n8n Tutorial #8: Integrate AI Using Sequential LLM Chaining

[@fernandozuniga6590]

This is a superb video series, I love the way you explain complex subjects making them seem simple and straight forward. That's the sign of a great teacher.

[@Sam_On_Tech]

Nice breakdown of the process! Love it!

[@BR.Leandro]

So obvious and so magnificent. Thank you!

[@box4soumendu4ever]

Yes that's the way it is! Thank you Sir 👍👍

[@WillWehi]

Thanks Ben. Great Video and great advice. Joined your community :)

[@RamonTomzer]

awesome video brother

[@wulfrum5567]

Could you use a similar workflow into telling it where you want to grab context? For instance you have several collections in your Qdrant vector store, then have the LLM chain ask the user questions and then decide which collection it should grab contextual knowledge from?

[@SiraEkabutPlus]

thx a lot. really good example ❤

[@grokit]

Hi Ben, I like your videos! This one was pretty smart. I learned a lot. I have a question for you. Perhaps you could point me to a possible solution with n8n, AI agents or LLM chains? This is a common problem we face. How to prepare scanned documents for further processing. Let' say we have scanned a bunch of invoices in one go, resulting in a rather large PDF file of 50 or so pages. Each invoice is one, two or more pages long. Most invoices are from different companies, but some are from the same. Let's say I have 30 invoices in this 50 page file. Would it be possible for n8n and any kind of AI agent, to split that 50 page file into 30 files, each containing just a single invoice? I would be *very* interested in something like that! Dan

[@anshumanngupta5030]

Great Video. Is it possible to use custom LLMs if we have their API? in particular I m looking to connect Nvidia's new Nemotron 70B. I also had a question if me using an API key would mean that it'll use my GPU or the LLM hosting server's GPU...

[@kel78v2]

Never knew about llm chain availability. One could also just use openai assistants which are basically custom agents in chatgpt.

[@BenYoungAI]

Yes! There are now so many ways to access AI... just gotta choose one that suits your needs the best!

[@MariushAI]

Does n8n have the functionality to build agents as in Flowise?(Sequential Agents)

[@BenYoungAI]

With n8n's AI features, it has a lot of overlapping functionality compared to Flowise where you can achieve the same results (like AI Agents), but where n8n really shines is its additional built-in ability to integrate with and automate other systems. With Flowise, one often needs to pair it with an automation tool like n8n/make.com/zapier, etc. to get the same result.