Documentation Home
HeatWave Release Notes
Related Documentation Download these Release Notes
PDF (US Ltr) - 382.4Kb
PDF (A4) - 382.2Kb


HeatWave Release Notes  /  Changes in MySQL HeatWave  /  Changes in MySQL HeatWave 9.0.0 (2024-07-02, General Availability)

Changes in MySQL HeatWave 9.0.0 (2024-07-02, General Availability)

MySQL HeatWave AutoML

  • MySQL HeatWave AutoML has increased the maximum model size from 900MB. The MySQL HeatWave cluster shape you set for a DB system now defines the total memory available to train a model and for all loaded models. For imported models, we recommend individual models have a size of 4GB or less. (WL #15931)

MySQL HeatWave Autopilot

  • MySQL HeatWave Autopilot includes improvements to cardinality estimation for queries that run in MySQL HeatWave and MySQL HeatWave Lakehouse. This improves the query plan, and provides improved performance (WL #15995)

  • MySQL HeatWave Autopilot now includes Auto Indexing Advisor that offers indexing suggestions to improve the performance and latency of OLTP workloads running on the MySQL HeatWave primary engine. (WL #15663)

MySQL HeatWave GenAI

  • MySQL HeatWave GenAI introduces similarity search capabilities that support the DISTANCE function that measures the distance between two vector values. It can include an optional distance_metric that can have a value of DOT, COSINE or EUCLIDIAN. This is available in the primary and secondary engines. (WL #16081)

  • MySQL HeatWave GenAI introduces the new native VECTOR data type and in-database vector store support. This provides a fast, end-to-end, fully integrated pipeline which automates the vector store creation:

    • Reading unstructured data in PDF, HTML, TXT, PPT or DOCX format from object store.

    • Parsing the text in the documents.

    • Partitioning the text into smaller paragraphs and segments.

    • Encoding the paragraphs.

    • Storing the encoded paragraphs in a standard MySQL table in MySQL HeatWave.

    (WL #16106)

  • MySQL HeatWave GenAI introduces a set of intuitive chat functionalities that enable enterprises to quickly build their own AI powered chatbot. It also introduces an out-of-the-box chatbot – MySQL HeatWave Chat, which integrates the chat functionalities that enable users to interact with MySQL HeatWave using natural language in addition to SQL. (WL #16248)

  • MySQL HeatWave GenAI introduces in-database LLM with support for the following LLMs, see Perform AI-Powered Search and Content Generation:

    • Mistral-7B-Instruct.

    • Llama-2-8B-Instruct.

    • LLMs from OCI GenAI.

    (WL #15844, WL #16145)

MySQL HeatWave Lakehouse

  • MySQL HeatWave Lakehouse now supports unstructured documents, and loads them to the GenAI vector store. Supported formats include PDF, HTML, TXT, PPT and DOCX. (WL #16100)

  • MySQL HeatWave Lakehouse introduces Lakehouse Incremental Load that uses change propagation to refresh data views following changes to a loaded table. (WL #15817)

MySQL HeatWave

Functionality Added or Changed