|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/basic-to-advanced-retreival-augmented-generation-rag-course/
课程评论：没有评论
课程名称：从基础到高级：检索增强生成（RAG） 课程概述： 通过我们的检索增强生成（RAG）和LangChain综合课程，提升您的开发技能。无论您是希望进入人工智能领域的开发者，还是想要掌握RAG的经验丰富程序员，本课程提供理论与实践的完美结合，帮助您构建可生产的AI应用程序。 您将学习： - 构建三个专业级的聊天机器人：网站聊天机器人、SQL聊天机器人和多媒体PDF聊天机器人 - 从基础到高级技术掌握RAG架构和实现 - 运行和优化开源及商业大型语言模型（LLMs） - 实施向量数据库和嵌入技术以提高信息检索效率 - 使用LangChain框架创建复杂的AI应用程序 - 部署高级技术，如提示缓存和查询扩展 课程内容： 1. **RAG基础** - 理解检索增强生成架构 - RAG系统的核心组成部分和工作流程 - RAG实施的最佳实践 - 真实应用案例 2. **大型语言模型（LLMs）— 实践** - 设置和运行开源LLMs - 模型选择和优化技术 - 性能调整和资源管理 - 本地LLM部署的实践练习 3. **向量数据库与嵌入** - 深入了解嵌入模型及其应用 - FAISS、ANNOY 和 HNSW方法的手动实现 - 速度与准确性优化策略 - 与Pinecone管理数据库的集成 - 实践向量可视化和分析 4. **LangChain框架** - 文本分块策略与优化 - LangChain架构和组件 - 高级链组合技术 - 与向量存储和LLMs的集成 - 使用真实数据的实践练习 5. **高级RAG技术** - 查询扩展与优化 - 结果重排序策略 - 提示缓存实施 - 性能优化技术 - 高级索引方法 6. **构建生产级聊天机器人** - 网站聊天机器人 - 架构与实现 - 内容索引与检索 - 响应生成与优化 - SQL聊天机器人 - 自然语言到SQL转换 - 查询优化与安全 - 数据库集成最佳实践 - 多媒体PDF聊天机器人 - 多模态内容处理 - PDF解析与索引 - 丰富媒体响应生成 课程对象： - 希望在AI应用领域专业化的软件开发人员 - 想要掌握RAG实现的AI工程师 - 有兴趣构建智能聊天机器人的后端开发人员 - 寻求实践LLM经验的技术专业人员 课程前提： - 基础的Python编程知识 - 对REST API的了解 - 基本数据库概念的理解 - 基本机器学习概念（有帮助但不是必需） 选择这门课程的理由： - 行业内相关技能当前需求高 - 通过真实示例获得实践经验 - 使用特斯拉汽车数据库进行的实际实现 - 从基础到高级概念的全面覆盖 - 可生产的代码与最佳实践 - 工作坊测试内容与经过验证的结果 通过本课程的学习，您将构建三个专业级聊天机器人，并获得RAG系统实施、向量数据库集成、LLM优化和高级检索技术的实践经验，从而开发出可生产的AI应用程序。加入我们，共同踏上掌握RAG和LangChain的激动人心的旅程，站在AI开发的最前沿。
Transform your development skills with our comprehensive course on Retrieval-Augmented Generation (RAG) and LangChain. Whether you're a developer looking to break into AI or an experienced programmer wanting to master RAG, this course provides the perfect blend of theory and hands-on practice to help you build production-ready AI applications.What You'll LearnBuild three professional-grade chatbots: Website, SQL, and Multimedia PDFMaster RAG architecture and implementation from fundamentals to advanced techniquesRun and optimize both open-source and commercial LLMsImplement vector databases and embeddings for efficient information retrievalCreate sophisticated AI applications using LangChain frameworkDeploy advanced techniques like prompt caching and query expansionCourse ContentSection 1: RAG FundamentalsUnderstanding Retrieval-Augmented Generation architectureCore components and workflow of RAG systemsBest practices for RAG implementationReal-world applications and use casesSection 2: Large Language Models (LLMs) - Hands-on PracticeSetting up and running open-source LLMs with OllamaModel selection and optimization techniquesPerformance tuning and resource managementPractical exercises with local LLM deploymentSection 3: Vector Databases & EmbeddingsDeep dive into embedding models and their applicationsHands-on implementation of FAISS, ANNOY, and HNSW methodsSpeed vs. accuracy optimization strategiesIntegration with Pinecone managed databasePractical vector visualization and analysisSection 4: LangChain FrameworkText chunking strategies and optimizationLangChain architecture and componentsAdvanced chain composition techniquesIntegration with vector stores and LLMsHands-on exercises with real-world dataSection 5: Advanced RAG TechniquesQuery expansion and optimizationResult re-ranking strategiesPrompt caching implementationPerformance optimization techniquesAdvanced indexing methodsSection 6: Building Production-Ready ChatbotsWebsite ChatbotArchitecture and implementationContent indexing and retrievalResponse generation and optimizationSQL ChatbotNatural language to SQL conversionQuery optimization and safetyDatabase integration best practicesMultimedia PDF ChatbotMulti-modal content processingPDF parsing and indexingRich media response generationWho This Course is ForSoftware developers looking to specialize in AI applicationsAI engineers wanting to master RAG implementationBackend developers interested in building intelligent chatbotsTechnical professionals seeking hands-on LLM experiencePrerequisitesBasic Python programming knowledgeFamiliarity with REST APIsUnderstanding of basic database conceptsBasic understanding of machine learning concepts (helpful but not required)Why Take This CourseIndustry-relevant skills currently in high demandHands-on experience with real-world examplesPractical implementation using Tesla Motors databaseComplete coverage from fundamentals to advanced conceptsProduction-ready code and best practicesWorkshop-tested content with proven resultsWhat You'll BuildBy the end of this course, you'll have built three professional-grade chatbots and gained practical experience with:RAG system implementationVector database integrationLLM optimizationAdvanced retrieval techniquesProduction-ready AI applicationsJoin us on this exciting journey to master RAG and LangChain, and position yourself at the forefront of AI development.
