafana for login)
    1. Open up dahsboard named "Intelligent Gateway Overview"
    2. On this dashboard you can see reuqest latency and number of requests