app.py

import google.generativeai as genai
import gradio as gr
import numpy as np
import PIL.Image
import os

gemini_api_key = os.getenv("GEMINI_API_KEY")
genai.configure(api_key=gemini_api_key)

def ImageChat(image, prompt):

  # load model
  model = genai.GenerativeModel("gemini-1.5-flash")

  # check image file and convert to a Numpy array
  if isinstance(image, np.ndarray):

        img = PIL.Image.fromarray(image)
  else:
        img = PIL.Image.open(image)

  response =  model.generate_content([prompt, img])

  return response.text


app = gr.Interface(ImageChat,
                   inputs = [gr.Image(label = "Image"), gr.Text(label = "Prompt")],
                   outputs = gr.Markdown("<center><strong>Response</strong></center>"),
                   title = "Image Chat",
                   theme = "Taithrah/Minimal")

app.launch()