How to predict the feature importance for complex ML model by SHAP?

I found that many times the output model of TPOT is a combination of multiple models, or feature processing，For example, this model ：_StackingEstimator(estimator=DecisionTreeRegressor(max_depth=7, min_samples_leaf=13, min_samples_split=15)),
PolynomialFeatures(degree=2, include_bias=False, interaction_only=False),
XGBRegressor(learning_rate=0.1, max_depth=5, min_child_weight=4, n_estimators=100, n_jobs=1, objective="reg:squarederror", subsample=0.6000000000000001, verbosity=0)_
Then it is difficult to predict the importance of the original features using SHAP values. Is there any way to restrict TPOT to outputting only relatively simple models?