|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/building-a-simple-data-analyst-ai-agent-with-llama-and-flask/
课程评论：没有评论
课程名称：构建简单的数据分析师AI代理（使用Llama和Flask） 课程概述：解锁AI的力量，构建自己的简单数据分析师AI代理，无需昂贵的API或复杂的编程经验。在这个实践课程中，您将学习如何在本地设置和运行一个开源语言模型（Llama），并构建一个轻量级的Flask应用程序，该应用程序可以根据存储在Postgres数据库中的信息回答问题，类似于一个简单的增强检索生成（RAG）系统。课程从提示工程的基础知识开始，介绍了关键技术，如上下文学习（ICL）、思维链（CoT）和思维树（ToT）。您将练习创建、调试和优化提示，以指导AI提供更好、更准确的答案。接下来，我们将进入构建您的第一个AI驱动的应用程序。您将设置Flask服务器，将其与Postgres数据库连接，并构建一个接受用户问题、处理问题并通过AI逻辑返回数据库答案的端点。 您将学习： - 如何在自己的机器上安装和运行开源LLM模型（Llama） - 关键的提示工程技术及其如何改善AI推理 - 如何构建简单的Flask应用程序并将其连接到Postgres数据库 - 如何处理用户输入并从数据库提供AI生成的答案 课程面向： - 对AI、提示工程和轻量级AI应用感兴趣的初学者 - 希望探索AI增强工作流程的数据分析师 - 有兴趣实验增强检索生成（RAG）原理的开发者 - 数据工程师 - 任何希望以实用、快速、清晰的方式了解在现实世界小型项目中使用LLMs的人 课程要求： - 对数据库的基本知识（无需深入了解SQL） - Python和SQL经验有帮助，但不是必需的；所有关键概念都会得到解释 - 有学习和实验的意愿 无论您是首次接触AI，还是希望找到一个实用的项目以丰富您的作品集，本课程将帮助您构建真实且功能性强的项目，同时建立坚实的提示工程和AI应用基础。今天就注册，开始构建吧！
Unlock the power of AI and build your own simple Data Analyst AI Agent without needing expensive APIs or heavy programming experience.In this hands-on course, you will learn how to set up and run an open-source language model (Llama) locally and build a lightweight Flask app that can answer questions based on information stored in a Postgres database, similar to a simple Retrieval-Augmented Generation (RAG) system. We start with the foundations of prompt engineering, introducing essential techniques like In-Context Learning (ICL), Chain of Thought (CoT), and Tree of Thought (ToT). You will practice creating, debugging, and refining prompts that guide your AI to better, more accurate answers.Then, we move into building your first AI-powered app. You will set up a Flask server, connect it to a Postgres database, and build an endpoint that accepts user questions, processes them, and returns database answers through AI logic. What You Will LearnHow to install and run an open-source LLM model (Llama) on your own machine Core prompt engineering techniques and how they improve AI reasoning How to build a simple Flask application and connect it to a Postgres database How to process user input and deliver AI-generated answers from a database Who This Course Is ForBeginners curious about AI, prompt engineering, and lightweight AI applications Data analysts who want to explore AI-enhanced workflowsDevelopers interested in experimenting with Retrieval-Augmented Generation (RAG) principles Data engineersAnyone who wants a practical, fast, and clear introduction to using LLMs in real-world mini-projectsRequirementsBasic knowledge of what a database is (no need to know SQL in depth) Python and SQL experience are helpful but not required; all key concepts are explainedA willingness to learn and experimentWhether you are taking your first steps into AI or looking for a practical project to enhance your portfolio, this course will help you build something real and functional while developing a strong foundation in prompt engineering and AI applications. Enroll today and start building!
