API-based deployment in Prompt Engineering / GenAI - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Understanding API-based deployment benefits

Which of the following is the primary advantage of deploying a machine learning model via an API?

A It eliminates the need for any server or cloud infrastructure.

B It automatically improves the model's accuracy over time without retraining.

C It allows real-time access to the model from different applications without sharing the model code.

D It stores the entire training dataset within the API for faster predictions.

💡 Hint

Think about how APIs let different programs talk to each other.

APIs provide a way for applications to send data to the model and get predictions without exposing the model's internal code or requiring local installation.

❓ Predict Output

intermediate

Output of a simple API call to a deployed model

Given the following Python code snippet calling a deployed ML model API, what is the printed output?

Prompt Engineering / GenAI

import requests
response = requests.post('https://api.example.com/predict', json={'input': [1, 2, 3]})
print(response.json())

A {"prediction": [0.1, 0.5, 0.4]}

B {'error': 'Invalid input format'}

C {'prediction': [1, 0, 1]}

D requests.exceptions.ConnectionError

💡 Hint

Assume the API is working correctly and returns prediction probabilities.

The API returns a JSON with prediction probabilities for the input data, so the output is a dictionary with a 'prediction' key and a list of floats.

❓ Hyperparameter

advanced

Choosing timeout settings for API deployment

When deploying a machine learning model via an API, which timeout setting is most important to ensure good user experience without overloading the server?

A Set timeout to zero to prioritize requests in the order they arrive.

B Set a very high timeout so the server never cancels requests, even if slow.

C Disable timeout settings to allow unlimited request processing time.

D Set a low timeout to quickly reject requests that take too long, preventing server overload.

💡 Hint

Think about balancing responsiveness and server health.

A low timeout helps reject slow requests early, keeping the server responsive and preventing overload from stuck or slow calls.

❓ Metrics

advanced

Evaluating API latency metrics

You deployed a model via API and collected these latency times (in milliseconds) for 5 requests: [120, 150, 130, 200, 170]. What is the average latency?

A 154 ms

B 170 ms

C 150 ms

D 1540 ms

💡 Hint

Calculate the sum of all latencies and divide by the number of requests.

Sum is 120+150+130+200+170 = 770 ms. Divide by 5 requests = 154 ms average latency.

🔧 Debug

expert

Identifying cause of API deployment failure

After deploying your ML model as an API, clients report a 500 Internal Server Error when sending valid requests. Which of the following is the most likely cause?

A The client is sending requests with wrong input data types.

B The model file path is incorrect or missing on the server.

C The API endpoint URL is misspelled in the client code.

D The server has no internet connection.

💡 Hint

500 errors usually mean server-side problems, not client mistakes.

A 500 error indicates a server error, often caused by missing model files or code errors during prediction, not client input or URL issues.

Practice

1. What is the main purpose of API-based deployment in AI?

easy

A. To train AI models faster on local machines

B. To share AI models as easy-to-use services over the internet

C. To store large datasets securely

D. To visualize AI model results on graphs

Solution

1. Step 1: Understand API-based deployment

   API-based deployment allows AI models to be accessed remotely as services.

2. Step 2: Identify the main purpose

   This means apps can get predictions without running the model themselves, making sharing easy.

3. Final Answer:

   To share AI models as easy-to-use services over the internet -> Option B

4. Quick Check:

   API deployment = share models online [OK]

Hint: API deployment means sharing models as services online [OK]

Common Mistakes:

• Confusing deployment with training
• Thinking API stores data
• Assuming API is for visualization only

2. Which Python library is commonly used to create a simple API server for deploying AI models?

easy

A. NumPy

B. Matplotlib

C. Flask

D. Pandas

Solution

1. Step 1: Recall common Python libraries

   NumPy is for math, Pandas for data, Matplotlib for plots, Flask for web servers.

2. Step 2: Identify the API server library

   Flask is a lightweight web framework used to create APIs easily.

3. Final Answer:

   Flask -> Option C

4. Quick Check:

   Flask = simple API server [OK]

Hint: Flask is the go-to for simple Python APIs [OK]

Common Mistakes:

• Choosing data libraries instead of web frameworks
• Confusing Flask with data processing tools
• Thinking Matplotlib creates APIs

3. Given this Flask API code snippet, what will be the output when sending a POST request with JSON {"input": 5}?

from flask import Flask, request, jsonify
app = Flask(__name__)

@app.route('/predict', methods=['POST'])
def predict():
    data = request.get_json()
    x = data['input']
    result = x * 2
    return jsonify({'output': result})

if __name__ == '__main__':
    app.run()

medium

A. {"output": 10}

B. {"output": 5}

C. {"output": 25}

D. Error: Missing input key

Solution

1. Step 1: Understand the input and processing

   The API receives JSON with key 'input' and value 5, then multiplies it by 2.

2. Step 2: Calculate the output

   5 * 2 = 10, so the output JSON will have 'output': 10.

3. Final Answer:

   {"output": 10} -> Option A

4. Quick Check:

   Input 5 doubled = 10 [OK]

Hint: Multiply input by 2 as per code logic [OK]

Common Mistakes:

• Confusing input and output values
• Assuming output equals input
• Missing JSON key causes error

4. Identify the error in this Flask API code for deploying a model:

from flask import Flask, request, jsonify
app = Flask(__name__)

@app.route('/predict', methods=['POST'])
def predict():
    data = request.json()
    x = data['input']
    result = x + 1
    return jsonify({'output': result})

if __name__ == '__main__':
    app.run()

medium

A. Incorrect HTTP method, should be GET

B. Missing route decorator

C. Returning plain string instead of JSON

D. Using request.json() instead of request.get_json()

Solution

1. Step 1: Check how JSON is accessed in Flask

   Flask's request object uses get_json() method, not json() function.

2. Step 2: Identify the error

   Using request.json() will cause an AttributeError; correct is request.get_json().

3. Final Answer:

   Using request.json() instead of request.get_json() -> Option D

4. Quick Check:

   Use get_json() to parse JSON [OK]

Hint: Use request.get_json(), not request.json() [OK]

Common Mistakes:

• Confusing request.json with get_json()
• Changing HTTP method unnecessarily
• Forgetting route decorator

5. You want to deploy a machine learning model via an API that predicts house prices. The model expects a JSON with features like 'size' and 'bedrooms'. Which approach best ensures your API handles missing features gracefully?

hard

A. Fill missing features with default values before prediction

B. Return an error if any feature is missing without processing

C. Ignore missing features and predict with available data only

D. Restart the server to reset missing data

Solution

1. Step 1: Understand missing feature handling

   Missing features can cause prediction errors if not handled properly.

2. Step 2: Choose a robust approach

   Filling missing features with default or average values allows prediction to continue safely.

3. Final Answer:

   Fill missing features with default values before prediction -> Option A

4. Quick Check:

   Use defaults for missing inputs [OK]

Hint: Use default values to handle missing features [OK]

Common Mistakes:

• Stopping API on missing data
• Ignoring missing features causing errors
• Restarting server unrelated to missing data