I’ve been experimenting with Spring AI to see how what it can do for Spring applications. Here is a simple demo that uses Spring AI, OpenAI and OpenWeather to look up weather conditions for a city using a natural language prompt. You can give it a query like What’s the weather like in Rome today? and it will return with a result, in JSON format, like this: {"main":{"temp":23.67,"feels_like":24.16,"temp_min":22.49,"temp_max":24.31,"pressure":1019, "humidity":79,"sea_level":1019,"grnd_level":992}, "weather":[{"id":803,"main":"Clouds","description":"broken clouds","icon":"04n"}],"name":"Rome"} The code is here

Today I experimented with hooking up a REST API to OpenAI via the Chat Completion “tool” framework (originally I had intended to use a Model Context Protocol server, but discovered that OpenAI’s integration for that was in a state of disarray…) Components: An OpenWeather api key An OpenAI platform api key A lambda that encapsulates calls to the weather api A python script that uses a “tool” definition to call the lambda The Lambda 🔗This is pretty straightforward:

Recently AWS made a new feature available in Cloudwatch: AI Operations. What does it do? In it’s own words: Amazon Q Developer now includes a new generative-AI investigations experience that helps you troubleshoot operational issues by automating information gathering, analyzing observability data, and providing tailored recommendations. With this tool one is able to create a trail or notebook of observations and have AWS automatically find new hopefully relevant observations and even suggest causes and actions.