|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/langchain/
课程评论：没有评论
课程名称：LangChain - 使用LangChain开发LLM驱动的应用程序 概述：本课程已重新录制并支持LangChain版本0.3+。理想的学生为软件开发人员、数据科学家、AI/ML工程师。本课程旨在快速教会您如何利用LangChain库的强大功能开发LLM应用程序，为您提供开发尖端LLM解决方案所需的技能和知识。 请注意，本课程并不适合初学者。课程假设您具有软件工程背景，并精通Python。尽管我将使用Pycharm IDE进行演示，您也可以使用任何编辑器，因为我们只使用IDE的基本功能，如调试和运行脚本。 在本课程中，您将从头开始，构建一个实际的LLM驱动应用程序，主要包括以下三个项目： 1. Ice Breaker - LangChain代理，根据提供的姓名在谷歌上搜索LinkedIn和Twitter资料，抓取互联网信息，并生成个性化的聊天开场白。 2. 文档助手 - 创建一个针对Python软件包文档的聊天机器人（以及其他数据）。 3. ChatGPT代码解释器的简化版本。 课程内容涵盖： - LangChain - LLM和生成AI历史 - LLM：少量提示、思维链、ReAct提示 - 聊天模型 - 开源模型 - 提示、提示模板、langchainub输出解析器、Pydantic输出解析器 - 链接：create_retrieval_chain、create_stuff_documents_chain - 代理、自定义代理、Python代理、CSV代理、代理路由 - OpenAI函数、工具调用 - 工具和工具包 - 内存 - 向量存储（Pinecone、FAISS） - RAG（检索增强生成） - 文档加载器、文本分割器 - Streamlit（用于用户界面） - LCELLangSmith - LangGraph介绍 - FireCrawl - Cursor IDE和Cursor Composter简介 - Cursor Chat - MCP - 模型上下文协议与LangChain生态系统LangGraph 在整个课程中，您将通过实际练习和真实项目来巩固概念和技术的理解。到课程结束时，您将熟练掌握使用LangChain创建强大、高效和多功能的LLM应用程序，以满足各种使用需求。 特别说明：请注意，本课程并不适合初学者，需具备软件工程背景并精通Python。课程的第一个项目（Ice-Breaker）需要使用第三方API（Scrapin/ProxyURL、Tavily、Twitter API），这些一般是付费服务。不过，这些第三方提供免费配额供我们创建存根响应进行开发和测试。
COURSE WAS RE-RECORDED and supports- LangChain Version 0.3+**Ideal students are software developers / data scientists / AI/ML Engineers**Welcome to first LangChain Udemy course - Unleashing the Power of LLM!This course is designed to teach you how to QUICKLY harness the power the LangChain library for LLM applications. This course will equip you with the skills and knowledge necessary to develop cutting-edge LLM solutions for a diverse range of topics.Please note that this is not a course for beginners. This course assumes that you have a background in software engineering and are proficient in Python. I will be using Pycharm IDE but you can use any editor you'd like since we only use basic feature of the IDE like debugging and running scripts.In this course, you will embark on a journey from scratch to building a real-world LLM powered application using LangChain. We are going to do so by build 3 main applications:Ice Breaker- LangChain agent that given a name, searches in google to find Linkedin and twitter profiles, scrape the internet for information about a name you provide and generate a couple of personalized ice breakers to kick off a conversation with the person.Documentation Helper- Create chatbot over a python package documentation. (and over any other data you would like)A slim version of ChatGPT Code-Interpreter Prompt Engineering Theory SectionIntroduction to LangGraphIntroduction to Model Context Protocol (MCP)The topics covered in this course include:LangChainLLM + GenAI HistoryLLMs: Few shots prompting, Chain of Thought, ReAct promptingChat ModelsOpen Source ModelsPrompts, PromptTemplates, langchainubOutput Parsers, Pydantic Output ParsersChains: create_retrieval_chain, create_stuff_documents_chainAgents, Custom Agents, Python Agents, CSV Agents, Agent RoutersOpenAI Functions, Tool CallingTools, ToolkitsMemoryVectorstores (Pinecone, FAISS)RAG (Retrieval Augmentation Generation)DocumentLoaders, TextSplittersStreamlit (for UI)LCELLangSmithIntro to LangGraphFireCrawlGIST of Cursor IDE Cursor ComposterCurser ChatMCP - Model Context Protocol & LangChain Ecosystem LangGraphThroughout the course, you will work on hands-on exercises and real-world projects to reinforce your understanding of the concepts and techniques covered. By the end of the course, you will be proficient in using LangChain to create powerful, efficient, and versatile LLM applications for a wide array of usages.DISCLAIMERSPlease note that this is not a course for beginners. This course assumes that you have a background in software engineering and are proficient in Python. I will be using Pycharm IDE but you can use any editor you'd like since we only use basic feature of the IDE like debugging and running scripts.The first project of the course (Ice-Breaker) requires usage of 3rd party APIs-Scrapin / ProxyURL, Tavily, Twitter API which are generally paid services.All of those 3rd parties have a free tier we will use to create stub responses development and testing.
