PlanSightRAG: A Visual-First Multimodal RAG for Automating Question Answering and Compliance Checking for Civil Standard Plans
Presents novel architecture for multimodal RAG with specialized applications in civil engineering compliance automation.
AI Summary
Researchers developed PlanSightRAG, a visual-first RAG system that achieves 91.47% recall on zero-shot retrieval for civil engineering plan compliance checking.
Excerpt
Civil infrastructure compliance checking has long relied on engineers manually reading legacy 2D plans; however, OCR-based automation strips away the geometry and layout essential for interpreting these plans. We present a Visual-First Multimodal Retrieval-Augmented Generation (RAG) framework called PlanSightRAG. It indexes and reasons directly over plan imagery, integrates a ColNomic-3B multi-vector retrieval, an agentic Planner-Retriever-Auditor-Synthesizer, and MaxSim heatmaps as an evidence
