I have a react-native app where I scan the qr code using expo and takes images from my mobile phone, this image is rendered in the app and send it to a flask endpoint, the data is sent but gives an error in the return of the backend function.
React-native:

const sendImageToServer = async (base64Image) => {
        const url = 'http://127.0.0.1:5000/predict';
        try {
            console.log("Sending image to server...");
            const response = await fetch(url, {
                method: 'POST',
                headers: {
                    'Content-Type': 'application/json',
                },
                body: JSON.stringify({ image: base64Image })
            });
            const jsonResponse = await response.json();
            console.log("Response from server: ", jsonResponse);
        } catch (error) {
            console.error("Error sending image to server: ", error);
        }
    };

    const captureFrame = async () => {
        if (cameraRef.current) {
            const photo = await cameraRef.current.takePictureAsync({
                quality: 0.5, // Reduce quality to decrease image size and increase upload speed
                base64: true,
            });
            setCurrentFrame(photo.uri); // Update the current frame
            sendImageToServer(photo.base64);
        }
    };

and flask code is:

from flask import Flask, request, jsonify, render_template
import tensorflow as tf
import numpy as np
from PIL import Image
import io

from ultralytics import YOLO


app = Flask(__name__)

# Load your model (adjust path and model loading as necessary)
model = YOLO('D:/CMP Year two/second semester/Advanced micro/Project/detector/dirt-debris/dirt-debris.pt')

@app.route('/predict', methods=['POST'])
def predict():
    
    title = request.json['title']
    body = request.json['body']
    print(body)
    return jsonify({"methods" : "1"})

if __name__ == '__main__':
    app.run(debug=True, host='127.0.0.1', port=5000)

I actually want the flask file to process the image and make classification and then send results back.
Any ideas?