Search Results
https://dev.mysql.com/doc/mysql-ai/9.7/en/mys-ai-genai-byo-embedding-tables.html
The ML_RAG and ML_RAG_TABLE routines let you specify the table column names to use as filters for finding relevant tables for context retrieval. In addition to the specified column names, the ML_RAG and ML_RAG_TABLE routines use the name of the ...
https://dev.mysql.com/doc/heatwave/en/mys-hw-genai-byo-embedding-tables.html
The ML_RAG and ML_RAG_TABLE routines let you specify the table column names to use as filters for finding relevant tables for context retrieval. In addition to the specified column names, the ML_RAG and ML_RAG_TABLE routines use the name of the ...
https://dev.mysql.com/doc/heatwave/en/mys-hw-genai-rag.html
As of MySQL 9.2.1, for context retrieval, the ML_RAG routine uses the name of the embedding model used to embed the input query to find relevant vector store tables that contain vector embeddings from the same embedding model. This topic contains ...
https://dev.mysql.com/doc/heatwave/en/mys-hwgenai-vector-store-load.html
language: specifies the text content language used in the files to be ingested into the vector store. embed_model_id: specifies the embedding model to use for encoding the text. In earlier versions of MySQL, default value is minilm for English text ... The VECTOR_STORE_LOAD routine generates vector embedding for the specified files or folders that are stored in the bucket, and loads the embeddings into a new vector store ...
https://dev.mysql.com/doc/refman/9.7/en/innodb-parameters.html
It does not apply to external pages used for TEXT or BLOB entries. innodb_ft_aux_table System Variable innodb_ft_aux_table Scope Global Dynamic Yes SET_VAR Hint Applies No Type String Specifies the qualified name of an InnoDB table containing a ...
https://dev.mysql.com/doc/refman/9.7/en/xml-functions.html
(Bug #32911) ExtractValue(xml_frag, xpath_expr) ExtractValue() takes two string arguments, a fragment of XML markup xml_frag and an XPath expression xpath_expr (also known as a locator); it returns the text (CDATA) of the first text node which is a ... Table 14.16 XML Functions Name Description ExtractValue() Extract a value from an XML string using XPath notation UpdateXML() Return replaced XML fragment This section discusses XML and related functionality in ...
https://dev.mysql.com/doc/heatwave/en/mys-hw-genai-summarize-content.html
The following sections in this topic describe how to summarize exiting content using MySQL HeatWave GenAI: Before You Begin Summarize Text Run Batch Queries What's Next Before You Begin Review the MySQL HeatWave GenAI requirements and privileges.
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. The generated table contains text segments that are used as input text for the ML_GENERATE and ML_GENERATE_TABLE routines ...You need to first ingest these documents into vector store tables using Auto Parallel ...
https://dev.mysql.com/doc/heatwave/en/mys-hw-genai-vector-store-load.html
The specified LLM must be capable of processing both textual and visual inputs. As of MySQL 9.3.2, you can optionally set the following chunking parameters for customized text segmentation during vector store creation: SplitBy: method to use for ...
https://dev.mysql.com/doc/refman/9.7/en/audit-log-filter-definitions.html
query_digest([str]) This function has differing behavior depending on whether an argument is given: With no argument, query_digest returns the statement digest value corresponding to the statement literal text in the current event. As Table 8.43, ...