Some PDIs are currently unavailable, and PDI actions are paused. View the latest updates here. Read More

Try NLU Model Error

gustavocami
Tera Contributor

Hello!

I was creating new Vocabulary Sources and Entities for one NLU Model (it's included in a Multi-lingual NLU Model set). 

After creation, I trained the model, and then when I tried to test in the NLU Workbench, the website threw an error:

Exception caught in the predict call - reason: {"status":"failure","exception":"sn_ml.MLServiceUtil.predict(): com.snc.ml.prediction.common.ServiceException: java.lang.Exception: SE0217:The solution metadata is null. Unable to retrieve: ml_x_bueu_global_global_ab2768e31b5435907c4bdd39cd4bcba9_1 [knowledge_pb.knowledge_pbCompiledFsa.json, knowledge_pb.knowledge_pb.zip, lookupSourceConfig.json]"}

gustavocami_0-1783986875982.png


I tried to Sync the Vocabulary sources again and retrain, but it didn't work.

6 REPLIES 6

@gustavocami 

You find references to these solutions in sys_nlu_vocabulary as  provided in @Vikram Reddy's response. Vocabulary source lists (Static Lookups) are only trained with the NLU Model, and cannot be manually synced like Vocabulary source tables (Table Lookups). Either follow the steps provided by Vikram or make a small change on the Vocabulary source list, and it will trigger the retraining of the vocabulary source list when you train the NLU Model again. BR, Brian