Vector Stores
A vector store indexes and stores vector embeddings (the vectorial representation of documents) for fast retrieval and semantic search. Embeddings are generated by AI models, in the context of machine learning these features represent different dimensions of the data that are essential for understanding patterns, relationships, and underlying structures.
You handle the vector stores in Administration > Artificial Intelligence > Embeddings > Vector Stores
At the time of writing, LogicalDOC just supports MariaDB as vector store; in the future, more vector store providers will be made available.
It is therefore required to insert the connection details to a MariaDB (version 11.8 or greater) database; you may use the wizard icon to get some help in composing the connection Url.
MariaDB
Since LogicalDOC 9.2.2, the Windows installer also includes a modern MariaDB with vector capabilities and automatically uses it without having you to take any action. In the same way, if you already installed LogicalDOC using an older version but already connected to a MariaDB >= 11.8, the 9.2.2 update will automatically use it as vector store.
In all the other cases, you must provide an installation of MariaDB 11.8 or greater and manually configure the connection to it.
Please refer to the product's website for installing MariaDB: https://mariadb.org/download