Knowledge bases

A knowledge base is a core concept in the MatrixOne Intelligence product model. This page explains the problems it solves, its relationships with other objects, and its usage boundaries.

Definition

  • A knowledge base combines sources, semantic configuration, searchable chunks, and versions.

  • Files or tables provide sources of facts, chunks control retrieval granularity, and semantic configuration describes the business meaning of fields and entities.

  • Evaluation sets are used to continuously compare retrieval results and the evidence supporting answers.

Object relationships

  1. Knowledge sources come from Catalog, so source state and authorization affect indexing and retrieval.

  2. Agents can bind knowledge bases and retrieve relevant chunks at conversation runtime as evidence for answers.

  3. Changes to sources, parsing, chunking, or semantics produce new processing results that must be validated before consumers switch to them.

Design principles

  • Use least privilege and keep credentials in managed configuration.

  • Start by validating with minimal data or test objects, then expand the scope.

  • Version executable configuration and retain each run as an execution record.

  • Do not equate a visible entry with backend availability or resource authorization.

Note

These pages follow the current MOI 5.0 product model. If an entry is missing, check the workspace, permissions, and feature flags.

Operational guidance