Support Google VertexAI Gemini-specific parameters

[wclssdn]

Describe the change
Support Google VertexAI Gemini-specific parameters.

Provide OpenAI documentation link

https://cloud.google.com/vertex-ai/generative-ai/docs/migrate/openai/overview#gemini-specific_parameters

Describe your solution
Just add two fields to ChatCompletionRequest struct

Tests
I did not add any tests.

Additional context
nothing

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 99.59%. Comparing base (181c0e8) to head (5622952).

Additional details and impacted files

@@           Coverage Diff           @@
##           master    #1048   +/-   ##
=======================================
  Coverage   99.59%   99.59%           
=======================================
  Files          34       34           
  Lines        2205     2205           
=======================================
  Hits         2196     2196           
  Misses          6        6           
  Partials        3        3           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[sashabaranov]

@wclssdn thank you for the PR!

I suggest we go with typed approach similar to #1034 instead of map[string]any.

[wclssdn]

@wclssdn thank you for the PR!

I suggest we go with typed approach similar to #1034 instead of map[string]any.

Currently, the vast majority of model providers support OpenAI's API standards, while also offering some personalized capabilities. How to better support these capabilities is a relatively challenging issue. My suggestion is to use generics, with each manufacturer having a generic support. However, this workload is too heavy for me~ I hope someone can implement this~