Fundamentals of Large Language Models →mediumMultiple ChoiceObjective-mapped

1Z0-1127-25 Fundamentals of Large Language Models Practice Question

A multi-turn chatbot needs to maintain context across user queries. The context window is limited. What design should be used?

⚠ Common exam trap

Oracle often tests the misconception that storing context externally (Option B) bypasses the context window limit, but the retrieved data must still be injected into the model's input, which is constrained by the same token budget.

Answer choices

Why each option matters

Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.

Correct answer & explanation

✓

Use a summary of previous turns and add new input.

Summarizing previous turns and appending the new input efficiently manages the limited context window of large language models (LLMs). This approach preserves essential conversational context without exceeding token limits, ensuring coherent multi-turn interactions.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✓
Use a summary of previous turns and add new input.
Why this is correct
Correct: Summarization preserves context within limits.
✗
Store context in a separate database and retrieve each time.
Why it's wrong here
Incorrect: Adds external dependencies and complexity.
✗
Reset context after each turn.
Why it's wrong here
Incorrect: Loses all prior context.
✗
Keep the entire conversation history in each request.
Why it's wrong here
Incorrect: Likely exceeds context window.

Go deeper

1Z0-1127-25 Fundamentals of Large Language Models Practice Question

Why each option matters

Option-by-option breakdown

Related to this question