Teach on Udemy

Turn what you know into an opportunity and reach millions around the world.

Learn More

Your cart is empty.

Keep shopping

Prompt Engineering and Generative AI - Fundamentals

Name: Prompt Engineering and Generative AI - Fundamentals
Rating: 4.1 (10 reviews)

Large Language Models, GPT, Gemini, LLM fine-tuning, Few-Shot, Chain-of-Thought, Tree-of-Thoughts, Guardrails, Langchain

Created bySathish Jayaraman

Last updated 10/2026

English

English [Auto],

What you'll learn

Fundamentals of Prompt Engineering and Generative AI.
Prompt Engineering Techniques : Zero-Shot, Few-Shot and Chain-of-Thought, Tree of Thoughts
Retrieval Augmented Generation fundamentals
RAGAS Evaluation Framework for LLM and LangSmith
Fine-tuning a Large Language Model
Guardrails for validating LLM response
Course Notebooks verified using Claude Code

Course content

5 sections • 19 lectures • 1h 31m total length

Introduction1:46
Explore the fundamentals of prompt engineering and generative AI, covering zero-shot, few-shot, chain-of-thought and tree-of-thought techniques, retrieval augmented generation with Lang chain framework, and guardrails.

Fundamentals of Prompt Engineering - Set up Colab Notebook with Gemini Model4:30
Explore fundamentals of prompt engineering and generative AI by setting up Colab notebooks, structuring prompts, and applying Gemini Pro model and GPT models with one-shot and few-shot techniques.
Streaming a response from LLM and Best Practices in Prompt Engineering5:43
Learn to stream large language model responses, apply best practices in prompt engineering, and tune temperature and token limits with the Gemini model, including chunked outputs and practical Python prompts.
Zero Shot Prompting Technique2:11
Master zero-shot prompting and related techniques—few-shot, chain of thought, and tree of thoughts—using the Gemini Pro model, with retrieval augmented generation and practical parallelogram and sentiment examples.
Few-shot and Chain-of-thought prompting technique4:38
Explore few-shot prompting and in-context learning to guide models with examples, and examine chain-of-thought prompting to provide step-by-step reasoning for complex tasks.
Setup the model from OpenAI -GPT 4 : Example of a Prompt2:05
Set up a Google Colab notebook to run OpenAI's GPT-4, install the OpenAI library, manage the API key, and apply prompt engineering with system and user prompts for chat completions.
Tree-of-thoughts prompting technique using GPT-3.5-turbo3:02
Explore the tree-of-thoughts prompting technique with GPT-3.5-turbo to enable backtracking, trial-and-error reasoning, and collaborative expert steps for complex tasks.
Tree-of-Thoughts agents implemented by LangChain3:09
Explore the tree of thoughts prompting technique and its LangChain agents, using backtracking to improve large language model reasoning, demonstrated on a 4x4 Sudoku puzzle with a dot checker.

RAG Pipeline : Chroma Vector Store, Conversational Retrieval Chain with CSV file5:54
Learn retrieval augmented generation using a chroma vector store and conversational retrieval chain to handle csv data in colab, create embeddings, chunk text, and enable conversational question answering.
RAG Pipeline : FAISS Vector DB, Arxiv Loader and Conversational Retrieval Chain6:02
Explore retrieval augmented generation with LangChain, FAISS vector database, arXiv loader, and a conversational retrieval chain for accurate, source-based responses.
Retrieval Augmented Generation Assessment : RAGAS Framework6:05
Explore retrieval augmented generation to improve factual consistency by grounding responses in relevant context, reduce hallucinations, and apply ragas metrics: faithfulness, relevancy, context precision, and context recall for evaluation.
Retrieval Augmented Generation Assessment with LangSmith5:46
Learn to evaluate retrieval augmented generation with the ragas framework and Lang Smith, building embeddings-based retrieval chains using a vector store and assessing faithfulness, relevancy, and context precision.
Document Search with the Gemini Model4:06
Use the Gemini model to create text embeddings with embeddings 001 and perform document search for a qa system, comparing mistral, llama, and smog 72b models, and exploring prompt engineering.

Prompting vs Fine-tuning a Large Language Model10:29
Explore how large language models like GPT and Llama predict the next token and master prompt engineering across decoder-only and encoder-decoder models.
Fine-tuning a Large Language Model - Setting up the Colab Notebook and EDA5:58
Set up a Google Colab notebook to fine-tune a language model with supervised training, including data loading, cleaning, visualization, and train/eval splits (90/10).
Fine-tuning a Large Language Model - Model Training and Inference5:15
Fine-tune a bert base cased model using tokenizers, input IDs, and attention masks for supervised sequence classification, with training, evaluation, and saving to the Huggingface hub.

Guardrails for Large Language Models : Examples from OpenAI5:15
Apply guardrails to align large language models with safety and ethical standards, reducing biases and hallucinations. Demonstrate system prompts and input-output filtering in OpenAI chat, implemented in Colab with the OpenAI library.
GuardrailsAI : Extracting Information from Text4:55
Apply the guardrails ai framework to extract structured information from text while enforcing safety criteria with pedantic validators and a guard object in a Colab workflow.
Guardrails AI : Generating Structured Data and Interface with Chat Model4:56
Generate structured data with guardrails ai using a chat model, validate with pydantic, create 20 user rows with order validation, and extract pdf information using guardrails and pedantic.

Requirements

Basic knowledge of data science and ML principles will be helpful
Familiarity with Python
A computer with internet to access course material

Description

This course delves into the fundamental concepts related to Prompt Engineering and Generative AI. The course has subsections on Fundamentals of Prompt Engineering, Retrieval Augmented Generation, Fine-tuning a large language model (LLM) and Guardrails for LLM.

Section on Prompt Engineering Fundaments :

The first segment provides a definition of prompt engineering, best practices of prompt engineering and an example of a prompt given to the Gemini-Pro model with references for further reading.

The second segment explains what streaming a response is from a large language model, examples of providing specific instructions to the Gemini-Pro model as well as temperature and token count parameters.

The third segment explains what Zero-Shot Prompting technique is with examples using the Gemini Model.

The fourth segment explains Few-shot and Chain-of-Thought Prompting techniques with examples using the Gemini Model.

Subsequent segments in this section shall discuss setting up the Google Colab notebook to work with the GPT model from OpenAI and provide examples of Tree-of-Thoughts prompting technique, including the Tree-of-Thoughts implementation from Langchain to solve the 4x4 Sudoku Puzzle.

Section on Retrieval Augmented Generation (RAG) :

In this section, the first segment provides a definition of Retrieval Augmented Generation Prompting technique, the merits of Retrieval Augmented Generation and applying Retrieval Augmented Generation to a CSV file, using the Langchain framework

In the second segment on Retrieval Augmented Generation, a detailed example involving the Arxiv Loader, FAISS Vector Database and a Conversational Retrieval Chain is shown as part of the RAG pipeline using Langchain framework.

In the third segment on Retrieval Augmented Generation, evaluation of response from a Large Language Model (LLM) using the RAGAS framework is explained.

In the fourth segment on Retrieval Augmented Generation, the use of Langsmith is shown complementing the RAGAS framework for evaluation of LLM response.

In the fifth segment, use of the Gemini Model to create text embeddings and performing document search is explained.

Section on Large Language Model Fine-tuning :

In this section, the first segment provides a summary of prompting techniques with examples involving LLMs from Hugging Face repository and explaining the differences between prompting an LLM and fine-tuning an LLM.

The second segment provides a definition of fine-tuning an LLM, types of LLM fine-tuning and extracting the data to perform EDA (including data cleaning) prior to fine-tuning an LLM.

Third segment explains fine-tuning a pre-trained large language model on a task specific labeled dataset in detail.

Section on Guardrails for Large Language Models:

In this section, the first segment provides a definition of Guardrails as well as examples of Guardrails from OpenAI.

In the second segment on Guardrails, examples of open source Guardrail implementations are discussed with a specific focus on GuardrailsAI for extracting information from text.

In the third section, use of GuardrailsAI for generating structured data and interfacing GuardrailsAI with a Chat Model have been explained.

Each of these segments has a Google Colab notebook included.
The course notebooks were checked and updated using Claude Code in October 2026. The PDF in the first segment has the link to the updated notebooks and the steps to run them

Who this course is for:

This course is suited for anyone interested in the realm of Natural Language Processing, Large Language Models, Prompting Engineering and Generative AI and Data Science

Prompt Engineering and Generative AI - Fundamentals

What you'll learn

Explore related topics

Course content

Introduction1 lecture • 2min

Prompt Engineering Fundamentals7 lectures • 25min

Retrieval Augmented Generation5 lectures • 28min

Large Language Model Fine-tuning3 lectures • 22min

Guardrails for Large Language Models3 lectures • 15min

Requirements

Description

Who this course is for: