vision.py

from dotenv import load_dotenv

load_dotenv()

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

import google.generativeai as genai

os.getenv("GOOGLE_API_KEYS")
genai.configure(api_keys = os.getenv("GOOGLE_API_KEYS"))

#function to load genai model and get response

def get_gemini_response(input,image)
    model = genai.GenerativeModel('gemini-pro-vision')
    if input!="":
        response = model.generate_content([input,image])
    else:
        response  = model.generate_content(image)
    return response.text      


##streamlit

st.header("Decoding Data Science image Recognition Demo")
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)


if submit:
    response= get_gemini_response(input,image)
    st.subheader("The Image Response is")
    st.write(response)