50000 +
Students Enrolled
(500)
Ratings
16 Weeks
Duration
Our Alumni Work at Top Companies
RAG & AI Search Course Curriculum
It stretches your mind, think better and create even better.
Topics:
0.1 Programming and ML Foundations
Week 1: Python and Deep Learning Basics
Python for RAG Systems
Advanced Python Programming
Async Programming for I/O
Data Structures and Algorithms
Memory Management
Performance Optimization
Machine Learning Essentials
Supervised Learning Basics
Neural Network Fundamentals
Gradient Descent and Backpropagation
Overfitting and Regularization
Model Evaluation Metrics
NLP Fundamentals
Text Processing and Tokenization
Word Embeddings (Word2Vec, GloVe)
Language Models Basics
Sequence Processing
Text Classification
Vector Mathematics
Vector Spaces
Cosine Similarity
Euclidean Distance
Dot Product
Dimensionality Reduction (PCA, t-SNE)
0.2 LLMs and Search Foundations
Week 2: Core Technologies
Large Language Models
Transformer Architecture Basics
Attention Mechanisms
Pre-trained Models Overview
Prompt Engineering Fundamentals
API Integration (OpenAI, Anthropic)
Information Retrieval Basics
Boolean Retrieval
TF-IDF
BM25 Algorithm
Inverted Indexes
Query Processing
Database Fundamentals
SQL Basics
NoSQL Concepts
Database Indexing
Query Optimization
ACID Properties
Development Environment
VS Code Setup
Jupyter Notebooks
Git Version Control
Docker Basics
Cloud Platform Basics
Lab Project
Build a basic search engine with TF-IDF and implement simple question-answering
Topics:
1.1 RAG Fundamentals
Week 1: Core Concepts
What is RAG?
RAG vs Fine-tuning
When to Use RAG
Benefits and Limitations
Use Cases and Applications
Industry Adoption
RAG Architecture Overview
Data Ingestion Layer
Indexing and Storage
Retrieval Mechanisms
Generation Component
Orchestration Layer
Core Components
Document Processors
Embedding Models
Vector Stores
Retrieval Strategies
LLM Integration
RAG Workflow
Query Understanding
Document Retrieval
Context Formation
Answer Generation
Response Synthesis
Types of RAG
Simple/Naive RAG
Advanced RAG
Modular RAG
Hybrid RAG
Agentic RAG
1.2 Embeddings and Vector Representations
Week 2: Understanding Embeddings
Embedding Fundamentals
What are Embeddings?
Semantic Similarity
Vector Dimensions
Distance Metrics
Embedding Properties
Text Embedding Models
Sentence Transformers
OpenAI Embeddings
Cohere Embeddings
Instructor Models
BGE Models
Embedding Techniques
Dense Embeddings
Sparse Embeddings
Hybrid Embeddings
Cross-Encoders
Bi-Encoders
Advanced Concepts
Embedding Fine-tuning
Domain Adaptation
Multilingual Embeddings
Multimodal Embeddings
Compression Techniques
Quality and Evaluation
Embedding Quality Metrics
Semantic Similarity Tests
Retrieval Benchmarks
A/B Testing
Performance Analysis
Project
Build a semantic search system using different embedding models
Topics:
2.1 Document Ingestion
Week 1: Data Processing Pipeline
Document Types and Parsing
PDF Processing (PyPDF, PDFPlumber)
HTML/Web Scraping
Office Documents (DOCX, XLSX)
Markdown and Plain Text
Structured Data (JSON, XML)
Text Extraction Techniques
OCR for Scanned Documents
Table Extraction
Image Caption Extraction
Metadata Preservation
Layout Analysis
Data Cleaning
Text Normalization
Noise Removal
Deduplication
Language Detection
Encoding Issues
Preprocessing Strategies
Sentence Segmentation
Paragraph Detection
Section Identification
Header/Footer Removal
Reference Resolution
2.2 Chunking Strategies
Week 2: Optimal Chunking
Chunking Methods
Fixed-Size Chunking
Sentence-Based Chunking
Paragraph-Based Chunking
Semantic Chunking
Recursive Chunking
Advanced Chunking
Sliding Window Approach
Context-Aware Chunking
Hierarchical Chunking
Document Structure Chunking
Topic-Based Chunking
Chunk Optimization
Optimal Chunk Size
Overlap Strategies
Chunk Boundaries
Context Preservation
Metadata Attachment
Special Considerations
Code Chunking
Table Chunking
Multi-Column Documents
Cross-Reference Handling
Multi-Document Chunking
Quality Assurance
Chunk Coherence
Information Completeness
Retrieval Testing
Edge Case Handling
Performance Impact
Lab
Implement and compare different chunking strategies
Topics:
3.1 Vector Database Technologies
Week 1: Vector Storage Systems
Vector Database Overview
Why Vector Databases?
CRUD Operations
Indexing Mechanisms
Query Processing
Scalability Considerations
Popular Vector Databases
Pinecone Architecture
Weaviate Features
Qdrant Capabilities
Milvus/Zilliz
ChromaDB
Open Source Solutions
FAISS (Facebook AI)
Annoy (Spotify)
HNSW Implementation
ScaNN (Google)
Vespa
Database Features
Filtering and Metadata
Hybrid Search Support
Multi-Tenancy
Backup and Recovery
Security Features
Performance Optimization
Index Types (IVF, HNSW, LSH)
Quantization Methods
Caching Strategies
Batch Operations
Hardware Acceleration
3.2 Indexing Strategies
Week 2: Advanced Indexing
Index Types
Flat Index
IVF (Inverted File)
HNSW (Hierarchical NSW)
LSH (Locality Sensitive Hashing)
Product Quantization
Hybrid Indexing
Dense + Sparse Vectors
Keyword + Semantic
Hierarchical Indexes
Multi-Modal Indexes
Graph-Enhanced Indexes
Index Management
Index Building
Incremental Updates
Index Versioning
Reindexing Strategies
Index Optimization
Scalability
Distributed Indexing
Sharding Strategies
Replication
Load Balancing
Horizontal Scaling
Production Considerations
Index Size Management
Memory vs Disk Trade-offs
Query Latency
Throughput Optimization
Cost Management
Project
Build and optimize a vector database for large-scale document retrieval
Topics:
4.1 Basic Retrieval Methods
Week 1: Core Retrieval
Similarity Search
k-NN Search
Approximate NN Search
Range Queries
Threshold-Based Retrieval
Diversified Search
Ranking Algorithms
Cosine Similarity
Dot Product Scoring
Euclidean Distance
Manhattan Distance
Custom Scoring Functions
Query Processing
Query Embedding
Query Expansion
Query Rewriting
Multi-Query Strategy
Query Decomposition
Filtering and Constraints
Metadata Filtering
Date Range Filtering
Category Constraints
Access Control
Custom Filters
4.2 Advanced Retrieval
Week 2: Sophisticated Techniques
Hybrid Search
Combining Dense and Sparse
BM25 + Vector Search
Reciprocal Rank Fusion
Weight Optimization
Cross-Encoder Reranking
Multi-Step Retrieval
Coarse-to-Fine Retrieval
Iterative Refinement
Chain-of-Retrieval
Recursive Retrieval
Hierarchical Search
Contextual Retrieval
Context-Aware Embeddings
Session-Based Retrieval
Personalized Search
Temporal Awareness
Location-Based Retrieval
Reranking Strategies
Cross-Encoder Reranking
MMR (Maximum Marginal Relevance)
DPR (Dense Passage Retrieval)
ColBERT Reranking
Learning to Rank
Lab
Implement and benchmark different retrieval strategies
Topics:
5.1 Building RAG Systems
Week 1: Core Implementation
RAG Pipeline Architecture
Component Design
Data Flow Management
Error Handling
Async Processing
Pipeline Orchestration
LangChain for RAG
Document Loaders
Text Splitters
Vector Stores Integration
Retrieval Chains
QA Chains
LlamaIndex Implementation
Index Types
Query Engines
Response Synthesis
Node Postprocessors
Storage Management
Custom RAG Development
From Scratch Implementation
Component Integration
State Management
Caching Layers
Performance Optimization
Context Management
Context Window Limits
Context Compression
Relevant Context Selection
Context Ordering
Token Management
5.2 Answer Generation
Week 2: Response Synthesis
Generation Strategies
Single Document Answering
Multi-Document Synthesis
Abstractive Summarization
Extractive Answering
Hybrid Generation
Prompt Engineering for RAG
System Prompts
Context Injection
Citation Instructions
Format Control
Error Handling Prompts
Quality Enhancement
Answer Verification
Fact Checking
Hallucination Prevention
Confidence Scoring
Source Attribution
Response Formatting
Structured Outputs
Citation Addition
Highlighting Key Points
Multi-Format Support
Streaming Responses
Conversation Management
Multi-Turn RAG
Context Carryover
Memory Systems
Session Management
User Personalization
Project
Build a complete RAG system from scratch
Topics:
6.1 Semantic Search
Week 1: Deep Semantic Understanding
Semantic Search Principles
Intent Understanding
Query Analysis
Semantic Matching
Concept Extraction
Entity Recognition
Query Understanding
Query Classification
Intent Detection
Entity Extraction
Query Disambiguation
Spell Correction
Semantic Expansion
Synonym Expansion
Concept Expansion
Related Terms
Knowledge Graph Integration
Ontology Mapping
Cross-Lingual Search
Multilingual Embeddings
Translation Strategies
Language Detection
Cross-Lingual Retrieval
Zero-Shot Transfer
6.2 Neural Information Retrieval
Week 2: Advanced Neural Methods
Dense Retrieval Models
DPR (Dense Passage Retrieval)
ANCE (Approximate Nearest Neighbor)
RocketQA
SBERT Fine-tuning
Domain Adaptation
Learned Sparse Retrieval
SPLADE
DeepImpact
DocT5Query
Term Importance Learning
Sparse-Dense Hybrids
Neural Ranking Models
BERT for Ranking
T5 Ranking
MonoBERT
DuoBERT
Cross-Encoders
Training Strategies
Contrastive Learning
Hard Negative Mining
Knowledge Distillation
Curriculum Learning
Multi-Task Learning
Lab
Implement and fine-tune neural search models
Topics:
7.1 Hybrid Search Systems
Combining Search Methods
Lexical + Semantic
Dense + Sparse
Global + Local
Exact + Fuzzy
Structured + Unstructured
Fusion Strategies
Score Normalization
Rank Fusion
Weight Learning
Reciprocal Rank Fusion
Machine Learning Fusion
Optimization Techniques
Parameter Tuning
A/B Testing
Online Learning
Bandits for Search
Reinforcement Learning
7.2 Federated and Distributed Search
Distributed Architecture
Federated Search Design
Index Distribution
Query Routing
Result Aggregation
Load Balancing
Multi-Source Integration
Database Integration
API Integration
File System Search
Cloud Storage Search
Real-time Data Streams
Project
Build a hybrid search system with multiple data sources
Topics:
8.1 Modular and Agentic RAG
Modular RAG
Component Modularity
Plug-and-Play Modules
Module Composition
Interface Design
Module Optimization
Agentic RAG
Agent-Based Retrieval
Tool Use in RAG
Planning and Reasoning
Multi-Step Retrieval
Self-Improving RAG
Adaptive RAG
Query Routing
Dynamic Pipeline Selection
Confidence-Based Routing
Fallback Mechanisms
Performance Monitoring
Self-RAG
Self-Reflection
Retrieval Necessity Detection
Answer Quality Assessment
Iterative Improvement
Verification Loops
8.2 Specialized RAG Patterns
Conversational RAG
Dialogue Context Management
Turn-Taking Strategies
Memory Integration
Persona Consistency
Clarification Handling
Code RAG
Code Understanding
Repository Indexing
API Documentation RAG
Code Example Retrieval
Debugging Assistance
Graph RAG
Knowledge Graph Integration
Graph Traversal
Entity Relationship Extraction
Graph-Enhanced Retrieval
Reasoning over Graphs
Multimodal RAG
Image-Text RAG
Video RAG
Audio RAG
Document Layout RAG
Cross-Modal Retrieval
Lab
Implement advanced RAG patterns
Topics:
9.1 Knowledge Graph Integration
Knowledge Graph Basics
Graph Data Models
RDF and SPARQL
Property Graphs
Graph Databases (Neo4j)
Ontology Design
Entity and Relation Extraction
Named Entity Recognition
Relation Extraction
Coreference Resolution
Entity Linking
Knowledge Base Population
Graph Construction
Automatic Graph Building
Semi-Structured Data
Schema Design
Graph Validation
Quality Assurance
Graph-Based Retrieval
Subgraph Matching
Path Finding
Graph Embeddings
Neighborhood Aggregation
Graph Neural Networks
9.2 Structured Data RAG
Table Understanding
Table Parsing
Schema Extraction
Cell Understanding
Table Embeddings
Table QA
SQL Generation
Text-to-SQL
Natural Language Interfaces
Query Validation
Result Interpretation
Error Handling
Structured + Unstructured
Hybrid Retrieval
Join Operations
Data Fusion
Consistency Checking
Cross-Reference Resolution
Time-Series and Streaming
Temporal RAG
Real-time Updates
Stream Processing
Event-Driven RAG
Historical Context
Project
Build a knowledge graph-enhanced RAG system
Topics:
10.1 Performance Optimization
Latency Optimization
Query Optimization
Index Optimization
Caching Strategies
Prefetching
Parallel Processing
Throughput Scaling
Batch Processing
Request Queuing
Load Distribution
Horizontal Scaling
Vertical Scaling
Memory Management
Embedding Compression
Index Compression
Cache Management
Memory Mapping
Garbage Collection
Cost Optimization
Resource Allocation
Compute Optimization
Storage Optimization
API Cost Management
Infrastructure Choices
10.2 Quality Optimization
Retrieval Quality
Relevance Tuning
Precision/Recall Balance
Ranking Optimization
Diversity Enhancement
Freshness Scoring
Generation Quality
Prompt Optimization
Context Selection
Answer Quality Metrics
Hallucination Reduction
Factuality Enhancement
End-to-End Optimization
Pipeline Tuning
Component Balancing
Feedback Loops
Online Learning
Continuous Improvement
A/B Testing
Experiment Design
Metric Selection
Statistical Analysis
Result Interpretation
Rollout Strategies
Lab
Optimize a RAG system for production performance
Topics:
11.1 RAG Evaluation
Evaluation Frameworks
RAGAS Framework
Custom Metrics
Human Evaluation
Automated Testing
Benchmark Suites
Retrieval Metrics
Precision@K
Recall@K
MRR (Mean Reciprocal Rank)
MAP (Mean Average Precision)
NDCG
Generation Metrics
Faithfulness
Answer Relevance
Context Precision
Context Recall
Answer Similarity
11.2 Testing and Monitoring
Testing Strategies
Unit Testing
Integration Testing
End-to-End Testing
Load Testing
Stress Testing
Production Monitoring
Performance Dashboards
Quality Monitoring
Error Tracking
Usage Analytics
Cost Monitoring
Project
Implement comprehensive evaluation for a RAG system
Topics:
12.1 Production Architecture
System Architecture
Microservices Design
API Gateway
Service Mesh
Message Queues
Event Streaming
Deployment Strategies
Containerization (Docker)
Orchestration (Kubernetes)
Serverless Deployment
Edge Deployment
Multi-Region Setup
High Availability
Redundancy Design
Failover Mechanisms
Disaster Recovery
Backup Strategies
Health Checks
Security and Compliance
Authentication/Authorization
Data Encryption
Access Control
Audit Logging
Compliance (GDPR, HIPAA)
12.2 Enterprise Features
Multi-Tenancy
Tenant Isolation
Resource Allocation
Data Segregation
Custom Configurations
Billing Integration
Administration
User Management
Content Management
Configuration Management
Version Control
Rollback Procedures
Integration
Enterprise Systems
SSO Integration
API Management
Webhook Support
Event Integration
Operations
DevOps Practices
CI/CD Pipelines
Infrastructure as Code
Monitoring and Alerting
Incident Response
Final Project
Deploy a production-ready enterprise RAG system
TOOlS & PLATFORMS
Our AI Programs
Build a complete multi-agent customer service system with: - Natural language understanding - Intent recognition and routing - Knowledge base integration - Escalation handling - Sentiment analysis - Performance monitoring
Develop an AI research agent capable of: - Literature review automation - Data collection and analysis - Report generation - Citation management - Collaborative research - Quality validation
Create an agent system for business process automation: - Workflow orchestration - Document processing - Decision automation - Integration with enterprise systems - Compliance checking - Performance optimization
LEARNERS
BATCHES
YEARS
SUPPORT
100000+ uplifted through our hybrid classroom & online training, enriched by real-time projects and job support.
Come and chat with us about your goals over a cup of coffee.
2nd Floor, Hitech City Rd, Above Domino's, opp. Cyber Towers, Jai Hind Enclave, Hyderabad, Telangana.
3rd Floor, Site No 1&2 Saroj Square, Whitefield Main Road, Munnekollal Village Post, Marathahalli, Bengaluru, Karnataka.
