MySQL HeatWave User Guide

7.6.1 Generate New Content

The following sections in this topic describe how to generate new text-based content using MySQL HeatWave GenAI:

Before You Begin

Generate Content

To generate text-based content using MySQL HeatWave GenAI, perform the following steps:

  1. To define your natural-language query, set the @query variable: 

    mysql> SET @query="QueryInNaturalLanguage";

    Replace QueryInNaturalLanguage with a natural-language query of your choice. For example: 

    mysql> SET @query="Write an article on Artificial intelligence in 200 words.";

  2. To generate text-based content, pass the query to the LLM using the ML_GENERATE routine with the task parameter set to generation: 

    mysql> SELECT sys.ML_GENERATE(@query,
JSON_OBJECT("task", "generation", "model_id", "ModelID", "language", "Language"));

    Replace the following:

    • ModelID: LLM to use.

    • Language: the two-letter ISO 639-1 code for the language you want to use. Default language is en, which is English. To view the list of supported languages, see Languages.

      The language parameter is supported as of MySQL 9.0.1-u1.

    For example: 

    mysql> SELECT sys.ML_GENERATE(@query,
JSON_OBJECT("task", "generation", "model_id", "mistral-7b-instruct-v3", "language", "en"));

    Text-based content that is generated by the LLM in response to your query is printed as output. It looks similar to the text output shown below: 

    | {"text": "\nTitle: Artificial Intelligence in 2023: A New Era of
Innovation\n\nArtificial Intelligence (AI) has been a transformative
force, reshaping various sectors and revolutionizing our daily lives.
In 2023, AI continues to evolve at an unprecedented pace, offering
unparalleled opportunities for innovation and growth.\n\nOne significant
development is the advancement of machine learning algorithms, enabling
AI systems to learn from vast amounts of data more efficiently than
ever before. This progress has led to improvements in areas such as image
recognition, natural language processing, and predictive analytics, making
AI more intuitive and user-friendly.\n\nAnother notable trend is the
increasing integration of AI into everyday devices, from smartphones to
home appliances. These advancements not only enhance convenience but also
contribute to energy savings and improved safety features.\n\nIn the
realm of healthcare, AI is playing a crucial role in diagnostics, drug
discovery, and personalized treatment plans. By analyzing vast amounts of
medical data, AI can help doctors make more accurate diagnoses and develop
targeted therapies, ultimately improving patient outcomes.\n\nHowever,
with great power comes great responsibility. As AI becomes more pervasive,"} |

Run Batch Queries

To run multiple generation queries in parallel, use the ML_GENERATE_TABLE routine. This method is faster than running the ML_GENERATE routine multiple times.

Note

In versions older than MySQL 9.2.1, to alter an existing table or create a new table, MySQL requires you to set the sql-require-primary-key system variable to 0.

The ML_GENERATE_TABLE routine is supported as of MySQL 9.0.1-u1.

To run the steps in this section, you can create a new database demo_db and table input_table: 

mysql> CREATE DATABASE demo_db;
mysql> USE demo_db;
mysql> CREATE TABLE input_table (id INT AUTO_INCREMENT, Input TEXT, primary key (id));
mysql> INSERT INTO input_table (Input) VALUES('Describe what is MySQL in 50 words.');
mysql> INSERT INTO input_table (Input) VALUES('Describe Artificial Intelligence in 50 words.');
mysql> INSERT INTO input_table (Input) VALUES('Describe Machine Learning in 50 words.');

To run batch queries using ML_GENERATE_TABLE, perform the following steps:

  1. In the ML_GENERATE_TABLE routine, specify the table columns containing the input queries and for storing the generated text-based responses: 

    mysql> CALL sys.ML_GENERATE_TABLE("InputDBName.InputTableName.InputColumn", "OutputDBName.OutputTableName.OutputColumn",
JSON_OBJECT("task", "generation", "model_id", "ModelID", "language", "Language"));

    Replace the following:

    • InputDBName: the name of the database that contains the table column where your input queries are stored.

    • InputTableName: the name of the table that contains the column where your input queries are stored.

    • InputColumn: the name of the column that contains input queries.

    • OutputDBName: the name of the database that contains the table where you want to store the generated outputs. This can be the same as the input database.

    • OutputTableName: the name of the table where you want to create a new column to store the generated outputs. This can be the same as the input table. If the specified table doesn't exist, a new table is created.

    • OutputColumn: the name for the new column where you want to store the output generated for the input queries.

    • ModelID: LLM to use.

    • Language: the two-letter ISO 639-1 code for the language you want to use. Default language is en, which is English. To view the list of supported languages, see Languages.

    For example: 

    mysql> CALL sys.ML_GENERATE_TABLE("demo_db.input_table.Input", "demo_db.output_table.Output",
JSON_OBJECT("task", "generation", "model_id", "mistral-7b-instruct-v3", "language", "en"));

  2. View the contents of the output table: 

    mysql> SELECT * FROM output_table\G
*************************** 1. row ***************************
    id: 1
Output: {"text": "\nMySQL is an open-source relational database
management system (RDBMS) that uses SQL (Structured Query
Language) to manage and manipulate data. It's widely used for
web-based applications, including those built with PHP, Python,
and Java. MySQL offers high performance, reliability, and 
scalability, making it a popular choice for developers 
worldwide.\n\n[DONE]", "error": null}
*************************** 2. row ***************************
    id: 2
Output: {"text": "\nArtificial Intelligence (AI) refers to the 
simulation of human intelligence in machines that are programmed 
to think, learn, and make decisions like humans. AI can perform 
tasks such as visual perception, speech recognition, 
decision-making, and language translation. It's a rapidly 
evolving field with applications in various sectors including 
healthcare, finance, and entertainment.\n\n[END]", 
"error": null}
*************************** 3. row ***************************
    id: 3
Output: {"text": "\nMachine Learning is a method of data 
analysis that automates the building of analytical models. It's 
based on algorithms and statistical models that computer 
systems use to perform tasks without being explicitly programmed,
learning from data instead.\n\n[END]", "error": null}

    As of MySQL 9.3.0, the output table generated using the ML_GENERATE_TABLE routine contains an additional details for error reporting. In case the routine fails to generate output for specific rows, details of the errors encountered and default values used are added for the row in the output column.

If you created a new database for testing the steps in this section, ensure that you delete the database to avoid being billed for it: 

mysql> DROP DATABASE demo_db;

To learn more about the available routine options, see ML_GENERATE_TABLE Syntax.

What's Next

Learn how to Summarize Existing Content.

MySQL Documentation Library