Add model handler from Gemini PRO

What does this merge request do and why?

This MR adds a model handler for GenerativeModels so that we can use Gemini PRO as an answering model.

How to set up and validate locally

1. Run a regular pipeline with the answering model "gemini-1.0-pro-001"
2. Verify that the resulting table is populated by answers from Gemini

Example results: dev-ai-research-0e2f8974.duo_chat_experiments.aherczeg_gemini__independent_llm_judge

Merge request checklist

• I've ran the affected pipeline(s) to validate that nothing is broken.
• Tests added for new functionality. If not, please raise an issue to follow up.
• Documentation added/updated, if needed.

Links to #183 (closed)