Reliable, fully local RAG agents with LLaMA3

With the release of LLaMA3, we're seeing great interest in agents that can run reliably and locally (e.g., on your laptop). Here, we show to how build reliable local agents using LangGraph and LLaMA3-8b from scratch. We combine ideas from 3 advanced RAG papers (Adaptive RAG, Corrective RAG, and Self-RAG) into a single control flow. We run this locally w/ a local vectorstore c/o @nomic_ai & @trychroma, @tavilyai for web search, and LLaMA3-8b via @ollama.

Code:

[ronnitroyburman]

this looks so crisp! brilliant knowledge transfer! thank you.

[rone]

That’s fast! Thanks Lance, Your video is always helpful to us❤

[BedfordGibsons]

Great focused, to the point and well demonstrated delivery. Thank you

[wshobson]

Brilliant! Straight to the point, like reading the K&R. Thanks Lance.

[asetkn]

Vance thank you for the great value you provide for this community!

[jellz]

Really enjoying your videos, Lance! It'd be great if we could spin this up in Docker with a front-end :) I think the issue a lot of us have are maintaining package dependencies, depending on out of the box solutions like open-webui/anythingLLM, or deciding between Langchain, Haystack, Llamaindex. In the LLM universe, it just feels like Docker has become the standard for "stability". Again, love your work!

[MattHudsonS]

Great video. Advanced concepts but simple to understand.

[uuvquhp]

so appreciate your demonstration. It’s really helpful .

[eaall-genai-exploration]

That’s really awesome and very useful! I literally have implemented a similar flow today, using another langraph use-case, but the fallback workflow at the end makes much more sense to increase answer quality. Thanks and brilliant communicated.

[chriskingston]

Wow this is awesome. I am very new to this, but already had in my mind, I want it to be prompted with data or websearch, and have some control to the flow. But this is so cool, thank you for explaining this! ❤️❤️❤️

[Trashpanda_]

Thanks for the video and all you do bother! Def go down in history as a driving force!

[postcristiano]

Awesome video and easy to understand, really appreciate!

[spencerfunk]

thank you for this you answered all the question ive had about this project im wanting to make in one swoop

[collinvelarde]

Incredible. Great stuff brotha. Thank you.

[davidtindell]

Yes. Very Useful. Especially running 'reliably' on my local machine (in this case MS_Win with NVidia GPU") !
Thank You. Yet Again !!!!

[karost]

Thanks, well document materials, live demo, present process step by step that help beginner like me :D

[duanesearsmith]

Wow, a most excellent video! I didn't know that Ollama had already adapted Llama3 into the mix. Now, I want to replicate what you did using Clojure/Java (Langchain4j).

[JaroslavInsights]

super helpful. thanks for sharing. I take it the Models can be swapped and varied for every stage, obv given the local system spec is able to handle such load

[havenqi]

my mac M1 pro ran into this error at the beginning,
"RuntimeError: Unable to instantiate model: CPU does not support AVX" at this step all libs are upgraded. switched to ollama embedding lib but it almost killed the mac with the fan roaring

[EmirSyailendra]

Thanks for the amazing video Lance! Very clear explanation, this is really helpful to my work too.

I really like the graphic for the workflow, what tools that you used for that?