Thursday, July 25, 2024

Gemini Flash LLM use to process image

You can use following code to process images using Googel Gemini LLM. 

import streamlit as st
import os
import google.generativeai as genai
from PIL import Image

genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
model=genai.GenerativeModel("gemini-1.5-flash")

def get_gemini_response(input,image):
    if input!="":
        response=model.generate_content([input,image])
    else:
        response=model.generate_content(image)
    return response.text

st.set_page_config(page_title="Generative AI")
st.header("Gemini Image App")
input=st.text_input("input : ",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)
submit=st.button("Tell me about image")

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

Refer gitlab source for more information;

https://gitlab.com/sujithdc/gemini-ai-text-image

Gemini Pro AI Text Processing

You can use the following python code to process your text using Google Gemini GPT pro LLM model. To execute the code, you need to get API key from "https://aistudio.google.com/app/apikey" and install required python packages using "pip install <library>".

from dotenv import load_dotenv
load_dotenv()
import streamlit as st
import os
import google.generativeai as genai

genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
model=genai.GenerativeModel("gemini-pro")
def get_gemini_response(question):
    response=model.generate_content(question)
    return response.text

st.set_page_config(page_title="Generative AI")
st.header("Gemini AI App")
input=st.text_input("input : ",key="input")
submit=st.button("Ask Question")

if submit:
    response=get_gemini_response(input)
    st.subheader("Gemini Response")
    st.write(response)

Refer gitlab source for more information;

https://gitlab.com/sujithdc/gemini-ai-text-image