app.py

# importing libraries
import streamlit as st
import google.generativeai as genai
from dotenv import load_dotenv
from PIL import Image
import os

load_dotenv() # load all the environment variables from .env

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

# Function to load Gemini Pro Vision
# In Gemini Pro, model takes it in a list
model = genai.GenerativeModel('gemini-pro-vision')

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

def input_image_details(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")
    

# streamlit setup
st.set_page_config(layout="wide", page_title="Multilanguage Invoice Extractor")

st.header("Gemini Application")
input=st.text_input("Input Prompt: ",key="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, caption="Uploaded Image.", use_column_width=True)

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

input_prompt = """
 You are an expert in understanding invoices.
               You will receive input images as invoices &
               you will have to answer questions based on the input 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)