RAG evaluation metrics in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to calculate the recall score for RAG model predictions.

Prompt Engineering / GenAI

from sklearn.metrics import [1]
recall = [1](true_labels, predicted_labels)

Drag options to blanks, or click blank then click option'

Af1_score

Bprecision_score

Caccuracy_score

Drecall_score

Attempts:

3 left

💡 Hint

Common Mistakes

Using precision_score instead of recall_score

Using accuracy_score which is less informative for retrieval tasks

The recall_score function measures how many relevant items are selected by the model. It is important for RAG evaluation to check if the model retrieves all relevant information.

2fill in blank

medium

Complete the code to compute the F1 score for RAG model outputs.

Prompt Engineering / GenAI

from sklearn.metrics import [1]
f1 = [1](true_labels, predicted_labels)

Drag options to blanks, or click blank then click option'

Af1_score

Baccuracy_score

Crecall_score

Dprecision_score

Attempts:

3 left

💡 Hint

Common Mistakes

Using accuracy_score which does not balance precision and recall

Confusing precision_score with f1_score

The F1 score balances precision and recall, giving a single metric to evaluate RAG model performance.

3fill in blank

hard

Fix the error in the code to calculate precision for RAG evaluation.

Prompt Engineering / GenAI

from sklearn.metrics import precision_score
precision = precision_score(true_labels, [1])

Drag options to blanks, or click blank then click option'

Apredicted_labels

Btrue_labels

Cpredictions

Dlabels

Attempts:

3 left

💡 Hint

Common Mistakes

Passing true_labels twice

Using an undefined variable like 'labels'

The precision_score function requires the predicted labels as the second argument to compare against true labels.

4fill in blank

hard

Fill both blanks to create a dictionary of evaluation metrics for RAG.

Prompt Engineering / GenAI

metrics = {
    'precision': [1](true_labels, predicted_labels),
    'recall': [2](true_labels, predicted_labels)
}

Drag options to blanks, or click blank then click option'

Aprecision_score

Brecall_score

Cf1_score

Daccuracy_score

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up precision_score and recall_score

Using accuracy_score which is less relevant here

This dictionary stores precision and recall scores computed from true and predicted labels, key metrics for RAG evaluation.

5fill in blank

hard

Fill all three blanks to compute precision, recall, and F1 score for RAG evaluation.

Prompt Engineering / GenAI

results = {
    'precision': [1](true_labels, predicted_labels),
    'recall': [2](true_labels, predicted_labels),
    'f1': [3](true_labels, predicted_labels)
}

Drag options to blanks, or click blank then click option'

Aprecision_score

Brecall_score

Cf1_score

Daccuracy_score

Attempts:

3 left

💡 Hint

Common Mistakes

Using accuracy_score instead of f1_score

Swapping recall_score and precision_score

This code calculates the three key metrics to evaluate RAG models: precision, recall, and F1 score.