def get_chunks()

in chunking/chunkers/transcription_chunker.py [0:0]

• 18 lines of code
• 3 McCabe index (conditional complexity)

    def get_chunks(self):           
        chunks = [] 
        logging.info(f"[transcription_chunker][{self.filename}] Running get_chunks.")

        # Extract the text from the vtt file
        text = self._vtt_process()
        logging.debug(f"[transcription_chunker][{self.filename}] transcription text: {text[:100]}")

        # Get the summary of the text
        prompt = f"Provide clearly elaborated summary along with the keypoints and values mentioned for the transcript of a conversation: {text} "
        summary = self.aoai_client.get_completion(prompt)
        text_chunks = self._chunk_document_content(text)
        chunk_id = 0
        for text_chunk in text_chunks:
            chunk_id += 1
            chunk_size = self.token_estimator.estimate_tokens(text_chunk)
            if chunk_size > self.max_chunk_size:
                logging.debug(f"[transcription_chunker][{self.filename}] truncating {chunk_size} size chunk to fit within {self.max_chunk_size} tokens")
                text_chunk = self._truncate_chunk(text_chunk)
            chunk_dict = self._create_chunk(chunk_id=chunk_id, content=text_chunk, embedding_text=summary, summary=summary) 
            chunks.append(chunk_dict)      
        return chunks