vision_api_call.py

from openai import OpenAI
import os
import base64
from io import BytesIO
from PIL import Image
from utils import pil_to_base64, result_cleaner


my_key = os.environ.get('MY_OPENAI_KEY')
client = OpenAI(
    api_key= my_key
)

prompt="""

You'll be analyzing purchase receipts you will extract the following information:
-date: date of the purchase in the format YYYY-MM-DD
-Store: Name of the store where items or services were purchased
-Store_type: Type of store (supermarket, restaurant, bookstore, etc)
-Purchase_summary: in maximum 5 words summarize the purchase (cleaning products, breakfast, books, food items for home, online services, clothes ,etc)
-items: create a list of all the items in the receipt
-total: total amount spent

Provide your answer in a dictionary like the following
{{date: "xxxx-xx-xx"
store: "example store",
store_type: "supermarket",
purchase_summary: "food items for home",
items: "xxxx, xxxx, xxx"
total: xxxx }}
"""


def analyse_image(processed_image):
    #
    response = client.chat.completions.create(
        model="gpt-4o-mini",
        messages=[
            {
                "role": "user",
                "content": [
                    {
                        "type": "text",
                        "text": prompt,
                    },
                    {
                        "type": "image_url",
                        "image_url": {"url": f"data:image/jpeg;base64,{processed_image}"},
                    },
                ],
            }
        ],
    )
    return response.choices[0].message.content

def process_image(img):
    image_base64=pil_to_base64(img)
    analysis_result=analyse_image(image_base64)
    clean_analysis_result=result_cleaner(analysis_result)
 
    return clean_analysis_result