Deploy model on vertex ai endpoint

[theophileleparm]

I am trying to deploy a simple model on GCP whit a docker image (i want to deploy the model on a customize container because it will change later) 

This is my hello world model : 

from fastapi import FastAPI
import joblib
import os

app = FastAPI()

# Chargement du modèle
model = joblib.load('model.joblib')

AIP_HEALTH_ROUTE = os.environ.get('AIP_HEALTH_ROUTE', '/health')

@app.post("/predict")
def predict(input: list):
    prediction = model.predict([input])
    return {"prediction": prediction.tolist()}

@app.get(AIP_HEALTH_ROUTE, status_code=200)
async def health():
    return {'health': 'ok'}

# Utiliser une image de base Python
FROM python:3.8-slim

# Définir le répertoire de travail
WORKDIR /app

# Copier les fichiers nécessaires dans le conteneur
COPY model.joblib model.joblib
COPY main.py main.py

# Installer les dépendances
RUN pip install fastapi uvicorn scikit-learn joblib python-multipart

# Exposer le port pour FastAPI
EXPOSE 80

# Commande pour exécuter l'application
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "80"]

import numpy as np
from sklearn.linear_model import LinearRegression
import joblib

# Création de données d'exemple
X = np.array([[1, 1], [1, 2], [2, 2], [2, 3]])
y = np.dot(X, np.array([1, 2])) + 3

# Entrainement du modèle
model = LinearRegression().fit(X, y)

# Sauvegarde du modèle
joblib.dump(model, 'model.joblib')

i put the docker image on my artifact registry but when i deployed it on a endpoint in vertex ai, it is not working and i don't have any logs
Could you help me plz