ByteChef LogoByteChef

MariaDB Vector Store

MariaDB Vector Store uses MariaDB 11.7+ native vector storage and similarity search capabilities to store and query document embeddings.

Categories: Artificial Intelligence

Type: mariaDbVectorStore/v1


Connections

Version: 1

custom

Properties

NameLabelTypeDescriptionRequired
urlJDBC URLSTRINGMariaDB JDBC connection URL (e.g., jdbc:mariadb://localhost:3306/mydb).true
usernameUsernameSTRINGMariaDB database username.true
passwordPasswordSTRINGMariaDB database password.true
tableNameTable NameSTRINGName of the database table used to store vector embeddings.false
schemaNameSchema NameSTRINGDatabase schema name. If not specified, the default schema is used.false
distanceTypeDistance TypeSTRING
Options COSINE, EUCLIDEAN
Distance function used for vector similarity comparison.false
dimensionsDimensionsINTEGERNumber of dimensions for the vector embeddings. If not specified, inferred from the embedding model.false
initializeSchemaInitialize SchemaBOOLEAN
Options true, false
Whether to create the vector store table automatically if it does not exist.false

Actions

Load Data

Name: load

Loads data into the vector store using LLM embeddings.

Example JSON Structure

{
  "label" : "Load Data",
  "name" : "load",
  "type" : "mariaDbVectorStore/v1/load"
}

Output

This action does not produce any output.

Search Data

Name: search

Query data from the vector store using LLM embeddings.

Properties

NameLabelTypeDescriptionRequired
queryQuerySTRINGThe query to be executed.true
topKTop KINTEGERThe top 'k' similar results to return.false
similarityThresholdSimilarity ThresholdNUMBERSimilarity threshold score to filter the search response by. Only documents with similarity score equal or greater than the threshold will be returned. A threshold value of 0 means any similarity is accepted. A threshold value of 1 means an exact match is required.false

Example JSON Structure

{
  "label" : "Search Data",
  "name" : "search",
  "parameters" : {
    "query" : "",
    "topK" : 1,
    "similarityThreshold" : 0.0
  },
  "type" : "mariaDbVectorStore/v1/search"
}

Output

The output for this action is dynamic and may vary depending on the input parameters. To determine the exact structure of the output, you need to execute the action.

How is this guide?

Last updated on

On this page