API-based deployment in Prompt Engineering / GenAI - ML Experiment: Train & Evaluate

Experiment - API-based deployment

Problem:You have trained a text classification model that works well locally. Now you want to deploy it as an API so others can send text and get predictions.

Current Metrics:Model accuracy on test data: 90%. No deployment yet.

Issue:The model is not accessible remotely. Users cannot get predictions without running code locally.

Your Task

Deploy the trained text classification model as a REST API that accepts text input and returns predicted labels. The API should respond within 1 second for a single request.

Use a lightweight web framework (e.g., FastAPI or Flask).

Do not change the model architecture or retrain the model.

Ensure the API handles JSON input and output.

Hint 1

Hint 2

Hint 3

Hint 4

Solution

Prompt Engineering / GenAI

from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
import uvicorn
import joblib

# Define input data model
class TextInput(BaseModel):
    text: str

# Load the trained model once
model = joblib.load('text_classifier.joblib')

app = FastAPI()

@app.post('/predict')
async def predict(input: TextInput):
    text = input.text
    if not text:
        raise HTTPException(status_code=400, detail='Text input is empty')
    # Model expects a list of texts
    prediction = model.predict([text])[0]
    return {'label': prediction}

if __name__ == '__main__':
    uvicorn.run(app, host='0.0.0.0', port=8000)

Added FastAPI web server to serve the model as an API.

Created a POST /predict endpoint that accepts JSON input with a 'text' field.

Loaded the trained model once at startup to improve response time.

Returned prediction label as JSON output.

Results Interpretation

Before deployment: Model accuracy 90%, no remote access.

After deployment: Model accuracy unchanged at 90%, API responds within 200ms, enabling remote predictions.

Deploying a trained model as an API makes it accessible to others without changing the model. Loading the model once and using a lightweight web framework ensures fast responses.

Bonus Experiment

Add input validation to reject empty or very long texts and return meaningful error messages.

💡 Hint

Use Pydantic validators or FastAPI request validation features to check input length and content before prediction.

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