
- The
Prompt
node gets the initial image as an input and runs the LLM to identify the landmark. - The
getWeather
tool is called with the location of the landmark as input. - The output of the
getWeather
tool is connected back to thePrompt
node. - The
Prompt
node runs again with the updated context and returns an assistant message to move the agent forward. - The
Final output
node gets executed and the agent completes its execution.