CS6998 Assignment 1-Dining Concierge Assistant Solution

You could do this assignment in team of 2 people. The PDF version is here:
Customer Service is a core service for a lot of businesses around the world and it is getting disrupted at the moment by Natural Language Processingpowered applications. In this first assignment you will implement a serverless, microservice-driven web application. Specifically, you will build a Dining Concierge chatbot that sends you restaurant suggestions given a set of preferences that you provide the chatbot with through conversation.
Outline:
This assignment has the following requirements:
Build and deploy the frontend of the application
1. Repurpose the following frontend starter application to interface with your chatbot
1. https://github.com/ndrppnc/cloud-hw1-starter
Host your frontend in an AWS S3 bucket
1. Set the bucket up for website hosting
2. https://docs.aws.amazon.com/AmazonS3/latest/dev/Host ingWebsiteOnS3Setup.html
Build the API for the application
1. Use API Gateway to setup your API
1. use the following API/Swagger specification for your
API
https://github.com/001000001/aics-columbias2018/blob/master/aics-swagger.yaml
Use http://editor.swagger.io/ to visualize this file
You can import the Swagger file into API Gateway
https://docs.aws.amazon.com/apigateway/lates t/developerguide/api-gateway-importapi.html
Create a Lambda function (LF0) that performs the chat operation
Use the request/response model (interfaces) specified in the API specification above
2. For now, just implement a boilerplate response to all messages:
ex. User says anything, Bot responds: "I’m still under development. Please come back later."
2. Notes
1. You will need to enable CORS on your API methods https://docs.aws.amazon.com/apigateway/latest/dev eloperguide/how-to-cors.html
2. API Gateway can generate an SDK for your API, which you can use in your frontend. It will take care of calling your API, as well as session signing the API calls -- an important security feature https://docs.aws.amazon.com/apigateway/latest/dev eloperguide/how-to-generate-sdk-javascript.html
Build a Dining Concierge chatbot using Amazon Lex.
1. Create a new bot using the Amazon Lex service. Read up the documentation on all things Lex, for more information: https://docs.aws.amazon.com/lex/latest/dg/gettingstarted.html
2. Create a Lambda function (LF1) and use it as a code hook for Lex, which essentially entails the invocation of your Lambda before Lex responds to any of your requests -- this gives you the chance to manipulate and validate parameters as well as format the bot’s responses. More documentation on Lambda code hooks at the following link: https://docs.aws.amazon.com/lex/latest/dg/using-lambda.html
3. Bot Requirements:
1. Implement at least the following three intents:
GreetingIntent
ThankYouIntent
DiningSuggestionsIntent
2. The implementation of an intent entails its setup in Amazon Lex as well as handling its response in the Lambda function code hook.
Example: for the GreetingIntent you need to 1. create the intent in Lex, 2. train and test the intent in the Lex console, 3. implement the handler for the GreetingIntent in the Lambda code hook, such that when you receive a request for the GreetingIntent you compose a response such as “Hi there, how can I help?”
3. For the DiningSuggestionsIntent, you need to collect at least the following pieces of information from the user, through conversation:
Location
Cuisine
Dining Time
Number of people
Phone number
4. Based on the parameters collected from the user, push the information collected from the user (location, cuisine, etc.) to an SQS queue (Q1). More on SQS queues here: https://aws.amazon.com/sqs/ Also confirm to the user that you received their request and that you will notify them over SMS once you have the list of restaurant suggestions.
Integrate the Lex chatbot into your chat API
1. Use the AWS SDK to call your Lex chatbot from the API Lambda (LF0).
2. When the API receives a request, you should 1. extract the text message from the API request, 2. send it to your Lex chatbot, 3. wait for the response, 4. send back the response from Lex as the API response.
Use the Yelp API to collect 5,000+ random restaurants from Manhattan.
1. Use the following tools:
1. Yelp API
Get restaurants by your self-defined cuisine types You can do this by adding cuisine type in the search term ( ex. Term: chinese restaurants)
Each cuisine type should have 1,000 restaurants or so. Make sure your restaurants don’t duplicate.
2. DynamoDB (a noSQL database)
Create a DynamoDB table and named “yelp-restaurants” Store the restaurants you scrape, in DynamoDB (one thing you will notice is that some restaurants might have more or less fields than others, which makes DynamoDB ideal for storing this data)
Store those that are necessary for your recommendation.
(Requirements: Business ID, Name, Address,
Coordinates, Number of Reviews, Rating, Zip Code)
3. Note: you can perform this scraping from your computer or from your AWS account -- your pick.
Create an ElasticSearch instance using the AWS ElasticSearch Service.
Create an ElasticSearch index called “restaurants”
Create an ElasticSearch type under the index “restaurants” called “Restaurant”
Store partial information for each restaurant scraped in ElasticSearch under the “restaurants” index, where each entry has a “Restaurant” data type.
You only need to store RestaurantID and Cuisine for each restaurant
Build a suggestions module, that is decoupled from the Lex chatbot.
1. Create a new Lambda function (LF2) that acts as a queue worker. Whenever it is invoked it 1. pulls a message from the SQS queue (Q1), 2. gets a random restaurant recommendation for the cuisine collected through conversation from ElasticSearch and DynamoDB, 3. formats them and 4. sends them over text message to the phone number included in the SQS message, using SNS (https://docs.aws.amazon.com/sns/latest/dg/SMSMessages.html).
1. Use the DynamoDB table “yelp-restaurants” (which you created from Step 1) to fetch more information about the restaurants (restaurant name, address, etc.), since the restaurants stored in ElasticSearch will have only a small subset of fields from each restaurant.
2. Modify the rest of the LF2 function if necessary to send the user text/email.
2. Set up a CloudWatch event trigger that runs every minute and invokes the Lambda function as a result:
https://docs.aws.amazon.com/AmazonCloudWatch/latest/events/Ru nLambdaSchedule.html. This automates the queue worker Lambda to poll and process suggestion requests on its own.


Extra Credit: 10 pts

Implement state for your concierge application, such that it remembers your last search for both location and category. When a user returns to the chat, they should automatically receive a recommendation based on their previous search. You can use DynamoDB to store intermediary state information and a separate Lambda function to handle the recommendation based on the last search.

Example Interaction

User: Hello
Bot: Hi there, how can I help?
User: I need some restaurant suggestions.
Bot: Great. I can help you with that. What city or city area are you looking to dine in?
User: Manhattan
Bot: Got it, Manhattan. What cuisine would you like to try?
User: Japanese
Bot: Ok, how many people are in your party?
User: Two
User: Today
Bot: What time?
User: 7 pm, please
Bot: Great. Lastly, I need your phone number so I can send you my findings.
User: 123-456-7890
Bot: You’re all set. Expect my suggestions shortly! Have a good day.
User: Thank you!
Bot: You’re welcome.

(a few minutes later)

User gets the following text message:

“Hello! Here are my Japanese restaurant suggestions for 2 people, for today at 7 pm: 1. Sushi Nakazawa, located at 23 Commerce St, 2. Jin Ramen, located at 3183 Broadway, 3. Nikko, located at 1280 Amsterdam Ave. Enjoy your meal!”
ANNEX
Architecture Diagram: