[QST] Help w/ exporting Retrieval Model.

❓ Questions & Help

Details

my current set up is on a vertex ai workbench w/ Tesla T4 GPU, 120 GB RAM, 32vCPUs, and using nvcr.io/nvidia/merlin/merlin-tensorflow:nightly container image.

I am currently working on a retrieval based model and depending on the version of the dataset I use, I cannot export the query tower.

The different dataset's that I've been using are as follows:

v3: various continuous and categorical features for both users and the items we want to recommend.

• exporting the query tower works fine in this case.

v4: features of v3 + item embeddings generated from sentence transformer.

• dim size is 384
• in the NVTabular Workflow, I just tagged the embedding columns as item features. not sure if this is the cause of the issues but I wanted to include this just in case.

v5: features of v3 + item embeddings generated from sentence transformer + multi-hot encoding of user history as implicit feedback.

• dim of multi-hot encoding is 332
• in the NVTabular Workflow, I just tagged the these columns Categorify() >> TagAsUserFeatures(). not sure if this is the cause of the issues but I wanted to include this just in case.

so when training a model w/ either v4 or v5 and save the query encoder, I get the following message:
query_tower = model.query_encoder
query_tower.save(...)

• note: this screen shot is with v4, when using v5 ds, I get more functions that wont be available.

when I load the query_tower and then try to turn the model into a top_k_model I get another error.
query_tower = tf.keras.models.load_model(".../query_tower_based_on_v5",compile=False)
model = mm.TwoTowerModelV2(query_tower, candidate)
model.compile()
candidate_features = unique_rows_by_features(train, Tags.ITEM, Tags.ITEM_ID)
topk_model = model.to_top_k_encoder(candidate_features, k=10, batch_size=1)

sorry for cutting the error message off but its talking about the encoder for the query tower.

sorry for being private w/ the data but its not public.

I hope i was able to portray the issue and any suggestions would be appreciated!

Start with the v4 and v5 NVTabular feature definitions and the full errors from query_tower.save/load_model and model.to_top_k_encoder. Compare the working v3 export with v4 and v5, then determine whether the added item embeddings or multi-hot user-history features cause the failure; done means the unsupported operation is reproduced and its cause or required change is documented.