src/image_summarizer.py

import base64
import os
from typing import Optional
from openai import OpenAI

class ImageSummarizer:
    """Summarizes images using OpenAI's vision API."""
    
    def __init__(self, api_key: Optional[str] = None):
        """Initialize OpenAI client."""
        self.client = OpenAI(api_key=api_key or os.getenv("OPENAI_API_KEY"))
    
    def summarize_image_base64(self, 
                               image_base64: str,
                               image_format: str = "png") -> str:
        """
        Summarize image using OpenAI vision.
        
        Args:
            image_base64: Base64 encoded image
            image_format: Image format (png, jpg, etc.)
        
        Returns:
            Image description/summary
        """
        try:
            response = self.client.chat.completions.create(
                model="gpt-4o-mini",  # or "gpt-4-vision-preview"
                messages=[
                    {
                        "role": "user",
                        "content": [
                            {
                                "type": "image_url",
                                "image_url": {
                                    "url": f"data:image/{image_format};base64,{image_base64}"
                                }
                            },
                            {
                                "type": "text",
                                "text": "Пожалуйста, опишите детально содержание этого изображения на русском языке. Укажите все видимые объекты, текст, диаграммы, графики и их взаимосвязь."
                            }
                        ]
                    }
                ],
                max_tokens=500
            )
            
            return response.choices[0].message.content
        
        except Exception as e:
            print(f"Error summarizing image: {e}")
            return f"Изображение на странице (ошибка обработки: {str(e)})"


def process_images_in_documents(documents_data: list,
                                image_summarizer: ImageSummarizer) -> list:
    """
    Process images in extracted PDF documents and add summaries.
    
    Args:
        documents_data: List of document content dictionaries
        image_summarizer: ImageSummarizer instance
    
    Returns:
        Updated documents with image summaries
    """
    for doc in documents_data:
        for page in doc.get("pages", []):
            for image in page.get("images", []):
                if image.get("base64"):
                    print(f"Summarizing image from page {page.get('page_number')}")
                    summary = image_summarizer.summarize_image_base64(
                        image.get("base64"),
                        image.get("format", "png")
                    )
                    image["summary"] = summary
    
    return documents_data