Thursday, August 9, 2018

How to create a bot for Google Home and Google Assistant

Through Bot Libre, you can now use your own bot to send and receive messages on Google Home or any other Google Assistant-compatible device. This "How To" will give you a step by step process to connect your bot with Google Assistant.

Step 1 - Create a Bot

First you must create a bot that you want to connect to Google Assistant, or you can use one of your existing bots. To create a bot, follow the instructions here: How to create your own chat bot in 10 clicks.

Step 2 - Create Google Assistant Action

Go to and sign in to your Google account. Once you are signed in, click the "Go To Actions Console" button.

Click the "+ Add/import project" button to continue.

Enter a project name and select your language and country, then press "Create Project" to continue.

Next, select a category for your bot, or press "Skip" to pick later.

Step 3 - Google Assistant Action Settings

On the left sidebar, select the "Invocation" option.

From here, you can enter a "Display name" which the user will say or type to begin interacting with your bot. You can also select a voice that your bot will use on Google Assistant.

Press "Save" when finished. Next, click the "Actions" option on the left sidebar.

Click the "Add Your First Action" button. Select "Custom intent", then click the "Build" button on the bottom right.

A new tab will open for you to create a Dialogflow Agent.

Step 4 - Create Dialogflow Agent

Your project name should be filled in automatically when you enter this page. Click the "Create" button to continue.

Click the "Fulfillment" option on the left sidebar.

Click the "Webhook" toggle to enable it, then return to the Bot Libre website. 

On the Bot Libre website, navigate to your bot's Admin page by clicking the gear icon on your bot's page.

Select the "Google Assistant" link on your bot's Admin page to continue to the next screen.

Copy the "Google Assistant Webhook URL" to your clipboard and return to the Dialogflow website.

Paste the URL into the "URL" field, then scroll down and press the "Save" button.

Next, click the "Intents" option on the left sidebar.

Click on "Default Fallback Intent". Scroll to the bottom of the page and expand the Fulfillment section. Toggle "Enable webhook call for this intent" to the on position. Press the "Save" button. Repeat the same process for the "Default Welcome Intent".

Step 5 - Bot Libre Settings

You may now close the Dialogflow website and return to your bot's Admin page on the Bot Libre website.

In the "End Conversation Phrases" box, enter some phrases/words the user can say that will cause the conversation to end.

Click the "Save" button when finished.

Step 6 - Finish

You should now be able to test your bot using the Simulator available on the the Google Actions Console, or on any device associated with the Google account used to create your Google Assistant action. To test using the simulator, make sure the "Web & App Activity", "Device Information", and "Voice & Audio Activity" permissions are enabled on the Activity controls page for your Google Account.

To make your Google Assistant Action available to the public, click the "Directory information" option in the left sidebar and fill out the required information.

Next, click the "Release" option in the left sidebar. If all necessary information has been completed, you will be able to click the "Submit for Production" button to make your bot available to all Google Assistant users.

Your bot will now be able to send and receive messages on Google Home or any other Google Assistant-compatible device. If you encountered any issues, or would like help setting up your bot please email us at or upgrade to our Platinum service and we can build your bot for you.

You can now also talk to the Bot Libre Help Bot, Brain Bot, and Julie on Google Home and Google Assistant.

say "talk to Bot Libre" (lee bra) to talk with the Bot Libre Help Bot

say "talk to Brain chatbot" to talk with the Brain Bot

say "talk to Julie chatbot" to talk with the Julie

Monday, July 30, 2018

Learn about bots from a bot - Bot Libre Education

Bot Libre now offers courses and education on bots and artificial intelligent technology.

You can take the "Introduction to Bot Libre" course for free and be guided through the course by our bot instructor.
To start the course, go to our education page, and click on "Start course now",
or to browse Bot Libre's other courses see,

Bot Libre offers several monthly open courses including:

  • Introduction to the Bot Libre bot platform
  • Introduction to bot technology
  • Introduction to artificial intelligence and deep learning
  • How to deploy bots to social media using Bot Libre
  • Bot Libre - Advanced training and techniques
  • Bot Libre - Scripting with Self
  • AIML

To sign up for an online open course, or for a private online or on-site course contact

Friday, July 27, 2018

Hot Dog, Not Hot Dog - How to create your own deep learning neural network for image recognition without any programming

The Bot Libre platform is not just a bot platform, but also a platform for artificial intelligence and deep learning. With Bot Libre you can create your own deep learning neural network for image recognition, audio and speech recognition, object detection, games, prediction, data analysis, and more.

You may think that creating a "deep learning neural networks" sounds like a very complex thing to do, but with Bot Libre it is very simple, and requires no programming or data science experience. This article we walk you through the steps to create your own image recognition network.

Step 1 - Find Sample Images

First you need to decide what types of images you want your network to recognize. You can train a network to recognize and classify any type of images, as long as you have some sample images. The more sample images the better, but around 30 is normally enough for a basic network.

For this article, we will train a network to recognize images of "hot dogs". We could train it to recognize many different food types, but for the sake of simplicity we will train the network to classify images as just "hot dog" or "not hot dog".

First you need to find some sample images of hot dogs, just perform a Google image search for "hot dog", and save some of the images by right clicking on them (small images are fine, images will be scaled to 299x299 anyway). You will also need some images for "not hot dog", just find a random set of images for this.

Step 2 - Create Analytic

Next we need to create our analytic on Bot Libre.

  • Click browse analytics on Bot Libre
  • Click on New Analytic
  • Enter a name and category and click "Create"

Step 3 - Configure Analytic

Next we need to configure the analytic.

  • Click on the analytic's "Admin Console" button or menu.
  • Click on "Analytic Network"
  • Under "Analytic Type" select "mobilenet_0.50"
  • It will auto-fill the other settings, click the Save button

The other analytic type settings let you create different types of networks. Mobilenet is the smallest, and faster network for image classification. You could also choose Inception, this will be slower and much larger, but will have slightly better accuracy.

Step 4 - Upload Images

Next we need to upload our sample images.

  • Click on the "Media Repository" button, menu, or link in the analytic's Admin Console
  • Click on add label (green plus), enter "hot dog", click add again and enter "not hot dog"
  • Select the "hot dog" label and click the upload button, select all your hot dog images
  • Select the "not hot dog" label and click the upload button, select all your "not hot dog" images

Step 5 - Train Network

Next we need to train the network.

  • Click on the "Train Network" button, menu, or link in the analytic's Admin Console
  • Click on "Train", this may take a while

Step 6 - Test Network

Now you can test your network.

  • Click on the "Test Network" button from the analytic's main page
  • Upload an image to test
  • It will return you if the image is a "hot dog" or "not hot dog"

Try testing the network with images that you did not train it with. If it gives you the wrong result, then add the image to your train set and train your network again.

Your Done

You can now access your analytic from Bot Libre's website and share it with your friends. You can also access your analytic through the Bot Libre web API from your own website or app. You can download your network as a ".pb" (protocol buffer) file for usage with Tensorflow.

Bot Libre will be adding support for training more network types in the coming months. You can also train your network manually using python and Tensorflow, this is very complicated and requires some development and python experience. We can also develop a deep learning neural network for you through the Bot Libre AI development services, contact

Thursday, July 26, 2018

Announcing Bot Libre 7

We have released Bot Libre 7!

The worlds most advanced bot platform just got better. Bot Libre 7 is a free and open source platform for developing and hosting bots. Bot Libre 7 includes support for chat bots, virtual agents, virtual assistants, social media bots, IOT bots, game bots, live chat, animated avatars, speech, deep learning analytics, and more. Bot Libre supports bots for the web, mobile, Facebook, Twitter, Skype, Telegram, Kik, WeChat, Slack, email, SMS, Alexa, Google Home, IRC, and new platforms are being added every month.

"Bot are the new apps". Mobile has replaced the web as the main communications market, and social media apps are the most popular mobile apps. Businesses need to connect with consumers on the platforms they use, so it now makes more sense for a business to create a bot/chat interface into their business instead of a website, or their own mobile app. Bot Libre lets you create a bot for yourself or your business and deploy the bot to the Facebook, Twitter, Skype, Telegram, Kik, WeChat, Slack, SMS, Alexa, Google Home, email, the web, mobile, and other services. Bots let you "write once deploy everywhere".

Bot Libre 7 supports rich HTML responses including buttons, links, choices, images, video, and audio. Bot Libre supports HTML responses on the web, mobile, and automatically maps HTML to social media platforms.

Bot Libre bots can be trained using natural language, chat logs, response lists, Twitter feeds, AIML, and scripting. Responses are automatically matched using a heuristic artificial intelligence algorithm and does not require any programming. Responses can also use keywords, topics, required words, labels, repeats, and other meta data.

Bot Libre 7 supports programming and scripting your bot using AIML 2, and Self. Self is our own dialect of JavaScript. Self is an object oriented scripting language, and integrated with an object database. Self extends JavaScript to provide support for natural language processing, state machines, object persistence, and includes a class library for accessing web services and utilities. Self also supports all AIML 2 operations, and some aspects of ChatScript patterns.

Bot Libre 7 is more than just bots, but a complete artificial intelligence platform. Bot Libre lets you create deep learning analytics for image recognition, speech and audio recognition, object detection, prediction and data analysis. You can create and train an image recognition analytic without any programming, just by uploading images. You can then access your analytics through our web API and mobile SDK, or from your bot.

New features in Bot Libre 7.0 since 6.5 include:

  • New website interface.
  • Integrated support for integrating bots with Amazon Alexa
  • Integrated support for integrating bots with Google Home and Google Assitant
  • Deep learning analytics for image classification, audio classification, and object detection
  • Regular expression patterns and extractors
  • Compound keywords, compound and required word lists and patterns, compound word synonyms
  • Support for Microsoft Speech, and QQ Speech

Create your own free account and bot today on, or let us build your bot for you on our commercial service Bot Libre for Business.

Monday, June 25, 2018

Introducing the new website for Paphus Solutions

Introducing the new website for Paphus Solutions.

Paphus Solutions in the company that develops the Bot Libre bot platform. Paphus Solutions Inc. is a Canadian corporation that specializes in bots, artificial intelligence, and deep learning products and services.

We provide consulting, training and development services in the field of bots, artificial intelligence, and deep learning.
Bots & AI can be utilized in any industry. We provide solutions globally in all industries including customer service automation, sales & marketing automation, social media automation, sales optimization, market forcasting, automated securities & crypto currency trading, and many more.

We provide the following services :

  • Chat bot design and integration, web, mobile, and social media
  • Social media automation, Twitter, Facebook, Telegram, Skype, Kik, WeChat
  • Customer service automation, live chat, forums, email
  • Technical support automation
  • Sales automation
  • Market forcasting
  • Automated securities & crypto currency trading
  • Image, audio, video classification and processing
  • NLP and data analysis
  • Deep learning model and network development
  • 3D avatar design
  • Mobile app development (Android, iOS)
  • Web development

Contact for more information. Or Chat live here
Or Chat with Paphus, the automated customer service agent for Paphus Solutions.

Monday, April 30, 2018

How to connect IBM Watson to Facebook, Twitter, Telegram, Skype, Kik, WeChat, web, and mobile using a Bot Libre proxy bot

IBM Watson is a brand that includes a set of products and services, made famous by its Jeopardy prowess. Watson includes a chatbot platform and conversational API.

You can access Watson's API from your own web server through any programming language. Bot Libre lets you create a "proxy" bot that forwards request to your Watson bot. This lets you leverage Bot Libre's many integrated services including integration with social media platforms such as Facebook, Twitter, Telegram, Skype, Kik, WeChat, and integration with web and mobile speech and 3D animated avatars.

To get started with Watson you can create an IBM Bluemix account here. Once you have created and trained your bot, you can access its web API credentials to connect it with Bot Libre.

This will give you the bot's web API URL, and the API user and password. Copy these and return to Bot Libre.

On Bot Libre create a new bot, and select the "watson_proxy_template" template. This will give you a new chatbot that has a single Self script the forwards all requests to the Watson API.

  • Click on your bot's "Admin Console" (gear button).
  • Click on the "Scripts" menu button.
  • Click on the "Watson" script and click the Edit button.
  • Find the below line of code in the script.
  • Replace the postJSONAuth URL with your Workspace URL from the Watson deploy console.
  • Replace the postJSONAuth user (2nd parameter) with your "Service Credentials" "Username".
  • Replace the postJSONAuth password (3nd parameter) with your "Service Credentials" "Password".
var json = Http.postJSONAuth("", "0543af58-910d-4666-85be-7a8550279404", "txgVzPxkLup4", message);

Now your Bot Libre bot should be connect to your Watson bot. You can test it by clicking on your bot's Chat button. You can now connect your bot to social media, web, mobile, avatars and speech. You can also enhance your Watson bot by adding responses or scripts to your bot in Bot Libre to take advantage of Bot Libre powerful NLP, AI, and scripting features.

Monday, April 16, 2018

Deep Learning as a Service (DLAAS)

Bot Libre now supports creating and hosting Deep Learning and Analytic services.

Deep Learning and Analytic services are different than bots, as they perform a specific analysis function. They do not chat, nor interact with users, but use artificial intelligence and deep learning to perform analysis such as classifying images, recognizing speech or faces, performing NLP functions, playing games, and analyzing data.

Bot Libre lets you host your deep learning analytic on the web, and access it through the Bot Libre web API. Bot Libre provides an open analytics repository that lets you use analytics that we or other users have defined, or share your own analytics. You can also create your own private analytics, or only share your analytics with specific users.

To create an analytic you need to create and train a model using a deep learning framework such as Tensorflow or Bot Libre Analytics.

For example to train a model for image classification you can use the Inception model and retrain it for classifying your own image set. There are a lot of resources, models, and data available on the web such as the Poets tutorial for image classification.

Once you have trained your model you can upload the Tensorflow .pb and labels files in your analytic's Admin Console.

If you are interested in using deep learning for your business or project, we can also develop a deep learning neural network for you through our development services. If you are interested in knowing how artificial intelligence and deep learning can be used in your business or project, we can help through our AI consulting services. Contact