Reliable, fully local RAG agents with LLaMA3.2-3b

LLaMA3.2 has released a new set of compact models designed for on-device use cases, such as locally running assistants. Here, we show how LangGraph can enable these types of local assistant by building a multi-step RAG agent - this combines ideas from 3 advanced RAG papers (Adaptive RAG, Corrective RAG, and Self-RAG) into a single control flow using LangGraph. But we show LangGraph makes it possible to run a complex agent locally.
Code:
langchain-ai.g...
Llama3.2:
huggingface.co...
Full course on LangGraph:
academy.langch...

[@adriangpuiu]

@lance, please add langgraph documentation to the chat. the community will appreciate that. Let me know what you think

[@user-wr4yl7tx3w]

Can you consider doing an example of contextual retrieval that Anthropic recently introduced.

[@ravivarman7291]

Amazing session and content explained very nicely in just 30 mins; Thanks so much

[@sidnath7336]

If different tools require different key word arguments, how can these be passed in for the agent to access?

[@aiamfree]

it's sooooo fast!

[@AlexEllis]

Thanks for the video and sample putting all these parts together. What did you use to draw the diagram at the beginning of the video? Was it generated by a DSL/config?

[@blakenator123]

looks like excalidraw

[@VictorDykstra]

Very well explained.😊

[@thepeoplesailab]

Very informative ❤❤

[@andresmauriciogomezr3]

thank you

[@jamie_SF]

Awesome

[@fernandobarros9834]

Great tutorial! Is it necessary to add a prompt format?

[@skaternationable]

Using PromptTemplate/ChatPromptTemplate works as well. It seems that the .format here is equivalent to the `input_variables` param within the former 2 classes

[@fernandobarros9834]

@@skaternationable Thanks!

[@ghostwhowalks2324]

amazing stuff which can be done with few lines of code. disruption coming everywhere

[@SavvasMohito]

That's a great tutorial that shows the power of LangGraph. It's impressive you can now do this locally with decent results. Thank you!

[@johnrogers3315]

Great tutorial, thank you