I’m making a recommendation system of the H&M Personalized Fashion Recommendations dataset so that it gives a user who bought a dress some recommendations on 2-3 other dresses he might be interested in, however I’m getting this error and I can’t move forward, could someone give me a hand? Thanks in advance

ratings = transactions[["customer_id", "article_id", "price"]]
ratings["customer_id"] = ratings["customer_id"].astype(str)
ratings["article_id"] = ratings["article_id"].astype(str)

user_ids = tf.constant(ratings["customer_id"].values, dtype=tf.string)
article_ids = tf.constant(ratings["article_id"].values, dtype=tf.string)


class HMRecommendationModel(tfrs.Model):
    def __init__(self):
        super().__init__()
        # Definisci gli embedding per gli utenti e gli articoli
        self.user_embeddings = tf.keras.layers.StringLookup(mask_token=None)
        self.article_embeddings = tf.keras.layers.StringLookup(mask_token=None)
        self.task = tfrs.tasks.Retrieval(metrics=tfrs.metrics.FactorizedTopK(articles["article_id"].unique()))

    def compute_loss(self, features, training=False):
        user_embeddings = self.user_embeddings(features["customer_id"])
        article_embeddings = self.article_embeddings(features["article_id"])
        return self.task(user_embeddings, article_embeddings)

# Addestra il modello
model = HMRecommendationModel()
model.compile(optimizer=tf.keras.optimizers.Adagrad(learning_rate=0.1))
model.fit({"customer_id": user_ids, "article_id": article_ids}, epochs=3)

user_id = "user_id_da_considerare"
_, recommended_articles = model({"customer_id": tf.constant([user_id], dtype=tf.string)})
print(f"Top 5 raccomandazioni per l'utente {user_id}: {recommended_articles[0, :5]}")

error:

ValueError: in user code:

File "/usr/local/lib/python3.10/dist-packages/keras/src/engine/training.py", line 1401, in train_function  *
    return step_function(self, iterator)
File "/usr/local/lib/python3.10/dist-packages/keras/src/engine/training.py", line 1384, in step_function  **
    outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/usr/local/lib/python3.10/dist-packages/keras/src/engine/training.py", line 1373, in run_step  **
    outputs = model.train_step(data)
File "/usr/local/lib/python3.10/dist-packages/tensorflow_recommenders/models/base.py", line 68, in train_step
    loss = self.compute_loss(inputs, training=True)
File "<ipython-input-8-3e90eeed72fc>", line 16, in compute_loss
    return self.task(user_embeddings, article_embeddings)
File "/usr/local/lib/python3.10/dist-packages/keras/src/utils/traceback_utils.py", line 70, in error_handler
    raise e.with_traceback(filtered_tb) from None
File "/tmp/__autograph_generated_file91f6wgvn.py", line 42, in tf__call
    scores = ag__.converted_call(ag__.ld(tf).linalg.matmul, (ag__.ld(query_embeddings), ag__.ld(candidate_embeddings)), dict(transpose_b=True), fscope)

ValueError: Exception encountered when calling layer 'retrieval' (type Retrieval).

in user code:

    File "/usr/local/lib/python3.10/dist-packages/tensorflow_recommenders/tasks/retrieval.py", line 160, in call  *
        scores = tf.linalg.matmul(

    ValueError: Shape must be rank 2 but is rank 1 for '{{node retrieval/MatMul}} = MatMul[T=DT_INT64, transpose_a=false, transpose_b=true](string_lookup/Identity, string_lookup_1/Identity)' with input shapes: [?], [?].


Call arguments received by layer 'retrieval' (type Retrieval):
  • query_embeddings=tf.Tensor(shape=(None,), dtype=int64)
  • candidate_embeddings=tf.Tensor(shape=(None,), dtype=int64)
  • sample_weight=None
  • candidate_sampling_probability=None
  • candidate_ids=None
  • compute_metrics=True
  • compute_batch_metrics=True