Output guardrails in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to set a maximum length for the generated text.

Prompt Engineering / GenAI

output = model.generate(input_text, max_length=[1])

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

Atemperature

Bmax_tokens

C50

Dstop_sequence

Attempts:

3 left

💡 Hint

Common Mistakes

Using parameters that control randomness instead of length.

The max_length parameter limits how many tokens the model generates, controlling output length.

2fill in blank

medium

Complete the code to stop generation when a specific word appears.

Prompt Engineering / GenAI

output = model.generate(input_text, stop=[1])

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

A'end'

B100

CTrue

Dtemperature

Attempts:

3 left

💡 Hint

Common Mistakes

Using numbers or booleans instead of strings for stop.

The stop parameter tells the model to stop generating when it sees the given string.

3fill in blank

hard

Fix the error in the code to prevent generating harmful content by setting a safety filter.

Prompt Engineering / GenAI

output = model.generate(input_text, [1]=True)

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

Astop

Bmax_length

Ctemperature

Denable_safety_filter

Attempts:

3 left

💡 Hint

Common Mistakes

Confusing safety filter with output length or randomness controls.

Setting enable_safety_filter=True activates content filters to avoid harmful outputs.

4fill in blank

hard

Fill both blanks to set temperature and top_p for safer, more focused output.

Prompt Engineering / GenAI

output = model.generate(input_text, temperature=[1], top_p=[2])

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

A0.2

B0.9

C0.8

D1.5

Attempts:

3 left

💡 Hint

Common Mistakes

Using high temperature or top_p values that increase randomness.

Lower temperature (like 0.2) reduces randomness. Setting top_p to 0.8 limits token choices to the top 80% probability, making output safer and focused.

5fill in blank

hard

Fill all three blanks to add output guardrails: max tokens, stop sequence, and safety filter.

Prompt Engineering / GenAI

output = model.generate(input_text, max_tokens=[1], stop=[2], [3]=True)

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

A'\n'

Benable_safety_filter

C100

Dtemperature

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up parameter names or using wrong types for stop.

Set max_tokens to 100 to limit output length, stop to '\n' to end generation at a newline, and enable_safety_filter=True to prevent harmful content.