Covariance Estimation including uncertainties

I have a variable X with shape (100, 2) with uncertainties X_error (100, 2). I would like to estimate the covariance matrix between the 2 features X[:, 0] and X[:, 1]. How can I do that using a LKJCholesky prior and MvNormal (or using something else)? How do I incorporate X_error into the below code?

with pm.Model() as model:
    chol, corr, stds = pm.LKJCholeskyCov(
        "chol", n=2, eta=2.0, sd_dist=pm.Exponential.dist(1.0), compute_corr=True
    )
    cov = pm.Deterministic("cov", chol.dot(chol.T))
    μ = pm.Normal("μ", 0.0, 10, shape=2, testval=X.mean(axis=0))
    obs = pm.MvNormal("obs", μ, chol=chol, shape=(len(X),2), observed=X)