app.py

#AIzaSyBSA2bVH9C5uO4mwVE3OS12YMKa5D9AR1Q
from dotenv import load_dotenv
load_dotenv() #load all environment variables from .env
import streamlit as st 
from PIL import Image 
import google.generativeai as genai
import os
genai.configure(api_key=os.environ["GOOGLE_API_KEY"])

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_seetup(uploaded_file):
    if uploaded_file is not None:
        byte_data = uploaded_file.getvalue()
        imaage_parts = [
            {
                "mime_type":uploaded_file.type,
                "data" : byte_data
            }
        ]
        return imaage_parts
    else:
        raise FileNotFoundError("No file uploaded")
    
st.set_page_config(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","png","jpeg"])
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. We will upload a image as invoice and you will have to answer any questions based on the uploaded invoice image"""

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