Multimodal RAPTOR for Disaster Documents using ColVBERT & BLIP. Hierarchical retrieval system over 46 tsunami-related PDFs (2378 pages), combining BLIP-based image captioning, ColVBERT embeddings, and GPT-OSS-20b long-context summarization. Optimized for fast multimodal tree construction and disaster knowledge preservation.
image-captioning embedding-models raptor document-retrieval blip tsunami multimodal-retrieval knowledge-tree pdf-processing colbert long-context knowledge-preservation vision-language-models multimodal-rag llm-summarization disaster-knowledge-base hadr-ai domain-specific-rag hierarchical-retrieval disaster-documents
-
Updated
Jan 18, 2026 - Python