app.py

from dotenv import load_dotenv

load_dotenv()  # take environment variables from .env.

import streamlit as st
import os
from PIL import Image


import google.generativeai as genai


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

## Function to load OpenAI model and get respones

def get_gemini_response(input,image,prompt):
    model = genai.GenerativeModel('gemini-1.5-flash')
    response = model.generate_content([input,image[0],prompt])
    return response.text
    

def input_image_setup(uploaded_file):
    # Check if a file has been uploaded
    if uploaded_file is not None:
        # Read the file into 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="Gemini Image Demo")

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

input_prompt="""
You are an expert in understanding invoices. We will upload a a image as invoice
and you will have to answer any questions based on the uploaded invoice image. If the required information is not available in the uploaded image,
say it and then try to answer according to your own capability. Also mention that the answer is according to your information.
If the input prompt is not related to the invoice, mention it and then answer according to your capabilities.
"""


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