Creating a Retrieval Augmented Generation (RAG) system with Ollama, Llama3 and Langchain | RAG

Показать описание

This YouTube video tutorial explains how to create a Retrieval-Augmented Generation (RAG) question-answering system using the LangChain library. The presenter introduces RAG, which combines Large Language Models (LLMs) with contextual information from external sources to enhance text generation. The specific project demonstrated involves creating an RAG system based on Adobe Photoshop documentation, which consists of 1017 pages.

The process includes:

Loading the PDF documentation using LangChain's PyPDFLoader.
Splitting the text into chunks with the RecursiveCharacterTextSplitter for better semantic retention.
Embedding the text chunks using a model from the Massive Text Embedding Benchmark (MTEB) leaderboard.
Implementing a vector search database with Facebook's FAISS (Facebook AI Similarity Search) to efficiently handle and retrieve similar text vectors.
The video also covers installing necessary packages and provides code snippets throughout the tutorial. The complete notebook and code will be shared in the video description.

Follow me here:

Рекомендации по теме

Комментарии

Can you explain more the cell 27, the db.as_retriever? Does that mean you are passing to the LLM the entire db? How much tokens does that eat up? I'm trying to understand pricing since I am using your example for a POC at work! :) Thank you!!!

lesptitsoiseaux

Creating a Retrieval Augmented Generation (RAG) system with Ollama, Llama3 and Langchain | RAG

What is Retrieval-Augmented Generation (RAG)?

Build a Large Language Model AI Chatbot using Retrieval Augmented Generation

How to set up RAG - Retrieval Augmented Generation (demo)

Build a Retrieval-Augmented Generation Chatbot in 5 Minutes

Local Retrieval Augmented Generation (RAG) from Scratch (step by step tutorial)

Build a RAG Based LLM App in 20 Minutes! | Full Langflow Tutorial

Build your own RAG (retrieval augmented generation) AI Chatbot using Python | Simple walkthrough

RAG + Langchain Python Project: Easy AI/Chat For Your Docs

Fine-Tuning Embeddings for Better Retrieval

Back to Basics: Understanding Retrieval Augmented Generation (RAG)

How to build Multimodal Retrieval-Augmented Generation (RAG) with Gemini

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

Getting started with (Retrieval Augmented Generation) RAG in Java & Spring AI

Chatbots with RAG: LangChain Full Walkthrough

What is RAG? (Retrieval Augmented Generation)

How to Improve LLMs with RAG (Overview + Python Code)

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

Build a RAG system in 4 lines of code | Retrieval-Augmented Generation

Intro to RAG for AI (Retrieval Augmented Generation)

Building A Retrieval-Augmented Generation (RAG) Application Using Snowflake Cortex And Streamlit

Retrieval Augmented Generation (RAG) Explained: Embedding, Sentence BERT, Vector Database (HNSW)

Making Retrieval Augmented Generation Better with @jamesbriggs

Retrieval Augmented Generation with OpenAI/GPT and Chroma

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