Perplexity for research and fact-checking in AI for Everyone - Time & Space Complexity

Time Complexity: Perplexity for research and fact-checking

O(n)

Understanding Time Complexity

We want to understand how the effort to check facts or research using Perplexity grows as the questions or data get bigger.

How does the time needed change when we ask more or more complex questions?

Scenario Under Consideration

Analyze the time complexity of the following code snippet.

function fetchAnswers(questions) {
  let results = [];
  for (let q of questions) {
    let answer = queryPerplexityAPI(q);
    results.push(answer);
  }
  return results;
}

This code sends each question to Perplexity's API one by one and collects the answers.

Identify Repeating Operations

• Primary operation: Sending a query to Perplexity API for each question.
• How many times: Once for each question in the input list.

How Execution Grows With Input

Each new question adds one more API call, so the total work grows directly with the number of questions.

Input Size (n)	Approx. Operations
10	10 API calls
100	100 API calls
1000	1000 API calls

Pattern observation: The time grows in a straight line as the number of questions increases.

Final Time Complexity

Time Complexity: O(n)

This means the time needed grows directly in proportion to how many questions you ask.

Common Mistake

[X] Wrong: "Adding more questions won't affect the total time much because the API is fast."

[OK] Correct: Even if each call is fast, doing many calls one after another adds up, so more questions mean more total time.

Interview Connect

Understanding how time grows with input size helps you explain how your code will behave with bigger data, a key skill in real projects and interviews.

Self-Check

"What if we sent all questions in one batch request instead of one by one? How would the time complexity change?"