Embedding a categorical variable and concatenating with a numerical variable, in a many-to-one sequence problem with multiple features

I have a small data set where I track 4 variables across 4 time periods, 1 categorical and 1 numerical variable. Below is picture of data set that I am using:

• cat1 – Categorical variable encoded
• num1 – Numerical variable

Below is picture of my data set (to show the format; my X and Y is the same cause I am trying to learn how GRUs work and am not concerned much about the model accuracy).

Here is my GRU model code. It runs well and it predicts ok.

inputs = Input(shape=(4,2))
x = Bidirectional(GRU(256, activation='relu'))(inputs)
x = Dense(32, activation='relu')(x)
outputs = Dense(4)(x)
model = Model(inputs=inputs, outputs=outputs, name="func_loss_res")
model.summary()
plot_model(model, "my_first_model_with_shape_info.png", show_shapes=True)

model.compile(optimizer='adam', loss='mse')
my_callbacks = [tf.keras.callbacks.EarlyStopping(patience=10)]
print(X_train)
history = model.fit(X_train, Y_train, epochs=250, validation_split=0.25, batch_size=4, callbacks=my_callbacks)

My question is, if I were to Embed the cat1 variable say with 5 unique values and embedding size of 3 (I want to scale this model with 146 categories later and add 22 numerical variables), how can I concatenate cat1 and num1 to make it work for my given GRU? Any assistance is highly appreciated!