diff options
Diffstat (limited to 'docs/posts/2021-06-27-Crude-ML-AI-Powered-Chatbot-Swift.html')
| -rw-r--r-- | docs/posts/2021-06-27-Crude-ML-AI-Powered-Chatbot-Swift.html | 267 |
1 files changed, 0 insertions, 267 deletions
diff --git a/docs/posts/2021-06-27-Crude-ML-AI-Powered-Chatbot-Swift.html b/docs/posts/2021-06-27-Crude-ML-AI-Powered-Chatbot-Swift.html deleted file mode 100644 index ca49edd..0000000 --- a/docs/posts/2021-06-27-Crude-ML-AI-Powered-Chatbot-Swift.html +++ /dev/null @@ -1,267 +0,0 @@ -<!DOCTYPE html> -<html lang="en"> -<head> - - <meta http-equiv="X-UA-Compatible" content="IE=edge"> - <meta http-equiv="content-type" content="text/html; charset=utf-8"> - <meta name="viewport" content="width=device-width, initial-scale=1.0"> - <meta name="theme-color" content="#6a9fb5"> - - <title>Making a Crude ML Powered Chatbot in Swift using CoreML</title> - - <!-- - <link rel="stylesheet" href="https://unpkg.com/latex.css/style.min.css" /> - --> - - <link rel="stylesheet" href="/assets/c-hyde.css"> - - <link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Abril+Fatface"> - <link rel="stylesheet" href="https://fonts.googleapis.com/css?family=PT+Sans:400,400italic,700"> - - <link rel="stylesheet" href="/assets/main.css"> - <meta name="viewport" content="width=device-width, initial-scale=1.0"> - <meta name="og:site_name" content="Navan Chauhan"> - <link rel="canonical" href="https://web.navan.dev/posts/2021-06-27-Crude-ML-AI-Powered-Chatbot-Swift.html"> - <meta name="twitter:url" content="https://web.navan.dev/posts/2021-06-27-Crude-ML-AI-Powered-Chatbot-Swift.html"> - <meta name="og:url" content="https://web.navan.dev/posts/2021-06-27-Crude-ML-AI-Powered-Chatbot-Swift.html"> - <meta name="twitter:title" content="Making a Crude ML Powered Chatbot in Swift using CoreML"> - <meta name="og:title" content="Making a Crude ML Powered Chatbot in Swift using CoreML"> - <meta name="description" content="Writing a simple Machine-Learning powered Chatbot (or, daresay virtual personal assistant ) in Swift using CoreML."> - <meta name="twitter:description" content="Writing a simple Machine-Learning powered Chatbot (or, daresay virtual personal assistant ) in Swift using CoreML."> - <meta name="og:description" content="Writing a simple Machine-Learning powered Chatbot (or, daresay virtual personal assistant ) in Swift using CoreML."> - <meta name="twitter:card" content="summary_large_image"> - <meta name="viewport" content="width=device-width, initial-scale=1.0"> - <link rel="shortcut icon" href="/images/favicon.png" type="image/png"> - <link href="/feed.rss" type="application/atom+xml" rel="alternate" title="Sitewide Atom feed"> - <meta name="twitter:image" content="https://web.navan.dev/images/opengraph/posts/2021-06-27-Crude-ML-AI-Powered-Chatbot-Swift.png"> - <meta name="og:image" content="https://web.navan.dev/images/opengraph/posts/2021-06-27-Crude-ML-AI-Powered-Chatbot-Swift.png"> - <meta name="google-site-verification" content="LVeSZxz-QskhbEjHxOi7-BM5dDxTg53x2TwrjFxfL0k"> - <script data-goatcounter="https://navanchauhan.goatcounter.com/count" - async src="//gc.zgo.at/count.js"></script> - <script defer data-domain="web.navan.dev" src="https://plausible.io/js/plausible.js"></script> - <link rel="manifest" href="/manifest.json"> - -</head> -<body class="theme-base-0d"> - <div class="sidebar"> - <div class="container sidebar-sticky"> - <div class="sidebar-about"> - <h1><a href="/">Navan</a></h1> - <p class="lead" id="random-lead">Alea iacta est.</p> - </div> - - <ul class="sidebar-nav"> - <li><a class="sidebar-nav-item" href="/about/">about/links</a></li> - <li><a class="sidebar-nav-item" href="/posts/">posts</a></li> - <li><a class="sidebar-nav-item" href="/3D-Designs/">3D designs</a></li> - <li><a class="sidebar-nav-item" href="/feed.rss">RSS Feed</a></li> - <li><a class="sidebar-nav-item" href="/colophon/">colophon</a></li> - </ul> - <div class="copyright"><p>© 2019-2024. Navan Chauhan <br> <a href="/feed.rss">RSS</a></p></div> - </div> -</div> - -<script> -let phrases = [ - "Something Funny", "Veni, vidi, vici", "Alea iacta est", "In vino veritas", "Acta, non verba", "Castigat ridendo mores", - "Cui bono?", "Memento vivere", "अहम् ब्रह्मास्मि", "अनुगच्छतु प्रवाहं", "चरन्मार्गान्विजानाति", "coq de cheval", "我愛啤酒" - ]; - -let new_phrase = phrases[Math.floor(Math.random()*phrases.length)]; - -let lead = document.getElementById("random-lead"); -lead.innerText = new_phrase; -</script> - <div class="content container"> - - <div class="post"> - <h1 id="making-a-crude-ml-powered-chatbot-in-swift-using-coreml">Making a Crude ML Powered Chatbot in Swift using CoreML</h1> - -<p>A chatbot/virtual assistant, on paper, looks easy to build. -The user says something, the programs finds the best action, checks if additional input is required and sends back the output. -To do this in Swift, I used two separate ML Models created using Apple's Create ML App. -First is a Text Classifier to classify intent, and the other a word tagger for extracting input from the input message. -Disclaimer: This is a very crude proof-of-concept, but it does work.</p> - -<h2 id="text-classifier">Text Classifier</h2> - -<p>I opened a CSV file and added some sample entries, with a corresponding label.</p> - -<p><img src="/assets/posts/swift-chatbot/intent-csv.png" alt="Screenshot of Sample Dataset" /></p> - -<pre><code>text,label -hey there,greetings -hello,greetings -good morning,greetings -good evening,greetings -hi,greetings -open the pod bay doors,banter -who let the dogs out,banter -ahh that's hot,banter -bruh that's rad,banter -nothing,banter -da fuq,banter -can you tell me details about the compound aspirin,deez-drug -i want to know about some compounds,deez-drug -search about the compound,deez-drug -tell me about the molecule,deez-drug -tell me about something,banter -tell me something cool,banter -tell a joke,banter -make me a sandwich,banter -whatcha doing,greetings -i love you,banter -</code></pre> - -<p><img src="/assets/posts/swift-chatbot/create-intent.png" alt="Screenshot of Create ML Text Classifier" /></p> - -<h2 id="word-tagging">Word Tagging</h2> - -<p>This is useful to extract the required variables directly from the user's input. -This model will be only called if the intent from the classifier is a custom action. -I created a sample JSON with only 3 examples (I know, very less, but works for a crude PoC).</p> - -<p><img src="/assets/posts/swift-chatbot/drugs-json.png" alt="Screenshot of Sample Dataset" /></p> - -<div class="codehilite"> -<pre><span></span><code><span class="p">[</span> -<span class="w"> </span><span class="p">{</span> -<span class="w"> </span><span class="nt">"tokens"</span><span class="p">:</span><span class="w"> </span><span class="p">[</span><span class="s2">"Tell"</span><span class="p">,</span><span class="s2">"me"</span><span class="p">,</span><span class="s2">"about"</span><span class="p">,</span><span class="s2">"the"</span><span class="p">,</span><span class="s2">"drug"</span><span class="p">,</span><span class="s2">"Aspirin"</span><span class="p">,</span><span class="s2">"."</span><span class="p">],</span> -<span class="w"> </span><span class="nt">"labels"</span><span class="p">:</span><span class="w"> </span><span class="p">[</span><span class="s2">"NONE"</span><span class="p">,</span><span class="s2">"NONE"</span><span class="p">,</span><span class="s2">"NONE"</span><span class="p">,</span><span class="s2">"NONE"</span><span class="p">,</span><span class="s2">"NONE"</span><span class="p">,</span><span class="s2">"COMPOUND"</span><span class="p">,</span><span class="s2">"NONE"</span><span class="p">]</span> -<span class="w"> </span><span class="p">},</span> -<span class="w"> </span><span class="p">{</span> -<span class="w"> </span><span class="nt">"tokens"</span><span class="p">:</span><span class="w"> </span><span class="p">[</span><span class="s2">"Please"</span><span class="p">,</span><span class="s2">"tell"</span><span class="p">,</span><span class="s2">"me"</span><span class="p">,</span><span class="s2">"information"</span><span class="p">,</span><span class="s2">"about"</span><span class="p">,</span><span class="s2">"the"</span><span class="p">,</span><span class="s2">"compound"</span><span class="p">,</span><span class="s2">"salicylic"</span><span class="p">,</span><span class="s2">"acid"</span><span class="p">,</span><span class="s2">"."</span><span class="p">],</span> -<span class="w"> </span><span class="nt">"labels"</span><span class="p">:</span><span class="w"> </span><span class="p">[</span><span class="s2">"NONE"</span><span class="p">,</span><span class="s2">"NONE"</span><span class="p">,</span><span class="s2">"NONE"</span><span class="p">,</span><span class="s2">"NONE"</span><span class="p">,</span><span class="s2">"NONE"</span><span class="p">,</span><span class="s2">"NONE"</span><span class="p">,</span><span class="s2">"NONE"</span><span class="p">,</span><span class="s2">"COMPOUND"</span><span class="p">,</span><span class="s2">"COMPOUND"</span><span class="p">,</span><span class="s2">"NONE"</span><span class="p">]</span> -<span class="w"> </span><span class="p">},</span> -<span class="w"> </span><span class="p">{</span> -<span class="w"> </span><span class="nt">"tokens"</span><span class="p">:</span><span class="w"> </span><span class="p">[</span><span class="s2">"Information"</span><span class="p">,</span><span class="s2">"about"</span><span class="p">,</span><span class="s2">"the"</span><span class="p">,</span><span class="s2">"compound"</span><span class="p">,</span><span class="s2">"Ibuprofen"</span><span class="p">,</span><span class="s2">"please"</span><span class="p">,</span><span class="s2">"."</span><span class="p">],</span> -<span class="w"> </span><span class="nt">"labels"</span><span class="p">:</span><span class="w"> </span><span class="p">[</span><span class="s2">"NONE"</span><span class="p">,</span><span class="s2">"NONE"</span><span class="p">,</span><span class="s2">"NONE"</span><span class="p">,</span><span class="s2">"NONE"</span><span class="p">,</span><span class="s2">"COMPOUND"</span><span class="p">,</span><span class="s2">"NONE"</span><span class="p">,</span><span class="s2">"NONE"</span><span class="p">]</span> -<span class="w"> </span><span class="p">}</span> -<span class="p">]</span> -</code></pre> -</div> - -<p><img src="/assets/posts/swift-chatbot/create-tagger.png" alt="Screenshot of Create ML Text Classifier" /></p> - -<h2 id="time-to-get-swift-y">Time to Get Swift-y</h2> - -<p>The initial part is easy, importing CoreML and NaturalLanguage and then initializing the models and the tagger.</p> - -<p><img src="/assets/posts/swift-chatbot/carbon.png" alt="Screenshot" /></p> - -<div class="codehilite"> -<pre><span></span><code><span class="kd">import</span> <span class="nc">CoreML</span> -<span class="kd">import</span> <span class="nc">NaturalLanguage</span> - -<span class="kd">let</span> <span class="nv">mlModelClassifier</span> <span class="p">=</span> <span class="k">try</span> <span class="n">IntentDetection_1</span><span class="p">(</span><span class="n">configuration</span><span class="p">:</span> <span class="bp">MLModelConfiguration</span><span class="p">()).</span><span class="n">model</span> -<span class="kd">let</span> <span class="nv">mlModelTagger</span> <span class="p">=</span> <span class="k">try</span> <span class="n">CompoundTagger</span><span class="p">(</span><span class="n">configuration</span><span class="p">:</span> <span class="bp">MLModelConfiguration</span><span class="p">()).</span><span class="n">model</span> - -<span class="kd">let</span> <span class="nv">intentPredictor</span> <span class="p">=</span> <span class="k">try</span> <span class="bp">NLModel</span><span class="p">(</span><span class="n">mlModel</span><span class="p">:</span> <span class="n">mlModelClassifier</span><span class="p">)</span> -<span class="kd">let</span> <span class="nv">tagPredictor</span> <span class="p">=</span> <span class="k">try</span> <span class="bp">NLModel</span><span class="p">(</span><span class="n">mlModel</span><span class="p">:</span> <span class="n">mlModelTagger</span><span class="p">)</span> - -<span class="kd">let</span> <span class="nv">tagger</span> <span class="p">=</span> <span class="bp">NLTagger</span><span class="p">(</span><span class="n">tagSchemes</span><span class="p">:</span> <span class="p">[.</span><span class="n">nameType</span><span class="p">,</span> <span class="n">NLTagScheme</span><span class="p">(</span><span class="s">"Apple"</span><span class="p">)])</span> -<span class="n">tagger</span><span class="p">.</span><span class="n">setModels</span><span class="p">([</span><span class="n">tagPredictor</span><span class="p">],</span> <span class="n">forTagScheme</span><span class="p">:</span> <span class="n">NLTagScheme</span><span class="p">(</span><span class="s">"Apple"</span><span class="p">))</span> -</code></pre> -</div> - -<p>Now, we define a simple structure which the custom function(s) can use to access the provided input. -It can also be used to hold additional variables. -This custom action for our third label, uses the Word Tagger model to check for the compound in the user's message. -If it is present then it displays the name, otherwise it tells the user that they have not provided the input. -The latter can be replaced with a function which asks the user for the input. </p> - -<p><img src="/assets/posts/swift-chatbot/carbon-2.png" alt="Screenshot" /></p> - -<div class="codehilite"> -<pre><span></span><code><span class="kd">struct</span> <span class="nc">User</span> <span class="p">{</span> - <span class="kd">static</span> <span class="kd">var</span> <span class="nv">message</span> <span class="p">=</span> <span class="s">""</span> -<span class="p">}</span> - -<span class="kd">func</span> <span class="nf">customAction</span><span class="p">()</span> <span class="p">-></span> <span class="nb">String</span> <span class="p">{</span> - <span class="kd">let</span> <span class="nv">sampleMessage</span> <span class="p">=</span> <span class="n">User</span><span class="p">.</span><span class="n">message</span> - <span class="kd">var</span> <span class="nv">actionable_item</span> <span class="p">=</span> <span class="s">""</span> - <span class="n">tagger</span><span class="p">.</span><span class="n">string</span> <span class="p">=</span> <span class="n">sampleMessage</span> - <span class="n">tagger</span><span class="p">.</span><span class="n">enumerateTags</span><span class="p">(</span><span class="k">in</span><span class="p">:</span> <span class="n">sampleMessage</span><span class="p">.</span><span class="n">startIndex</span><span class="p">..<</span><span class="n">sampleMessage</span><span class="p">.</span><span class="n">endIndex</span><span class="p">,</span> <span class="n">unit</span><span class="p">:</span> <span class="p">.</span><span class="n">word</span><span class="p">,</span> - <span class="n">scheme</span><span class="p">:</span> <span class="n">NLTagScheme</span><span class="p">(</span><span class="s">"Apple"</span><span class="p">),</span> <span class="n">options</span><span class="p">:</span> <span class="p">.</span><span class="n">omitWhitespace</span><span class="p">)</span> <span class="p">{</span> <span class="n">tag</span><span class="p">,</span> <span class="n">tokenRange</span> <span class="k">in</span> - <span class="k">if</span> <span class="kd">let</span> <span class="nv">tag</span> <span class="p">=</span> <span class="n">tag</span> <span class="p">{</span> - <span class="k">if</span> <span class="n">tag</span><span class="p">.</span><span class="n">rawValue</span> <span class="p">==</span> <span class="s">"COMPOUND"</span> <span class="p">{</span> - <span class="n">actionable_item</span> <span class="o">+=</span> <span class="n">sampleMessage</span><span class="p">[</span><span class="n">tokenRange</span><span class="p">]</span> - <span class="p">}</span> - <span class="p">}</span> - <span class="k">return</span> <span class="kc">true</span> - <span class="p">}</span> - <span class="k">if</span> <span class="n">actionable_item</span> <span class="p">==</span> <span class="s">""</span> <span class="p">{</span> - <span class="k">return</span> <span class="s">"You did not provide any input"</span> - <span class="p">}</span> <span class="k">else</span> <span class="p">{</span> - <span class="k">return</span> <span class="s">"You provided input </span><span class="si">\(</span><span class="n">actionable_item</span><span class="si">)</span><span class="s"> for performing custom action"</span> - <span class="p">}</span> - -<span class="p">}</span> -</code></pre> -</div> - -<p>Sometimes, no action needs to be performed, and the bot can use a predefined set of responses. -Otherwise, if an action is required, it can call the custom action.</p> - -<p><img src="/assets/posts/swift-chatbot/carbon-3.png" alt="Screenshot" /></p> - -<div class="codehilite"> -<pre><span></span><code><span class="kd">let</span> <span class="nv">defaultResponses</span> <span class="p">=</span> <span class="p">[</span> - <span class="s">"greetings"</span><span class="p">:</span> <span class="s">"Hello"</span><span class="p">,</span> - <span class="s">"banter"</span><span class="p">:</span> <span class="s">"no, plix no"</span> -<span class="p">]</span> - -<span class="kd">let</span> <span class="nv">customActions</span> <span class="p">=</span> <span class="p">[</span> - <span class="s">"deez-drug"</span><span class="p">:</span> <span class="n">customAction</span> -<span class="p">]</span> -</code></pre> -</div> - -<p>In the sample input, the program is updating the User.message and checking if it has a default response. -Otherwise, it calls the custom action.</p> - -<p><img src="/assets/posts/swift-chatbot/carbon-4.png" alt="Screenshot" /></p> - -<div class="codehilite"> -<pre><span></span><code><span class="kd">let</span> <span class="nv">sampleMessages</span> <span class="p">=</span> <span class="p">[</span> - <span class="s">"Hey there, how is it going"</span><span class="p">,</span> - <span class="s">"hello, there"</span><span class="p">,</span> - <span class="s">"Who let the dogs out"</span><span class="p">,</span> - <span class="s">"can you tell me about the compound Geraniin"</span><span class="p">,</span> - <span class="s">"what do you know about the compound Ibuprofen"</span><span class="p">,</span> - <span class="s">"please, tell me more about the compound"</span><span class="p">,</span> - <span class="s">"please, tell me more about the molecule dihydrogen-monoxide"</span> -<span class="p">]</span> - -<span class="k">for</span> <span class="n">sampleMessage</span> <span class="k">in</span> <span class="n">sampleMessages</span> <span class="p">{</span> - <span class="n">User</span><span class="p">.</span><span class="n">message</span> <span class="p">=</span> <span class="n">sampleMessage</span> - <span class="kd">let</span> <span class="nv">prediction</span> <span class="p">=</span> <span class="n">intentPredictor</span><span class="p">.</span><span class="n">predictedLabel</span><span class="p">(</span><span class="k">for</span><span class="p">:</span> <span class="n">sampleMessage</span><span class="p">)</span> - - <span class="k">if</span> <span class="p">(</span><span class="n">defaultResponses</span><span class="p">[</span><span class="n">prediction</span><span class="p">!]</span> <span class="o">!=</span> <span class="kc">nil</span><span class="p">)</span> <span class="p">{</span> - <span class="bp">print</span><span class="p">(</span><span class="n">defaultResponses</span><span class="p">[</span><span class="n">prediction</span><span class="p">!]</span><span class="o">!</span><span class="p">)</span> - <span class="p">}</span> <span class="k">else</span> <span class="k">if</span> <span class="p">(</span><span class="n">customActions</span><span class="p">[</span><span class="n">prediction</span><span class="p">!]</span> <span class="o">!=</span> <span class="kc">nil</span><span class="p">)</span> <span class="p">{</span> - <span class="bp">print</span><span class="p">(</span><span class="n">customActions</span><span class="p">[</span><span class="n">prediction</span><span class="p">!]</span><span class="o">!</span><span class="p">())</span> - <span class="p">}</span> -<span class="p">}</span> -</code></pre> -</div> - -<p><img src="/assets/posts/swift-chatbot/output.png" alt="Output" /></p> - -<p>So easy.</p> - -<p>If I ever release a part-2, it will either be about implementing this in Tensorflow.JS or an iOS app using SwiftUI ;)</p> - - </div> - <blockquote>If you have scrolled this far, consider subscribing to my mailing list <a href="https://listmonk.navan.dev/subscription/form">here.</a> You can subscribe to either a specific type of post you are interested in, or subscribe to everything with the "Everything" list.</blockquote> - <script data-isso="https://comments.navan.dev/" - src="https://comments.navan.dev/js/embed.min.js"></script> - <div id="isso-thread"> - <noscript>Javascript needs to be activated to view comments.</noscript> - </div> - - </div> - <script src="assets/manup.min.js"></script> - <script src="/pwabuilder-sw-register.js"></script> -</body> -</html>
\ No newline at end of file |