Generative AI with RAG and VectorDB
Design and implement production‑ready RAG systems combining Vector databases with LLMs.
Get Course Info
Audience: Developers, data scientists, team leads, project managers
Duration: 3 days (split into intro & advanced parts if desired)
Format: Lectures and hands‑on labs (50% – 50%)
Overview
Generative AI with Large Language Models (LLM) opens ways to building smart applications as never before. The most popular architecture for that is Retrieval‑Augmented Generation (RAG) built with semantic search. In this course, students learn how to build RAG systems using VectorDB (DataStax) and various LLMs such as ChatGPT or local LLaMA.
Objective
Design and implement production‑ready RAG systems combining Vector databases with LLMs.
What You Will Learn
- Prompt Engineering (intro, iterative development, summarising, inferring, transforming, expanding, chatbots)
- Semantic search and VectorDB
- Retrieval‑Augmented Generation (RAG)
- Hybrid & facial similarity search, anomaly detection
- LangChain glue: models, prompts, memory, chains, evaluation
- Architecture, testing, and continuous improvements across Amazon, Azure, and Google clouds
Course Details
Audience: Developers, data scientists, team leads, project managers
Duration: 3 days (split into intro & advanced parts if desired)
Format: Lectures and hands‑on labs (50% – 50%)
- General familiarity with machine learning
Setup: Zero‑install cloud lab • Modern laptop • Chrome browser
Detailed Outline
- Introduction to AI and LLM
- Iterative development
- Summarising
- Inferring
- Transforming
- Expanding
- Chatbot
- Document organisation
- Semantic search basics
- Retrieval Augmented Generation
- Recommender systems
- Hybrid search
- Facial similarity search
- Anomaly detection
- Models, prompts, parsers
- Memory
- Chains
- Q&A
- Evaluation
- Conversational bot
- Cloud options (AWS, Azure, Google)
- Evaluating & debugging Gen‑AI
- Practical demos
Ready to Get Started?
Contact us to learn more about this course and schedule your training.