Deep Agentsライブラリのアーキテクチャを活用した、ハーネス構成のRAGシステムです。複数のエージェントが協調動作し、質問の粒度に応じて最適なRAGシステム(Naive RAG / ColBERT RAG)を自動選択します。

multi-agent-systems dynamic-routing rag modular-ai hadr colbert dense-retrieval retrieval-augmented-generation agent-coordination adaptive-rag deep-agents system-orchestration query-granularity rag-selection disaster-knowledge-base hadr-ai

• Updated Dec 14, 2025
• Python

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

An advanced RAG (Retrieval-Augmented Generation) system using RAPTOR algorithm to hierarchically organize and retrieve lessons from the 2011 Great East Japan Earthquake and Tsunami for educational purposes.

raptor document-retrieval educational-resources tsunami rag knowledge-tree long-context retrieval-augmented-generation knowledge-preservation llm-summarization disaster-knowledge-base hadr-ai domain-specific-rag hierarchical-retrieval great-east-japan-earthquake disaster-lessons disaster-education disaster-information-management learning-support

• Updated Oct 20, 2025
• HTML