Unlock the transformative power of Generative AI with Python! This comprehensive course equips you with the essential knowledge and practical Python skills to master the core technologies driving this revolution, enabling you to build intelligent applications that understand, generate, and interact with language remarkably.

You'll delve into the fundamentals of Large Language Models (LLMs) and the crucial role of Vector Databases for efficient information retrieval. Discover the power of Retrieval-Augmented Generation (RAG), which allows your AI to answer complex questions using your own data, making it smarter and more contextually aware.

Furthermore, you'll explore the exciting domain of Agentic Systems, learning how to design and build autonomous AI agents capable of performing tasks and making decisions.

In my course I will teach you:

• Large-Language Models

  • Classical NLP vs. LLM

  • Narrow AI Achievements

  • Model Performance and Achievements

  • Model Training Process

  • Model Improvement Options

  • Model Providers

  • Model Benchmarking

  • Interaction with LLMs

  • Message Types

  • LLM Parameters

  • Local Use of Models

  • Large Multimodal Models

  • Tokenization

  • Reasoning Models

  • Small Language Models

  • JailBreaking

  • Working with Chains

  • Parallel Chains, Router Chains, ...

• Vector Databases

  • Data Ingestion Pipeline

  • Data source and data loading

  • data chunking

  • embeddings

  • data storage

  • data querying

• Retrieval-Augmented Generation

  • Baseline RAG

  • Context Enrichment

  • Corrective RAG

  • Hybrid RAG

  • Query Expansion

  • Speculative RAG

  • Agentic RAG

• Agentic Systems

  • crewAI

  • Google ADK

  • OpenAI Agents SDK

  • AG2

  • LangGraph (coming soon)

• Agent Interactions

  • MCP

  • ACP

  • A2A

Large-Language Models

• Classical NLP vs. LLM

• Narrow AI Achievements

• Model Performance and Achievements

• Model Training Process

• Model Improvement Options

• Model Providers

• Model Benchmarking

• Interaction with LLMs

• Message Types

• LLM Parameters

• Local Use of Models

• Large Multimodal Models

• Tokenization

• Reasoning Models

• Small Language Models

• JailBreaking

• Working with Chains

• Parallel Chains, Router Chains, ...

Classical NLP vs. LLM

Narrow AI Achievements

Model Performance and Achievements

Model Training Process

Model Improvement Options

Model Providers

Model Benchmarking

Interaction with LLMs

Message Types

LLM Parameters

Local Use of Models

Large Multimodal Models

Tokenization

Reasoning Models

Small Language Models

JailBreaking

Working with Chains

Parallel Chains, Router Chains, ...

Vector Databases

• Data Ingestion Pipeline

• Data source and data loading

• data chunking

• embeddings

• data storage

• data querying

Data Ingestion Pipeline

Data source and data loading

data chunking

embeddings

data storage

data querying

Retrieval-Augmented Generation

• Baseline RAG

• Context Enrichment

• Corrective RAG

• Hybrid RAG

• Query Expansion

• Speculative RAG

• Agentic RAG

Baseline RAG

Context Enrichment

Corrective RAG

Hybrid RAG

Query Expansion

Speculative RAG

Agentic RAG

Agentic Systems

• crewAI

• Google ADK

• OpenAI Agents SDK

• AG2

• LangGraph (coming soon)

crewAI

Google ADK

OpenAI Agents SDK

AG2

LangGraph (coming soon)

Agent Interactions

• MCP

• ACP

• A2A

MCP

ACP

A2A