Name: RAG - Retrieval-Augmented Generation
Availability: InStock

RAG - Retrieval-Augmented Generation

Live Online (VILT) & Classroom Corporate Training Course

Design, build and evaluate Retrieval-Augmented Generation systems - document ingestion, parsing, text splitting, chunking, embeddings, vector databases, retrieval, metadata filtering, context construction and document question-answering.

Expert-Led VILT & Classroom 16 Hours Level: Intermediate Certificate of Completion

Overview

What You Will Learn

By the end of this course, learners will be able to:

Explain RAG fundamentals and the complete retrieval-generation pipeline.
Design RAG architectures for document-based knowledge applications.
Build document ingestion pipelines using appropriate loaders and preprocessing.
Apply fixed, recursive, semantic and structure-aware chunking strategies.
Generate and use embeddings for semantic retrieval.
Work with vector databases, similarity search and metadata filtering.
Implement dense, hybrid, multi-query and reranked retrieval strategies.
Construct grounded prompts and inject retrieved context into LLMs.
Evaluate retrieval quality, answer relevance and groundedness.
Build and demonstrate a document-based Q&A system.

Prerequisites

Basic Python programming, LLM fundamentals and familiarity with APIs are recommended. Prior experience with databases is helpful but not required.

Course Outline

What is Retrieval-Augmented Generation?
Why RAG?
Limitations of LLM Knowledge and Context
RAG vs Fine-Tuning
Core RAG Architecture
Retrieval and Generation Pipeline
RAG Components and Data Flow
RAG Use Cases
Common RAG Design Patterns
RAG Challenges and Trade-offs

Document Ingestion Fundamentals
Sources of Knowledge for RAG
PDF, Word, Text, HTML and Web Documents
Document Loaders
Parsing and Extracting Document Content
Handling Tables, Headers and Lists
Cleaning and Normalizing Text
Document Metadata
Building an Ingestion Pipeline
Ingestion Quality Checks

Why Text Splitting is Required
Chunk Size and Chunk Overlap
Fixed-Length Chunking
Recursive Text Splitting
Sentence and Paragraph-Based Chunking
Semantic Chunking
Structure-Aware Chunking
Chunking for Tables and Structured Documents
Choosing the Right Chunking Strategy
Chunk Quality and Retrieval Impact
Practical Chunking Experiments

What are Embeddings?
Text-to-Vector Representation
Semantic Similarity
Embedding Dimensions
Embedding Models
Document and Query Embeddings
Cosine Similarity and Distance Metrics
Choosing an Embedding Model
Embedding Quality and Retrieval Performance

What is a Vector Database?
Vector Indexing
Storing Documents, Vectors and Metadata
Similarity Search
Top-k Retrieval
Cosine, Dot Product and Euclidean Distance
Metadata Filtering
Namespace and Collection Concepts
Vector Database Selection
Querying and Updating a Vector Store
Managing Indexes and Data Lifecycle

Retrieval Fundamentals
Dense Vector Retrieval
Keyword and Sparse Retrieval
Hybrid Retrieval
Top-k and Similarity Thresholds
Query Expansion and Transformation
Multi-Query Retrieval
Maximum Marginal Relevance
Reranking Retrieved Documents
Filtering and Retrieval Constraints
Selecting a Retrieval Strategy

RAG Prompt Architecture
Combining User Queries with Retrieved Context
Context Injection
Context Formatting and Ordering
Grounded Answer Generation
Citation and Source Attribution
Handling Missing or Insufficient Context
Preventing Unsupported Answers
Managing Context Windows and Token Budgets
Designing Reliable RAG Prompts

Why Evaluate RAG Systems?
Retrieval vs Generation Evaluation
Retrieval Relevance
Precision, Recall and Top-k Retrieval Quality
Answer Relevance
Faithfulness and Groundedness
Context Relevance
Building a RAG Evaluation Dataset
Human Evaluation
Automated and LLM-Based Evaluation
Diagnosing Retrieval Failures

Define the Document Q&A Use Case
Design the RAG Architecture
Prepare and Load Documents
Implement Document Parsing and Cleaning
Implement Text Splitting and Chunking
Generate Document Embeddings
Create and Configure a Vector Database
Store Vectors and Document Metadata
Implement Similarity Search
Add Metadata Filtering
Implement the Retrieval Pipeline
Construct the RAG Prompt
Inject Retrieved Context into the LLM
Generate Grounded Answers
Add Source References
Test the Q&A System with Real Documents
Evaluate Retrieval and Answer Quality
Optimize Chunking, Retrieval and Prompting
Final Demonstration

RAG - Retrieval-Augmented Generation

Overview

What You Will Learn

Prerequisites

Course Outline

Why enterprise teams pick Synergific.

Live Hands-On Cloud Labs

Hire-Train-Deploy

Four-Hour Solutions SLA

Voucher-Backed Certification

Authorised Curriculum, Local Delivery

Pick the format that fits your team.

Live Online (VILT)

Classroom

Self-Paced

Blended

How a course becomes measurable skill.

Discover & set goals

Curate the right path

Deliver hands-on training

Assess & mentor

Certify & apply on the job

RAG - Retrieval-Augmented Generation

Overview

What You Will Learn

Prerequisites

Course Outline

Module 1: RAG Fundamentals & Architecture (75 min)

Module 2: Document Ingestion & Document Loaders (75 min)

Module 3: Text Splitting & Chunking Strategies (90 min)

Module 4: Embeddings (60 min)

Module 5: Vector Databases & Similarity Search (90 min)

Module 6: Retrieval Strategies (90 min)

Module 7: Prompt Construction & Context Injection (60 min)

Module 8: RAG Evaluation (60 min)

Module 9: Hands-on Project - Build a Document Q&A System (240 min)

Why enterprise teams pick Synergific.

Live Hands-On Cloud Labs

Hire-Train-Deploy

Four-Hour Solutions SLA

Voucher-Backed Certification

Authorised Curriculum, Local Delivery

Pick the format that fits your team.

Live Online (VILT)

Classroom

Self-Paced

Blended

How a course becomes measurable skill.

Discover & set goals

Curate the right path

Deliver hands-on training

Assess & mentor

Certify & apply on the job