MySQL AI  /  AI-Powered Search and Content Generation  /  Supported LLM, Embedding Model, and Languages

5.4 Supported LLM, Embedding Model, and Languages

This topic provides the list of languages that GenAI feature of MySQL AI supports and the embedding models as well as large language models (LLMs) that are available.

This topic contains the following sections:

Viewing Available Models

Once you are connected to the DB System, you can view the list of available models as shown below:

mysql> SELECT * FROM sys.ML_SUPPORTED_LLMS;

The output is similar to the following:

+----------+-------------------------+-------------------+---------------------+---------------+
| provider | model_id                | availability_date | capabilities        | default_model |
+----------+-------------------------+-------------------+---------------------+---------------+
| HeatWave | llama3.2-3b-instruct-v1 | 2025-05-20        | ["GENERATION"]      |             1 |
| HeatWave | all_minilm_l12_v2       | 2024-07-01        | ["TEXT_EMBEDDINGS"] |             0 |
| HeatWave | multilingual-e5-small   | 2024-07-24        | ["TEXT_EMBEDDINGS"] |             1 |
+----------+-------------------------+-------------------+---------------------+---------------+

In-Database LLM

The following in-database LLM is available: llama3.2-3b-instruct-v1

In-Database Embedding Model

The following in-database embedding model is available:

  • all_minilm_l12_v2

  • multilingual-e5-small

Languages

GenAI feature of MySQL AI supports natural-language communication, ingesting documents, as well as generating text-based content in multiple languages. The quality of the generated text outputs depends on the training and ability of the LLM to work with the language.

Following is a list of languages supported by the GenAI:

  • English (en)

  • French (fr)

  • German (de)

  • Hindi (hi)

  • Italian (it)

  • Portuguese (pt)

  • Spanish (es)

  • Thai (th)

Note

To set the value of the language parameter in GenAI routines that support this parameter, do not use the language name to specify the language. Use the two-letter ISO 639-1 code for the language instead. For example, to use French, use the ISO 639-1 code for French, which is fr.