Generative AI Architectures with LLM, Prompt, RAG, Vector DB

<div>In this course, you'll learn how to Design Generative AI Architectures with integrating AI-Powered S/LLMs into EShop Support Enterprise Applications using Prompt Engineering, RAG, Fine-tuning and Vector DBs.</div><div><br></div><div>We will design Generative AI Architectures with below components;</div><div><ul><li><span style="font-size: 1rem;">Small and Large Language Models (S/LLMs)</span></li><li><span style="font-size: 1rem;">Prompt Engineering</span></li><li><span style="font-size: 1rem;">Retrieval Augmented Generation (RAG)</span></li><li><span style="font-size: 1rem;">Fine-Tuning</span></li><li><span style="font-size: 1rem;">Vector Databases</span></li></ul></div><div><br></div><div>We start with the basics and progressively dive deeper into each topic. We'll also follow LLM Augmentation Flow is a powerful framework that augments LLM results following the Prompt Engineering, RAG and Fine-Tuning.</div><div><br></div><div>Large Language Models (LLMs) module;</div><div><ul><li><span style="font-size: 1rem;">How Large Language Models (LLMs) works?</span></li><li><span style="font-size: 1rem;">Capabilities of LLMs: Text Generation, Summarization, Q&amp;A, Classification, Sentiment Analysis, Embedding Semantic Search, Code Generation</span></li><li><span style="font-size: 1rem;">Generate Text with ChatGPT: Understand Capabilities and Limitations of LLMs (Hands-on)</span></li><li><span style="font-size: 1rem;">Function Calling and Structured Output in Large Language Models (LLMs)</span></li><li><span style="font-size: 1rem;">LLM Models: OpenAI ChatGPT, Meta Llama, Anthropic Claude, Google Gemini, Mistral Mixral, xAI Grok</span></li><li><span style="font-size: 1rem;">SLM Models: OpenAI ChatGPT 4o mini, Meta Llama 3.2 mini, Google Gemma, Microsoft Phi 3.5</span></li><li><span style="font-size: 1rem;">Interacting Different LLMs with Chat UI: ChatGPT, LLama, Mixtral, Phi3</span></li><li><span style="font-size: 1rem;">Interacting OpenAI Chat Completions Endpoint with Coding</span></li><li><span style="font-size: 1rem;">Installing and Running Llama and Gemma Models Using Ollama to run LLMs locally</span></li><li><span style="font-size: 1rem;">Modernizing and Design EShop Support Enterprise Apps with AI-Powered LLM Capabilities</span></li><li><span style="font-size: 1rem;">Develop .NET to integrate LLM models and performs Classification, Summarization, Data extraction, Anomaly detection, Translation and Sentiment Analysis use cases.</span></li></ul></div><div><br></div><div>Prompt Engineering module;</div><div><ul><li><span style="font-size: 1rem;">Steps of Designing Effective Prompts: Iterate, Evaluate and Templatize</span></li><li><span style="font-size: 1rem;">Advanced Prompting Techniques: Zero-shot, One-shot, Few-shot, Chain-of-Thought, Instruction and Role-based</span></li><li><span style="font-size: 1rem;">Design Advanced Prompts for EShop Support – Classification, Sentiment Analysis, Summarization, Q&amp;A Chat, and Response Text Generation</span></li><li><span style="font-size: 1rem;">Design Advanced Prompts for Ticket Detail Page in EShop Support App w/ Q&amp;A Chat and RAG</span></li></ul></div><div><span style="font-size: 1rem;"><br></span></div><div><span style="font-size: 1rem;">Retrieval-Augmented Generation (RAG) module;</span></div><div><ul><li><span style="font-size: 1rem;">The RAG Architecture Part 1: Ingestion with Embeddings and Vector Search</span></li><li><span style="font-size: 1rem;">The RAG Architecture Part 2: Retrieval with Reranking and Context Query Prompts</span></li><li><span style="font-size: 1rem;">The RAG Architecture Part 3: Generation with Generator and Output</span></li><li><span style="font-size: 1rem;">E2E Workflow of a Retrieval-Augmented Generation (RAG) - The RAG Workflow</span></li><li><span style="font-size: 1rem;">Design EShop Customer Support using RAG</span></li><li><span style="font-size: 1rem;">End-to-End RAG Example for EShop Customer Support using OpenAI Playground</span></li><li><span style="font-size: 1rem;">Develop RAG – Retrieval-Augmented Generation with .NET, implement the full RAG flow with real examples using .NET</span></li></ul></div><div><br></div><div>Fine-Tuning module;</div><div><ul><li><span style="font-size: 1rem;">Fine-Tuning Workflow</span></li><li><span style="font-size: 1rem;">Fine-Tuning Methods: Full, Parameter-Efficient Fine-Tuning (PEFT), LoRA, Transfer</span></li><li><span style="font-size: 1rem;">Design EShop Customer Support Using Fine-Tuning</span></li><li><span style="font-size: 1rem;">End-to-End Fine-Tuning a LLM for EShop Customer Support using OpenAI Playground</span></li></ul></div><div><span style="font-size: 1rem;"><br></span></div><div><span style="font-size: 1rem;">Also, we will discuss</span></div><div><ul><li><span style="font-size: 1rem;">Choosing the Right Optimization – Prompt Engineering, RAG, and Fine-Tuning</span></li></ul></div><div><br></div><div>Vector Database and Semantic Search with RAG module</div><div><ul><li><span style="font-size: 1rem;">What are Vectors, Vector Embeddings and Vector Database?</span></li><li><span style="font-size: 1rem;">Explore Vector Embedding Models: OpenAI - text-embedding-3-small, Ollama - all-minilm</span></li><li><span style="font-size: 1rem;">Semantic Meaning and Similarity Search: Cosine Similarity, Euclidean Distance</span></li><li><span style="font-size: 1rem;">How Vector Databases Work: Vector Creation, Indexing, Search</span></li><li><span style="font-size: 1rem;">Vector Search Algorithms: kNN, ANN, and Disk-ANN</span></li><li><span style="font-size: 1rem;">Explore Vector Databases: Pinecone, Chroma, Weaviate, Qdrant, Milvus, PgVector, Redis</span></li></ul></div><div><span style="font-size: 1rem;">Lastly, we will Design EShopSupport Architecture with LLMs and Vector Databases</span></div><div><ul><li><span style="font-size: 1rem;">Using LLMs and VectorDBs as Cloud-Native Backing Services in Microservices Architecture</span></li><li><span style="font-size: 1rem;">Design EShop Support with LLMs, Vector Databases and Semantic Search</span></li><li><span style="font-size: 1rem;">Azure Cloud AI Services: Azure OpenAI, Azure AI Search</span></li><li><span style="font-size: 1rem;">Design EShop Support with Azure Cloud AI Services: Azure OpenAI, Azure AI Search</span></li></ul></div><div><br></div><div>This course is more than just learning Generative AI, it's a deep dive into the world of how to design Advanced AI solutions by integrating LLM architectures into Enterprise applications.</div><div><br></div><div>You'll get hands-on experience designing a complete EShop application, including LLM capabilities like Summarization, Q&amp;A, Classification, Sentiment Analysis, Embedding Semantic Search, Code Generation.</div>

What you'll learn:

• Generative AI Model Architectures (Types of Generative AI Models)
• Transformer Architecture: Attention is All you Need
• Large Language Models (LLMs) Architectures
• Text Generation, Summarization, Q&A, Classification, Sentiment Analysis, Embedding Semantic Search
• Generate Text with ChatGPT: Understand Capabilities and Limitations of LLMs (Hands-on)
• Function Calling and Structured Outputs in Large Language Models (LLMs)
• LLM Providers: OpenAI, Meta AI, Anthropic, Hugging Face, Microsoft, Google and Mistral AI
• LLM Models: OpenAI ChatGPT, Meta Llama, Anthropic Claude, Google Gemini, Mistral Mixral, xAI Grok
• SLM Models: OpenAI ChatGPT 4o mini, Meta Llama 3.2 mini, Google Gemma, Microsoft Phi 3.5
• How to Choose LLM Models: Quality, Speed, Price, Latency and Context Window
• Interacting Different LLMs with Chat UI: ChatGPT, LLama, Mixtral, Phi3
• Installing and Running Llama and Gemma Models Using Ollama
• Modernizing Enterprise Apps with AI-Powered LLM Capabilities
• Designing the 'EShop Support App' with AI-Powered LLM Capabilities
• Advanced Prompting Techniques: Zero-shot, One-shot, Few-shot, COT
• Design Advanced Prompts for Ticket Detail Page in EShop Support App w/ Q&A Chat and RAG
• The RAG Architecture: Ingestion with Embeddings and Vector Search
• E2E Workflow of a Retrieval-Augmented Generation (RAG) - The RAG Workflow
• End-to-End RAG Example for EShop Customer Support using OpenAI Playground
• Fine-Tuning Methods: Full, Parameter-Efficient Fine-Tuning (PEFT), LoRA, Transfer
• End-to-End Fine-Tuning a LLM for EShop Customer Support using OpenAI Playground
• Choosing the Right Optimization – Prompt Engineering, RAG, and Fine-Tuning
• Vector Database and Semantic Search with RAG
• Explore Vector Embedding Models: OpenAI - text-embedding-3-small, Ollama - all-minilm
• Explore Vector Databases: Pinecone, Chroma, Weaviate, Qdrant, Milvus, PgVector, Redis
• Using LLMs and VectorDBs as Cloud-Native Backing Services in Microservices Architecture
• Design EShop Support with LLMs, Vector Databases and Semantic Search
• Design EShop Support with Azure Cloud AI Services: Azure OpenAI, Azure AI Search
• Develop .NET to integrate LLM models and performs Classification, Summarization, Data extraction, Anomaly detection, Translation and Sentiment Analysis use case
• Develop RAG – Retrieval-Augmented Generation with .NET, implement the full RAG flow with real examples using .NET and Qdrant