AI Generative
Master AI GenerativeFrom Zero to Production
32h
12 modules
+500 apprenants
LangChain & LlamaIndexRAG PipelineFine-tuning LoRAAWS/GCP Deployment
Investment
1 490 DH
or 3x interest-free • CPF eligible
- 32h of HD videos available forever
- 5 practical projects with detailed feedback
- Access to dedicated Slack community
- Monthly live Q&A sessions with instructor
- Ready-to-use templates and Jupyter notebooks
30-day satisfaction guarantee or your money back
Full Program
6Modules
32hContent
Complete program
32h of content
|6 modulesFundamentals & IntermediateModules 1–3
Module 1
AI Generative Fundamentals
4h5 topics17%
Transformer Architecture A to Z
Multi-head attention mechanism
Tokenization & semantic embeddings
LLM Overview: GPT-4, Claude, Mistral, Gemini
Module 2
Advanced Prompt Engineering
5h6 topics33%
Zero-shot, one-shot, few-shot prompting
Chain-of-Thought & Self-Consistency
ReAct and step-by-step reasoning
Tree-of-Thought for complex problems
Module 3★ Key
RAG — Retrieval Augmented Generation
6h6 topics50%
Naive vs advanced RAG architecture
Chunking strategies (fixed, semantic, hierarchical)
Vector databases: Pinecone, Qdrant, Weaviate, pgvector
Reranking and result fusion
Module 1
AI Generative Fundamentals
4h5 topics17%
Transformer Architecture A to Z
Multi-head attention mechanism
Tokenization & semantic embeddings
LLM Overview: GPT-4, Claude, Mistral, Gemini
Module 2
Advanced Prompt Engineering
5h6 topics33%
Zero-shot, one-shot, few-shot prompting
Chain-of-Thought & Self-Consistency
ReAct and step-by-step reasoning
Tree-of-Thought for complex problems
Module 3★ Key
RAG — Retrieval Augmented Generation
6h6 topics50%
Naive vs advanced RAG architecture
Chunking strategies (fixed, semantic, hierarchical)
Vector databases: Pinecone, Qdrant, Weaviate, pgvector
Reranking and result fusion
Module 1
AI Generative Fundamentals
4h5 topics17%
Transformer Architecture A to Z
Multi-head attention mechanism
Tokenization & semantic embeddings
LLM Overview: GPT-4, Claude, Mistral, Gemini
Module 2
Advanced Prompt Engineering
5h6 topics33%
Zero-shot, one-shot, few-shot prompting
Chain-of-Thought & Self-Consistency
ReAct and step-by-step reasoning
Tree-of-Thought for complex problems
Module 3★ Key
RAG — Retrieval Augmented Generation
6h6 topics50%
Naive vs advanced RAG architecture
Chunking strategies (fixed, semantic, hierarchical)
Vector databases: Pinecone, Qdrant, Weaviate, pgvector
Reranking and result fusion
Module 1
AI Generative Fundamentals
4h5 topics17%
Transformer Architecture A to Z
Multi-head attention mechanism
Tokenization & semantic embeddings
LLM Overview: GPT-4, Claude, Mistral, Gemini
Module 2
Advanced Prompt Engineering
5h6 topics33%
Zero-shot, one-shot, few-shot prompting
Chain-of-Thought & Self-Consistency
ReAct and step-by-step reasoning
Tree-of-Thought for complex problems
Module 3★ Key
RAG — Retrieval Augmented Generation
6h6 topics50%
Naive vs advanced RAG architecture
Chunking strategies (fixed, semantic, hierarchical)
Vector databases: Pinecone, Qdrant, Weaviate, pgvector
Reranking and result fusion
Module 1
AI Generative Fundamentals
4h5 topics17%
Transformer Architecture A to Z
Multi-head attention mechanism
Tokenization & semantic embeddings
LLM Overview: GPT-4, Claude, Mistral, Gemini
Module 2
Advanced Prompt Engineering
5h6 topics33%
Zero-shot, one-shot, few-shot prompting
Chain-of-Thought & Self-Consistency
ReAct and step-by-step reasoning
Tree-of-Thought for complex problems
Module 3★ Key
RAG — Retrieval Augmented Generation
6h6 topics50%
Naive vs advanced RAG architecture
Chunking strategies (fixed, semantic, hierarchical)
Vector databases: Pinecone, Qdrant, Weaviate, pgvector
Reranking and result fusion
Module 1
AI Generative Fundamentals
4h5 topics17%
Transformer Architecture A to Z
Multi-head attention mechanism
Tokenization & semantic embeddings
LLM Overview: GPT-4, Claude, Mistral, Gemini
Module 2
Advanced Prompt Engineering
5h6 topics33%
Zero-shot, one-shot, few-shot prompting
Chain-of-Thought & Self-Consistency
ReAct and step-by-step reasoning
Tree-of-Thought for complex problems
Module 3★ Key
RAG — Retrieval Augmented Generation
6h6 topics50%
Naive vs advanced RAG architecture
Chunking strategies (fixed, semantic, hierarchical)
Vector databases: Pinecone, Qdrant, Weaviate, pgvector
Reranking and result fusion
Module 1
AI Generative Fundamentals
4h5 topics17%
Transformer Architecture A to Z
Multi-head attention mechanism
Tokenization & semantic embeddings
LLM Overview: GPT-4, Claude, Mistral, Gemini
Module 2
Advanced Prompt Engineering
5h6 topics33%
Zero-shot, one-shot, few-shot prompting
Chain-of-Thought & Self-Consistency
ReAct and step-by-step reasoning
Tree-of-Thought for complex problems
Module 3★ Key
RAG — Retrieval Augmented Generation
6h6 topics50%
Naive vs advanced RAG architecture
Chunking strategies (fixed, semantic, hierarchical)
Vector databases: Pinecone, Qdrant, Weaviate, pgvector
Reranking and result fusion
Advanced & DeploymentModules 4–6
Module 4
Agents & LLM Tools
5h6 topics67%
ReAct Agents with LangChain
LangGraph for complex workflows
Function calling & tool use
Multi-step and reflective agents
Module 5
Fine-tuning & Model Adaptation
5h6 topics83%
When to fine-tune vs RAG vs prompting
LoRA and QLoRA — technique and practice
Dataset preparation and formatting
Fine-tuning Mistral 7B with Unsloth
Module 6★ Key
Production Deployment & Observability
7h7 topics100%
FastAPI for LLM serving
Containerization & orchestration
AWS Bedrock / GCP Vertex AI deployment
Monitoring: latency, cost, response quality
Module 4
Agents & LLM Tools
5h6 topics67%
ReAct Agents with LangChain
LangGraph for complex workflows
Function calling & tool use
Multi-step and reflective agents
Module 5
Fine-tuning & Model Adaptation
5h6 topics83%
When to fine-tune vs RAG vs prompting
LoRA and QLoRA — technique and practice
Dataset preparation and formatting
Fine-tuning Mistral 7B with Unsloth
Module 6★ Key
Production Deployment & Observability
7h7 topics100%
FastAPI for LLM serving
Containerization & orchestration
AWS Bedrock / GCP Vertex AI deployment
Monitoring: latency, cost, response quality
Module 4
Agents & LLM Tools
5h6 topics67%
ReAct Agents with LangChain
LangGraph for complex workflows
Function calling & tool use
Multi-step and reflective agents
Module 5
Fine-tuning & Model Adaptation
5h6 topics83%
When to fine-tune vs RAG vs prompting
LoRA and QLoRA — technique and practice
Dataset preparation and formatting
Fine-tuning Mistral 7B with Unsloth
Module 6★ Key
Production Deployment & Observability
7h7 topics100%
FastAPI for LLM serving
Containerization & orchestration
AWS Bedrock / GCP Vertex AI deployment
Monitoring: latency, cost, response quality
Module 4
Agents & LLM Tools
5h6 topics67%
ReAct Agents with LangChain
LangGraph for complex workflows
Function calling & tool use
Multi-step and reflective agents
Module 5
Fine-tuning & Model Adaptation
5h6 topics83%
When to fine-tune vs RAG vs prompting
LoRA and QLoRA — technique and practice
Dataset preparation and formatting
Fine-tuning Mistral 7B with Unsloth
Module 6★ Key
Production Deployment & Observability
7h7 topics100%
FastAPI for LLM serving
Containerization & orchestration
AWS Bedrock / GCP Vertex AI deployment
Monitoring: latency, cost, response quality
Module 4
Agents & LLM Tools
5h6 topics67%
ReAct Agents with LangChain
LangGraph for complex workflows
Function calling & tool use
Multi-step and reflective agents
Module 5
Fine-tuning & Model Adaptation
5h6 topics83%
When to fine-tune vs RAG vs prompting
LoRA and QLoRA — technique and practice
Dataset preparation and formatting
Fine-tuning Mistral 7B with Unsloth
Module 6★ Key
Production Deployment & Observability
7h7 topics100%
FastAPI for LLM serving
Containerization & orchestration
AWS Bedrock / GCP Vertex AI deployment
Monitoring: latency, cost, response quality
Module 4
Agents & LLM Tools
5h6 topics67%
ReAct Agents with LangChain
LangGraph for complex workflows
Function calling & tool use
Multi-step and reflective agents
Module 5
Fine-tuning & Model Adaptation
5h6 topics83%
When to fine-tune vs RAG vs prompting
LoRA and QLoRA — technique and practice
Dataset preparation and formatting
Fine-tuning Mistral 7B with Unsloth
Module 6★ Key
Production Deployment & Observability
7h7 topics100%
FastAPI for LLM serving
Containerization & orchestration
AWS Bedrock / GCP Vertex AI deployment
Monitoring: latency, cost, response quality
Module 4
Agents & LLM Tools
5h6 topics67%
ReAct Agents with LangChain
LangGraph for complex workflows
Function calling & tool use
Multi-step and reflective agents
Module 5
Fine-tuning & Model Adaptation
5h6 topics83%
When to fine-tune vs RAG vs prompting
LoRA and QLoRA — technique and practice
Dataset preparation and formatting
Fine-tuning Mistral 7B with Unsloth
Module 6★ Key
Production Deployment & Observability
7h7 topics100%
FastAPI for LLM serving
Containerization & orchestration
AWS Bedrock / GCP Vertex AI deployment
Monitoring: latency, cost, response quality
Hover to pause
Standard module
Key module
Prerequisites
2 items01Intermediate Python (functions, classes, libraries)
02Machine learning basics (recommended but not required)
Target Audience
4 items01Developers looking to integrate generative AI into their applications
02Data Scientists wanting to specialize in LLMs
03Tech Leads in charge of an AI strategy
04ML Engineers seeking to master modern architectures
AI Generative
Master AI Generative
From Zero to Production
1 490 DH
32h12 modules
- LangChain & LlamaIndex
- RAG Pipeline
- Fine-tuning LoRA
- AWS/GCP Deployment
✦ 30-day satisfaction guarantee · Priority support included