What is Agentic RAG?

[@norbertschmidt]

You make the best LLM + RAG explainers in the world. Thanks so much.

[@lesmoe524]

Fantastic description, it seems using agents to help you route to potentially different databases is a game changer, thank you.

[@sqweepsrussell9412]

Thanks for this well explained video. This is the most simplified explanation of agentic rag that sank into my grey matter

[@jaffarbh]

Thanks. This is pretty useful and much better than the naïve approach of overloading the model with lot's of irrelevant data from the vector DB.

[@sterlingabbot695]

Please do RAG + Big Data next

[@IBMTechnology]

An interesting suggestion, any specific element or question you have about the topic?

[@hi5wifi-s567]

“More responsible, more accurate, more adaptable, “ plus more secure as well?

[@StalinDeLaTorre]

Where can I learn this approach?

[@Ijmeisner]

In the reflection I think that’s the teleprompter… or maybe I am hallucinating 🤣

[@MikewasG]

What is the difference between this and semantic routing?

[@IBMTechnology]

Semantic routing uses more straightforward methods like cosine similarity and other predefined rules to make the decision on which route to take. The example I drew used an LLM agent, which can understand and interpret more complex/nuanced queries, understand context, but is much heavier (compute and latency) because it is using an LLM. -David

[@PriyeshYadav]

So the Agent is also a pretrained LLM with those 2 vector db ???

[@sjmediaonline]

IBM’s main task is now to create the catchup teaching videos. No innovation or breakthroughs are coming out from them. I see so many IBM old timers are watching with amazement how smaller open source innovators are moving lightning fast in GenAI and then they start recording teaching videos… I do not see any new things / new demos coming out from IBM.

[@AK-be7jh]

So the agent will acts like a controller here .

[@marcomaiocchi5808]

This pipeline doesnt make a lot of sense.

[@funkfreeze]

Overkill for most consumer facing applications and, as the answer to generalist queries, not specific enough a system for internal tooling. Lots of noise introduced here.

[@amotorcyclerider3230]

Jesus. He did not even say how the agent uses the llm to select the right data source. He did not even say how agent is implemented. So incomplete.. this video is incomplete. Delete and present with a complete one.

[@StMarkAdebayo]

Make your own