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.