Getting Started with Retrieve-Augmented Generation (RAG)
Chapter 1: Introduction to Retrieve-Augmented Generation
Limitations of Standard Large Language Models
What is Retrieve-Augmented Generation (RAG)?
The Core Architecture of a RAG System
RAG vs. Fine-tuning: Understanding the Differences
Benefits of Using RAG
Quiz for Chapter 1
Chapter 2: The Retrieval Component
Role of the Retriever in RAG
Introduction to Vector Embeddings
Common Embedding Models
Similarity Search: Finding Relevant Vectors
Introduction to Vector Databases
Choosing a Vector Database: Considerations
Practice: Generating Text Embeddings
Quiz for Chapter 2
Chapter 3: Preparing Data for Retrieval
Loading Documents from Various Sources
The Need for Document Chunking
Fixed-Size Chunking Strategies
Content-Aware Chunking Approaches
Metadata Association with Chunks
Storing Processed Data in a Vector Database
Hands-on Practical: Chunking Documents
Quiz for Chapter 3
Chapter 4: The Generation Component and Augmentation
Role of the Generator (LLM) in RAG
Structuring Prompts for RAG
Context Injection Methods
Managing Context Length Limitations
Generating the Final Response
Attributing Sources in Generated Output
Quiz for Chapter 4
Chapter 5: Building a Basic RAG Pipeline
Overview of RAG Frameworks (e.g., LangChain, LlamaIndex)
Setting up the Environment
Implementing the Retriever
Implementing the Generator Integration
Combining Retrieval and Generation
Running Queries Through the Pipeline
Hands-on Practical: End-to-End RAG System
Quiz for Chapter 5
Chapter 6: Evaluating and Improving RAG Systems
Challenges in Evaluating RAG
Component-Level Evaluation: Retrieval
Component-Level Evaluation: Generation
End-to-End RAG Evaluation Frameworks
Common Failure Modes
Basic Strategies for Improvement
Practice: Analyzing RAG Output Quality
Quiz for Chapter 6
Structuring Prompts for RAG
Was this section helpful?
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks, Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Narsimha Chilkuri, Max Bartolo, Jeff Lu, Minqi Jiang, Harun Šaríć, Fabio Soares, Yury Kastryulin, Leon Bottou, Sebastian Riedel, Pasquale Minervini, 2020 NeurIPS DOI: 10.48550/arXiv.2005.11401 - Introduces the original Retrieval-Augmented Generation (RAG) framework, detailing how retrieved documents are used to augment a language model's generation process.
- Lost in the Middle: How Language Models Use Long Contexts, Nelson F. Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Percy Liang, Matei Zaharia, 2023 NeurIPS (Preprint on arXiv) DOI: 10.48550/arXiv.2307.03172 - Investigates the influence of context item placement on large language model performance, discussing phenomena such as recency bias in long contexts.
- Prompt engineering, OpenAI, 2024 (OpenAI) - Provides practical guidelines for designing effective prompts for large language models, covering structuring instructions and integrating external information.
- A Survey on Retrieval-Augmented Generation for Large Language Models, Yunfan Gao, Yun Xiong, Xinyang Feng, Zhangyang Wang, Xunlei Wu, Jie Zhou, Wenqi Wang, Peng Zhang, Song Guo, Cheng-Zhong Xu, 2024 arXiv preprint DOI: 10.48550/arXiv.2312.10997 - Offers a comprehensive review of RAG systems, discussing various prompting strategies and context integration methods within the generation component.