Add support for transformers.js (#6)

- Add support for transformers.js (8eea22cb12cc5d205be48fc8120523d887f4abfe)


Co-authored-by: Joshua <[email protected]>

README.md

@@ -8,6 +8,7 @@ tags:
 - mteb
 - arctic
 - snowflake-arctic-embed
+- transformers.js
 model-index:
 - name: snowflake-arctic-m-long
   results:
@@ -3020,6 +3021,37 @@ If you use the long context model with more than 2048 tokens, ensure that you in
 model = AutoModel.from_pretrained('Snowflake/snowflake-arctic-embed-m-long', trust_remote_code=True, rotary_scaling_factor=2)
 ```
 
+### Using Transformers.js
+
+If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@xenova/transformers) by running:
+```bash
+npm i @xenova/transformers
+```
+
+You can then use the model to compute embeddings as follows:
+
+```js
+import { pipeline, dot } from '@xenova/transformers';
+
+// Create feature extraction pipeline
+const extractor = await pipeline('feature-extraction', 'Snowflake/snowflake-arctic-embed-m-long', {
+    quantized: false, // Comment out this line to use the quantized version
+});
+
+// Generate sentence embeddings
+const sentences = [
+    'Represent this sentence for searching relevant passages: Where can I get the best tacos?',
+    'The Data Cloud!',
+    'Mexico City of Course!',
+]
+const output = await extractor(sentences, { normalize: true, pooling: 'cls' });
+
+// Compute similarity scores
+const [source_embeddings, ...document_embeddings ] = output.tolist();
+const similarities = document_embeddings.map(x => dot(source_embeddings, x));
+console.log(similarities); // [0.36740492125676116, 0.42407774292046635]
+```
+
 
 ## FAQ