Local Agentic RAG with LLaMa 3.1 - Use LangGraph to perform private RAG

Показать описание

In this video, you'll learn how to use Agentic RAG with a locally running, open-source model. We'll use the latest model, Llama 3.1 from Meta, in combination with Ollama. We'll write the agent using Langgraph and structure the code so that we can switch from Llama to OpenAI models simply by changing the value of an environment variable.

Timestamps:
0:00 Introduction
0:35 Download & Install Ollama
2:43 Agent walkthrough
3:48 Create functions for Nodes & Edges
13:20 Create Agent with StateGraph
15:30 Llama 3.1 vs GPT-4o-mini

#langgraph #llama3

Рекомендации по теме

Комментарии

I cannot tell you how thankful I am for your videos

SpenceDuke

Thanks for the video. Very educational! Would love to see you covering this topic on a bigger scale applications with unstructured KB. By the way, your Udemy course was awesome too!

sylap

Markus, you are a legend!!! This was very helpful, JUST like your other videos!!! Allow me to suggest topics for more videos. So, LangGraph is obviously great, so is LangChain, and so is LangSmith. But LangSmith isn't free. There are alternatives like Langfuse and Arize emerging. They use callbacks and I guess tracers module in langchain_core. The problem is it's rarely documented. If you can make a video, just like you did with runnable interface, for callbacks or tracers, then it will be very helpful. If you wanna provide more and go out of syllabus, you can integrate it with ELK stack or datadog or similar and replicate the logging behavior of all the chain internals or something. Anyway, I love your videos! Waiting for the next

AbhishekSingh-pjoo

Hy there! Markus, will you cover meta's new llama-agentic-system too? 🙏 plzZz, you teach like no other 🙃😊
Llama3.1 8b q8 function calls seems to work absolutely flawlessly. Thx for all your hard work!

FredericusRex-fp

like usual a great video ;) Question: wouldn't it make more sense to check the initial query for rewriting instead post retrieval ? this is my preference for 2 reasons: it allows users to not be very specific with their initial query and by rewriting the first query using the first retrieval will already be good. Using a fast smaller model like Command-R with Groq the speed is negligent.

awakenwithoutcoffee

would you provide a simple UI for this code?

artur

Great video Markus!
RAG and llama 3.1 8b worked totally fine for me! Just the token window with 128 k is a joke! Using more than 2000 characters (!) leads to unusable results. No difference to llama 3.0.
One question: why are you always return the entire state (graph nodes)? I always do the exact opposite. I just return the changed values. What is benefit? Thx

ki-werkstatt

Local Agentic RAG with LLaMa 3.1 - Use LangGraph to perform private RAG

'I want Llama3 to perform 10x with my private knowledge' - Local Agentic RAG w/ llama3

Local Agentic RAG with LLaMa 3.1 - Use LangGraph to perform private RAG

Fully local RAG agents with Llama 3.1

Agentic RAG with Llama 3.2 on Custom Dataset Locally - Easy Tutorial

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

Run ALL Your AI Locally in Minutes (LLMs, RAG, and more)

I Ditched Traditional RAG for Agentic RAG and Got SHOCKING Results!

Build Agentic RAG Applications with MongoDB and LlamaIndex

Build an agentic RAG step by step, powered by Crew AI and a local Llama 3.2

Create a LangChain Agentic RAG system using the IBM Granite-3.0-8B-Instruct model

Make Your RAG Agents Actually Work! (No More Hallucinations)

'I want Llama3.1 to perform 10x with my private knowledge' - Self learning Local Llama3.1 ...

Agentic RAG: Make Chatting with Docs Smarter

Building an Agentic RAG locally with Milvus, Ollama and LangGraph

End to End Multi AI Agents RAG With LangGraph AstraDB And Llama 3.1

ADVANCED Python AI Agent Tutorial - Using RAG

RAG in 2024: Advancing to Agents

Python RAG Tutorial (with Local LLMs): AI For Your PDFs

Real time RAG App using Llama 3.2 and Open Source Stack on CPU

Build Agents from Scratch (Building Advanced RAG, Part 3)

Learn RAG From Scratch – Python AI Tutorial from a LangChain Engineer

Let's build a RAG system - The Ollama Course

What is Retrieval-Augmented Generation (RAG)?

Ollama Course – Build AI Apps Locally