Elite IT Academy
Home / AI Agents with Modern C++

AI ENGINEERING · MODERN C++ · HANDS-ON COURSE

AI Agents with Modern C++
RAG, Tools and Agentic AI

Build practical AI applications with LLMs, retrieval, tools and agents—directly in Modern C++.

Go to the Udemy course ↗View course contents ↓

COURSE SUMMARY

AI Engineering with Modern C++: LLMs, RAG, AI Agents & GenAI

Learn how to build real-world AI applications with Modern C++. Work with Large Language Models (LLMs), Generative AI, embeddings, vector search, Retrieval-Augmented Generation (RAG), AI reranking, local LLMs, and AI agents.

Most Generative AI courses focus on Python. This course takes a different approach: you will learn how to integrate modern AI capabilities directly into C++ applications, combining the performance and flexibility of C++ with today's powerful AI technologies.

This is a hands-on AI Engineering course focused on building working applications rather than studying AI theory. You will progressively move from your first LLM API call to advanced RAG pipelines, hybrid retrieval, reranking, AI agents, and Agentic RAG.

What you will learn

  • Build AI-powered applications using Modern C++ and LLM APIs.
  • Integrate OpenAI and Groq APIs into C++ applications.
  • Understand tokens, embeddings, tensors, context windows, and LLM inference.
  • Generate embeddings and implement semantic search.
  • Build searchable knowledge bases using document chunking and embeddings.
  • Implement Retrieval-Augmented Generation (RAG) applications.
  • Build Vector RAG using SQLite and FAISS.
  • Combine keyword and semantic search using BM25 and vector search.
  • Improve retrieval quality using Reciprocal Rank Fusion (RRF).
  • Apply AI reranking models to improve RAG results.
  • Run local LLMs using llama.cpp and GGUF models.
  • Build AI agents that use tools and perform multi-step tasks.
  • Design orchestrated AI agent workflows.
  • Build Agentic RAG applications that combine retrieval, reasoning, and tools.

What you will build

  • LLM applications using OpenAI and Groq APIs.
  • Local LLM applications using llama.cpp.
  • Semantic search engines and searchable knowledge bases using embeddings.
  • Vector RAG applications using SQLite and high-performance Vector RAG using FAISS.
  • Hybrid RAG using BM25, vector search, and RRF, plus AI-reranked RAG systems.
  • Calculator and orchestrated AI agents.
  • An Agentic RAG-based AI medical assistant.

Course roadmap

AI Engineering Fundamentals → LLM APIs → Local LLMs → Embeddings → Vector Search → RAG → FAISS → Hybrid RAG → Reranking → AI Agents → Agentic RAG

Each concept builds on the last, giving you a practical understanding of how modern AI applications are designed and implemented.

Technologies you will use

Modern C++OpenAI APIGroq APIllama.cppSQLiteFAISSBM25Reciprocal Rank FusionONNX RuntimeEmbeddingsVector SearchRAGAI Agents

Why learn AI Engineering with C++?

C++ remains essential for high-performance software, systems programming, enterprise applications, edge computing, and performance-sensitive workloads. This course shows you how to bring modern Generative AI and LLM capabilities into the C++ ecosystem, integrating AI into real C++ applications instead of learning only through Python notebooks.

Who is this course for?

  • C++ developers moving into AI Engineering.
  • Software engineers interested in Generative AI and LLM applications.
  • Backend and systems developers building AI-powered software.
  • Developers learning RAG and semantic search.
  • Programmers interested in AI agents and Agentic AI.
  • Developers who want to run LLMs locally with C++.
  • Students and professionals looking for practical AI Engineering skills.

Prerequisites

Basic C++ programming knowledge is recommended.

No prior experience with LLMs, RAG, embeddings, vector databases, AI agents, or Generative AI is required. These concepts are introduced progressively throughout the course.

Start building AI with Modern C++

Move beyond traditional software development and follow a practical path from LLM fundamentals to RAG, vector search, reranking, AI agents, and Agentic RAG. Learn the concepts, write the C++ code, build the applications, and develop the skills to engineer modern AI systems.

LESSON-BY-LESSON OUTLINE

Course contents

Expand a module to explore its lessons and durations.

Course Setup and Development Environments23 lessons
  1. Welcome to AI Engineering with Modern C++
  2. What You'll Build in This AI Engineering Course
  3. Installing Visual Studio 2026 for C++ AI Development
  4. Installing Git for AI Engineering
  5. Installing CMake for C++ AI Projects
  6. Installing vcpkg: The C++ Package Manager
  7. Setting Up the Course Source Code
  8. Installing the C++ AI Libraries and Tools
  9. Installing ONNX Runtime for C++ AI Applications
  10. Installing Pandoc for Document Processing
  11. Downloading LLM, Embedding and Reranking Models
  12. Configuring Dependencies for the C++ AI Solution
  13. Building and Testing the Course Solution
  14. Creating and Configuring a Groq API Key
  15. Creating and Configuring an OpenAI API Key
  16. Installing the Course Demonstration Source Code in Ubuntu
  17. Installing the Libraries and Tools Required for the Course
  18. Building All Course Projects from the Source Code
  19. Installing Visual Studio Code for Ubuntu and WSL
  20. Creating Groq and OpenAI API Keys
  21. Downloading the LLM, Embedding and ReRanking Models
  22. Building and Debugging Course Projects Using Visual Studio Code
  23. Setting Up the API Key Environment for the Course Projects
AI Fundamentals and LLM Applications with C++18 lessons
  1. Understanding Tokens and Tokenization in AI
  2. Understanding Embeddings in AI
  3. Using Cosine Similarity for Semantic Search
  4. Understanding Tensors in AI and Machine Learning
  5. Understanding Context Windows in LLMs
  6. Understanding AI Models and LLMs
  7. Understanding AI Inference Engines
  8. Prompt Engineering Fundamentals for LLMs
  9. REST API Fundamentals for AI Applications
  10. Making HTTP Requests in C++ with libcurl
  11. Calling the OpenAI API from C++
  12. Parsing JSON in C++ with nlohmann::json
  13. Building an OpenAI API Client Class in C++
  14. Controlling LLM Output: Temperature, Max Tokens, Top-P and N
  15. Streaming LLM Responses in C++
  16. Generating JSON and Structured Outputs from LLMs
  17. Using Function Calling with LLMs
  18. Building a C++ LLM Chat Application
Local LLMs with llama.cpp4 lessons
  1. Why Run LLMs Locally?
  2. Running LLMs Locally with llama.cpp
  3. Understanding GGUF Models for Local LLMs
  4. Building a Local LLM Chat Application in C++
Embeddings, Vector Search and RAG with SQLite10 lessons
  1. Creating Embeddings for RAG
  2. RAG Indexing Pipeline: Preparing Documents for Indexing
  3. RAG Document Chunking: Why Chunking Matters
  4. Chunking Markdown Documents with MD4C
  5. Windows Embeddings Running Slowly? Build in Release Mode!
  6. Generating Embeddings for Document Chunks
  7. Storing Chunks and Embeddings in SQLite
  8. Implementing Vector Search with SQLite
  9. Understanding Retrieval-Augmented Generation (RAG)
  10. Building Vector RAG with SQLite and OpenAI
FAISS, Hybrid RAG and AI Reranking10 lessons
  1. Indexing Documents with FAISS and SQLite
  2. Implementing Vector Search with FAISS and SQLite
  3. Building High-Performance Vector RAG with FAISS and SQLite
  4. Understanding BM25 and Full-Text Search
  5. Building a Hybrid BM25 and Vector Search Index
  6. Understanding Reciprocal Rank Fusion (RRF)
  7. Building Hybrid RAG with BM25, Vector Search and RRF
  8. Understanding Reranking in RAG
  9. Tokenizing Text for AI Reranking
  10. Building RAG with AI Reranking and ONNX Runtime
AI Agents and Agentic RAG6 lessons
  1. Understanding AI Agents and Agentic AI
  2. Building a Calculator AI Agent in C++
  3. Building Orchestrated AI Agents in C++
  4. Understanding Agentic RAG
  5. Building the Knowledge Base for Agentic RAG
  6. Building an AI Medical Assistant with Agentic RAG

READY TO BUILD?

Learn AI Engineering with Modern C++.

Explore LLMs, retrieval, agents and Agentic RAG on Udemy.

Go to the Udemy course ↗