Scope check

• This is core LLM communication (not application logic)
• This benefits most users (not just my use case)
• This can't be solved in application code with current RubyLLM
• I read the Contributing Guide

Due diligence

• I searched existing issues
• I checked the documentation

What problem does this solve?

From Gemini API documentation https://ai.google.dev/gemini-api/docs/api-versions there are currently two versions v1 and v1beta. In the RubyLLM project the default api version is v1beta which is considered a early-access version of the Gemini API that shouldn't be utilised for production code.

The way I found this issue was when trying to use the model gemini-1.5-flash-8b which is not support in the v1beta api version.

Proposed solution

A proposed solution is to add the configuration instance variable @config.gemini_api_base to lib/ruby_llm/providers/gemini.rb. A suggested solution:

def api_base
  @config.gemini_api_base || 'https://generativelanguage.googleapis.com/v1beta'
end

Why this belongs in RubyLLM

This belongs in RubyLLM as would be good for developers/users to switch between the default Gemini api base url to different versions.