app.py

import streamlit as st
import os
import pathlib
import textwrap
from PIL import Image

import google.generativeai as genai

genai.configure(api_key='AIzaSyCeNgXfZx0kJ736XFVtxXxev_RdscB0i5s')

## Function to load OpenAI model and get respones

def get_gemini_response(input,image,prompt):
    model = genai.GenerativeModel('gemini-pro-vision')
    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("Generative AI : Business Card Reader")
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)
input=st.text_input("Input Prompt(optional): ",key="input")


submit=st.button("Submit")

input_prompt = """
               You are an expert in understanding business cards.
               Input: Image of a business card
               Task: Extract and label the following information in JSON format:
               Labels : person_name, company_name, occupation, contact_number, email addresse, website, address(street address, city, state, pincode), other_details (services, features, etc.)
               Constraints: Do not include missing information. Maintain appropriate data types (e.g., phone numbers as strings).
               """

## If ask button is clicked

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