MOI preserves tables, flowcharts, charts, SmartArt, and embedded images across PDF and Office files, creating structured, traceable inputs for knowledge bases and Agents.
Excel floating images and formulas, PowerPoint flowcharts and SmartArt, and cross-page PDF tables lost geometry and reading order when flattened into text, reducing retrieval reliability.
The parser reconstructs tables as HTML and separates titles, notes, and embedded images. When reliable reconstruction is not possible, original table or image assets are preserved instead of silently dropped.
Structured content and source objects stay linked for multimodal indexing and evidence citation, while difficult cross-page and low-resolution cases use conservative handling with explicit review boundaries.