RAG vs. CAG
Description
Watch: full video.A clear comparison of RAG and CAG, two ways to help AI models answer questions using knowledge they may not already contain. The useful distinction is simple: RAG retrieves relevant information when a question is asked, while CAG gives the model a prepared body of context before it answers. For knowledge workers, this helps explain why some AI systems can answer from fresh or private information, why context size matters, and why different knowledge workflows need different designs.
Official video embed
Martin Keen / IBM Technology, YouTube · 2025-03-17
Martin Keen / IBM Technology, YouTube · 2025-03-17
This video is hosted by a third-party provider. It will load only after you choose to press Play.
This video can load through the original platform's official player where available.
Open original sourceKey Takeaways
- RAG is useful when the AI needs to search or retrieve relevant information at the time of the question, especially from large or changing knowledge sources.
- CAG is useful when the relevant material can be prepared in advance and placed into the model’s context, reducing the need for live retrieval.
- The choice is not about which acronym is better; it depends on the work: freshness, scale, latency, complexity, and how much relevant context can fit into the model.