Deep Rag

Features • Quick Start • How It Works • Architecture • Configuration Traditional RAG systems: - ❌ Split documents into fragments, losing structure - ❌ Can only "find similar" content, not "find opposite" - ❌ Struggle with numerical comparisons and negation logic - ❌ Cannot perform multi-hop reasoning across documents - ❌ Lack global understanding for aggregation queries Deep RAG provides: - ✅ File Summary as Knowledge Map: LLM sees the entire structure - ✅ Active Navigation: Model retrieves what it needs, when it needs it - ✅ Multi-round Retrieval: Supports complex multi-hop reasoning - ✅ Complete Context: Retrieves full files/directories, not fragments Deep Rag is the open-source project boluo2077/deep-rag (https://github.com/boluo2077/deep-rag) by boluo2077, released under Apache-2.0. Ion packages it unmodified from commit 71d933c279d7, adding only a manifest, an icon and a start script.

Written by boluo2077, published to Oikou by Ben Grande.

• ★ 214 stars on GitHub
• Licence: Apache-2.0
• Built from commit 71d933c279d7

View the repository on GitHub

Not rated. Nobody has said who this app is suitable for, so Personal Clouds and the Oikou app treat it as 18+.

Internet

It asks to reach nothing on the internet.

Personal Cloud tools

None. It uses nothing from your Personal Cloud beyond its own storage.

Notifications

It does not send push notifications.

Storage

Up to 512 MB on your Personal Cloud.

Sign in to add this web app to a Personal Cloud of yours. It runs there, on your own computer, and you open it from there; nothing is installed on your phone.

Sign in to add