Skip to main content

Creating a Chatbot with RiveScript in Java

Motivation

"Artificial Intelligence (AI) is considered a major innovation that could disrupt many things. Some people even compare it to the Internet. A large investor firm predicted that some AI startups could become the next Apple, Google or Amazon within five years" 
- Prof. John Vu, Carnegie Mellon University.

Using chatbots to support our daily tasks is super useful and interesting. In fact, "Jenkins CI, Jira Cloud, and Bitbucket" have been becoming must-have apps in Slack of my team these days.

There are some existing approaches for chatbots including pattern matching, algorithms, and neutral networks. RiveScript is a scripting language using "pattern matching" as a simple and powerful approach for building up a Chabot.

Architecture

Actually, it was flexible to choose a programming language for the used Rivescript interpreter like Java, Go, Javascript, Python, and Perl. I went with Java.


Used Technologies and Tools

  • Oracle JDK 1.8.0_151
  • Apache Maven 3.5.2
  • Apache Tomcat 7.0.85
  • RiveScript-Java
  • Jersey sever/client
  • MyFaces

Module ChatBot Backend

I had a backend for chatbot's brain which provided APIs responding to received messages from users via a GUI.

1. Generate a web app project via Maven

mvn archetype:generate \
-DgroupId=vn.nvanhuong \
-DartifactId=chatbot_rivescript_backend \
-DarchetypeArtifactId=maven-archetype-webapp \
-DinteractiveMode=false;

Tips: When importing the project into Eclipse, I encountered an error "The superclass "javax.servlet.http.HttpServlet" was not found on the Java Build Path". I solved it by "Right click on the project/Properties/Project Facets/Runtimes/Check Apache Tomcat v.7.0"

2. Add dependencies needed in `pom.xml`

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
 xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
 <modelVersion>4.0.0</modelVersion>
 <groupId>vn.nvanhuong</groupId>
 <artifactId>chatbot_rivescript_backend</artifactId>
 <packaging>war</packaging>
 <version>1.0-SNAPSHOT</version>
 <name>chatbot_rivescript_backend Maven Webapp</name>
 <url>http://maven.apache.org</url>

 <dependencies>
  <!-- ChatBot Brain -->
  <dependency>
   <groupId>com.rivescript</groupId>
   <artifactId>rivescript-core</artifactId>
   <version>0.10.0</version>
  </dependency>

  <!-- RESTful APIs -->
  <dependency>
   <groupId>com.sun.jersey</groupId>
   <artifactId>jersey-server</artifactId>
   <version>1.8</version>
  </dependency>

  <!-- JSON -->
  <dependency>
   <groupId>org.json</groupId>
   <artifactId>json</artifactId>
   <version>20160810</version>
  </dependency>

  <!-- Unit tests -->
  <dependency>
   <groupId>junit</groupId>
   <artifactId>junit</artifactId>
   <version>4.12</version>
   <scope>test</scope>
  </dependency>
 </dependencies>

 <build>
  <finalName>chatbot_rivescript_backend</finalName>
 </build>
</project>

3. Create chatbot's brain with RiveScript

I created a file "chatbot_brain.rive" under the folder "src/main/resources/rivescript". I copied the content of template file "rs_standard.rive" at https://www.rivescript.com/try
+ hello bot
- Hello human!

4. Create RESTful APIs

package vn.nvanhuong.chatbot.rivescript.backend;

import javax.ws.rs.POST;
import javax.ws.rs.Path;

import com.rivescript.Config;
import com.rivescript.RiveScript;
import com.sun.jersey.spi.resource.Singleton;

@Path("/bot")
@Singleton
public class ChatBot {
 private RiveScript bot;
 
 public ChatBot() {
  String rivescriptFilePath = ChatBot.class.getClassLoader().getResource("rivescript").getFile();
  bot = new RiveScript(Config.utf8());
  
  bot.loadDirectory(rivescriptFilePath);
        bot.sortReplies();
 }
 
 @POST
 public String getMsg(String msg) {
  return bot.reply("user", msg);
 }

}

5. Configure RESTful at `web.xml`

<web-app id="WebApp_ID" version="2.4"
 xmlns="http://java.sun.com/xml/ns/j2ee"
 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
 xsi:schemaLocation="http://java.sun.com/xml/ns/j2ee
 http://java.sun.com/xml/ns/j2ee/web-app_2_4.xsd">
 <display-name>Restful Web Application</display-name>

 <servlet>
  <servlet-name>jersey-serlvet</servlet-name>
  <servlet-class>
                     com.sun.jersey.spi.container.servlet.ServletContainer
                </servlet-class>
  <init-param>
       <param-name>com.sun.jersey.config.property.packages</param-name>
       <param-value>vn.nvanhuong.chatbot.rivescript.backend</param-value>
  </init-param>
  <load-on-startup>1</load-on-startup>
 </servlet>

 <servlet-mapping>
  <servlet-name>jersey-serlvet</servlet-name>
  <url-pattern>/rest/*</url-pattern>
 </servlet-mapping>

</web-app>

6. Write a test case

package vn.nvanhuong.chatbot.rivescript.backend.test;

import static org.junit.Assert.assertEquals;

import org.junit.Test;

import vn.nvanhuong.chatbot.rivescript.backend.ChatBot;

public class ChatBotTest {
 
 @Test
 public void should_say_hello() {
  ChatBot bot = new ChatBot();
  
  assertEquals("Hello Human!", bot.getMsg("Hello Bot"));
 }
}

7. Test the API with Postman

URL: http://localhost:8080/chatbot_rivescript_backend/rest/bot

Module ChatBot GUI

1. Generate a web app project via Maven

mvn archetype:generate \
-DgroupId=vn.nvanhuong \
-DartifactId=chatbot_rivescript_gui \
-DarchetypeArtifactId=maven-archetype-webapp \
-DinteractiveMode=false

2. Add dependencies needed in pom.xml

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
 xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
 <modelVersion>4.0.0</modelVersion>
 <groupId>vn.nvanhuong</groupId>
 <artifactId>chatbot_rivescript_gui</artifactId>
 <packaging>war</packaging>
 <version>1.0-SNAPSHOT</version>
 <name>chatbot_rivescript_gui Maven Webapp</name>
 <url>http://maven.apache.org</url>

 <dependencies>
  <!-- JAX-RS Client -->
  <dependency>
   <groupId>org.glassfish.jersey.core</groupId>
   <artifactId>jersey-client</artifactId>
   <version>2.25.1</version>
  </dependency>

  <!-- JSF Pages -->
  <dependency>
   <groupId>org.apache.myfaces.core</groupId>
   <artifactId>myfaces-api</artifactId>
   <version>2.2.0</version>
  </dependency>
  <dependency>
   <groupId>org.apache.myfaces.core</groupId>
   <artifactId>myfaces-impl</artifactId>
   <version>2.2.0</version>
  </dependency>

  <!-- Unit test -->
  <dependency>
   <groupId>junit</groupId>
   <artifactId>junit</artifactId>
   <version>4.12</version>
   <scope>test</scope>
  </dependency>
 </dependencies>

 <build>
  <finalName>chatbot_rivescript_gui</finalName>
 </build>
</project>

3. Configure JSF at web.xml

<?xml version="1.0" encoding="UTF-8"?>
<web-app xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" 
 xmlns="http://java.sun.com/xml/ns/javaee"
 xmlns:web="http://java.sun.com/xml/ns/javaee/web-app_2_5.xsd"
 xsi:schemaLocation="http://java.sun.com/xml/ns/javaee http://java.sun.com/xml/ns/javaee/web-app_2_5.xsd"
 version="2.5">
  
 <!-- JSF mapping -->
 <servlet>
  <servlet-name>Faces Servlet</servlet-name>
  <servlet-class>javax.faces.webapp.FacesServlet</servlet-class>
  <load-on-startup>1</load-on-startup>
 </servlet>
 <servlet-mapping>
  <servlet-name>Faces Servlet</servlet-name>
  <url-pattern>*.xhtml</url-pattern>
 </servlet-mapping>
   
  <!-- welcome page -->
  <welcome-file-list>
    <welcome-file>index.xhtml</welcome-file>
  </welcome-file-list>
</web-app>

4. Create a GUI

Rename index.jsp to index.xthml

<!DOCTYPE html>
<html xmlns="http://www.w3.org/1999/xhtml"
 xmlns:f="http://java.sun.com/jsf/core"
 xmlns:h="http://java.sun.com/jsf/html"
 xmlns:p="http://xmlns.jcp.org/jsf/passthrough">
 <h:head>
  <title>RiveScript</title>
  <style>
   
   .container {
    display: block;
     margin: 50px auto;
     width: 90%;
   }
   
   .chatbox {
    height: 600px;
     border: solid 1px #039;
     background-image: url(bot_logo.png);
     background-repeat: no-repeat;
     background-position: center;
     background-size: contain;
     display: flex;
     justify-content: center;
     align-items: center;
   }
   
   .chatbox .bot-dialog {
    width: 90%;
     border: dashed 1px purple;
     text-align: center;
     background-color: orange;
   }
   
   .chatbox .bot-dialog > span{
    font-size: larger;
   }
   
   .message {
    display: flex;
    justify-content: space-between;
    
   }
   .message > input.message-input {
    width: 90%;
    margin-top: 10px;
    line-height: 2.3;
   }
   
   .message > input.submit {
    width: 9%;
     background-color: #039;
     color: white;
     font-size: 15px;
     margin-top: 10px;
   }
   
   .message-display > span {
     font-style: italic;
 }
 .message-display > label {
     font-weight: bold;
 }
 .message-display {
     margin-top: 5px;
 }
   
  </style>
 </h:head>
 <h:body>
 <h:form>
    <h:panelGroup layout="block" styleClass="container">
      <h:panelGroup layout="block" styleClass="chatbox">
       <h:panelGroup layout="block" styleClass="bot-dialog">
        <h:outputText id="botMessage" value="#{controller.botMessage}" escape="false"/>
       </h:panelGroup>
      </h:panelGroup>
      
      <h:panelGroup layout="block" styleClass="message">
       <h:inputText id="input" value="#{controller.humanMessage}" styleClass="message-input" 
        p:placeholder="Send a message to the bot"
        p:autofocus="true"
        onblur="this.focus()"/>
       <h:commandButton id="button" value="Send" actionListener="#{controller.onSend}" styleClass="submit"/>
      </h:panelGroup>
      
      <h:panelGroup layout="block" styleClass="message-display" rendered="#{not empty controller.humanMessageDisplay}">
       <h:outputLabel for="messageDisplay" value="You just said: "/>
       <h:outputText id="messageDisplay" value="#{controller.humanMessageDisplay}"/>
      </h:panelGroup>
    </h:panelGroup>
 </h:form>
 </h:body>
</html>

5. Create a Controller to call the RESTful APIs

package vn.vanhuong.chatbot.rivescript.gui;

import javax.faces.bean.ManagedBean;
import javax.faces.event.ActionEvent;
import javax.ws.rs.client.ClientBuilder;
import javax.ws.rs.client.Entity;
import javax.ws.rs.core.MediaType;
import javax.ws.rs.core.Response;

@ManagedBean(name = "controller")
public class Controller {
 
 private String humanMessage;
 private String botMessage;
 private String humanMessageDisplay;

 public void onSend(ActionEvent event) {
  Response response = ClientBuilder.newClient().target("http://localhost:8080/chatbot_rivescript_backend/rest/bot")
    .request(MediaType.APPLICATION_FORM_URLENCODED)
    .post(Entity.entity(humanMessage, MediaType.APPLICATION_FORM_URLENCODED));
  this.botMessage = response.readEntity(String.class);
  this.humanMessageDisplay = humanMessage;
  this.humanMessage = null;
 }

 public String getHumanMessage() {
  return humanMessage;
 }

 public void setHumanMessage(String humanMessage) {
  this.humanMessage = humanMessage;
 }

 public String getBotMessage() {
  return botMessage;
 }

 public void setBotMessage(String botMessage) {
  this.botMessage = botMessage;
 }

 public String getHumanMessageDisplay() {
  return humanMessageDisplay;
 }

 public void setHumanMessageDisplay(String humanMessageDisplay) {
  this.humanMessageDisplay = humanMessageDisplay;
 }
}

6. Enjoy playing with your ChatBot

Check out my source code as below

- Backend: https://github.com/vnnvanhuong/chatbot_rivescript_backend.git
- GUI: https://github.com/vnnvanhuong/chatbot_rivescript_gui.git

References:
[1]. http://science-technology.vn/?p=5761
[2]. https://www.rivescript.com/interpreters
[3]. https://github.com/aichaos/rivescript-java
[4]. https://youtu.be/wf8w1BJb9Xc
Labels:

Comments

Post a Comment

Popular posts from this blog

Set up a web server for learning HTTP headers

Motivation We all follow the client-server model using the HTTP protocol for most of our web apps today. In development, we simply may have a backend API server and a frontend (web pages or mobile apps) only. However, it seemed that a proxy server is always required for production. In fact, most of the hardest issues in production come from integration. The requests and responses might be modified by the proxy server. Therefore, the understanding of HTTP protocol is one of the key skills to resolve those issues. I wanted to dive deep into HTTP with some core concepts such as caching, cookies, and CORS. I didn't intend to go quickly rather than moved slowly to have a well understanding of what I do. Prepare a server The easiest way is to use my laptop as a server then I can just use "localhost". I can also use ngrok to make my web server online. Finally, I use an online tool such as RedBot to check the HTTP headers. To make it more excited though, I deployed the app on A...
Post a Comment
Read more

The power of acceptance test

User Story is the place PO gives his ideas about features so that developers are able to know what requirements are. Acceptance tests are these show the most valuable things of the features represented by some specific cases. Usually PO defines them, but not always. Therefore, refining existing acceptance tests – even defining new ones that cover all features of the User Story must be a worth task. Acceptance test with Given When Then pattern If we understand what we are going to do, we can complete it by 50% I have worked with some members those just start implementing the features one by one and from top to down of the User Story description. Be honest, I am the one used to be. What a risky approach! Because it might meet a case that is very easy to miss requirements or needs to re-work after finding any misunderstood things. I have also worked with some members those accept spending a long time to clarify the User Story. Reading carefully of whole User Story by defining...
Post a Comment
Read more

What the heck is Meteor DDP?

I was using Meteor for my messenger project. I was so curious about the real time connection. I wanted to know how exactly this mechanism works. In this post, I will go through the DDP Specification, an overview of WebSocket, and a simple demo about how to subscribe a publication of Rocket.Chat (containing a DDP server) from an external webpage. At a glance, I knew that Meteor invented a protocol called DDP which uses for handling real time connection. So then, what is DDP? "DDP (Distributed Data Protocol) is the stateful WebSocket protocol that Meteor uses to communicate between the client and the server." [1] All right! Why does DDP matter? "DDP is a standard way to solve the biggest problem facing client-side JavaScript developers: querying a server-side database, sending the results down to the client, and then pushing changes to the client whenever anything changes in the database" . [2] In order to understand deeply the protocol, I decided ...
Post a Comment
Read more

DevOps Toolchain Enhancement

 Historically, our company ubitec had started with a customer project. Agile/Scrum was our proposal for working with customers. Time by time, Agile/Scrum also became our culture for software development. To be successful with this development approach, we somehow needed to have a fast release for customers (i.e. every one week). Back then, we had a build tool Jenkins which was responsible for having sprint release packages for our customers. The build job pipelines contain some steps such as gathering the artifacts, checking the code convention, running the tests, building docker images, and packaging an archived file (a zip file). The set of tools involved in a pipeline is roughly called a toolchain. It is just a part of a bigger process called the DevOps toolchain. Source: https://www.ibm.com/blogs/cloud-archive/2016/11/devops-architecture-available-on-bluemix-garage-method-site/ DevOps is a proven method that fits Agile. Today,  it is even treated as a mandatory factor...
Post a Comment
Read more

How I did customize "rasa-nlu-trainer" as my own tool

Check out my implementation here Background I wanted to have a tool for human beings to classify intents and extract entities of texts which were obtained from a raw dataset such as Rocket.chat's conversation, Maluuba Frames or  here . Then, the output (labeled texts) could be consumed by an NLU tool such as Rasa NLU. rasa-nlu-trainer was a potential one which I didn't need to build an app from scratch. However, I needed to add more of my own features to fulfill my needs. They were: 1. Loading/displaying raw texts stored by a database such as MongoDB 2. Manually labeling intents and entities for the loaded texts 3. Persisting labeled texts into the database I firstly did look up what rasa-nlu-trainer 's technologies were used in order to see how to implement my mentioned features. At first glance rasa-nlu-trainer was bootstrapped with Create React App. Create React App is a tool to create a React app with no build configuration, as it said. This too...
Post a Comment
Read more