Reconsider the Type float/Float in the API

[ullenboom]

A floating-point number with limited precision is commonly used in AI. However, using float or Float as a data type in the API might be impractical, and it could be worth reevaluating this decision.

For instance, your own example in the reference documentation (https://docs.spring.io/spring-ai/reference/api/clients/ollama-chat.html) results in a compiler error, guess why :)

ChatResponse response = chatClient.call(
    new Prompt(
        "Generate the names of 5 famous pirates.",
        OllamaOptions.create()
            .withModel("llama2")
            .withTemperature(0.4)
    ));

[ThomasVitale]

It would be nice to use Double instead of Float in all the ModelOptions implementations. It would make the API more convenient to work with and the code more readable.

[markpollack]

I agree, thanks for raising the issue. I will aim to fix this for the M2 release that is coming up shortly.

[csterwa]

@markpollack should this be moved to next milestone or release candidate?

[ThomasVitale]

I'm available to submit a PR on this. I had already done some preliminary analysis when working on the observability features. I should have the PR ready by the end of this week.

[ThomasVitale]

The PR is ready for review: #1325