def process()

in LLM/language_model.py [0:0]

• 30 lines of code
• 7 McCabe index (conditional complexity)

    def process(self, prompt):
        logger.debug("infering language model...")
        language_code = None
        if isinstance(prompt, tuple):
            prompt, language_code = prompt
            if language_code[-5:] == "-auto":
                language_code = language_code[:-5]
                prompt = f"Please reply to my message in {WHISPER_LANGUAGE_TO_LLM_LANGUAGE[language_code]}. " + prompt

        self.chat.append({"role": self.user_role, "content": prompt})
        thread = Thread(
            target=self.pipe, args=(self.chat.to_list(),), kwargs=self.gen_kwargs
        )
        thread.start()
        if self.device == "mps":
            generated_text = ""
            for new_text in self.streamer:
                generated_text += new_text
            printable_text = generated_text
            torch.mps.empty_cache()
        else:
            generated_text, printable_text = "", ""
            for new_text in self.streamer:
                generated_text += new_text
                printable_text += new_text
                sentences = sent_tokenize(printable_text)
                if len(sentences) > 1:
                    yield (sentences[0], language_code)
                    printable_text = new_text

        self.chat.append({"role": "assistant", "content": generated_text})

        # don't forget last sentence
        yield (printable_text, language_code)