Add transformers.js sample code (#6)

- Add transformers.js sample code (f2ec3aa090aaa90df1481872580bf64c338fada8)


Co-authored-by: Joshua <Xenova@users.noreply.huggingface.co>

README.md

@@ -185,6 +185,26 @@ embeddings = model.encode([
 print(cos_sim(embeddings[0], embeddings[1]))
 ```
 
+You can also use the [Transformers.js](https://huggingface.co/docs/transformers.js) library to compute embeddings in JavaScript.
+```js
+// npm i @xenova/transformers
+import { pipeline, cos_sim } from '@xenova/transformers';
+
+const extractor = await pipeline('feature-extraction', 'jinaai/jina-embeddings-v2-base-code', {
+    quantized: false, // Comment out this line to use the 8-bit quantized version
+});
+
+const texts = [
+    'How do I access the index while iterating over a sequence with a for loop?',
+    '# Use the built-in enumerator\nfor idx, x in enumerate(xs):\n    print(idx, x)',
+]
+const embeddings = await extractor(texts, { pooling: 'mean' });
+
+const score = cos_sim(embeddings[0].data, embeddings[1].data);
+console.log(score);
+// 0.7281748759529421
+```
+
 ## Plans
 
 1. Bilingual embedding models supporting more European & Asian languages, including Spanish, French, Italian and Japanese.