brain.py

import os
from dotenv import load_dotenv

# Load environment variables
load_dotenv()
GOOGLE_AI_STUDIO_API_KEY = os.environ.get("GOOGLE_AI_STUDIO_API_KEY")

import base64
def encode_image(image_path):   
    image_file=open(image_path, "rb")
    return base64.b64encode(image_file.read()).decode('utf-8')

#Step3: Setup Multimodal LLM 
import google.generativeai as genai

def analyze_image_with_query(query, model, encoded_image):
    genai.configure(api_key=GOOGLE_AI_STUDIO_API_KEY)
    
    # Setup the model
    gemini_model = genai.GenerativeModel(model)
    
    # Create the content with text and image
    image_parts = [
        {
            "mime_type": "image/jpeg",
            "data": encoded_image
        }
    ]
    
    # Generate response
    response = gemini_model.generate_content(
        contents=[
            query,
            image_parts[0]
        ]
    )

    return response.text