Modern C++ AI 工程实战：从 LLM、RAG 到智能体开发_CG群

告别 Python 依赖，本课程用 Modern C++ 带你从 API 调用、嵌入向量出发，逐步实现本地大模型、FAISS 向量检索、BM25+RRF 混合检索与 Agentic RAG，打造高性能生产级 AI 应用。

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

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

这门打破“AI开发专属于Python”传统认知的进阶实战课程，旨在教导具备基础 C++ 功底的开发者，如何利用 Modern C++ 构建高性能、生产级别的生成式 AI 与大语言模型（LLM）应用。课程摒弃了纯理论推导，完全以工程落地为导向，带你从最基本的 OpenAI/Groq API 调用与 Token 概念出发，一路平滑演进至本地大模型（llama.cpp/GGUF）、语义搜索及基于 SQLite 和 FAISS 的向量检索系统。你将亲手用 C++ 实现混合检索（BM25 + 向量搜索）、RRF 重排（Reciprocal Rank Fusion）等工业级优化手段，并最终融合工具调用与自主推理，打造出诸如智能医疗助手在内的复杂 AI 智能体（Agentic RAG）系统。

在此基础上，课程将高性能语言的底层优势与前沿 AI 架构深度融合，全面赋能企业级后端、系统编程及边缘计算场景。学员不仅能够填补市面上 C++ 缺少 AI 落地教程的空白，还能在不依赖 Python 繁重生态的前提下，掌握利用 ONNX Runtime 等底层工具链管理上下文窗口、嵌入向量（Embeddings）和张量（Tensors）的硬核技术。通过本课程构建的完整项目作品集，你将能够自信地迈向高性能 AI 工程师（AI Engineer）岗位，成功解锁在高性能软件中直接植入前沿 AI 能力的独家技能。

Learn LLM Integration, Retrieval-Augmented Generation, and Agentic AI Using Modern C++

What you’ll learn
⚡ Build AI applications in C++ using OpenAI APIs, embeddings, and large language models.
⚡ Create Vector RAG systems that retrieve and generate accurate responses from custom knowledge bases
⚡ Implement Hybrid RAG pipelines combining vector search and keyword search for improved retrieval quality.
⚡ Enhance RAG performance with reranking models to improve relevance and response accuracy.
⚡ Develop Agentic RAG systems that use tools, reasoning, and retrieval to solve complex tasks autonomously.

Description

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 intoC++ applications, combining the performance and flexibility of C++ with today’s powerful AI technologies.

This is ahands-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
By the end of this course, you will be able to

✨ 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
Throughout the course, you will build practical C++ AI applications including

✨ LLM applications using OpenAI and Groq APIs

✨ Local LLM applications using llama.cpp

✨ Semantic search engines using embeddings

✨ Searchable knowledge bases

✨ Vector RAG applications using SQLite

✨ High-performance Vector RAG using FAISS

✨ Hybrid RAG using BM25, vector search, and RRF

✨ RAG systems enhanced with AI reranking

✨ Calculator and orchestrated AI agents

✨ An Agentic RAG-based AI medical assistant

Course Roadmap
The course follows a progressive path from AI fundamentals to advanced AI Engineering

AI Engineering Fundamentals → LLM APIs → Local LLMs → Embeddings → Vector Search → RAG → FAISS → Hybrid RAG → Reranking → AI Agents → Agentic RAG
You will build upon each concept as you progress, giving you a practical understanding of how modern AI applications are designed and implemented.

Technologies You Will Use

Modern C++ • OpenAI API • Groq API • llama.cpp • SQLite • FAISS • BM25 • Reciprocal Rank Fusion • ONNX Runtime • Embeddings • Vector Search • RAG • AI 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 modernGenerative AI and LLM capabilities into the C++ ecosystem. Instead of learning AI only through Python notebooks, you will learn how AI technologies can be integrated into real C++ applications and systems.

Who Is This Course For?
This course is designed for

✨ C++ developers who want to move into AI Engineering.

✨ Software engineers interested in Generative AI and LLM applications.

✨ Backend and systems developers building AI-powered software.

✨ Developers who want to learn 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.
You do not need prior experience with LLMs, RAG, embeddings, vector databases, AI agents, or Generative AI. These concepts are introduced progressively throughout the course.

Start Building AI with Modern C++
If you are a C++ developer looking to move beyond traditional software development and start building modern AI applications, this course gives you a practical path fromLLM 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 needed to engineer modern AI systems with C++.

Who this course is for
⭐ C++ developers who want to learn how to build AI-powered applications using modern AI engineering techniques.
⭐ Software engineers interested in integrating Large Language Models (LLMs) into their C++ applications.
⭐ Developers who want to understand and implement Retrieval-Augmented Generation (RAG) systems from scratch.
⭐ Programmers looking to build intelligent AI assistants, chatbots, and agent-based applications.
⭐ Backend and systems programmers who want to add AI capabilities to enterprise and production software.
⭐ Students and technology enthusiasts interested in practical AI engineering rather than AI theory or research.
⭐ Developers who want hands-on experience with OpenAI APIs, embeddings, vector search, reranking, and Agentic RAG.
⭐ C++ professionals seeking to expand their skills in Generative AI and stay current with modern AI application development.

隐藏内容

此处内容需要权限查看