|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/rag-raising-the-potential-of-chatgpt-llms-to-the-next-level/
课程评论：没有评论
课程名称：RAG：使ChatGPT和大型语言模型能够访问定制知识 课程概述： 本课程专为希望通过检索增强生成系统（RAGS）充分挖掘ChatGPT等语言模型潜力的专业人士设计。我们将深入探讨RAGS如何通过提供直接、实时的相关信息访问，将这些语言模型转变为高性能的专家工具，应用于多个领域。 RAGS在语言模型中的重要性： RAGS是大型语言模型（LLMs）如ChatGPT演变的重要基础。通过实时集成外部知识，这些系统使LLMs能够访问大量最新信息，并且能够持续学习和适应新信息。这种检索和学习能力显著提高了文本生成的准确性和相关性，尤其在医疗、金融分析等需要高度准确性和上下文关联性的应用中，具有重要意义。 课程内容： 1. 生成式AI和RAG基础 - 介绍辅助内容生成和语言模型。 - 探讨生成式AI的基本概念、挑战及LLMs的演变。 - 生成式AI对各行业的影响。 2. 大型语言模型的深入研究 - LLM的介绍和发展，包括基础模型和调优模型。 - 研究LLMs当前的格局及其局限性，并探讨如何规避常见问题。 3. LLM的访问与使用 - 实践使用ChatGPT，包括实验室实践和OpenAI API的访问。 4. LLM优化 - 改善模型性能的高级技术，包括结合知识图谱的RAG和自定义模型开发。 5. RAG的应用与案例 - 讨论RAG的优缺点，并举例说明其在不同行业中的实际应用及影响。 6. RAG开发工具 - 使用特定的工具进行RAG开发的指导，包括Flowise、LangChain和LlamaIndex等无代码平台。 7. 技术与高级RAG组件 - RAG架构、索引管道、文档碎片化及嵌入和向量数据库的使用详解。 8. 实践实验室和项目 - 一系列实践实验室和项目，指导参与者从头到尾开发RAG，使用Flowise和LangChain等工具。 教学方法： 课程结合理论课程与实践课程，深入理解RAGS并让参与者在受控的真实场景中实际测试技术。该项目非常适合希望将ChatGPT和其他语言模型功能提升到前所未有水平的学习者，RAGS将成为人工智能领域不可或缺的工具。 课程要求： 不需要之前的编程经验。课程将使用无代码工具以便利RAGS的学习与实施。
This course is designed specifically for professionals who want to unlock the full potential of language models such as ChatGPT through Retrieval Augmented Generation Systems (RAGS). We will delve into how RAGS transform these language models into high-performance, expert tools across multiple disciplines by providing them with direct, real-time access to relevant, up-to-date information.Importance of RAGS in Language ModelsRAGS are fundamental to the evolution of large language models (LLMs), such as ChatGPT. Through the integration of external knowledge in real time, these systems enable LLMs to not only access a vast amount of up-to-date information but also learn and adapt to new information on a continuous basis. This retrieval and learning capability significantly improves text generation, allowing models to respond with unprecedented accuracy and relevance. This knowledge enrichment is crucial for applications that demand high accuracy and contextualization, opening up new possibilities in fields such as healthcare, financial analysis, and more.Course ContentGenerative AI and RAG FundamentalsIntroduction to assisted content generation and language models.Classes on the fundamentals of generative AI, key terms, challenges and evolution of LLMs.Impact of generative AI in various sectors.In-depth study of Large Language ModelsIntroduction and development of LLMs, including base models and tuned models.Exploration of the current landscape of LLMs, their limitations and how to mitigate common pitfalls such as hallucinations.Access and Use of LLMsHands-on use of ChatGPT, including hands-on labs and access to the OpenAI API.LLM OptimizationAdvanced techniques for improving model performance, including RAG with Knowledge Graphs and custom model development.Applications and Use Cases of RAGsDiscussion of the benefits and limitations of RAGs, with examples of real implementations and their impact in different industries.RAG Development ToolsInstruction on the use of specific tools for RAG development, including No-Code platforms such as Flowise, LangChain and LlamaIndex.Technical and Advanced RAG ComponentsDetails on RAG architecture, indexing pipelines, document fragmentation and the use of embeddings and vector databases.Hands-on Labs and ProjectsSeries of hands-on labs and projects that guide participants through the development of a RAG from start to finish, using tools such as Flowise and LangChain.MethodologyThe course alternates between theoretical sessions that provide an in-depth understanding of RAGS and hands-on sessions that allow participants to experiment with the technology in controlled, real-world scenarios.This program is perfect for those who are ready to take the functionality of ChatGPT and other language models to never-before-seen levels of performance, making RAGS an indispensable tool in the field of artificial intelligence.RequirementsNo previous programming experience is required. The course will include the use of No-Code tools to facilitate the learning and implementation of RAGS.
