Demo Using GenAI to Generate Steps for Lambda Deployment

Before automating AWS Lambda deployment with a Jenkins pipeline, it’s crucial to adapt a Node.js application (originally designed for Docker on EC2 and Kubernetes) to run seamlessly in a serverless environment. Instead of sifting through extensive AWS documentation, we used Microsoft Copilot to outline high-level steps. Below are the questions we asked and the concise answers that guided our Lambda-ready changes and pipeline design.

1. What are the steps required to deploy a Node.js application to AWS Lambda using a Jenkins pipeline?

Copilot mapped out these key stages:

1. Configure AWS and Jenkins

   • Ensure AWS CLI is installed and credentials are set:
     aws configure
   • Install Jenkins plugins: Git, NodeJS, AWS Lambda, Pipeline

2. Install Dependencies

   npm install
   

3. Run Tests (if applicable)

   npm test
   

4. Package the Application

   zip -r my-node-app.zip index.js node_modules
   

5. Deploy to Lambda

   aws lambda create-function \
     --function-name my-node-app \
     --zip-file fileb://my-node-app.zip \
     --handler index.handler \
     --runtime nodejs14.x \
     --role arn:aws:iam::<AWS_ACCOUNT_ID>:role/<ROLE_NAME>
   

6. Define Jenkins Pipeline (Jenkinsfile)

   pipeline {
     agent any
     stages {
       stage('Checkout') { steps { git url: 'https://repo-url.git' } }
       stage('Install')  { steps { sh 'npm install' } }
       stage('Test')     { steps { sh 'npm test' } }
       stage('Package')  { steps { sh 'zip -r my-node-app.zip index.js node_modules' } }
       stage('Deploy') {
         steps {
           withAWS(credentials: 'aws-creds') {
             sh '''
             aws lambda update-function-code \
               --function-name my-node-app \
               --zip-file fileb://my-node-app.zip \
               --publish
             '''
           }
         }
       }
     }
   }
   

To summarize, here’s a quick overview of each pipeline stage:

2. Are there any specific Lambda or serverless dependencies to add?

To adapt Express for Lambda’s event-driven model, install these packages:

npm install express serverless-http
# (Optional) Install the Serverless Framework CLI globally
npm install -g serverless

3. Do we need to modify the application code (app.js) for AWS Lambda?

Yes. Wrap your Express app using serverless-http and export the handler:

const express = require('express');
const serverless = require('serverless-http');
const app = express();

app.get('/', (req, res) => {
  res.send('Hello, AWS Lambda!');
});

module.exports.handler = serverless(app);

4. What is the AWS CLI command to update a Lambda function’s code?

If your function already exists, run:

aws lambda update-function-code \
  --function-name my-node-app \
  --zip-file fileb://my-node-app.zip \
  --publish

Or update from an S3 bucket:

aws lambda update-function-code \
  --function-name my-node-app \
  --s3-bucket my-bucket \
  --s3-key my-node-app.zip

5. How can we retrieve the Function URL configuration via AWS CLI?

To fetch the function URL settings after deployment:

aws lambda get-function-url-config \
  --function-name my-node-app

With these steps, you now have a clear roadmap:

• Integrate serverless-http into your Node.js app and export a Lambda handler.
• Zip your application code and dependencies.
• Use AWS CLI commands within a Jenkins pipeline to deploy and update your Lambda function.
• Retrieve and test the Function URL configuration with a simple CLI call.

In the next session, we’ll manually execute these commands to confirm the deployment before fully automating the workflow using our Jenkins pipeline.

Links and References

• AWS Lambda Developer Guide
• Jenkins Pipeline Syntax
• serverless-http on npm
• Serverless Framework Documentation