11.2.3 MySQL HeatWave AutoML Limitations

The following limitations apply to MySQL HeatWave AutoML. For MySQL HeatWave limitations, see: Section 11.2.1, “MySQL HeatWave Limitations”.

Text Handling Limitations

• MySQL HeatWave AutoML only supports datasets in the English language.

• MySQL HeatWave AutoML does not support TEXT columns with NULL values.

• MySQL HeatWave AutoML does not support target columns (a column with ground truth values) with a TEXT data type.

• MySQL HeatWave AutoML does not support recommendation tasks with columns that have a TEXT data type.

• For the forecasting task, endogenous_variables cannot be in TEXT.

Account Name Limitations

• The ML_TRAIN routine does not support MySQL user names that contain a period. For example, a user named 'joe.smith'@'%' cannot run the ML_TRAIN routine. The model catalog schema created by the ML_TRAIN procedure incorporates the user name in the schema name (e.g., ML_SCHEMA_joesmith), and a period is not a permitted schema name character.

Memory Limitations

• The table used to train a model cannot exceed 10 GB, 100 million rows, or 1017 columns.

• As of MySQL 9.0.0, the shape you set for the MySQL HeatWave cluster in the DB system defines the total memory available to train a model and for all loaded models. For imported models, we recommend individual models have a size of 4GB or less. ML_TRAIN will fail to run and raises an error if it attempts to train a model larger than this. Before MySQL 9.0.0, the limit was 900 MB. To query all loaded models and relevant model sizes, see ML_MODEL_ACTIVE

• MySQL HeatWave on AWS only supports MySQL HeatWave AutoML with the MySQL HeatWave.256GB node shape. To use MySQL HeatWave machine learning functionality, select that shape when creating a MySQL HeatWave Cluster.

Routine and Query Limitations

• ML_EXPLAIN_TABLE and ML_PREDICT_TABLE are compute intensive processes, with ML_EXPLAIN_TABLE being the most compute intensive. We recommend the following:

  • ML_EXPLAIN_TABLE: Before MySQL 9.4.1, use the batch_size option to limit operations to batches of 10 to 100 rows by splitting large tables into smaller tables. For tables with over ten columns, we suggest a batch_size value of 10. As of MySQL 9.4.1, the batch_size option is deprecated. Limit the input table to a maximum of 100 rows. If the input table has more than ten columns, limit it to ten rows.

  • ML_PREDICT_TABLE: Before MySQL 9.4.1, limit operations to batches of rows by splitting large tables into smaller tables by using the batch_size option. For MySQL 9.4.1 and later, if ML_PREDICT_TABLE takes a long time to complete, manually limit input tables to a maximum of 1,000 rows.

  • See Track Progress for MySQL HeatWave AutoML Routines to learn more.

• ML_EXPLAIN, ML_EXPLAIN_ROW, and ML_EXPLAIN_TABLE routines limit explanations to the 100 most relevant features.

• The ML_PREDICT_TABLE ml_results column contains the prediction results and the data. This combination must be less than 65,532 characters.

• Concurrent MySQL HeatWave analytics and MySQL HeatWave AutoML queries are not supported. A MySQL HeatWave AutoML query must wait for MySQL HeatWave analytics queries to finish, and vice versa. MySQL HeatWave analytics queries are given priority over MySQL HeatWave AutoML queries.

• The ML_PREDICT_ROW, ML_MODEL_IMPORT, and ML_MODEL_EXPORT routines are not supported with the TwoTower recommendation model.

Other Limitations

• If you delete a recommendation model trained with the TwoTower model from the model catalog, you need to run a Delete Model API to manage the generated embedding tables.