From ace13cf4aa724c078a6a6f36a6f243cd4821a548 Mon Sep 17 00:00:00 2001
From: dan <me@danrh.co.uk>
Date: Wed, 7 Jun 2023 17:20:38 -0400
Subject: proto: semantic search with indexdb caching embeddings

---
 semanticsearchscratchpad/create-embeddings.js |  30 +++++
 semanticsearchscratchpad/index.html           | 162 ++++++++++++++++++++++++++
 semanticsearchscratchpad/worker.js            |  11 ++
 3 files changed, 203 insertions(+)
 create mode 100644 semanticsearchscratchpad/create-embeddings.js
 create mode 100644 semanticsearchscratchpad/index.html
 create mode 100644 semanticsearchscratchpad/worker.js

(limited to 'semanticsearchscratchpad')

diff --git a/semanticsearchscratchpad/create-embeddings.js b/semanticsearchscratchpad/create-embeddings.js
new file mode 100644
index 0000000..bbb3a81
--- /dev/null
+++ b/semanticsearchscratchpad/create-embeddings.js
@@ -0,0 +1,30 @@
+onmessage = msg => {
+  const lines = msg.data;
+
+  const request = indexedDB.open("embeddings");
+
+  request.onupgradeneeded = (event) => {
+    console.log('onupgradeneeded')
+    const db = event.target.result;
+    db.createObjectStore('embeddings', {autoIncrement: true});
+    };
+  
+  let embeddings;
+  request.onsuccess = (event) => {
+    const db = event.target.result;
+    embeddings = db.transaction('embeddings', 'readwrite').objectStore('embeddings').getAll();
+    if (!embeddings || !embeddings.length) {
+    createEmbeddings(lines)
+      .then(xsembs => {
+        embeddings = xsembs;
+        const st = db
+            .transaction('embeddings', 'readwrite')
+            .objectStore('embeddings');
+        xsembs.forEach(emb => {
+            console.log(emb);
+            st.add(emb);
+        });
+      });
+  }
+  };
+}
diff --git a/semanticsearchscratchpad/index.html b/semanticsearchscratchpad/index.html
new file mode 100644
index 0000000..8a96b54
--- /dev/null
+++ b/semanticsearchscratchpad/index.html
@@ -0,0 +1,162 @@
+ <div class="controls" tabindex="0">
+      <form>
+        <div>
+          <label for="number1">Multiply number 1: </label>
+          <input type="text" id="number1" value="0" />
+        </div>
+        <div>
+          <label for="number2">Multiply number 2: </label>
+          <input type="text" id="number2" value="0" />
+        </div>
+      </form>
+
+      <p class="result">Result: 0</p>
+    </div>
+
+<script type="module">
+import { pipeline, env } from 'https://cdn.jsdelivr.net/npm/@xenova/transformers@2.1.1';
+env.allowLocalModels = false;
+
+let pipe = await pipeline('embeddings');
+
+let emb = x => pipe(x, {pooling:'mean', normalize:'true'});
+
+async function createEmbeddings(xs) {
+    return (await Promise.all(xs.map(emb))).map((x,i) => ({value: xs[i], embeddings: x.data}));
+}
+
+function dotp(x, y) {
+  function dotp_sum(a, b) {
+    return a + b;
+  }
+  function dotp_times(_, i) {
+    return x[i] * y[i];
+  }
+  return x.map(dotp_times).reduce((a, v) => a + v, 0);
+}
+
+function cosineSimilarity(A,B){
+  var similarity = dotp(A, B) / (Math.sqrt(dotp(A,A)) * Math.sqrt(dotp(B,B)));
+  return similarity;
+}
+
+
+
+/** Open DB **/
+
+
+/****/
+
+
+
+//const yemb = (await emb('I really like curry.')).data;
+//
+//
+//console.log('out', xsembs.map(x => ({value:x.value, similarity: cosineSimilarity(x.embeddings, yemb)})));
+//
+
+/******/
+
+const request = indexedDB.open("embeddings");
+request.onerror = (event) => {
+  console.error("Why didn't you allow my web app to use IndexedDB?!");
+};
+
+request.onupgradeneeded = (event) => {
+  console.log('onupgradeneeded')
+  const db = event.target.result;
+  db.createObjectStore('embeddings', {autoIncrement: true});
+  };
+
+var embeddings;
+
+
+number1.onchange = e => {
+  const request = indexedDB.open("embeddings");
+  request.onsuccess = (event) => {
+    const db = event.target.result;
+    const t = db.transaction('embeddings', 'readwrite').objectStore('embeddings').getAll();
+    t.onsuccess = e => {
+  //    embeddings.onsuccess =  =>
+     embeddings = e.target.result;
+      if (embeddings && embeddings.length) {    
+            emb('I really like curry.').then(yemb =>{
+            const r = embeddings
+              .map(x => ({value:x.value, similarity: cosineSimilarity(x.embeddings, yemb.data)}));
+              console.log(r)
+            result.innerHTML = r
+              .sort((a,b) => a.similarity > b.similarity)
+              .map(({value, similarity}) => `<div>${value}: ${similarity}</div>`)
+              .join('<br/>');
+              }
+              );
+      } else {
+          console.error(embeddings);
+      }
+    }
+  }
+}
+
+request.onsuccess = (event) => {
+  const db = event.target.result;
+  let t = db.transaction('embeddings', 'readwrite').objectStore('embeddings').getAll();
+  t.onerror = () => console.error('transaction failed');
+  t.onsuccess = e => {
+    const embeddings = e.target.result;
+    if (!embeddings || !embeddings.length) {
+        createEmbeddings(['Jim likes curry', 'I really dislike potatoes', 'We went to Mars last week'])
+      .then(xsembs => {
+        const st = db
+            .transaction('embeddings', 'readwrite')
+            .objectStore('embeddings');
+        xsembs.forEach(emb => {
+            console.log(emb);
+            st.add(emb);
+        });
+      });
+    }
+}
+}
+
+
+
+
+//request.onsuccess = (event) => {
+//  console.log('onsuccess')
+//  const db = event.target.result;
+//  const st = db
+//      .transaction('embeddings', 'readwrite')
+//      .objectStore('embeddings');
+//  xsembs.forEach(emb => {
+//      console.log(emb);
+//      st.add(emb);
+//  });
+//};
+
+/******/
+
+const first = document.querySelector('#number1');
+const second = document.querySelector('#number2');
+
+const result = document.querySelector('.result');
+
+const myWorker = new Worker("worker.js");
+
+//first.onchange = function() {
+//  myWorker.postMessage([first.value, second.value]);
+//  console.log('Message posted to worker', [first.value, second.value]);
+//}
+
+second.onchange = function() {
+  myWorker.postMessage([first.value, second.value]);
+  console.log('Message posted to worker', [first.value, second.value]);
+}
+
+myWorker.onmessage = function(e) {
+  result.textContent = e.data;
+  console.log('Message received from worker', e.data);
+}
+
+</script>
+
+
diff --git a/semanticsearchscratchpad/worker.js b/semanticsearchscratchpad/worker.js
new file mode 100644
index 0000000..447ede5
--- /dev/null
+++ b/semanticsearchscratchpad/worker.js
@@ -0,0 +1,11 @@
+onmessage = function(e) {
+  console.log('Worker: Message received from main script');
+  const result = e.data[0] * e.data[1];
+  if (isNaN(result)) {
+    postMessage('Please write two numbers');
+  } else {
+    const workerResult = 'Result: ' + result;
+    console.log('Worker: Posting message back to main script');
+    postMessage(workerResult);
+  }
+}
-- 
cgit v1.2.3