Search Results
https://dev.mysql.com/doc/relnotes/heatwave/en/news-9-4-1.html
These release notes were created with the assistance of MySQL HeatWave GenAI. MySQL HeatWave AutoML MySQL HeatWave GenAI MySQL HeatWave Lakehouse MySQL HeatWave MySQL HeatWave AutoML MySQL HeatWave AutoML now supports enhanced data preparation ...
https://dev.mysql.com/doc/internals/en/binlog-formats.html
Status of this subsection: Complete but not reviewed 2009-10-21 The binlog is organized as a linear sequence of events. An SQL query that modifies the database will generate one or more events and append them to the binlog. There are also auxiliary ...
https://dev.mysql.com/doc/heatwave/en/mys-hw-genai-generate-embeddings.html
This section describes how to generate vector embeddings using the ML_EMBED_ROW MySQL HeatWave GenAI routine. Vector embeddings are a numerical representation of the text that capture the semantics of the data and relationships to other data. You ...
https://dev.mysql.com/doc/heatwave/en/mys-hwgenai-hw-chat.html
The HEATWAVE_CHAT routine automatically calls the ML_RAG routine which loads an LLM and runs a semantic search on the available vector stores by default. If the routine cannot find a vector store, then it calls the ML_GENERATE routine and uses ...
https://dev.mysql.com/doc/heatwave/en/mys-hwgenai-ml-embed-row.html
The ML_EMBED_ROW routine uses the specified embedding model to encode the specified text or query into a vector embedding. The routine returns a VECTOR that contains a numerical representation of the specified text. This topic contains the ...
https://dev.mysql.com/doc/heatwave/en/mys-hwgenai-ml-embed-table.html
The ML_EMBED_TABLE routine runs multiple embedding generations in a batch, in parallel. 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 ...
https://dev.mysql.com/doc/heatwave/en/mys-hwgenai-ml-rag-table.html
The ML_RAG_TABLE routine runs multiple retrieval-augmented generation (RAG) queries in a batch, in parallel. The output generated for every input query is the same as the output generated by the ML_RAG routine. Note In versions older than MySQL ...
https://dev.mysql.com/doc/heatwave/en/mys-hwgenai-ml-rag.html
The ML_RAG routine performs retrieval-augmented generation (RAG) by: Taking a natural-language query. This routine aims to provide detailed, accurate, and contextually relevant answers by augmenting a generative model with information retrieved ...
https://dev.mysql.com/doc/heatwave/en/heatwave-errors.html
The following list contains all current MySQL HeatWave errors in numerical order. The entry for each error contains the error number, name (symbol), description, and suggested workaround for the condition that gave rise to the error. Error number: ...
https://dev.mysql.com/doc/heatwave/en/heatwave-system-variables.html
Most MySQL HeatWave variable settings are managed by OCI and cannot be modified directly. bulk_loader.data_memory_size Command-Line Format --bulk_loader.data_memory_size=# System Variable bulk_loader.data_memory_size Scope Global Dynamic Yes SET_VAR ...