LlamaIndex proposes two-pass just-in-time OCR for agent document pipelines

LlamaIndex proposes a two-pass just-in-time OCR pattern for agents working through document collections, avoiding parsing every page upfront.

LiteParse, an open-source Rust tool supporting 50+ formats, performs a fast layout-aware first pass with bounding boxes, headings, tables, and a per-page complexity flag, processing a full data room in 32 seconds.

LlamaParse then parses only the pages needing deeper analysis, returning cell-level tables, bounding boxes, and confidence scores.