14.2.4 HeatWave GenAI In-databse Embedding Models

For MySQL 9.3.2 and later, see View Available Models on how to view a list of the supported in-database embedding models.

For MySQL 9.3.1 and earlier, HeatWave GenAI supports the following in-database embedding models:

• multilingual-e5-small
  • As of MySQL 9.3.0, HeatWave GenAI uses this embedding model by default for encoding text or documents in all supported languages (in earlier versions of MySQL, HeatWave GenAI uses this embedding model by default for encoding text or documents in all supported languages other than English).
  • As of MySQL 9.2.1, can be used for encoding text or documents in all supported languages (in earlier versions of MySQL, can be used for encoding text or documents in all supported languages other than English).
  • This embedding model is available as of MySQL 9.0.1.
• all_minilm_l12_v2:
  • In MySQL 9.2.2 and earlier versions, HeatWave GenAI uses this embedding model by default for encoding English text or documents.
  • As of MySQL 9.2.1, can be used for encoding text or documents in any supported language
  • In earlier versions of MySQL, can be used for encoding text or documents in English only.

Use these models with ML_EMBED_ROW and ML_EMBED_TABLE (see HeatWave GenAI routines).