Completed
- Course Overview: Building Integrated AI Systems
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
RAG and MCP Fundamentals - A Hands-On Crash Course
Automatically move to the next video in the Classroom when playback concludes
- 1 - Course Overview: Building Integrated AI Systems
- 2 - The Simplest Explanation of RAG
- 3 - Real-world Use Case: Internal Policy Chatbot
- 4 - Understanding Retrieval, Augmenting, and Generation
- 5 - When to use Prompt Engineering, Fine-Tuning, or RAG
- 6 - Solving Voice and Style with Fine-Tuning
- 7 - Why RAG is Best for Dynamic Factual Information
- 8 - Keyword Search Techniques: TF-IDF and BM25
- 9 - Hands-on Lab 1: Basic Search and Keyword Limitations
- 10 - Introduction to Semantic Search and Meaning
- 11 - Embedding Models: Parameter Size and Local vs. API Models
- 12 - How Embeddings Convert Text into Mathematical Vectors
- 13 - Vector Similarity and the Dot Product
- 14 - Hands-on Lab 2: Implementing Semantic Search with Embedding Models
- 15 - Scaling with Vector Databases: Chroma and Pinecone
- 16 - Indexing Algorithms: HNSW, IVF, and LSH
- 17 - Hands-on Lab 3: Initializing and Querying a Vector Database
- 18 - The Precision Problem: Why Document Chunking is Essential
- 19 - Chunking Strategies: Fixed-size, Overlap, and Boundary Rules
- 20 - Hands-on Lab 4: Document Chunking and Optimized Retrieval
- 21 - Bringing it All Together: The RAG Pipeline
- 22 - Hands-on Lab 5: Building a Complete End-to-End RAG Pipeline
- 23 - Production Concerns: Caching, Monitoring, and Error Handling
- 24 - Implementation Strategies for Query, Embedding, and LLM Caching
- 25 - Essential Metrics for Tracking RAG Performance
- 26 - Production Architecture: Microservices on Kubernetes
- 27 - Introduction to Model Context Protocol MCP
- 28 - The Role of AI Agents in Action-Oriented Systems
- 29 - Why We Need Standardized Tools for Third-Party Interactions
- 30 - MCP Architecture: Clients, Servers, and Local vs. Remote Hosting
- 31 - Hands-on Lab 6: Setting up the AI Assistant Environment
- 32 - Core MCP Components: Resources, Tools, and Prompts
- 33 - Understanding the MCP Specification and JSON-RPC Protocol
- 34 - Hands-on Lab 7: Connecting to and Using an Existing MCP Server
- 35 - Building a Custom MCP Server with the Python SDK
- 36 - Testing with the MCP Inspector
- 37 - Hands-on Lab 8: Developing Resources, Tools, and Prompts for MCP
- 38 - Building an MCP Client: Roots, Sampling, and Elicitation
