Search Results
https://dev.mysql.com/doc/heatwave/en/mys-hw-genai-byo-embedding-tables.html
As of MySQL 9.2.1, MySQL HeatWave GenAI lets you use tables containing your own vector embedding to run retrieval-augemented generation (RAG) with vector search. The ML_RAG and ML_RAG_TABLE routines let you specify the table column names to use as ...
https://dev.mysql.com/doc/heatwave/en/mys-hw-genai-generate-content.html
The following sections in this topic describe how to generate new text-based content using MySQL HeatWave GenAI: Before You Begin Generate Content Run Batch Queries What's Next Before You Begin Review the MySQL HeatWave GenAI requirements and ...
https://dev.mysql.com/doc/mysql-ai/9.5/en/mys-mysqlai-ml-generate.html
The ML_GENERATE routine uses the specified large language model (LLM) to generate text-based content as a response for the given natural-language query. It can include the following parameters: task: specifies the task expected from the LLM.
https://dev.mysql.com/doc/heatwave/en/mys-hwgenai-ml-generate-table.html
The ML_GENERATE_TABLE routine runs multiple text generation or summarization queries in a batch, in parallel. The output generated for every input query is the same as the output generated by the ML_GENERATE routine. Note In versions older than ...
https://dev.mysql.com/doc/heatwave/en/mys-hw-genai-summarize-docs.html
As of MySQL 9.4.1, MySQL HeatWave GenAI lets you generate text summaries for unstructured files available in Object Storage. You need to first ingest these documents into vector store tables using Auto Parallel Load. The generated table contains ...
https://dev.mysql.com/doc/refman/8.4/en/mysql-cluster-programs-ndb-import.html
ndb_import imports CSV-formatted data, such as that produced by mysqldump --tab, directly into NDB using the NDB API. ndb_import requires a connection to an NDB management server (ndb_mgmd) to function; it does not require a connection to a MySQL ...
https://dev.mysql.com/doc/heatwave/en/mys-hw-about-heatwave.html
MySQL HeatWave is a fully-managed cloud service that enables organizations to efficiently run analytics, transactional processing, machine learning, generative AI, and vector processing using a single service without the need for extract, transfer, ...
https://dev.mysql.com/doc/heatwave/en/mys-hwaml-nl2ml.html
MySQL 9.4.0 introduces the NL2ML (natural language to machine learning) routine, which provides step-by-step guidelines on using MySQL HeatWave AutoML for a particular business problem. Use this routine to ask general questions about MySQL HeatWave ...
https://dev.mysql.com/doc/heatwave/en/mys-hw-genai-vector-store-load.html
This section describes how to generate vector embeddings for files or folders stored in Object Storage, and load the embeddings into a vector store table. If not already done, create an Oracle Cloud Infrastructure (OCI) bucket for storing files ...
https://dev.mysql.com/doc/heatwave/en/mys-hw-silos.html
Figure 1.3 MySQL HeatWave Features MySQL HeatWave MySQL HeatWave is ideal for data warehousing, real-time analytics, mixed workloads, transactional processing, and machine learning workloads when the main data source is the DB System without needing ...