app.py

import streamlit as st
from dotenv import load_dotenv

load_dotenv() ## load all env vriables from .env

import os

from PIL import Image
import google.generativeai as genai 

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

# create a function to load gemini pro vision
model = genai.GenerativeModel('gemini-pro-vision')

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

## create a function to return images bayets data

def input_image_details(uploaded_file):
    if uploaded_file is not None :
        # read the file into a bytes
        bytes_data = uploaded_file.getvalue()

        image_parts = [
            {
                "mime_type" : uploaded_file.type, # get the mime type of the uploaded file
                "data" : bytes_data
            }
        ] 
        return image_parts
    else :
        raise FileNotFoundError('No file uploaded')

## initialize our streamlit app

st.set_page_config(page_title = 'MultiLanguage Invoice Extractor')
st.header("MultiLanguage Invoice Extractor using Gemini Vision PRO ")

input = st.text_input('Input Prompt: ',key = 'input')
uploaded_file = st.file_uploader('Choose an image of the Invoice',type = ["jpg",'jpeg','png'])

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

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

input_prompt = """
you are a expert in understaning invoices. we will upload an image as invoice
and you will have to answer any questions based on the uploaded invoice image
"""

# if submit button is clicked

if submit :
    image_data = input_image_details(uploaded_file)
    response = get_gemini_response(input_prompt,image_data,input)
    st.subheader("The Response is ")
    st.write(response)