OPENAI_API_KEY

Gain insights into RAG systems by exploring pre- and post-retrieval optimization techniques, and discover how to build intelligent applications using LangChain with practical hands-on experience.

Retrieval_ augmenting_ generation - cover art.png

RAG-Final.tar.gz

naive

naive-SPA

naive-copy

code-widget

MultiQuery

RAG-Fusion

Decomposition

SemanticRouting

RoutingClassifier

CrossEncoderReranking

CrossEncoderReranking-copy

HyDE

The course explains RAG, which combines information retrieval and generative models. Learners will gain hands-on experience with state-of-the-art technologies throughout the course by implementing RAG systems using LangChain.

The course begins with an introduction to the core principles of RAG. As the course progresses, you’ll explore pre-retrieval optimization techniques, including strategies for optimizing indexing and query formulation, as these techniques are covered in depth. You will then focus on post-retrieval optimization, learning about reranking methods like RAG-Fusion and Cross Encoder reranking. 

Finally, you will work on a hands-on project to build an RAG application by applying the concepts learned in the course. By the end of this course, you’ll have gained sufficient experience and knowledge to build more intelligent systems using RAG.

Advanced RAG Techniques: Choosing the Right Approach

What is the main limitation addressed by RAG for large language models (LLMs)?

What is the main limitation addressed by RAG for large language models (LLMs)?

Advanced RAG combines retrieval functionalities with large language models (LLMs) to improve the accuracy and relevance of generated responses.

Advanced RAG can only be used for text-based data.

Advanced RAG leverages retrieved data to provide a strong foundation for LLMs to generate informative answers.

Advanced RAG offers various methods to optimize retrieval, such as sentence-window retrieval and re-ranking.

**(Select all that apply.)** Which statement is *true* about Advanced Retrieval-Augmented Generation (Advanced RAG)?

(Select all that apply.) Which statement is true about Advanced Retrieval-Augmented Generation (Advanced RAG)?

Increased ability to answer complex questions

What is *not* a benefit of using RAG models?

What is not a benefit of using RAG models?

To rewrite the user’s query for better retrieval results

To filter retrieved information based on the LLM’s assessment

To merge retrieved passages into a single representation for the LLM

To select the optimal data source for a specific query

What is the primary purpose of RAG-Fusion in advanced RAG?

What is the primary purpose of RAG-Fusion in advanced RAG?

The overall workflow involves retrieval, augmentation, and generation.

The use of pre-retrieval and post-retrieval optimization techniques.

The computational efficiency for processing information retrieval tasks.


The level of customization and flexibility offered for different tasks.

How is modular RAG different from advanced RAG?

How is modular RAG different from advanced RAG?

Test your understanding of RAG and its paradigms.

Getting Started

Introduction to Retrieval-Augmented Generation (RAG)

Advanced RAG: Pre-Retrieval (Optimizing Indexing)

Advanced RAG: Pre-Retrieval (Optimizing Query)

Advanced RAG: Post-Retrieval Process

Talk to Your Web Page: A RAG-Powered Chat Interface

Conclusion

Quiz: Introduction to RAG