node-red-contrib-chatbot/nodes/chatbot-nlp-train.html

REDBot a Chat bot for a full featured chat bot for Telegram, Facebook Messenger and Slack. Almost no coding skills required

<script type="text/javascript">
  $.RedBot.registerType('chatbot-nlpjs-train', {
    category: $.RedBot.config.name,
    color: '#FFCC66',
    defaults: {
      name: {
        value: '',
        validate: $.RedBot.validate.nlpModel
      },
      debug: {
        value: false
      }
    },
    inputs: 1,
    outputs: 1,
    paletteLabel: 'NLP.js Train',
    icon: 'chatbot-listen-lexicon.png',
    label: function() {
      return 'NLP.js Train' + (this.name != null && this.name !== '' ? ' (' + this.name + ')' : ' (default)');
    }
  });
</script>

<script type="text/x-red" data-template-name="chatbot-nlpjs-train">
<div class="form-row">
  <label for="node-input-name"><i class="icon-tag"></i> Model Name</label>
  <input type="text" id="node-input-name" placeholder="Model name">
  <span class="redbot-form-hint">
    Leave blank if you don't need to use more than one NLP model in the chatbot. Only use letters and numbers, no spaces.
  </span>
</div>
<div class="form-row">
  <label for="node-input-debug">Debug</label>
  <input type="checkbox" value="true" id="node-input-debug">
  <span class="redbot-form-hint">
    Show debug information while training the model
  </span>
</div>
</script>
<script type="text/x-red" data-help-name="chatbot-nlpjs-train"><p>The <code>NLP.js nodes</code> uses <a href="https://github.com/axa-group/nlp.js">NLP.js</a> for Natural Language Processing.</p>
<p>In order to work it requires a properly trained model using <code>NLP.js Train</code>, <a href="https://www.notion.so/c91af0a6fde74dc5b575aa7230565ba8">NLPjs Intent node</a>  and <a href="https://www.notion.so/f73d1e0200804467b8f03e077584fb16">NLPjs Entity</a> . An <em>intent</em> is a string representation of the abstract meaning of the user sentence, it requires an arbitrary name (that will be likely used in a <a href="https://www.notion.so/4113636f565d4ff4af08bc61a644206b">Rules node</a>  to control the chatbot flow) and one or more utterances (a set of all different way of expressing the same actions).</p>
<p>An <em>entity</em> is the variable part of the utterance, it can be detected and stored in a context variable and used later in the flow. Some entities are predefined (like numbers, dates, etc) while other can be defined, for example a chatbot that is able to understand a sentence like <code>I want to buy 3 apples</code> should have an intent with the utterance <code>I want to by %number% %fruit%</code>. In this example the entity <em>number</em> is built-it, while the entity <em>fruit</em> should be defined with the <a href="https://www.notion.so/f73d1e0200804467b8f03e077584fb16">NLPjs Entity</a>  and should include all kind of fruits with optional aliases (apple, orange, grape, etc).</p>
<p>All this intents and entities nodes must be chained to a <code>NLP.js Train</code> node which creates a precompiled model used to detect the sentences, it’s generally stored in a <em>JSON</em> file using the <a href="https://www.notion.so/4f99d9bfe1ee4683acbee70c02eb24d2">NLPjs Save</a>  and loaded when the flow is started (the train process could be long and can be avoided if the intents and entities are not changed).</p>
<p>The typical use in a flow is</p>
<p><img src="https://raw.githubusercontent.com/guidone/node-red-contrib-chatbot/master/docs/images/nlp-train.png" alt="Train model"></p>
<p>The scenario is a chatbot able to understand sentences like <em>“switch on the lights in the kitchen”</em>, <em>“turn on lights in dining room”</em>. The first <code>Inject node</code> is used to train the NLP.js node and store locally the trained model every time an intent or entity is changed. The second <code>Inject node</code> runs automatically at startup and loads the trained model.</p>
<p>The <a href="https://www.notion.so/c91af0a6fde74dc5b575aa7230565ba8">NLPjs Intent node</a>  looks like</p>
<p><img src="https://raw.githubusercontent.com/guidone/node-red-contrib-chatbot/master/docs/images/nlp-intent.png" alt=""></p>
<p>Where the <code>%room%</code> placeholder is an entity defined in the <code>NLP.js Entity node</code>, if there’s a match the <a href="https://www.notion.so/bbc3deb2d39a4b338fc6515eee337cd4">NLPjs Process</a>  will return the intent (in this case <code>switch.on</code>) and the extract variables for each placeholder (like <code>%room%</code>).</p>
<p><img src="https://raw.githubusercontent.com/guidone/node-red-contrib-chatbot/master/docs/images/nlp-entity.png" alt=""></p>
<p>When the model is trained and loaded into the flow, <code>NLP.js Process</code> can be used to analyse the sentences from the users</p>
<p><img src="https://raw.githubusercontent.com/guidone/node-red-contrib-chatbot/master/docs/images/nlp-process.png" alt="Train model"></p>
<p>If, for example, the user writes <em>“Turn on lights in the kitchen”</em>, the output of the <a href="https://www.notion.so/bbc3deb2d39a4b338fc6515eee337cd4">NLPjs Process</a>  will be</p>
<pre><code class="language-javascript">{  
    payload: {    
        type: &#39;intent,    
        intent: &#39;switch.on&#39;,    
        isFallback: false,      
        score: 0.7,    
        language: &#39;en&#39;,    
        variables: {    
            room: &#39;kitchen&#39;   
        } 
    }
}
</code></pre>
<p>The output of the <a href="https://www.notion.so/bbc3deb2d39a4b338fc6515eee337cd4">NLPjs Process</a>  can be chained directly to a <a href="https://www.notion.so/24a646bff58b4edfb249f1d27384230f">Context node</a>  to store the extracted variables in the chat context.</p>
<p>If not specified, the name of the module will be set to <em>“default”</em>, this is useful only if the chatbots needs more than one models in the same flow.</p>
</script>