app.py

from dotenv import load_dotenv

load_dotenv()  # take environment variables from .env.

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


import google.generativeai as genai


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

## 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")
        st.error('Please upload an image', icon="🚨")


##initialize our streamlit app

st.set_page_config(page_title="Image Chat")

st.header("Upload an Image and begin to chat")

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: ",key="input")
# if input is None:
#      st.error('Please add an input', icon="🚨")

#submit=st.button("Run")

input_prompt = """
               Analyze the image and give user a very descriptive information on the details in the image
               """

## If ask button is clicked

if 'messages' not in st.session_state:
    st.session_state['messages'] = [] #[{"role": "assistant", "content": "How can I help you?"}]

for msg in st.session_state.messages:
    st.chat_message(msg["role"]).write(msg["content"])


if prompt := st.chat_input():
    # if not openai_api_key:
    #     st.info("Please add your OpenAI API key to continue.")
    #     st.stop()

    #client = OpenAI(api_key=openai_api_key)
    #client = OpenAI()
    image_data = input_image_setup(uploaded_file)
    st.session_state.messages.append({"role": "user", "content": prompt})
    st.chat_message("user").write(prompt)
    #response = client.chat.completions.create(model="google/gemma-2b-it", messages=st.session_state.messages)
    response=get_gemini_response(input_prompt,image_data,prompt)

    msg = response  #response.choices[0].message.content
    st.session_state.messages.append({"role": "assistant", "content": msg})
    st.chat_message("assistant").write(msg)