Handle Responsible AI scenarios for OpenAI

Nobody has claimed this yet.

# High Level Proposal

I would like to extend `representation.OpenAI` to handle more scenarios that crop up when using OpenAI hosted by Azure. These scenarios affect usage of the [AzureOpenAI](https://github.com/openai/openai-python/blob/89478ce06e2161fda416c685b774a97a041ae185/src/openai/lib/azure.py#L64) class. Azure places its OpenAI instance behind Responsible AI (RAI) controls which reduce harm by limiting access to sensitive (violence, hate, self-harm, sexual) content but requires more edge-cases and errors to be accounted for.

I believe that handling more RAI based scenarios for OpenAI will improve the usability of modeling using that representation model for both folks who use AzureOpenAI and OpenAI.

## Technical Details

RAI triggers can be encountered in two scenarios:
1. Sending inappropriate input
2. GPT generating sensitive output based on the prompt

### Sending inappropriate input
- Log `repr_doc_ids` within [_extract_representative_docs](https://github.com/MaartenGr/BERTopic/blob/9e5558bc2d04797280b10576added63730459621/bertopic/_bertopic.py#L3813) which cause an exception to be raised

### GPT generating sensitive output based on the prompt
- Handle all four [`CompletionChoice.finish_reason`s](https://platform.openai.com/docs/guides/text-generation/chat-completions-api)
- Open question: How do you want to handle the `length` and `function_call` and `null` finish_reasons
- Log non-`stop` finish_reasons
- Log `repr_doc_ids` which caused sensitive responses

Start in bertopic/_bertopic.py at _extract_representative_docs and review how representation.OpenAI uses AzureOpenAI. Reproduce the two RAI scenarios described in the issue, then determine how the four CompletionChoice.finish_reason values should be handled. Done means logging repr_doc_ids for triggering inputs and sensitive responses, plus non-stop finish reasons, with the open handling questions resolved.

Written by the indexing model from the issue text.