-
Notifications
You must be signed in to change notification settings - Fork 1.7k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #135 from Weihong-Liu/RAG
update RAG course
- Loading branch information
Showing
31 changed files
with
9,157 additions
and
0 deletions.
There are no files selected for viewing
6 changes: 6 additions & 0 deletions
6
content/Building and Evaluating Advanced RAG Applications/.streamlit/config.toml
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,6 @@ | ||
[theme] | ||
primaryColor="#0A2C37" | ||
backgroundColor="#FFFFFF" | ||
secondaryBackgroundColor="F5F5F5" | ||
textColor="#0A2C37" | ||
font="sans serif" |
2 changes: 2 additions & 0 deletions
2
content/Building and Evaluating Advanced RAG Applications/.streamlit/credentials.toml
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,2 @@ | ||
[general] | ||
email="" |
24 changes: 24 additions & 0 deletions
24
content/Building and Evaluating Advanced RAG Applications/1. 简介 Introduction.md
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,24 @@ | ||
# 第一章 简介 | ||
|
||
本课程深入探讨如何利用检索增强生成(Retrieval-Augmented Generation, RAG)技术,使大型语言模型(Large Language Models, LLMs)能够在用户自有数据上回答问题。本课程的目标是介绍构建和实现高质量RAG系统所需的关键技术和评估框架。 | ||
|
||
## 一、背景 | ||
在本课程中,我们首先探讨了RAG技术的重要性,它通过有效的检索技术为LLM提供高度相关的上下文信息,从而生成准确的答案。此外,我们还将介绍如何通过有效的评估框架,在初始开发和部署后维护期间,高效地迭代和改进RAG系统。 | ||
|
||
## 二、课程内容概览 | ||
- **高级检索方法**:介绍了两种先进的检索方法——句子窗口检索和自动合并检索,这些方法比传统方法能够为LLM提供更好的上下文信息。 | ||
- **评估指标**:解释了如何使用三个评估指标(上下文相关性、根据性和答案相关性)来评估LLM问答系统的性能。 | ||
- **实践应用**:本课程后半部分将提供实践操作,教授如何使用这些检索方法和评估方法迭代优化RAG系统,并展示如何使用系统化的实验跟踪来建立基线并快速改进。 | ||
|
||
## 三、专家指导 | ||
- **Jerry Liu**:作为LlamaIndex的联合创始人兼CEO,Jerry将分享他在社交媒体上关于RAG实践进化的见解。 | ||
- **Anupam Datta**:作为TruEra的联合创始人兼首席科学家,Anupam将利用他在可信AI领域以及如何监控、评估和优化AI应用效果的十多年研究经验,为课程提供深入洞察。 | ||
|
||
## 四、课程亮点 | ||
- **句子窗口检索和自动合并检索**:这两种方法通过提供更连贯的文本块,优化了LLM的上下文理解能力。 | ||
- **RAG三元组评估体系**:介绍了一套有效的度量标准来评估RAG系统在检索、理解和生成答案方面的性能。 | ||
- **实践操作**:课程将通过代码演示和实际案例,让学员亲自实践这些高级检索和评估方法。 | ||
|
||
## 五、致谢 | ||
感谢所有参与本课程创建的人员,包括LlamaIndex团队的Logan Markehwich,TruEra团队的Shayak Sen、Joshua Reini、Barbara Lewis,以及DeepLearning.ai团队的Eddie Shyu和Dialla Ezzeddine。 | ||
|
Oops, something went wrong.