Learn RAG with LLMWare (2024)
Learn RAG: A beginner-friendly tutorial. Understand Retrieval Augmented Generation step-by-step. Boost your AI projects with this practical guide.
Course Content
Learn RAG with LLMWare (2024) is a beginner-level Udemy course taught by Darren Oberst. It runs 1h 27m and is taught in English. Learners rate it 4.6 out of 5 from 71 reviews, with 2,141 students enrolled. It is free to enroll, first published March 2024.
Unlock the Power of Generative AI with Retrieval Augmented Generation (RAG)
Ready to harness the potential of Generative AI? LLMWare makes getting started with Generative AI and Large Language Models (LLMs) fast and straightforward. This comprehensive course provides a step-by-step guide to Retrieval Augmented Generation (RAG), a crucial technique for connecting LLMs to your own data.
What is Retrieval Augmented Generation (RAG)?
RAG allows you to link a large language model (LLM) to a knowledge base – think of it as connecting AI to your documents (PDFs, Word documents, Excel spreadsheets, PowerPoint presentations, etc.). This course teaches you how to build effective RAG workflows.
Course Highlights:
This foundational course covers all the key components of RAG, empowering you to build effective AI workflows and chatbots. The course is structured around 7 short, practical videos.
Video 1: Introduction to Retrieval Augmented Generation (RAG)
- Learn the fundamentals of Retrieval Augmented Generation and how to get started with Generative AI.
- Discover how to install LLMWare, the basic requirements, and the core components of RAG.
- Build a state-of-the-art data pipeline using the latest LLMs – all on your laptop!
Video 2: Parsing, Text Chunking, and Indexing
- Create your first RAG library by mastering the initial steps of parsing, text chunking, and indexing documents.
- Learn how to prepare your data for efficient LLM interaction.
Video 3: Building Embeddings
- Understand embeddings, embedding models, vectors, and vector databases – the building blocks of semantic search.
- Build your first embeddings using Hugging Face and store them in a database.
- Use embeddings to perform powerful semantic queries.
Video 4: Prompt Models
- Master the art of prompting models with Hugging Face and OpenAI.
- Learn how to check model accuracy using LLMWare's similarity score.
- Capture model usage data (token consumption, output, processing time) for auditability.
Video 5: RAG with Text Query
- Unlock the power of RAG by combining your knowledge base with an LLM.
- Learn to construct effective RAG strategies using retrieval and querying techniques.
- Use LLMWare's lightweight BLING 1B model for contract analysis and automated information extraction.
Video 6: RAG with Semantic Query
- Dive into semantic search (natural language querying) and leverage the benefits of embeddings and vector databases.
- Query your knowledge base using natural language to answer complex questions (e.g., "What is the executive's base salary?").
- Learn the fundamentals of semantic search with practical examples.
Video 7: RAG with Multi-Step Query
- Recap everything you've learned and take your RAG skills to the next level.
- Utilize a quantized DRAGON-Yi-6b-GGUF model on your laptop.
- Perform multi-step hybrid queries for advanced information retrieval.
- Compare evidence and save outputs as JSON or CSV files for data analysis.
Who is this course for?
This course is ideal for anyone looking to:
- Build AI-powered chatbots.
- Automate information extraction from documents.
- Create enterprise-ready AI workflows.
- Learn Generative AI and RAG from the ground up.
Get started on your AI journey today! LLMWare provides an easy-to-use, open-source library for building powerful LLM applications.
Want AI in your product? Hire the team behind TutorialSearch.io
LLM features, RAG, agents and automation wired into a real product — built by the devs who shipped this site.