RAG-Driven Generative AI

RAG-Driven Generative AI

位教师：Packt - Course Instructors

访问权限由 New York State Department of Labor 提供

10个模块

深入了解一个主题并学习基础知识。

高级设置等级

推荐体验

2 周完成

在 10 小时一周

灵活的计划

自行安排学习进度

10个模块

深入了解一个主题并学习基础知识。

高级设置等级

推荐体验

2 周完成

在 10 小时一周

灵活的计划

自行安排学习进度

您将学到什么

Scale RAG pipelines to handle large datasets efficiently
Implement techniques that reduce hallucinations and improve response accuracy
Customize and scale RAG-driven AI systems across different domains

您将获得的技能

您将学习的工具

要了解的详细信息

可分享的证书

添加到您的领英档案

作业

10 项作业

授课语言：英语（English）

了解顶级公司的员工如何掌握热门技能

了解关于 Coursera for Business 的更多信息

Petrobras, TATA, Danone, Capgemini, P&G 和 L'Oreal 的徽标

该课程共有10个模块

This course introduces the powerful concept of Retrieval-Augmented Generation (RAG), a technique used to optimize the performance, accuracy, and cost of generative AI systems. Focused on building AI pipelines with LlamaIndex, Deep Lake, and Pinecone, this course will equip you with the skills to create robust AI models capable of handling complex datasets and delivering traceable, context-aware outputs.

You will explore how to scale RAG pipelines, implement strategies to minimize hallucinations, and improve response accuracy across multimodal AI systems. By the end of the course, you will have hands-on experience optimizing these systems for real-world applications, empowering you to enhance decision-making and operational efficiency. What sets this course apart is its unique combination of theory and practical implementation. By working with cutting-edge tools like LlamaIndex and Pinecone, you'll understand how to balance cost, performance, and accuracy, while gaining insight into the broader context of AI pipelines and decision-making. This course is ideal for data scientists, AI engineers, and MLOps professionals who are looking to expand their expertise in RAG and generative AI. A basic understanding of machine learning concepts is recommended, as the course builds on these foundations to explore more advanced techniques.

In this section, we explore Retrieval Augmented Generation (RAG) frameworks, focusing on naive, advanced, and modular configurations. We implement Python-based RAG systems for improved AI accuracy and adaptability.

涵盖的内容

2个视频6篇阅读材料1个作业

2个视频总计2分钟

Course Overview 1分钟
Why Retrieval Augmented Generation? - Overview Video 1分钟

6篇阅读材料总计65分钟

Introduction 15分钟
Human Feedback (E2) 10分钟
Advanced techniques and evaluation 10分钟
Metrics 10分钟
Generation 10分钟
Generation 10分钟

1个作业总计10分钟

Exploring Retrieval Augmented Generation 10分钟

In this section, we cover building and managing RAG pipelines with Deep Lake and OpenAI for efficient AI data handling.

涵盖的内容

1个视频4篇阅读材料1个作业

In this section, we explore index-based RAG pipelines using LlamaIndex, Deep Lake, and OpenAI to enhance traceability, precision, and control in AI-driven data retrieval and generation.

涵盖的内容

1个视频5篇阅读材料1个作业

1个视频总计1分钟

Building Index-Based RAG with LlamaIndex, Deep Lake, and OpenAI - Overview Video 1分钟

5篇阅读材料总计90分钟

Introduction 10分钟
Building a Semantic Search Engine and Generative Agent for Drone Technology 20分钟
Creating and Populating a Deep Lake Vector Store 10分钟
Vector Store Index Query Engine 20分钟
Tree Index Query Engine 30分钟

1个作业总计10分钟

Indexing and Retrieval in AI Systems 10分钟

In this section, we explore multimodal modular RAG for drone technology, integrating text and image data retrieval, generation, and performance evaluation using LLMs and MMLLMs.

涵盖的内容

1个视频5篇阅读材料1个作业

1个视频总计1分钟

Multimodal Modular RAG for Drone Technology - Overview Video 1分钟

5篇阅读材料总计70分钟

Introduction 10分钟
Building a Multimodal Modular RAG Program for Drone Technology 10分钟
Loading and Visualizing the Multimodal Dataset 20分钟
Building a Multimodal Query Engine 10分钟
Multimodal Modular Summary 20分钟

1个作业总计10分钟

Multimodal RAG in Drone Applications 10分钟

In this section, we explore adaptive RAG with human feedback loops, focusing on improving retrieval quality and integrating expert input.

涵盖的内容

1个视频4篇阅读材料1个作业

In this section, we explore scalable RAG techniques for bank customer data using Pinecone and OpenAI. Key concepts include EDA, vector scaling, and AI-driven recommendations to reduce churn.

涵盖的内容

1个视频7篇阅读材料1个作业

1个视频总计1分钟

Scaling RAG Bank Customer Data with Pinecone - Overview Video 1分钟

7篇阅读材料总计120分钟

Introduction 10分钟
Collecting the Dataset 10分钟
Data Preparation and Clustering 10分钟
Scaling a Pinecone Index (Vector Store) 10分钟
Chunking 30分钟
Upserting 20分钟
RAG Generative AI 30分钟

1个作业总计10分钟

Scaling RAG Bank Customer Data with Pinecone 10分钟

In this section, we explore building scalable RAG systems using knowledge graphs, implementing the Wikipedia API, populating a Deep Lake vector store, and constructing a LlamaIndex knowledge graph for semantic search.

涵盖的内容

1个视频5篇阅读材料1个作业

1个视频总计1分钟

Building Scalable Knowledge-Graph-Based RAG with Wikipedia API and LlamaIndex - Overview Video 1分钟

5篇阅读材料总计80分钟

Introduction 10分钟
Building Graphs from Trees 20分钟
Preparing the Data for Upsertion 30分钟
Re-ranking 10分钟
Metric Calculation and Display 10分钟

1个作业总计10分钟

Exploring Knowledge-Graph-Based RAG Systems 10分钟

In this section, we explore dynamic RAG using Chroma and Llama, focusing on embedding and querying temporary data for real-time decision-making with open-source tools.

涵盖的内容

1个视频5篇阅读材料1个作业

In this section, we explore RAG data reduction through fine-tuning, focusing on preparing JSONL datasets and evaluating model performance with OpenAI metrics for improved accuracy and cost-effectiveness.

涵盖的内容

1个视频3篇阅读材料1个作业

In this section, we explore RAG pipeline implementation for video generation, embedding video comments in Pinecone, and enhancing labels with GPT-4o analysis for efficient video stock production.