Search Results
https://dev.mysql.com/doc/heatwave/en/mys-hw-genai-quickstart.html
This quickstart shows how to set up a GenAI-powered Help Chat that uses the information available in MySQL HeatWave User Guide to provide answers to MySQL HeatWave-related questions. Note This quickstart assumes that you are familiar with MySQL ...
https://dev.mysql.com/doc/heatwave/en/mys-hw-genai-rag.html
The ML_RAG routine runs retrieval-augmented generation which aims to generate more accurate responses for your queries. As of MySQL 9.5.0, you can use hybrid search, which combines semantic search and keyword-based search to effectively retrieve ...
https://dev.mysql.com/doc/heatwave/en/mys-hw-genai-requirements.html
To use MySQL HeatWave GenAI, you need the following: A MySQL HeatWave DB system that meets the following requirements: The MySQL HeatWave DB system must be version 9.0.0 - Innovation or higher. For more information, see Creating a DB system and ...
https://dev.mysql.com/doc/heatwave/en/mys-hw-lakehouse-export-query-overview.html
This section provides an overview of exporting query results to Object Storage. Methods to Export Query Results You can export query results in the following ways. See OCIFS Documentation to learn more about OCIFS file format and its specifications. Pre-Authenticated Request (PAR): Create a temporary URL that is the export destination for the query ...
https://dev.mysql.com/doc/heatwave/en/mys-hw-lakehouse-export-query-permissions.html
Required Privileges to Export Query Results Ask the admin user to grant you the EXPORT_QUERY_RESULTS privilege. Replace user_name and database_name in the following command with the appropriate user name and database name. mysql>GRANT ...
https://dev.mysql.com/doc/heatwave/en/mys-hwaml-automl-workflow.html
A typical MySQL HeatWave AutoML workflow is described below: When you run the ML_TRAIN routine, MySQL HeatWave AutoML retrieves the data to use for training. The data can originate from either DB System tables or external Lakehouse tables. The ...
https://dev.mysql.com/doc/heatwave/en/mys-hwaml-load-model.html
You must load a machine learning model from the model catalog into MySQL HeatWave before running MySQL HeatWave AutoML routines other than ML_TRAIN. A model remains loaded and can be called repetitively by MySQL HeatWave AutoML routines until it is ...
https://dev.mysql.com/doc/heatwave/en/mys-hwaml-ml-explain-table.html
ML_EXPLAIN_TABLE explains predictions for an entire table of unlabeled data. Depending on your MySQL version, we recommend the following: Before MySQL 9.4.1, use the batch_size option to limit operations to batches of 10 to 100 rows by splitting ...
https://dev.mysql.com/doc/heatwave/en/mys-hwaml-ml-model-export.html
Use this routine to export a model from the model catalog to a user defined table. MySQL 9.0.0 also introduces support for large models that changes how MySQL HeatWave AutoML stores models. To learn how to use ML_MODEL_EXPORT to share models, see ...
https://dev.mysql.com/doc/heatwave/en/mys-hwaml-model-quality.html
ML_SCORE scores a model by generating predictions using the feature columns in a labeled dataset as input and comparing the predictions to ground truth values in the target column of the labeled dataset. You cannot score a model with a topic ...