RAG architecture overview in Prompt Engineering / GenAI - Cheat Sheet & Quick Revision

Recall & Review

beginner

What does RAG stand for in the context of AI architectures?

RAG stands for Retrieval-Augmented Generation. It combines retrieving relevant information with generating responses.

beginner

What are the two main components of the RAG architecture?

The two main components are: 1) A retriever that finds relevant documents or data, and 2) A generator that creates answers using the retrieved information.

intermediate

How does the retriever in RAG help improve the quality of generated answers?

The retriever finds useful, relevant information from a large database or documents, so the generator can use accurate facts instead of guessing.

beginner

Why is RAG architecture useful for tasks like question answering?

Because it combines searching for real information with generating natural language answers, making responses more accurate and informative.

beginner

What is the role of the generator in the RAG architecture?

The generator takes the retrieved documents and produces a clear, fluent answer or text based on that information.

What is the first step in the RAG architecture process?

A Evaluate accuracy

B Generate an answer

C Train the model

D Retrieve relevant documents

RAG first retrieves relevant documents before generating an answer.

Which component in RAG is responsible for creating natural language responses?

A Generator

B Retriever

C Indexer

D Tokenizer

The generator creates the natural language output using retrieved information.

Why does RAG use retrieval instead of only generation?

A To reduce model size

B To improve answer accuracy with real data

C To speed up training

D To avoid using neural networks

Retrieval provides real data that helps generate more accurate answers.

In RAG, what kind of data does the retriever search through?

A Large document collections or databases

B Predefined templates

C User input only

D Random noise

The retriever searches large collections of documents or databases for relevant info.

What is a key benefit of combining retrieval and generation in RAG?

A It eliminates the need for training

B It makes the model smaller

C It allows answers to be based on up-to-date information

D It removes the need for human input

Combining retrieval and generation lets the model use current, relevant information for answers.

Explain the main idea behind the RAG architecture and why it is useful.

Think about how searching and writing work together.

Describe the roles of the retriever and the generator in the RAG architecture.

One finds info, the other writes the answer.

Practice

1. What is the main purpose of the retriever component in a RAG architecture?

easy

A. To find relevant documents or information from a large dataset

B. To generate natural language answers from scratch

C. To train the model on labeled data

D. To evaluate the accuracy of the answers

Solution

1. Step 1: Understand the role of retriever in RAG

   The retriever searches a large collection of documents to find relevant information related to the question.

2. Step 2: Differentiate retriever from generator

   The generator uses the retrieved information to create a natural language answer, not to find documents.

3. Final Answer:

   To find relevant documents or information from a large dataset -> Option A

4. Quick Check:

   Retriever = Find info [OK]

Hint: Retriever searches data; generator writes answers [OK]

Common Mistakes:

• Confusing retriever with generator
• Thinking retriever generates answers
• Assuming retriever evaluates answers

2. Which of the following correctly describes the sequence of operations in a RAG model?

easy

A. Generate answer first, then retrieve documents

B. Retrieve documents first, then generate answer

C. Train model, then retrieve documents

D. Evaluate answer, then generate documents

Solution

1. Step 1: Recall RAG workflow

   RAG first retrieves relevant documents to provide context for the answer.

2. Step 2: Understand generation step

   After retrieval, the generator uses the documents to produce a final answer.

3. Final Answer:

   Retrieve documents first, then generate answer -> Option B

4. Quick Check:

   Retrieve before generate [OK]

Hint: Retrieve info before writing answer [OK]

Common Mistakes:

• Thinking generation happens before retrieval
• Mixing training with retrieval steps
• Confusing evaluation with generation

3. Consider this simplified Python pseudocode for a RAG-like process:

retrieved_docs = retriever.search(query)
answer = generator.generate(retrieved_docs, query)
print(answer)

What will be printed if the retriever returns an empty list?

medium

A. An answer generated without context, possibly generic or incorrect

B. A runtime error because generator cannot handle empty input

C. The original query string printed

D. An empty string printed

Solution

1. Step 1: Analyze retriever output

   The retriever returns an empty list, meaning no documents found.

2. Step 2: Understand generator behavior

   The generator tries to create an answer without context, so it may produce a generic or less accurate answer, but no error occurs.

3. Final Answer:

   An answer generated without context, possibly generic or incorrect -> Option A

4. Quick Check:

   Empty retrieval leads to generic answer [OK]

Hint: Empty retrieval means generic answer, not error [OK]

Common Mistakes:

• Assuming empty retrieval causes error
• Thinking query is printed directly
• Expecting empty string output

4. You have a RAG model that always returns irrelevant answers. Which of these is the most likely cause?

medium

A. The model is overfitting on training data

B. Generator is not trained on any data

C. Retriever is returning unrelated documents

D. The evaluation metric is incorrect

Solution

1. Step 1: Identify cause of irrelevant answers

   If answers are irrelevant, the source documents are likely unrelated to the question.

2. Step 2: Check retriever role

   The retriever finds documents; if it returns unrelated ones, the generator has poor context to answer.

3. Final Answer:

   Retriever is returning unrelated documents -> Option C

4. Quick Check:

   Bad retrieval causes irrelevant answers [OK]

Hint: Check retriever output first for relevance [OK]

Common Mistakes:

• Blaming generator without checking retrieval
• Confusing overfitting with retrieval errors
• Ignoring data quality issues

5. In a RAG system designed for a constantly updated news database, which advantage does RAG provide compared to a standard language model?

hard

A. It generates answers faster by skipping retrieval

B. It always produces shorter answers

C. It requires no training data at all

D. It can access fresh news by retrieving documents without retraining

Solution

1. Step 1: Understand RAG with dynamic data

   RAG retrieves documents from an external source, so it can use new data without retraining the generator.

2. Step 2: Compare with standard language models

   Standard models need retraining to learn new info, but RAG updates answers by searching fresh documents.

3. Final Answer:

   It can access fresh news by retrieving documents without retraining -> Option D

4. Quick Check:

   RAG updates answers via retrieval [OK]

Hint: RAG uses retrieval to handle new data easily [OK]

Common Mistakes:

• Thinking RAG skips retrieval
• Assuming no training data needed
• Believing RAG limits answer length