Build No-Code LLM Applications

Audience: 
This course is designed for non-coding software engineers, business analysts, QA, product managers who want to build Generative AI based applications without writing any code - no machine learning experience required.

Description:
Have you ever wished you could build your own AI-powered app like ChatGPT without needing to know how to code? Whether you're a product manager, business analyst, QA professional, or a curious technologist, this one-day immersive workshop will empower you to turn that vision into reality.

This workshop is your gateway into the world of Generative AI and Large Language Models (LLMs), designed specifically for professionals without a technical background. You'll gain practical, hands-on experience using Lang flow -  a powerful visual, drag-and-drop tool that lets you design and deploy LLM applications without writing a single line of code.

You will also dive into advanced concepts like Retrieval Augmented Generation (RAG) and Agentic-AI, all within the visual builder environment Lang flow provides. With Lang flow, you can prototype and deploy powerful applications in minutes - making it ideal for professionals looking to build, test, and iterate fast.

Whether you're looking to enhance workflows, build customer-facing AI solutions, or just stay ahead in your career, this course gives you the foundation to do so - quickly, creatively, and confidently.
 

Learning Objectives:
1. Understand what LLMs are and how they are used in industry
2. Craft effective prompts and use prompt templates (zero, one, few-shot)
3. Build conversational experiences using data in various formats (CSV, PDF, etc.)
4. Use agents to complete multi-step tasks automatically
5. Build RAG applications using embeddings and vector databases
6. Create multi-agent workflows using Agentic-AI principles

Topic Outline:
1. Introduction to Large Language Models (LLMs)
  a. A brief history of Generative AI and LLMs
  b. What is a Large Language Model?
  c. Why LLMs are disrupting industries
  d. Hands-on: Create the lab environment and work with LLM

2. Using Model Prompts and Prompt Templates
  a. What is a prompt?
  b. Types of prompts: zero-shot, one-shot, few-shot
  c. Hands-on: Build a simple chat application using prompt and prompt templates

3. Build a captivating conversation using different types of documents formats
  a. Introduction to data connectors
  b. Uploading and interacting with CSV, PDF, and other formats
  c. Hands-on: Load a CSV file and get insights in the data

4. Using Agents to perform tasks
  a. What are agents in context of AI?
  b. Types of agents: tool-using agents, reasoning agents, reactive agents
  c. Hands-on: couple of labs using agents

5. Building RAG applications
  a. What is Retrieval Augmented Generation (RAG)?
  b. Why RAG is important for custom knowledge applications
  c. Understanding embeddings and vector stores
  d. Hands-on: Build an RAG application with vector storage and embeddings

6. Using Agentic-AI to build multi-agent applications
  a. What is Agentic-AI?
  b. How agents can collaborate to perform complex workflows
  c. Tools that make multi-agent applications possible in no-code platforms
  d. Hands-on: Build financial report application using multiple agents

Training material provided: Yes (Digital format)

Hands-on Lab: Students can use either open-source models or OpenAI models. Instructions will be provided to install tools for local machines or a website build use (free of charge) to build applications.

Pre-requisite: 
No programming experience required, experience playing with ChatGPT or equivalent LLMs will be nice but not required