RAG architecture overview in Prompt Engineering / GenAI - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

What is the main purpose of the Retriever component in RAG?

In the Retrieval-Augmented Generation (RAG) architecture, the Retriever plays a key role. What is its main purpose?

A To train the model using labeled data

B To generate natural language text based on retrieved information

C To find relevant documents or passages from a large knowledge base based on the input query

D To evaluate the quality of generated answers

💡 Hint

Think about which part searches for information before generating answers.

The Retriever's job is to search a large set of documents to find the most relevant pieces of information related to the input question. This helps the Generator produce better answers.

❓ Predict Output

intermediate

What is the output shape of the combined embeddings in RAG?

Given a batch of 2 queries, each retrieving 3 documents, and each embedding vector has size 768, what is the shape of the combined embeddings tensor before generation?

Prompt Engineering / GenAI

batch_size = 2
num_docs = 3
embedding_size = 768

# Assume embeddings shape is (batch_size, num_docs, embedding_size)
embeddings_shape = (batch_size, num_docs, embedding_size)

# Combined embeddings shape after flattening documents per query
combined_shape = (batch_size, num_docs * embedding_size)

print(combined_shape)

A (2, 2304)

B (2, 3, 768)

C (6, 768)

D (2, 768)

💡 Hint

Multiply the number of documents by the embedding size for each query.

Each query has 3 documents, each with 768 features. Flattening the documents per query results in 3 * 768 = 2304 features per query. For 2 queries, shape is (2, 2304).

❓ Model Choice

advanced

Which model type is typically used as the Generator in RAG?

In the RAG architecture, which type of model is commonly used as the Generator to produce answers from retrieved documents?

A Sequence-to-sequence Transformer model like BART or T5

B Convolutional Neural Network (CNN)

C Recurrent Neural Network (RNN) without attention

D Feedforward Neural Network

💡 Hint

Think about models designed for text generation with attention mechanisms.

The Generator in RAG is usually a sequence-to-sequence Transformer model such as BART or T5, which can generate fluent text conditioned on retrieved documents.

❓ Hyperparameter

advanced

Which hyperparameter controls how many documents the Retriever fetches in RAG?

In RAG, you can adjust how many documents the Retriever returns for each query. What is this hyperparameter commonly called?

A embedding_dim

B batch_size

C learning_rate

D num_retrieved_docs

💡 Hint

It relates to the count of documents fetched per query.

The hyperparameter controlling how many documents are retrieved per query is often named num_retrieved_docs or similar, defining the number of passages used for generation.

❓ Metrics

expert

Which metric best evaluates the quality of answers generated by RAG on open-domain QA tasks?

When testing a RAG model on open-domain question answering, which metric is most suitable to measure how well the generated answers match the correct ones?

A Mean Squared Error (MSE)

B Exact Match (EM) score

C BLEU score

D Accuracy on classification labels

💡 Hint

Consider a metric that checks if the generated answer exactly matches the reference answer.

Exact Match (EM) score measures the percentage of generated answers that exactly match the ground truth answers, making it a standard metric for open-domain QA evaluation.