API7.ai

api7ai

Last year, I wrote my first . I liked the experience, so I'm trying one more time. Let the future decide if it will become a trend or not. yearly retrospective Before diving into our safe technological world, my thoughts go to Ukraine, to my friends who had to flee their own country, to other friends who fought on the front to defend it from an imperial power, and to all victims of an old kleptocrat who clings to power despite the cost to others. The free world needs to support Ukraine more. I hope 2024 will be the year of Ukrainian victory. The AI revolution Last year, I kept the post focused on what I did. However, AI is pervasive in our tech world, if not the whole world, and deserves a dedicated section. Nobody even remotely connected to tech can ignore the buzz surrounding AI. Even friends and families who don't work near tech probably talk about it. So far, I didn't weave any AI-related thing into any of my talks, despite the huge incentive to do so: having AI in your Call For Paper proposal vastly increases your chances of being selected. And yet, it doesn't mean that I'm not playing with it on a personal level. Here's my experience so far. I've been playing with Dall-E as a use case to try out web development in Rust. I found the results mind-blowing. However, the limitations are enormous; it seems the size is always square, and the set of possible dimensions is limited. I've used ChatGPT in several areas. First, I tried to generate conference abstracts. I fed an entire blog post and asked ChatGPT to turn it into an abstract. Despite my lack of prompt engineering skills, I've found results severely lacking. Abstracts felt artificial, like any content created with ChatGPT, but worse, the abstract revealed too much or not enough. I also tried to use it to refactor two nested Kotlin statements, one nested in the other, to the null-safe construct. The first result didn't compile; the second one forgot a branch. It led me to the correct solution, though. if else let Finally, I recently started using GitHub Copilot as an extension inside of IntelliJ IDEA. Its behavior is fascinating: most of the time, it does nothing, but once in a while, it offers a snippet of a couple of lines, which is either entirely correct or at least very close to the target solution. Even better, the suggestions seem to be more frequent and even more relevant with time. All in all, I'm far from impressed by the current state of AI. However, I like Copilot a lot: I prefer rare advice, which is relevant, than the opposite. Technical content Next February will mark the two-year milestone that I'm working for: on . I'm still very pleased about both. It allows me to do things I like a lot, such as writing posts and giving talks. API7.ai Apache APISIX In 2023, I published fifty blog posts on : one each week on Sunday, but on Christmas and the New Year - for obvious reasons. Here are the top most viewed pages: this blog Rank Post Views Avg. time on page #1 Leverage the richness of HTTP status codes 14,848 :29 #2 A list of cache providers 12,770 1:15 #3 Calling Rust from Python 8,780 :52 #4 My final take on Gradle (vs. Maven) 8,238 2:11 #5 Learning by doing: An HTTP API with Rust 6,642 1:00 I continue to cross-post on different sites. Here are the numbers compared with last year's: Site 2023 2022 Medium 741 564 Dev.to 8156 1,838 Hashnode 89 80 Absolute numbers are not that interesting, but comparing them is. Interestingly, numbers on are growing wildly, while on Hashnode, they plateau. Note that other sites provide no precise follower count or no count. dev.to Besides, I created a script to track daily metrics across sites and social media, just as I did for Apache APISIX. It displays interesting results: As above, numbers are much less important than the trend. Growth visibly happens mainly on and Bluesky for reasons I cannot fathom (yet?). dev.to Finally, I started a weekly newsletter, unoriginally named A Java Geek weekly. So far, I've written a . I list the posts and videos I found interesting during the week. Note that they contain the same links I post on , , and , with a bit more content, either a summary or my opinion. couple of them LinkedIn Mastodon BlueSky Open Source contributions In 2023, after over twenty years in software, I finally became ! I'm both excited and impressed; it's like belonging to a group of mythical beings I'd only heard about. an Apache committer Of course, working on Apache APISIX helped a lot. Yet, the exciting bit is that all my contributions are entirely unrelated to code; they are blog posts, reviews of blog posts written by others, issues, comments on issues, etc. Here's the GitHub summary: Conclusion Last year, my resolutions were: To deepen my understanding of the Apache APISIX ecosystem Write as many blog posts as in 2022 - it's hard to do better, anyway Design at least three new talks I fulfilled the two first goals but unfortunately failed the last item. I have only created two new talks, both based on previous posts. I'll keep them secret for now; they should appear soon on my page in case they are selected. Speaking I lack imagination, so I'll keep the same goals for this year as last year's and add exploring the ecosystem as well. Let's see how it fares. Happy New Year! API7.ai Originally on on January 7th, 2024 published A Java Geek

Everything I Achieved in 2023

is an excellent key-value distributed database used internally by Kubernetes and managed by the CNCF. It's a great option, and that's the reason why Apache APISIX uses it too. Yet, it's not devoid of issues. etcd First, some mention scalability, but one can expect this from a distributed data store that values consistency. Another issue may be the need for more familiarity with etcd. It's relatively new, so your Ops team may need help operating it correctly while having decades of operating MySQL or Postgres. Finally, only a few etcd users are aware that it lacks maintainers: In the last few months, primary maintainers G.L. (Amazon, announcement) and S.B. (Red Hat) have stopped actively participating in the project. This leaves the project with only one active and two occasionally-reviewing maintainers, M.S. (Google),  P.T. (Google), both are relatively new to the project (1 month and 1 year of tenure) and S.P.Z. (IBM). Other maintainers are either dormant or have very minimal activity over the last six months. . The project is effectively unmaintained (emphasis mine) -- Google Groups of Kubernetes Steering Committee, March 2022 For all those reasons, you may prefer to use a standard SQL database with Apache APISIX. In this post, I'll show how you can use MySQL. The kine project It would be a lot of effort if each product had to introduce an abstraction layer and different adapters for both etcd and other databases. kine is a project that aims to offer a translation step between etcd calls and other implementations: Kine is an etcdshim that translates etcd API to: SQLite Postgres MySQL NATS Jetstream Features Can be ran standalone so any k8s (not just K3s) can use Kine Implements a subset of etcdAPI (not usable at all for general purpose etcd) Translates etcdTX calls into the desired API (Create, Update, Delete) -- Kine (Kine is not etcd) In essence, kine is a Go library that translates etcd calls to the datastore you want (among those implemented). Yet, using kine directly is a non-trivial effort. Fortunately, , the company that gave Apache APISIX to the Apache Software Foundation, provides a component already focused on APISIX usage. api7 ETCD adapter ETCD adapter wraps kine to be APISIX-specific: ETCD Adapter mimics the ETCD V3 APIs best effort. It incorporates the kine as the Server side implementation, and it develops a totally in-memory watchable backend. Not all features in ETCD V3 APIs supported, this is designed for Apache APISIX, so it's inherently not a generic solution. -- ETCD adapter Two things of note: At the moment of this writing, the adapter supports either local in-memory storage or MySQL It's available as an embeddable library but also as a standalone component Therefore, we can design our architecture as the following: Demo Let's implement the above architecture with an additional admin UI over MySQL. I'll use Docker Compose: version: "3"

services:
  apisix:
    image: apache/apisix:3.4.0-debian                         #1
    volumes:
      - ./config.yaml:/usr/local/apisix/conf/config.yaml:ro
    ports:
      - "9080:9080"
      - "9180:9180"
    depends_on:
      - etcd-adapter
    restart: always                                           #2
  etcd-adapter:
    build: ./etcd-adapter                                     #3
    volumes:
      - ./adapter.yml:/etcd-adapter/conf/config.yaml:ro       #4
    depends_on:
      - mysql
    restart: always                                           #2
  mysql:
    image: bitnami/mysql:8.0                                  #5
    ports:
      - "3306:3306"
    environment:
      MYSQL_ROOT_PASSWORD: root
      MYSQL_USER: etcd
      MYSQL_PASSWORD: etcd
      MYSQL_DATABASE: apisix
  adminer:
    image: adminer:standalone                                 #6
    ports:
      - "8080:8080"
    environment:
      ADMINER_DEFAULT_SERVER: mysql
    depends_on:
      - mysql Latest version of Apache APISIX, yeah! To avoid any failure with dependencies between containers, restart until it works. Kubernetes's manifests would involve health checks still needs to provide a container. We need to build from the source code api7.ai Override the default configuration file with a context-specific one The regular MySQL image didn't work for me. Let's take the one from Bitnami Adminer, formerly known as PHP myAdmin, will help to visualize the database state ETCD-adapter's configuration looks like this: server:
  host: 0.0.0.0                 #1
  port: 12379

log:
  level: info

datasource:
  type: mysql                   #2
  mysql:
    host: mysql                 #3
    port: 3306                  #3
    username: etcd              #3
    password: etcd              #3
    database: apisix Bind any IP since Docker will assign a random one Implementation type. The default is ; we need to change it. btree As configured in the file docker-compose.yml Finally, here's Apache APISIX configuration: deployment:
  admin:
    allow_admin:
      - 0.0.0.0/0
  etcd:
    host:
      - "http://etcd-adapter:12379"   #1 Use this etcd instance, which is the adapter Testing Now that we are set let's test our system by creating a route: curl -H 'X-API-KEY: edd1c9f034335f136f87ad84b625c8f1' -X PUT -d '{                                          
  "methods": ["GET"],
  "uris": ["/get"],
  "upstream": {
    "nodes": {
      "httpbin.org:80": 1
    }
  }
}' http://localhost:9180/apisix/admin/routes/1 We can now get it: curl -H 'X-API-KEY: edd1c9f034335f136f87ad84b625c8f1' http://localhost:9180/apisix/admin/routes/1 We can also check via the Adminer interface that it has been persisted via MySQL: Unfortunately, we need to stop at this point. Getting all routes doesn't work: curl -H 'X-API-KEY: edd1c9f034335f136f87ad84b625c8f1' http://localhost:9180/apisix/admin/routes {"header":{"revision":"1689689596"},"message":"Key not found"} Worse, using the route fails: curl localhost:9080/get {"error_msg":"404 Route Not Found"} Conclusion etcd is an excellent piece of infrastructure Kubernetes uses, but there might be better choices in some contexts. Worse, it might become a security threat in the future - or is already one, because of the lack of maintenance. Being able to move away from etcd is a considerable benefit. kine offers an etcd-compatible facade and multiple implementations. Using kine with Apache APISIX requires some adaptation effort, already done in ETCD-Adapter. Currently, ETCD-Adapter is not feature-complete (to say the least) and requires more love. That's why it was not donated to the Apache Foundation yet. If you're a Go developer and are interested in the project, feel free to subscribe to the to offer your help. Apache APISIX mailing list and/or join our Slack The complete source code for this post can be found on . GitHub To go further: Kine ETCD Adapter "Goodbye etcd, Hello PostgreSQL: Running Kubernetes with an SQL Database" Originally published at on July 23rd, 2023 A Java Geek

Apache APISIX Without etcd?

In the world full of Siri, Cortana & Alexa, have you ever wondered you can create a new friend of yours. Well it might not be that intelligent but it not worthless to try creating  something new. With the current state of web apps, we can rely on various UI elements to interact with users. With the Web Speech API, we can develop rich web applications with natural user interactions and minimal visual interface, using voice commands. This enables countless use cases for richer web applications. Moreover, the API can make web apps accessible,helping people with physical or cognitive disabilities or injuries. The future web will be more conversational and accessible! Here, we will use the API to create an artificial intelligence (AI) voice chat interface in the browser. The app will listen to the user’s voice and reply with a synthetic voice. Because the Web Speech API is still experimental, the app works only in . The features used for this article, both speech recognition and speech synthesis, are currently only in the Chromium-based browsers, including Chrome 25+ and Opera 27+, while Firefox, Edge and Safari support only speech synthesis at the moment. supported browsers Let's get started To build the web app, we’re going to take three major steps: Use the Web Speech API’s interface to listen to the user’s voice. Speech Recognition Send the user’s message to a commercial natural-language-processing API as a text string. Once API.AI returns the response text back, use the SpeechSynthesis interface to give it a synthetic voice. Requirements and Installations Supported browser Installation of Node.js Installation of node modules like: : APIAI npm i apiai : Socket.io npm install socket.io : dotenv npm i dotenv-extended : Express npm install express --save Setting Up Your Application Set up a web app framework with Node.js. Create your app directory, and set up your app’s structure like this: .
├── index.js
├── files
│   ├── css
│   │   └── style.css
│   └── js
│       └── script.js
└── views
    └── index.html Then, run this command to initialize your Node.js app: npm init This will generate a package.json file that contains the basic info for your app. Now, install all of the dependencies needed to build this app: $ npm i apiai
$ npm install socket.io
$ npm i dotenv-extended
$ npm install express --save We are going to use , a Node.js web application server framework, to run the server locally. To enable real-time bidirectional communication between the server and the browser, we’ll use . Also, we’ll install the natural language processing service tool, in order to build an AI chatbot that can have an artificial conversation. Express Socket.IO APIAI Socket.IO is a library that enables us to use WebSocket easily with Node.js. By establishing a socket connection between the client and server, our chat messages will be passed back and forth between the browser and our server, as soon as text data is returned by the Web Speech API (the voice message) or by API.AI API (the “AI” message). Now, let’s create an file and instantiate Express and listen to the server: index.js ; apiai = ( ); APIAI_TOKEN =apiai( ); APIAI_SESSION_ID = ; express = ( ); app = express();

app.use(express.static(__dirname + )); 
app.use(express.static(__dirname + )); server = app.listen(process.env.PORT || , () => { .log( , server.address().port);
}); io = ( )(server);
io.on( , { .log( );
}); app.get( , (req, res) => {
  res.sendFile( );
});

io.on( , {
  socket.on( , (text) => { .log( + text); apiaiReq = APIAI_TOKEN.textRequest(text, { : APIAI_SESSION_ID
    });

    apiaiReq.on( , (response) => { aiText = response.result.fulfillment.speech; .log( + aiText);
      socket.emit( , aiText);
    });

    apiaiReq.on( , (error) => { .log(error);
    });

    apiaiReq.end();

  });
}); 'use strict' var require 'apiai' var " " //use a api token from the official site const " " //use a session id const require 'express' const '/views' '/files' const 3000 console 'Server listening on port %d ' const require 'socket.io' 'connection' ( ) function socket console 'a user connected' // Web UI '/' 'index.html' 'connection' ( ) function socket 'chat message' console 'Message: ' // Get a reply from API.ai let sessionId 'response' let console 'Bot reply: ' 'bot reply' 'error' console Now,we will integrate the front-end code with the Web Speech API. Creating The User Interface The UI of this app is simple: just a button to trigger voice recognition. Let’s set up our index.html file and include our front-end JavaScript file (script.js) and Socket.IO, which we will use later to enable the real-time communication: Recognito Recognito You said: ... Recognito replied: ... <!DOCTYPE html> < = > html lang "en" < > head < = > meta charset "utf-8" < = = > meta http-equiv "X-UA-Compatible" content "IE=edge,chrome=1" < = = > meta name "viewport" content "width=device-width" < > title </ > title < = = > link rel "stylesheet" href "https://cdnjs.cloudflare.com/ajax/libs/font-awesome/4.7.0/css/font-awesome.min.css" < = = = > link rel "stylesheet" type "text/css" href "css/style.css" </ > head < > body < > section < > h1 </ > h1 < = > button id "btn" < = > i class "fa fa-microphone" </ > i </ > button < > div < > p < = > em class "output-you" </ > em </ > p < > p < = > em class "output-bot" </ > em </ > p </ > div </ > section < = > script src "socket.io/socket.io.js" </ > script < = > script src "js/script.js" </ > script </ > body </ > html To style the button , refer to the style.css file in the . source code Capturing Voice With JavaScript In , invoke an instance of , the controller interface of the Web Speech API for voice recognition: script.js SpeechRecognition We’re including both prefixed and non-prefixed objects, because Chrome currently supports the API with prefixed properties. Also, we are using some of ECMAScript 6 syntax in this tutorial, because the syntax, including the const and arrow functions, are available in browsers that support both Speech API interfaces, and Speech Recognition SpeechSynthesis. Optionally, you can set varieties of to customize speech recognition: properties recognition.lang = ;
recognition.interimResults = ; 'en-US' false Then, capture the DOM reference for the button UI, and listen for the click event to initiate speech recognition. .querySelector( ).addEventListener( , () => {
  recognition.start();
}); document 'button' 'click' Once speech recognition has started, use the result event to retrieve what was said as text. This will return a SpeechRecognitionResultList object containing the result, and you can retrieve the text in the array. Also, as you can see in the code sample, this will return confidence for the transcription, too. recognition.addEventListener( , (e) => { last = e.results.length - ; text = e.results[last][ ].transcript; .log( + e.results[ ][ ].confidence); }); 'result' let 1 let 0 console 'Confidence: ' 0 0 // We will use the Socket.IO here later… Real-Time Communication With Socket.IO is a library for real-time web applications. It enables real-time bidirectional communication between web clients and servers. We are going to use it to pass the result from the browser to the Node.js code, and then pass the response back to the browser. Socket.IO You may be wondering why are we not using simple HTTP or AJAX instead. You could send data to the server via POST. However, we are using WebSocket via Socket.IO because sockets are the best solution for bidirectional communication, especially when pushing an event from the server to the browser. With a continuous socket connection, we won’t need to reload the browser or keep sending an AJAX request at a frequent interval. Instantiate Socket.IO in script.js somewhere: socket = io(); const Then, insert this code where you are listening to the result event from SpeechRecognition: socket.emit( , text); 'chat message' Now, let’s go back to the Node.js code to receive this text and use AI to reply to the user. To build a quick conversational interface, we will use because it provides a free developer account and allows us to set up a small-talk system quickly using its web interface and Node.js library. API.AI Setting Up APIAI Use this for reference: APIAI_TOKEN =apiai( ); APIAI_SESSION_ID = ; var "5afc4bdf601046b39972ff3866cca392" const "chatbot-clvxfh" or get your own by visiting the official site( )and signing up. Getting Started Now we will use the server-side Socket.IO to receive the result from the browser. io.on( , {
  socket.on( , (text) => { apiaiReq = apiai.textRequest(text, { : APIAI_SESSION_ID
    });

    apiaiReq.on( , (response) => { aiText = response.result.fulfillment.speech;
      socket.emit( , aiText); });

    apiaiReq.on( , (error) => { .log(error);
    });

    apiaiReq.end();

  });
}); 'connection' ( ) function socket 'chat message' // Get a reply from API.AI let sessionId 'response' let 'bot reply' // Send the result back to the browser! 'error' console Once the connection is established and the message is received, use the API.AI APIs to retrieve a reply to the user’s message.When API.AI returns the result, use Socket.IO’s to send it back to the browser. socket.emit() Giving   Voice  to the bot With The SpeechSynthesis Interface Create a function to generate a synthetic voice. This time, we are using the SpeechSynthesis controller interface of the Web Speech API. The function takes a string as an argument and enables the browser to speak the text: { synth = .speechSynthesis; utterance = SpeechSynthesisUtterance();
  utterance.text = text;
  synth.speak(utterance);
} ( ) function synthVoice text const window const new In the function, first, create a reference to the API entry point, . You might notice that there is no prefixed property this time: This API is more widely supported than SpeechRecognition, and all browsers that support it have already dropped the prefix for SpeechSysthesis. window.speechSynthesis Then, create a new instance using its constructor, and set the text that will be synthesised when the utterance is spoken. You can set other , such as voice to choose the type of the voices that the browser and operating system should support. SpeechSynthesisUtterance() properties Finally, use the to let it speak! SpeechSynthesis.speak() Now, get the response from the server using Socket.IO again. Once the message is received, call the function. ; socket = io(); outputYou = .querySelector( ); outputBot = .querySelector( ); SpeechRecognition = .SpeechRecognition || .webkitSpeechRecognition; recognition = SpeechRecognition();

recognition.lang = ;
recognition.interimResults = ;
recognition.maxAlternatives = ; .querySelector( ).addEventListener( , () => {
  recognition.start();
});

recognition.addEventListener( , () => { .log( );
});

recognition.addEventListener( , (e) => { .log( ); last = e.results.length - ; text = e.results[last][ ].transcript;

  outputYou.textContent = text; .log( + e.results[ ][ ].confidence);

  socket.emit( , text);
});

recognition.addEventListener( , () => {
  recognition.stop();
});

recognition.addEventListener( , (e) => {
  outputBot.textContent = + e.error;
}); { synth = .speechSynthesis; utterance = SpeechSynthesisUtterance();
  utterance.text = text;
  synth.speak(utterance);
}

socket.on( , {
  synthVoice(replyText); (replyText == ) replyText = ;
  outputBot.textContent = replyText;
}); 'use strict' const const document '.output-you' const document '.output-bot' const window window const new 'en-US' false 1 document 'button' 'click' 'speechstart' console 'Speech has been detected.' 'result' console 'Result has been detected.' let 1 let 0 console 'Confidence: ' 0 0 'chat message' 'speechend' 'error' 'Error: ' ( ) function synthVoice text const window const new 'bot reply' ( ) function replyText if '' '(No answer...)' It's done.Run the following command in your terminal. $ node index.js And search in any supported browser. localhost:3000 You can refer to my for further help. repository References https://caniuse.com/#search=speech https://developer.mozilla.org/en-US/docs/Web/API/SpeechRecognition https://www.npmjs.com/package/apiai https://socket.io/ https://www.npmjs.com/package/dotenv-extended https://expressjs.com/

Creating A Chatbot Using Socket.io, API.AI and Web Speech API

In this article, we will be sharing steps to integrate chatbot into your app. All you need to build a sample for an android app is and dialogflow Android chatbot Dialogflow Kommunicate. Below is an example of developed in android using Dialogflow. We actually use this bot on our website. If you wish to see the bot live in action, head . Kommunicate Support Bot here The actionable rich messaging powered bot can reply based on whether users are on chat for general queries, technical queries or scheduling a demo. You can use your existing dialogflow bot or checkout to build a qualifying bot of your own. Download the Kommunicate Support Bot from and import into your Dialogflow account. bot samples here Step 1: Setup an account in Kommunicate This is fairly simple. You can get a free account in . Signup and navigate to the . Click on in Dialogflow block. Kommunicate Bot section Settings Upload your Dialogflow provided client keys. In case you are using Dialogflow V1, you can copy paste your client and dev tokens. Though, we recommend using Dialogflow V2 for the latest capabilities. Step 2: Install Dialogflow integrated Android Chatbot SDK into your app Add Android SDK to your app Installing Kommunicate in your Android app is easy and fast. Kommunicate SDK comes with pre-configured dialogflow integration. Add the following in your app build.gradle dependency: Installation implementation 'io.kommunicate:kommunicate:1.6.3' **Initialize SDK**After the Gradle sync has finished with kommunicate dependency, you can initialize the SDK by calling the below method: Kommunicate.init(context, Your-APP-Key); You can get the Application Key by signing up on Kommunicate Dashboard.For full documentation, refer . here Sample Android app with Dialogflow Chatbot Here is a sample android app which has dialogflow chatbot integrated. and run it in android studio. Download Step 3: Launch Android chat app with Dialogflow integrated chatbot Now, you can send payload to dialogflow through chat screen and get text response from Dialogflow Agent.Kommunicate provides a ready to use Chat UI so only launching the chat screen is required in this step. Here are the instructions for launching the chat with Dialogflow bot: List<String> agentList = new ArrayList();agentList.add("agent1@yourdomain.com"); //add your agentID List<String> botList = new ArrayList();botList.add("bot1"); //enter your integrated bot Ids Kommunicate.launchSingleChat(context, "Support", Kommunicate.getVisitor(), false, true, agentList, botList, new KmCallback(){@Overridepublic void onSuccess(Object message) {Log.d(context, "ChatLaunch", "Success : " + message);} @Overridepublic void onFailure(Object error) {Log.d(context, "ChatLaunch", "Failure : " + error);}}); That’s all! Run the Android app and chat with the Dialogflow bot. You can easily integrate Dialogflow in Android apps in a few simple steps. In case you need more information, you can check out the Kommunicate documentation. Dialogflow Android SDK Dialogflow provides Android Client SDK that makes it easy to integrate speech recognition with API.AI natural language processing API on Android devices. If you are looking to develop your own chat implementation and directly integrate dialogflow into your android app without kommunicate SDK, then integrate with the following SDK. Github — Dialogflow Android Client SDK Read more about dialogflow and bot integration here: Integrate Dialogflow (Api.ai) Bot into Website Beginner’s Guide to Creating Chatbots Using Dialogflow This article is originally published . here

Build Android Chatbot with Dialogflow (API.ai)

(formerly ) gives users new ways to interact with your bot by building engaging voice and text-based conversational interfaces powered by . DialogFlow API.AI AI offers many in different programming languages: DialogFlow SDKs But unfortunately, there’s no for SDK Golang But dont be sad, I made an to integrate with : SDK DialogFlow Golang This library allows integrating agents from the natural language processing service with your application. DialogFlow Golang Issue the following command to install the library: go get github.com/mlabouardy/dialogflow-go-client The example below, display list of entities: Note: for more details about the available methods, check the project . Github repository For a real world example on how to use this library, check my , on how to create a in to show list of movies playing in cinema, and tv shows airing on TV: previous tutorial Messenger Bot Golang

DialogFlow (API.AI) Golang SDK

84 Stories To Learn About Chatbot

148 Stories To Learn About Chatbots

Let's learn about via these 46 free stories. They are ordered by most time reading created on HackerNoon. Visit the to find the most read stories about any technology. Chatbot Development /Learn Repo 1. What I learned from building a chat project with sockets.io and React Well, after some I did some search on Google, I found an article with a developer who had the same issue. One and the awarded response was to use socket. 2. 8 of the Best AI Chatbots for 2023 Thanks to artificial intelligence and machine learning, chatbots are becoming a practical tool in the business world. This is good news for many companies, as chatbots can increase engagement, revenue and ROI. The potential of artificial intelligence is there to be harnessed, and AI-powered chatbots are examples of the effective usage of the technology. However, choosing a chatbot can be overwhelming. Let's take a look at the most popular AI chatbots currently on the market. 3. My Top 4 ChatGPT/AI Chatbot Tools This tool has replaced Google for me... 4. How we built ToDoBot for Slack in 3 days Technically, it was four days, but we were working on it in between taking customer calls and fixing OneBar bugs so, let’s call it three ;) 5. Develop Chatbots for Learning Reinforcement Chatbots are a powerful way to teach and learn, and this course shows you how to build them from scratch. 6. 5 Common Use Cases of a WhatsApp Chatbot A WhatsApp bot is an automated conversational tool that you integrate on WhatsApp using WhatsApp Business API. Read our article about uses of a WhatsApp chatbot 7. 6 Chatbot Mistakes that Scare Your Customers Away Six unforgivable mistakes that scare off your customers and prospects? The Smart Tribune team answers you. 8. Bots + Legaltech = Meet AILIRA Ailira (www.ailira.com) the ”artificially intelligent legal information research assistant”, is an AI chatbot that uses natural language processing. The chatbot has been designed to understand and process sophisticated technical legal questions & search quickly. Ailira was created by Adrian Cartland, the founder of Cartland Tech and the law firm without lawyers. 9. Sea of Transformation: Chatbots in The Logistics Industry The usage of the new age customer support technology bots, popularly known as Chatbots is on the rise. Researches show that more than 80% of the customer communication that is done on websites or mobile apps are done through chatbots. Chatbots are highly valuable for the companies because they can work round the clock, are easy to use and do not make any kind of errors. 10. MLOps & Industrial AI Are Progressing Quickly and Are Unstoppable The continuous evolution in DevOps with the combination of AI and ML for corporate application development is a solid reason for industry transformation. 11. How to Write a Perfect Chatbot Script Writing a script for a chatbot is a challenging process that requires skills. This article discusses how to write an effective chatbot script and gives tips. 12. Top Chatbot Trends That Will Dominate Businesses in 2023 Chatbots are a type of artificial intelligence that is programmed to simulate human communication. They are able to understand the context of a conversation and provide answers in a natural-sounding way. 13. Drive Success with Conversational Marketing: The Feedback-Oriented Approach Conversational marketing can be a solution to achieve faster response times. In this guide, we discuss how to develop effective chatbot applications. 14. Technologies Behind No-code & Low-Code Solutions and How to Build Your Own Let’s find out how no-code / low-code platforms are built and what it takes to create your own solution. We’ll focus on the development approaches, architecture [15. New Way for Business Optimisation is Out Now: Rake System and Their Success Story](https://hackernoon.com/new-way-for-business-optimisation-is-out-now-rake-system-and-their-success-story-v8vy325u) The Rake system understands and manages client requests related to company services. Regardless of the requests: text, voice - Rake’s chatbots understand and process all of them using artificial intelligence. The chatbot has been designed for W5Golf, and is the company that provides customer experience optimisation solutions and helps develop customer experience strategies that deliver results. The company’s solution helps to strengthen relationships with your customers by providing a system that optimises relevant engagements and improved services. 16. Create A Voice Enabled Chatbot [A How To Guide] The advent of AI has made voice-enabled chatbots and voice assistants part of our lives. Imagine the likes of Siris and Google Assistants for your phones, Alexa and Google Home for your house. These aforementioned systems are nothing but voice-enabled chatbots. 17. How Chatbots Are Helping The Fight Against Covid-19 With the recent surge in the number of coronavirus cases and more countries joining those already in self-imposed-quarantines and lockdowns, people have been getting understandably anxious. There has been a surge in the Google Trends for coronavirus related search terms. 18. Chatbots: Yay or Nay? Why and Why Not? This Slack discussion by Sadia Mehmood, Alfredo de Candia, Klein, , Golda Velez, Linh Smooke, David Smooke, Shahmeer Khan and Sidra occurred in slogging's official #general channel, and has been edited for readability. 19. Mobile Application Development Trends In 2020 Technology is changing our way of life. Mobile applications have a particular impact on this. Some facilitate daily activities (reminders, calling an ambulance or simply ordering coffee), while others simply help to kill time (if there is free time at all). But without all of them, it’s hard to imagine today's existence. 20. ChatGPT: What It's Teaching to a +25 Year Senior Programmer To be a decent software engineer, we must be experts at learning, and ChatGPT is an amazing teacher. Not just for juniors. 21. Helpful Tips and Fundamentals About Creating a Better Chatbot Strategy Source: Pixabay 22. 6 Chatbot Builders You Can Use to Emulate Facebook's Messenger This list also includes Api.ai, Chatfuel, the IBM Watson conversation service, and more. Discover how easy it is to build your own chatbot today. 23. Where are the Chatbots and What is the Progress and Limitation of Virtual Assistants [2020 Edition] Cat's out of the bag: it may have been a long while since you’ve last conversed with a human customer service agent. More and more companies have turned to digital assistants to address the needs of customer inquiries. With messaging being the preferred method of communication, chatbots have taken over online facing services, due to their simplicity, affordability, and accuracy. 24. Discussing The Applications of AI Chatbots in Healthcare at the World Economic Forum The World Economic Forum is mostly known for its highly anticipated annual meeting in Davos, Switzerland — a scene of global intrigue and a convergence point for the planet’s most influential politicians, investors, activists, CEOs, and economists. 25. How do Chat Apps improve customer engagement in Businesses? Collaboration and communication in the digital age have come a long way as it is not restricted to emails and messages anymore. Having a platform for the stakeholders involved in a business that enables them to communicate with each other will be a strong driving force. The flawless communication that can be switched to multiple devices without any interruption is an added convenience. 26. Exploring The World of Chatbots What if I told you the 1st time people thought of machines replicating human conversations was almost 70 years ago! 27. The Magic of Conversational AI: 8 Ways Chatbots are Helping Businesses Have you heard stories about chatbots failing to deliver results? Well, we created a list of the 8 most important chatbot benefits that will prove the opposite. 28. How Chatbots Can Help Improve Your Customer Experience Chatbots or customized software can converse with humans through a chat interface. Be it a brand’s website or a mobile app, chatbots can be integrated anywhere to gather useful information and facilitate sales. Platforms like Skype, Facebook Messenger, and Whats App also use chatbots for building reputation and improving customer experience. 29. How To Build Chatbot Project Using Python Chatbots are extremely helpful for business organizations and also the customers. The majority of people prefer to talk directly from a chatbox instead of calling service centers. Facebook released data that proved the value of bots. More than 2 billion messages are sent between people and companies monthly. The HubSpot research tells that 71% of the people want to get customer support from messaging apps. It is a quick way to get their problems solved so chatbots have a bright future in organizations. 30. The 6 Best Platforms To Create Chatbots Without Additional Programming Today I want to share a small review of simple platforms for creating bots without any knowledge of programming languages 31. How To Create a ChatBot on Facebook Messenger Using Flask and Heroku Basic Facebook bot (will chat with you using random phrases you set up) using Flask and Python. You can start with this bot as a basic app to build something more difficult and useful. 32. Chat API Comparison: Sendbird vs TalkJS vs Stream vs PubNub vs Cometchat Choosing the right chat API requires a ton of research. This is a quick guide so you can compare the most well-known chat APIs. 33. Twilio: How to Connect with Existing Voice Assistant Today's post serves the purpose of explaining Twilio's recent bidirectional streaming feature, the very feature which made it possible to receive the call audio while still being able to send audio for playback asynchronously. 34. Black Mirror's 'Be Right Back' in Real Life: Clone Yourself as a Chatbot Replika AI has created a platform where anyone, including people with zero knowledge of machine learning, can create and train a chatbot of their own. 35. Chatbot vs Virtual Assistants: The 4 Key Differences Chatbots vs Virtual Assistants: To know the difference between them check out this space and look for the video in it. 4 major points have discussed here. 36. Enterprise Chatbot: Do You Really Need It? This Will Help You Decide 37. Chatbots: The end of the hype era or a bright new dawn? We live in an age of great innovation and technological marvel. Artificial intelligence and machine-learning technologies are developing at an insanely fast pace, which resulted in the slightly increased performance of digital applications. A few years ago, chatbots formed a new, highly popular trend and have consistently been regarded as the best potential help for the labor market, slightly reducing the need for staff workload. The chatbot sector is now growing fast, and the total market is predicted to reach around 1.25 billion US dollars in 2025, a significant increase from the market size in 2016, which stood at $190.8 million. While becoming more sophisticated over the years, AI-driven bots are being used more often in various fields: marketing, healthcare, CRM [Customer Relationship Management]. This hypetrain resulted in more efficient solutions and brighter light at the end of the tunnel. 38. 10 Best AI Chatbot Builder for Your Business in 2022 Chatbots are on a rise and are rapidly becoming one of the most important assets for businesses these days. From SMBs to Fortune 500 companies, almost every business is investing in chatbots to establish stronger communication and offer the best customer support service. 39. How To Make A Chatbot From Scratch How To Make A Great Chatbot From Scratch Expert tips to create a highly functional chatbot. 40. Best Chatbot Development Companies For SME's and Startups in India, USA| Hire Best Chatbot Developer Which is the best Chatbot development company in India & the United States? This is the most confusing question for modern developers and business owners.  But, not all chatbot companies are fully perfect in terms of quality.This is what creates an uproar among people to find the best when Chatbot is already a hot topic among us. 41. How to Build Basic Chatbot Without Coding and Deploy to Websites Build best automated AI chat bot using Google Dialog flow 42. How Chatbot Development Can Make Technology More Accessible? Disclosure: I work at Value Coders, a company that creates Chatbot Solutions. 43. Eleven Trending AI Chatbot Platforms The artificial intelligence of the chatbots is revolutionizing the customer experience. They can provide useful information to customers when they need it. Hence, a number of companies that use AI Chatbots have grown exponentially. It provides them with proactive assistance to their customers. 44. Create a NodeJS FAQ Chatbot - A Step-by-Step Guide A FAQ Chatbot have the purpose of answering the most common questions asked by users. We will build one using Bard and some of its funtionalities, that will help us to build a smarter chatbot. 45. 11 Of The Best Artificial Intelligence Enterprise Chatbots in 2022 Chatbots for businesses help them engage their website visitors and convert them into potential customers. 46. How to Build a ChatOps-Bot with Slack and Kubernetes ChatOps allows  you to manage your DevOps tasks using chat based interfaces. Learn how to build a simple bot to control a Kubernetes cluster using Slack. Thank you for checking out the 46 most read stories about Chatbot Development on HackerNoon. to find the most read stories about any technology. Visit the /Learn Repo

46 Stories To Learn About Chatbot Development

Disclaimer: I love no-code tools, I have been using them for about 7 years, and I believe that no-code solutions can really help you build new products and test out new ideas quicker and cheaper. For a very long time, I’ve been planning to write an opus magnum on using no-code solutions to build new products, but all the drafts I’ve had were becoming so lengthy, they’d be considered a novel by most. So let me give you a short intro to no-code tools for Product Managers instead. What is no-code? ‘No-code’ is a term that’s commonly used for building software without actually, you know, coding. This means that the no-code tools (at least in theory) can be used without any knowledge of programming languages, software architecture, etc, and you’ll still get a decent result. I’ve seen the term being used in many different contexts, from the horrific (people online saying that Salesforce is the most powerful no-code ecosystem) to pretty shady (online schools promising you a wild career and lucrative wages if you complete their no-code programme). No-code tools are just tools. Same as with AI tools like ChatGPT: you can use them to make your work less stressful and more impactful, but they won’t do your job for you and just knowing how to create a database with a working API in Airtable will not land you a job at FAANG. My favorite use case for no-code solutions is quickly mocking up working solutions for new ideas me or my team may have, closely followed by building internal tools. Most of these ideas and tasks don’t really require anything special. Of course, not all ideas can be tested with off-the-shelf technology. For example, it’s highly unlikely that some existing no-code solutions would have been able to help me test the efficiency of eye-tracking-based reading analytics. But even advanced projects that need a lot of research and development would benefit greatly from the dev teams not having to create all the boring databases and admin panels for every single test. And it looks like the more high-tech your project is nowadays, the more data you’ll need to collect and manage. Airtable Almost all the projects I have worked on in my life involve in some way. You can do almost anything with Airtable because in its essence it is an incredibly user-friendly database with auto-generated API, built-in integrations (including Gmail) and a great ecosystem of projects that work well with it. Airtable Example use cases Airtable is pushing itself as more of a project-managing solution, with most popular templates focused on PM and Marketing tasks, but that would be underselling itself. My favourite uses for Airtable would be these two: Crowdsourcing Imagine you’re collecting thousands of reading sessions from hundreds of participants for, say, a reading study. What would you normally use? An Excel table? Google Sheets? Google Drive with folders that are impossible to navigate? Since Airtable’s tables explicitly are composed of entities, it’s the best solution for keeping data with simple or complex relations and then actually working with it. In this example we have a simple structure: Respondents, who have Name (Relation) Personality survey they have completed (Relation) List of their reading sessions (Lookup field) List of reading materials mentioned in their reading sessions Personality surveys, consisting of: (Relation) Link to the Respondent that has completed them As many questions as you’d like to ask them Reading materials Name (Attachment) An EPUB file with this reading material (Relation) List of all reading sessions involving this Reading material (Lookup field) List of all Respondents that have read this Reading material (via Reading sessions) Reading sessions (Relation) The respondent that read it (Relation) Reading material that was read Date and time it was started Duration in minutes Try building something like this in Google Sheets, it won’t be easy. Building and maintaining the initial structure would take mere minutes, and you’ll be able to build all the extras on top, like: Easy-to-use data entry forms (less powerful than Google Forms, but built-in) Millions of views and filters for all sorts of purposes Airtable Interfaces (see below) Gmail integration that allows you to send confirmation emails and communicate in other ways One caveat: Airtable is not a data storage solution, so collecting stuff like videos or other larger files won’t really work: even with the premium plans you only get 20 Gb of storage per database. If you want to do that, you’ll either need to ask your dev team to build a custom submission form and some tiny backend that will upload files to S3, or use an Airtable clone like . However, they have their own limitations and integrations won’t be as no-code as I prefer them to be. Baserow Backend for MVP projects What if you have a new product idea but your backend team is super busy? Airtable lets you build your own perfectly functional backend! See, one of Airtable’s features (and in my view, its greatest) is the built-in API generation. This means that for all the tables, fields and records you create in Airtable, there is an API that allows a developer (this part is definitely not no-code) to access them. You can build a fully functional MVP backend in the same amount of time it would take to write a Jira task. Let’s take the same database from the Crowdsourcing scenario and see if we can build an app that would display a list of these Reading materials, download them and let its users read them. Airtable’s API (counterintuitively located away from the databases at ) lets you access this: api.airtable.com Like this: It provides a really well-documented API that uses actual data as examples and is super intuitive to use. This makes trying out new ideas that require storing some data on the backend much easier. You still will need to create a proper backend later on, but that will only have to happen once you’ve proven your idea actually works. Airtable Interfaces While I’m a big fan of the way Airtable looks and functions, I’ve encountered quite a few people that were absolutely overwhelmed by Airtable’s “it’s-a-table-but-not-quite-a-table” look. I guess this is why they’ve introduced Interfaces in 2022. It’s an absolutely fantastic feature that allows you to build great-looking views for your data. Unfortunately, they cannot be shared publicly and can only be used for internal tools. However, there are ways to match some of their functionality (and some more) with miniExtensions. I’ll probably write a separate article on that later. Connecting tools and services At some point in your no-code journey, you’ll want to connect the new stuff to your old stuff. You may want to send new Airtable entries to Mailchimp, or transform new files in a Google Drive folder into Airtable entities. There is one tool to do this that I like and one that I absolutely hate. The one I like: Make (formerly Integromat) lets you build all your connections visually, move them around, change the order of the steps and generally has a pretty good UI. This is probably the best tool to automate all the weird Google Drive to Airtable to Mailchimp dances if you have to make them. Make The one I hate: Zapier Until recently, once you created a flow in , that was it. Need to make changes? Want to reorder the actions? Tough luck, you have to go back to the last step before the action that’s not quite there and redo everything. They changed this at some point, but I’m still not touching Zapier with a 10-foot pole. Zapier Building websites There are so many web-building tools out there that claim to be the no-code solution to all life’s problems, I’ve lost count. But out of all the tools, only one can be easily used by a Product Manager with no design experience. Super: transform Notion pages into a website lets you transform a Notion page and all its child pages into an auto-updating website. It’s perfect for anything public-facing that doesn’t need to look very good, like developer documentation, support portals, terms and conditions and many other applications I can’t even think of. Super There are some competitors, including , but I liked Super the most. Simple.ink Creating internal tools Warning: this is going to be slightly less no-code than the rest of the sections, but will give you great powers. If you have an API or an existing database, but not a good UI to go with it, you can use no-code tools to access these APIs and provide ways to send or receive stuff over them with a pretty nice UX. The only no-code tool for this that I truly liked is . It allows you to build dashboards and CRUD (create, read, update, delete) apps with a WYSIWYG drag-and-drop interface. You need to know how APIs or SQL requests work, but it’s still much less time-consuming than having to develop stuff. Retool Further reading If you want to learn more, I’m a big fan of . It’s a lot more visual and fun than this overview, and while some time has passed since it was first published in 2020, most of the core tools remain the same. Vas3k’s article on No-code I hope this overview has inspired you to try no-code tools if you’ve never used them, taught you about a couple new approaches if you have, or simple hasn’t annoyed you if you consider yourself an expert in no-code solutions. If you are annoyed that your tool hasn’t been listed here, join the conversation in the comments below!

Best No-code Tools for Product Managers

Spoken Language Understanding SLU and Natural Language Understanding NLU aim to help machines understand human language. The main difference is the input data type. SLU deals with understanding speech, whereas NLU deals with understanding text. NLU is a part of SLU whether it’s trained independently or not. Research on NLU started in the 1960s: ’s Ph.D. dissertation Weizenbaum’s , a mock psychotherapist chatbot, and Winograd’s are the pioneer works in this space. SLU’s popularity started with the recent advances in speech recognition powered by deep learning. The query “spoken language” returns over 1000 studies on both and research publications websites. Bobrow ELIZA SHRDLU Amazon Microsoft Conventional SLU Approach The conventional SLU processes utterances in two steps - Speech-to-Text (STT) first, then NLU. Once STT transcribes the speech to text, NLU extracts meaning by processing the transcribed text. The performance relies on independently trained STT and NLU modules. If STT returns erroneous output, then it leads to incorrect NLU predictions. Hence machines cannot capture what humans say. Many voice applications, including voice assistants - Alexa, Siri, and Google use this approach. End-to-End SLU Approach The modern SLU uses an end-to-end model instead of two distinct components. Developers train STT and NLU jointly, resulting in higher accuracy. Picovoice calls this as it infers users’ intents directly from speech. Amazon calls it - Fusing ASR and NLU for SLU. Speech-to-Intent FANS Conventional SLU Approach vs. End-to-End SLU Approach The answer is It depends on the availability of corpora and information. If available, then the answer is modern end-to-end SLU. If not, then the conventional SLU. Text-based understanding (NLU) has been around longer than speech-based understanding (SLU). Thus, it has richer datasets. “it depends.” For domain-specific applications such as IVR systems, menu navigation on a website, or ordering food at a QSR, the modern end-to-end SLU is preferable. Nobody would discuss the meaning of life with a voice assistant while ordering a hamburger. For open-domain use cases such as voice assistants like Alexa, conventional -cascading SLU works better given the variety of topics they cover. One can discuss the meaning of life with Alexa - although there are better options. Top SLU and NLU engines in the market Free and Open-source SLU and NLU Engines: : Rasa is an open-source NLU engine that processes text inputs. The core software is free, and Rasa offers paid support and consulting services. Anyone can choose a speech-to-text service, and run Rasa on transcribed text. Rasa : Snips is an open-source SLU engine that uses the conventional method. Snips no longer maintains it after being acquired by Sonos. Yet the repo is still available on GitHub and used by developers. Snips : Wit.ai is a free platform and now requires a Facebook account after being acquired by Facebook. If one doesn’t (want to) have a Facebook account or deletes it, then they cannot use Wit. Wit.ai Top paid SLU and NLU Engines: : Google, after the API.ai acquisition, named it Dialogflow and offers both chatbot and voicebot tools under the same name. It uses the conventional approach. Dialogflow records and sends voice data to Google’s servers for transcription and then processes transcribed text. It charges based on usage. Dialogflow : Amazon’s Lex is an AWS offering. Like Dialogflow, Lex offers text and voice capabilities, uses the conventional approach, and transcribes speech and understanding separately in its cloud. It charges based on usage. Lex : Picovoice’s Rhino is an SLU engine that uses the end-to-end approach and infers intents and intent details . Rhino is voice-based and does not support text-based services. It charges based on the number of users and offers unlimited interactions per user. Rhino directly from speech

Stories, News & Mentions about API7AI

Api7ai’s Stories on HackerNoon