app.py

## Invoice Extractor..

from dotenv import load_dotenv
load_dotenv() ## load all environment variables into the project
import streamlit as st
import os
from PIL import Image
import google.generativeai as genai

## Configuring API key
genai.configure(api_key = os.getenv("GOOGLE_API_KEY"))


## Function to load Gemini Pro Vision Model and get Response
def get_gemini_response(input, image, prompt):
    # Loading the Gemini Model
    model = genai.GenerativeModel('gemini-pro-vision')
    response = model.generate_content([input, image[0], prompt])

    return response.text


def input_image_setup(uploaded_file):
    if uploaded_file is not None:
        # read the file into bytes
        bytes_data = uploaded_file.getvalue()
        image_part = [{
            "mime_type": uploaded_file.type,
            "data": bytes_data
        }]
        return image_part
    else:
        raise FileNotFoundError("No File Uploaded...")
    

# Initialize our streamlit app
st.set_page_config(page_title= "Invoice Extractor")

st.markdown("<h1 style='font-size:24px;'>Query with LangChain & GenAI: Image file(Jpeg,Jpg,Png)</h1>", unsafe_allow_html=True)
# 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 Invoice')

input_prompt = """
you are an expert in understanding invoices. 
you will receive input images as invoices and you will 
have to answer questions based on the input image.
"""
## If Submit button is clicked...

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)