Fix the Setance Splitting for text from LLM

[BossCodersHQ]

• Currently the sentence splitting works of a basic method
• Checks for a few things like commas, full stops, etc
• Unfortunately this split's up sentences that shouldn't be split up. E.g. if it was a coding interview and a ! was used or a . was used, then it would split up the code
• Instead a better method is to only check when it's at the end of a sentence. E.g. the code below taken from here

async def text_chunker(chunks):
    """Split text into chunks, ensuring to not break sentences."""
    splitters = (".", ",", "?", "!", ";", ":", "—", "-", "(", ")", "[", "]", "}", " ")
    buffer = ""

    async for text in chunks:
        if buffer.endswith(splitters):
            yield buffer + " "
            buffer = text
        elif text.startswith(splitters):
            yield buffer + text[0] + " "
            buffer = text[1:]
        else:
            buffer += text

    if buffer:
        yield buffer + " "