Search Results
https://dev.mysql.com/doc/heatwave/en/mys-hwaml-onnx-import-overview.html
The prediction column must contain a JSON object literal of name value keys. You cannot directly load models in ONNX format (.onnx) into a MySQL table. The models require string serialization and conversion to Base64 encoding before you use the ...
https://dev.mysql.com/doc/heatwave/en/mys-hwaml-predictions-ml-predict-row.html
ML_PREDICT_ROW generates predictions for one or more rows of data specified in JSON format. The following example trains a dataset with the classification machine learning task. mysql> CALL sys.ML_TRAIN('census_data.census_train', 'revenue', ...
https://dev.mysql.com/doc/heatwave/en/mys-hwaml-prepare-a-forecasting-model.html
mysql> CREATE TABLE electricity_demand ( date DATE PRIMARY KEY, demand FLOAT NOT NULL, temperature FLOAT NOT NULL ); Insert the sample data into the table. This topic describes how to prepare the data to use for a forecasting machine learning model. To prepare the data for this use case, you set up a training dataset and a testing ...
https://dev.mysql.com/doc/heatwave/en/mys-hwaml-scoring-an-anomaly-detection-model.html
After generating predictions, you can score the model to assess its reliability. For a list of scoring metrics you can use with anomaly detection models, see Anomaly Detection Metrics. For this use case, you use the test dataset for validation. In ...
https://dev.mysql.com/doc/heatwave/en/mys-hwaml-using-an-anomaly-detection-model.html
Requirements for Generating Predictions As of MySQL 9.4.1, if you run ML_PREDICT_TABLE with the log_anomaly_detection task, at least one column must act as the primary key to establish the temporal order of logs. To generate predictions, use the ...
https://dev.mysql.com/doc/heatwave/en/mys-hwgenai-ml-embed-row.html
This topic contains the following sections: ML_EMBED_ROW Syntax Syntax Examples See Also ML_EMBED_ROW Syntax mysql> SELECT sys.ML_EMBED_ROW('Text'[, options]); options: JSON_OBJECT(keyvalue[, keyvalue] ...) keyvalue: { 'model_id', {'ModelID'} ...
https://dev.mysql.com/doc/heatwave/en/mys-hwgenai-ml-generate.html
The ML_GENERATE routine uses the specified large language model (LLM) to generate text-based content as a response for the given natural-language query. As of MySQL 9.4.1, the ML_GENERATE lets you generate text-based responses for queries ...
https://dev.mysql.com/doc/heatwave/en/mys-hwgenai-nl-sql.html
The routine also runs the generated SQL statement and displays the result set. You can use this routine for generating and running SQL queries only for databases and tables that you have access to. The routine automatically detects these errors, and ...
https://dev.mysql.com/doc/heatwave/en/mys-hwgenai-vector-store-load.html
Each object in the list can include the following parameters: urioptions: JSON_OBJECT(urioptskeyvalue[, urioptskeyvalue]) urioptskeyvalue: { 'uri', 'URI' |'table_name', 'TableName' } uri: specifies the additional URI. It can include the following ...
https://dev.mysql.com/doc/relnotes/heatwave/en/news-8-0-26.html
Advisor Auto Parallel Load Auto Scheduling Functionality Added or Changed Advisor The new MySQL HeatWave Advisor provides string column encoding and data placement key recommendations based on machine learning models, data analysis, and MySQL ...