Complete Rag Testing Course With Ragas Deepeval And Python
Published 7/2025
MP4 | Video: h264, 1920x1080 | Audio: AAC, 44.1 KHz
Language: English | Size: 2.61 GB | Duration: 5h 10m
Published 7/2025
MP4 | Video: h264, 1920x1080 | Audio: AAC, 44.1 KHz
Language: English | Size: 2.61 GB | Duration: 5h 10m
Learn the complete way to test RAG implementations. From functional to performance from Python to RAGAs and DeepEval
What you'll learn
Understand the Basics of LLMs
Understand LLM Application types
Gain know how on types of AI - Weak and Generative
Understand How RAG works
Understand the types of RAG Testing
A lot of ready to use code that can be used from moment 0
Understand ML metrics such as Accuracy, Recall and F1
Understand RAG Testing Metrics such as Context Recall, Context Accuracy
Understand RAG Testing Metrics such as Answer Relevancy
Understand RAG Testing Metrics such as Truthfulness
Gain know how with RAGAs open source Testing framework
Gain know how with DeepEval open source Testing framework
Understand how to create custom metrics
Test for Coherence, Fluency, tone and other human specific metrics
Rapid validation tools for MVPs using RAG systems.
Deep understanding of metrics (fluency, coherence, relevance, conciseness), customizable test frameworks.
Requirements
Some basic Python programing experience
Basic understanding of LLMs and AI
A LLM API Key
Basic Testing understanding
Laptop/ PC with VS Code
Willingness to learn a new hot skill
Description
Master the art of evaluating Retrieval-Augmented Generation (RAG) systems with the most practical and complete course on the market — trusted by over 25,000 students and backed by 1,000+ 5-star reviews.Whether you're building LLM applications, leading AI QA efforts, or shipping reliable MVPs, this course gives you all the tools, code, and frameworks to test and validate RAG pipelines using DeepEval and RAGAS. What You’ll Learn Understand the Basics of LLMs and how they are applied across industries Explore different LLM Application Types and use cases Learn the difference between Weak AI and Generative AI Deep-dive into how RAG works, and where testing fits into the pipeline Discover the types of RAG Testing: factuality, hallucination detection, context evaluation, etc. Get hands-on with ready-to-use code from Day 0 — minimal setup required Master classic ML metrics (Accuracy, Recall, F1) and where they still matter Learn RAG-specific metrics:Context RecallContext AccuracyAnswer RelevancyTruthfulnessFluency, Coherence, Tone, Conciseness Build custom test cases and metrics with DeepEval and RAGASLearn how to use RAGAS and DeepEval open-source frameworks for production and research Validate MVPs quickly and reliably using automated test coverage Who is This For?AI & LLM Developers who want to ship trustworthy RAG systemsQA Engineers transitioning into AI testing rolesML Researchers aiming for reproducible benchmarksProduct Managers who want to measure quality in RAG outputsMLOps/DevOps professionals looking to automate evaluation in CI/CD
Overview
Section 1: Introduction
Lecture 1 Introduction
Lecture 2 Quick 5 Minute RAG Test
Section 2: Setup the environment - Installing dependencies
Lecture 3 Install Python
Lecture 4 Install PIP for Python
Lecture 5 Install NPM and Node.js
Lecture 6 Install VSCode
Lecture 7 Get an OPENAI API Key
Lecture 8 Github Repository link
Section 3: Types of AI and Model Lifecycle - Optional but highly recommended
Lecture 9 How AI Works
Lecture 10 Types of AI
Lecture 11 How does the App Tech Stack Look with AI
Lecture 12 What is a Foundation Model and a LLM
Lecture 13 Model - Lifecycle - Pretraining Phase of a Model
Lecture 14 Model - Lifecyle Fine Tunning Phase of a model
Lecture 15 AI Model - Some considerations around data
Lecture 16 Types of applications that use AI / LLMs
Section 4: Introduction to RAG
Lecture 17 How RAG works - a high level overview
Lecture 18 Hallucinations of RAG
Lecture 19 Types of RAG
Lecture 20 Applications of RAG
Lecture 21 Setting up the repo and dependencies
Lecture 22 Implementing a retriever and a Faiss DB
Lecture 23 RAG - Chunks and overlaps for documents
Lecture 24 RAG - Implementing an Augmentor
Lecture 25 RAG - Implementing Retriever + Augmenter + Generator
Section 5: How to Test RAG Systems
Lecture 26 Gen AI Param - TOP - K & P and Temperature
Lecture 27 Introducing top - K Documents
Lecture 28 Introducing Top - K Chunks
Lecture 29 Top K Chunks from most Relevant Document
Lecture 30 RAG - Testing Before pipeline is implemented
Lecture 31 RAG - Testing for the Retriever - Cosine Similarity
Lecture 32 RAG - Testing for the Augmentation
Lecture 33 RAG - Testing for the Generation
Section 6: Types of RAG Testing
Lecture 34 Manual or Human Testing
Lecture 35 Automated Testing with API validations - Pytest Demo
Lecture 36 Using LLM as a Judge to validate the response
Section 7: RAG Single and multihop Testing
Lecture 37 RAG Testing - Specific Query Synthesizer
Lecture 38 RAG Testing - Abstract Query Synthesizer
Lecture 39 RAG Testing - MultiHop Specific Query Synthesizer
Lecture 40 RAG Testing MultiHop Abstract Query Synthesizer
Lecture 41 Golden Nugget Metrics
Section 8: Important Machine Learning Metrics
Lecture 42 Ground Truth Table - source of Truth | Test Oracle
Lecture 43 Machine Learning Metrics - Accuracy
Lecture 44 Machine Learning Metrics - Precision
Lecture 45 Machine Learning Metrics - Recall
Lecture 46 Machine Learning Metrics - F1 Score
Section 9: Testing with the RAGAS library
Lecture 47 RAGAs Validation Framework - Retrieval
Lecture 48 RAG Metrics - Context Precision
Lecture 49 RAGAs - Python DEMO - Context Precision
Lecture 50 RAG Metrics - Context Recall
Lecture 51 RAGAs - Python DEMO - Context Recall
Lecture 52 RAG Metrics - Context Relevance
Lecture 53 RAGAs - Python DEMO - Context Relevance
Lecture 54 RAG Metric - Truthfulness
Lecture 55 RAGAs - Python DEMO - Faithfulness
Lecture 56 RAGAs Validation Framework - Retrieval - Augmentation - Generation
Lecture 57 Rag framework - Coherence, Fluency and Relevance
Section 10: Testing with Deepeval Library
Lecture 58 What is the DeepEval LLM Evaluation Platform
Lecture 59 Installing and running the first test
Lecture 60 Creating a Generative Metric
Lecture 61 Implementing a HTLM Report
AI Engineers & LLM Developers,QA/Test Automation Engineers transitioning to AI,ML Researchers & Applied Scientists,AI Product Managers