Project

Advanced RAG

31 completions

~ 10 hours

4.3

Before selecting this project, it is recommended that first complete the Introduction to LangChain project, Building the naive RAG and LLM Evals.

In this project, you will discover methods that can be integrated at various steps of the RAG pipeline. You'll explore techniques like query rewriting, hypothetical embeddings, and context re-ranking—each designed to guarantee that your RAG application delivers responses that are both relevant and of high quality.

Provided by

JetBrains Academy

About

Integrating retrieval-augmented generation into LLM applications is key to enhancing response quality. While basic RAG methods provide a solid base, they might not always achieve the superior quality you desire. This project presents a range of advanced techniques applicable at various stages of the RAG pipeline to elevate your system's output.

Training project

This project allows you to practice and strengthen your coding skills, helping you get ready for more advanced tasks ahead.

What you'll learn

Once you choose a project, we'll provide you with a study plan that includes all the necessary topics from your course to get it built. Here’s what awaits you:

Apply various data cleaning and improvement techniques to enhance your dataset.

Use the right data store to store the right data.

Decompose the user's query to capture their intent for more enhanced retrieval.

Generate a hypothetical document to enhance retrieval.

Score retrieved contexts to identify the most relevant documents based on the user's query.

Select the right data store based on the user's query.

Reviews

Anushka Weerasooriya

5 months ago

4.7

This was an interesting project, as you get to combine both relational and vector databases, then use tools to retrieve information from the appropriate stores to satisfy the user's queries. You get to cover quite a few technologies and AI concepts along the way, all with some fairly hands-on Python ...

Jennifer Hanna

5 months ago

4.7

I have learned some more retrieval augmented generation techniques and how to integrate retrieval related tools into an agent.

Marcin Borkowski

11 months ago

4.3

Very good project. It shows clearly how crucial is good prompt engineering.

4.3

Learners who completed this project within the course rated it as follows:

Usefulness

4.9

Fun

4.2

Clarity

3.9