Generative AI workshop

Offline

Generative AI & LLM Engineering

Master LLMs, Prompt Engineering, RAG architectures, and fine-tuning to build production-ready AI applications

Format
Offline
Duration
1 day
Level
Intermediate to Advanced

Tools covered

  • Python
  • LangChain
  • OpenAI API
  • FAISS
  • Hugging Face
  • Streamlit

Overview

What you'll learn

Key concepts and practical areas covered in this workshop.

  • 01Understand Transformer Architectures & Large Language Models
  • 02Master Advanced Prompt Engineering & In-Context Learning Techniques
  • 03Build Retrieval-Augmented Generation (RAG) Systems with Vector DBs
  • 04Fine-Tune Open-Source LLMs using LoRA & QLoRA Frameworks
  • 05Deploy AI Agents & Interactive APIs with LangChain & Streamlit

Curriculum

Workshop curriculum

Review the topics covered in each module before sending an enquiry.

  1. 01

    Introduction to Generative AI & LLMs

    1 day

    • Generative AI Ecosystem - Foundations, Transformers, Self-Attention & Embeddings
    • Understanding Tokens, Context Windows, Temperature & Model Parameters
    • API Integration - Working with OpenAI API, Anthropic Claude & Hugging Face Models
    • Prompt Engineering Strategies - Zero-shot, Few-shot, Chain-of-Thought & Directional Stimulus
    • Hands-on - Set up API connections, construct robust prompt templates & handle token budgets
  2. 02

    Retrieval-Augmented Generation (RAG)

    1 day

    • RAG Architecture - Data Chunking strategies, Vector Embeddings & Similarity Search
    • Vector Databases - Setting up and querying FAISS, ChromaDB & Pinecone
    • Contextual Retrieval - Query Expansion, Re-ranking & Context Compression
    • Hands-on - Build a Document Q&A system using custom PDFs and FAISS vector index
  3. 03

    Fine-Tuning & Model Customization

    1 day

    • Fine-Tuning vs RAG - Choosing the right approach for enterprise use cases
    • Parameter-Efficient Fine-Tuning (PEFT) - LoRA, QLoRA & Quantization concepts
    • Dataset Preparation - Formatting instruction-tuning datasets & data cleaning
    • Hands-on - Fine-tune an open-source model (e.g., Llama/Mistral) using Hugging Face TRL
  4. 04

    AI Agents & Application Deployment

    1 day

    • Autonomous AI Agents - Agent loops, Tool usage, Memory Management & ReAct framework
    • Framework Integration - Orchestrating multi-step workflows using LangChain or LlamaIndex
    • Application Interface - Building interactive web UIs with Streamlit & FastAPI backend
    • Hands-on - Build and deploy a complete Gen AI assistant with internet search capabilities

Before you begin

What you'll need

  • Laptop with internet connection
  • Basic understanding of Python programming
  • No prior Deep Learning or LLM experience needed

Instructor

Arun Kumar S

Need guidance?

Choose the workshop that fits your goals.

Send an enquiry and the Variable team can help you confirm the right workshop, availability, and next steps.

Send an enquiryExplore courses