add jailbreak filter result, add ContentFilterResults on output

[juliomartinsdev]

Adding field for prompt_filter_results which is in the open content filters to assess the content of the user input. Current implementation in go-openai will only return content filter information on the model output using ChatCompletionResponse. This is for AzureOpenAI spec.

Adding field for content_filter_results which is in the open content filters to assess the content of the user input. Current implementation in go-openai will only return content filter information on the model output using ChatCompletionChoice. This is for AzureOpenAI spec.

Adding field for jailbreak which is in a content filter. Current implementation in go-openai will only return content filter information on the error output using InnerError.ContentFilterResults. This is for AzureOpenAI spec.

Provide OpenAI documentation link
Relevant API doc: https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/content-filter

Describe your solution
Change struct

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 99.04%. Comparing base (774fc9d) to head (8033f54).
Report is 59 commits behind head on master.

Additional details and impacted files

@@            Coverage Diff             @@
##           master     #864      +/-   ##
==========================================
+ Coverage   98.46%   99.04%   +0.58%     
==========================================
  Files          24       26       +2     
  Lines        1364     1461      +97     
==========================================
+ Hits         1343     1447     +104     
+ Misses         15        8       -7     
  Partials        6        6              

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

[juliomartinsdev]

hey @sashabaranov could you take a look at this PR 😁

[sashabaranov]

Thank you!