summarizer.py

from openai import OpenAI
from typing import List
from logger_config import get_logger

logger = get_logger(__name__)

class ChapterSummarizer:
    def __init__(self, api_key: str, model: str, prompt: str):
        logger.info(f"Initializing ChapterSummarizer with model: {model}")
        self.client = OpenAI(api_key=api_key)
        self.model = model
        self.prompt = prompt
        logger.info(f"Prompt length: {len(prompt)} characters")

    def summarize_chunks(self, chunks: List[str]) -> str:
        logger.info(f"Starting summarization of {len(chunks)} chunks")
        summaries = []

        for idx, chunk in enumerate(chunks):
            logger.info(f"Processing chunk {idx + 1}/{len(chunks)}")
            logger.info(f"Chunk {idx + 1} length: {len(chunk)} characters")
            
            try:
                response = self.client.chat.completions.create(
                    model=self.model,
                    messages=[
                        {"role": "system", "content": "You are a system design expert."},
                        {
                            "role": "user",
                            "content": f"{self.prompt}\n\nChunk {idx+1}:\n{chunk}"
                        }
                    ]
                )
                
                summary = response.choices[0].message.content
                summaries.append(summary)
                
                logger.info(f"Successfully summarized chunk {idx + 1}")
                logger.info(f"Summary {idx + 1} length: {len(summary)} characters")
                logger.info(f"Tokens used - Prompt: {response.usage.prompt_tokens}, Completion: {response.usage.completion_tokens}, Total: {response.usage.total_tokens}")
                
            except Exception as e:
                logger.error(f"Failed to summarize chunk {idx + 1}", exc_info=True)
                raise

        total_summary_length = sum(len(s) for s in summaries)
        logger.info(f"All chunks summarized successfully. Total summary length: {total_summary_length} characters")
        
        return "\n\n".join(summaries)