app.py

from turtle import up
from dotenv import load_dotenv
import streamlit as st
import os
from PIL import Image
import google.generativeai as genai

load_dotenv()

genai.configure(api_key = os.getenv('GOOGLE_API_KEY'))

model = genai.GenerativeModel('gemini-pro-vision')

def get_response(input, image, prompt):
    response = model.generate_content([input, image[0], prompt])
    return response.parts

def input_image_setup(image):
    if image is not None:
        data = image.getvalue()

        image_data = [
            {
                "mime_type": image.type,
                "data": data
            }
        ]
        return image_data

    else:
        raise FileNotFoundError("NO FILE UPLOADED.")

st.set_page_config('Invoice Extractor')
st.header('Gemini Application')


prompt = st.text_input("Enter Prompt : " , key='prompt_input')
input = st.text_input("what do you want to know : " , key='user_input')
uploaded_file = st.file_uploader("Choose an image " , type=["jpg", "jpeg", "png"])

image = ""
if uploaded_file is not None:
    image = Image.open(uploaded_file)
    st.image(image, use_column_width=True)

submit = st.button("Tell me about the image")

if submit:
    image_data = input_image_setup(uploaded_file)
    response = get_response(input=input, image=image_data, prompt=prompt)
    st.subheader("The response is : ")
    st.write(response)




# You are an expert food analyst

# List all food items shown in image


# You are an invoice extractor

# what is total amount