Graph RAG Evolved: PathRAG (Relational Reasoning Paths)
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Related videos
The real reason Meghan Markle abandoned Harry during his worst week ever
NewsNation
23.1k views
The Real Reason You're Bloated After Eating
Dr. Eric Berg DC
49.9k views
MAGA Govs REVOLT Over Trump Ban On AI Regulation
Breaking Points
19.7k views
Gravitational Wave Discoveries Uncover Mysteries We Can't Explain
Anton Petrov
11.2k views
The REAL Reason NBA Players Are Scoring MORE Than Ever
The Arena
159.2k views
Pro Gardener Reacts to Unconventional Gardening Hacks
Epic Gardening
381.8k views
Pascal Lottaz: US-Russia Relations Decoupling From Europe?
Glenn Diesen
55.8k views
Read Prosecutor Adam Lally Testifies at Discovery Hearing
Emily D. Baker
215.4k views
The Truth about AI is Devastating: Proof by MIT, Harvard
Discover AI
65.2k views
AI is Burning - 5 New Papers
Discover AI
34.3k views
Top Comments (10)
I swear, I just came up with the idea I call "consideration nodes" using topological optimization to allow the model to construct its own reasoning chains integrated with the knowledge graph. Sounds a lot like PathRAG.
As usual your tutorials are the best. Thank you.
Fascinating to see the evolution of techniques. There was something missing from the video - given the researchers warning of hallucinations and limitations of RAG for the medical field, do we see lightRAG or PathRAG techniques as overcoming those challenges?
Fantasticaly explained, thank you!
could lightrag result be filtered to remove results produce the same results ?
Would this method work on a 10M tokens codebase whose repo tree map details inter-dependencies?
I really enjoyed following your tutorial, thanks a lot !
interesting video. med rag - are they using a sophisticated rag setup? how modern is their tech stack? feels rather silly without elaborating at length about their implementation
Great stuff! benchmarks look very good
How do you create your graph for PathRAG to work? Do you use the traditional pathRAG approach?
Unlock the Data Inside
Turn Videos into Knowledge
- Get FREE 10/day: transcripts, summaries, chats
- Chat with videos, export text & PDF
- $1 free API credit for RAG, chatbots & research
Free forever plan • All features unlocked
Top Comments (10)
I swear, I just came up with the idea I call "consideration nodes" using topological optimization to allow the model to construct its own reasoning chains integrated with the knowledge graph. Sounds a lot like PathRAG.
As usual your tutorials are the best. Thank you.
Fascinating to see the evolution of techniques. There was something missing from the video - given the researchers warning of hallucinations and limitations of RAG for the medical field, do we see lightRAG or PathRAG techniques as overcoming those challenges?
Fantasticaly explained, thank you!
could lightrag result be filtered to remove results produce the same results ?
Would this method work on a 10M tokens codebase whose repo tree map details inter-dependencies?
I really enjoyed following your tutorial, thanks a lot !
interesting video. med rag - are they using a sophisticated rag setup? how modern is their tech stack? feels rather silly without elaborating at length about their implementation
Great stuff! benchmarks look very good
How do you create your graph for PathRAG to work? Do you use the traditional pathRAG approach?